diff --git a/sb125_analyses/corridor_study/_utils.py b/sb125_analyses/corridor_study/_utils.py
new file mode 100644
index 000000000..aba4dcdc6
--- /dev/null
+++ b/sb125_analyses/corridor_study/_utils.py
@@ -0,0 +1,113 @@
+"""
+Replica and Streetlight Analysis Utils
+"""
+
+import pandas as pd
+from siuba import *
+import ast
+
+from calitp_data_analysis.sql import to_snakecase
+
+import altair as alt
+from calitp_data_analysis import calitp_color_palette as cp
+
+
+"""
+Replica Analysis Utils
+"""
+##function that returns Replica transit data into df we can analyze easier
+def get_tranist_agency_counts(df, primary_mode_col, transit_mode_col, transit_agency_col, activity_id_col):
+    ## return a df with the agency counts
+    agencies = (df
+         >>filter(_[primary_mode_col] =="public_transit")
+         >>group_by(_[primary_mode_col], _[transit_mode_col], _[transit_agency_col])
+         >>summarize(n =_[activity_id_col].nunique())
+         >>arrange(-_.n))
+    
+    agencies[transit_mode_col] = agencies[transit_mode_col].astype(str)
+    agencies[transit_agency_col] = agencies[transit_agency_col].astype(str)
+    
+    agencies['agency_count'] = [len(set(x.split(", "))) for x in
+                        agencies[transit_agency_col].str.lower()]
+    agencies['n_modes_taken'] = agencies[transit_mode_col].apply(lambda x: len(x.split()))
+    
+    ## return a df with the mode counts
+    modes = (df
+             >>filter(_[primary_mode_col] =="public_transit")
+             >>count(_[transit_mode_col])>>arrange(-_.n))
+    
+    modes[transit_mode_col] = modes[transit_mode_col].astype(str)
+    # modes[transit_agency_col] = modes[transit_agency_col].astype(str)
+    
+    modes['n_modes_taken'] = modes[transit_mode_col].apply(lambda x: len(x.split()))
+
+    return agencies, modes
+
+def get_list_of_agencies(df, transit_agency_col):
+    
+    ## Get just one columns
+    column = df[[transit_agency_col]]
+    #remove single-dimensional entries from the shape of an array
+    col_text = column.squeeze()
+    # get list of words
+    text_list = col_text.tolist()
+    # #join list of words 
+    text_list = ', '.join(text_list).title()
+    
+    text_list = text_list.replace(", ", "', '")
+    text_list = "['" + text_list + "']"
+    
+    agency_list = ast.literal_eval(text_list)
+    agency_list = set(agency_list)
+    
+    return agency_list
+
+def get_dummies_by_agency(df, col):
+    transit_agencies = set()
+    for agencies in df[col].str.split(', '):
+        transit_agencies.update(agencies)
+    unique_agencies = []
+    
+    for agency in transit_agencies:
+        df[agency] = df[col].str.count(agency)
+        unique_agencies.append(agency)
+
+    ### adding column for unique agencies list
+    def get_unique_agencies(agency_list):
+        unique_agencies = set()
+        for agencies in agency_list:
+            unique_agencies.update(agencies.split(', '))
+        return ', '.join(sorted(list(unique_agencies)))
+
+    # Applying the function to each row of the dataframe to get unique agencies
+    df['unique_agencies'] = df[col].str.split(', ').apply(lambda x: get_unique_agencies(x))
+    
+    return df
+
+def get_agencies_occurances(df):
+    
+    ##get list of columns that have agency names
+    columns_to_keep = list(df.columns.values)
+    
+    ## remove columns that are not agency names
+    unwanted_cols = {'transit_agency', 'unique_agencies', 'primary_mode', 'transit_submode', 'n', 'agency_count', 'n_modes_taken' }
+    columns_to_keep = [e for e in columns_to_keep if e not in unwanted_cols]
+    
+    df_agencies = df.loc[:, columns_to_keep]
+    
+    ## transpose the df again
+    df_agencies = pd.DataFrame(df_agencies).transpose().reset_index().rename(columns={'index':'agency'})
+    
+    ##sum up the number of trips by agency
+    df_agencies['n_trips'] = df_agencies[list(df_agencies.columns)].sum(axis=1)
+    
+    ## filter df to only have two cols
+    df_agencies = df_agencies>>select(_.agency, _.n_trips)
+    
+    return df_agencies
+
+"""
+Streetlight Analysis Utils
+"""
+
+
diff --git a/sb125_analyses/corridor_study/data_downloads_baybridge.ipynb b/sb125_analyses/corridor_study/data_downloads_baybridge.ipynb
new file mode 100644
index 000000000..181e33062
--- /dev/null
+++ b/sb125_analyses/corridor_study/data_downloads_baybridge.ipynb
@@ -0,0 +1,5807 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "82a53f1d-2622-4cb0-bfdd-36ceec652215",
+   "metadata": {},
+   "source": [
+    "# SB1 Big Data Downloads\n",
+    "An analysis into the corridor analysis data downloads from Streetlight and Replica"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "45233485-2055-499a-a89e-fc154fd56e63",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_483/4150955979.py:10: DeprecationWarning: Importing display from IPython.core.display is deprecated since IPython 7.14, please import from IPython display\n",
+      "  from IPython.core.display import display\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from siuba import *\n",
+    "\n",
+    "from calitp_data_analysis.sql import to_snakecase\n",
+    "\n",
+    "import altair as alt\n",
+    "from calitp_data_analysis import calitp_color_palette as cp\n",
+    "\n",
+    "from IPython.display import Markdown, HTML, display_html, display\n",
+    "from IPython.core.display import display\n",
+    "\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "577fe167-1d9d-4676-999c-ccb2b89575ff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import _utils"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "651aae92-5188-4676-8e5f-3c040f77077c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pd.set_option('display.max_columns', 500)\n",
+    "pd.set_option('display.max_colwidth', 100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "af402da0-0b03-4c71-a1af-19f97f67cef1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "GCS_PATH = \"gs://calitp-analytics-data/data-analyses/sb125/corridor_study_data/\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "71c1deda-8e83-45d8-a0f5-20b36b7051c0",
+   "metadata": {},
+   "source": [
+    "### Read in Replica Data Spring 2023"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "0e5c1b44-c981-4a9a-b6ea-e1cb2a7a279e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "replica_trips = \"replica-bay_bridge-03_06_24-trips_dataset.csv\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "b0bd67f0-6f82-4f2c-8da0-3627a2813571",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "replica_ppl = \"replica-bay_bridge-03_06_24-people_dataset.csv\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a9f14685-0953-4b1d-a636-882230fef1d5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "cb3dea26-4e6d-4dc7-acc8-27b899a0a537",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_483/2643890524.py:1: DtypeWarning: Columns (2,4,5,9,10,11,18,25,26,29,30,35,36,40,43,48,50) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+      "  r_trips = to_snakecase(pd.read_csv(f\"{GCS_PATH}{replica_trips}\"))\n"
+     ]
+    }
+   ],
+   "source": [
+    "r_trips = to_snakecase(pd.read_csv(f\"{GCS_PATH}{replica_trips}\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ca697494-b872-4de8-afd9-c538a455364c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong> Sample of data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong> Sample of data</strong></h4>\"))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "4713b1a5-ccac-4e1b-8552-850285cad53e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>origin_building_use</th>\n",
+       "      <th>trip_duration_minutes</th>\n",
+       "      <th>trip_taker_language</th>\n",
+       "      <th>origin_trct_2020</th>\n",
+       "      <th>trip_taker_household_id</th>\n",
+       "      <th>trip_taker_sex</th>\n",
+       "      <th>trip_taker_home_bgrp_2020</th>\n",
+       "      <th>origin_st_2020</th>\n",
+       "      <th>trip_taker_home_st_2020</th>\n",
+       "      <th>trip_taker_race_ethnicity</th>\n",
+       "      <th>transit_agency</th>\n",
+       "      <th>transit_route</th>\n",
+       "      <th>trip_taker_resident_type</th>\n",
+       "      <th>vehicle_type</th>\n",
+       "      <th>trip_taker_age</th>\n",
+       "      <th>activity_id</th>\n",
+       "      <th>destination_bgrp_2020</th>\n",
+       "      <th>destination_building_use</th>\n",
+       "      <th>trip_taker_wfh</th>\n",
+       "      <th>destination_st_2020</th>\n",
+       "      <th>destination_cty_2020</th>\n",
+       "      <th>trip_taker_work_bgrp_2020</th>\n",
+       "      <th>destination_trct_2020</th>\n",
+       "      <th>trip_taker_household_income</th>\n",
+       "      <th>origin_bgrp_2020</th>\n",
+       "      <th>trip_taker_commute_mode</th>\n",
+       "      <th>trip_taker_available_vehicles</th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>previous_trip_purpose</th>\n",
+       "      <th>trip_taker_building_type</th>\n",
+       "      <th>transit_submode</th>\n",
+       "      <th>trip_taker_work_st_2020</th>\n",
+       "      <th>trip_taker_household_size</th>\n",
+       "      <th>origin_cty_2020</th>\n",
+       "      <th>destination_land_use</th>\n",
+       "      <th>trip_taker_industry</th>\n",
+       "      <th>trip_taker_tenure</th>\n",
+       "      <th>vehicle_fuel_type</th>\n",
+       "      <th>trip_taker_home_trct_2020</th>\n",
+       "      <th>trip_taker_work_trct_2020</th>\n",
+       "      <th>trip_taker_education</th>\n",
+       "      <th>trip_start_time</th>\n",
+       "      <th>trip_taker_individual_income</th>\n",
+       "      <th>trip_taker_employment_status</th>\n",
+       "      <th>trip_purpose</th>\n",
+       "      <th>origin_land_use</th>\n",
+       "      <th>trip_taker_work_cty_2020</th>\n",
+       "      <th>trip_distance_miles</th>\n",
+       "      <th>trip_taker_school_grade_attending</th>\n",
+       "      <th>trip_taker_home_cty_2020</th>\n",
+       "      <th>trip_taker_person_id</th>\n",
+       "      <th>trip_end_time</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>199078</th>\n",
+       "      <td>multi_family</td>\n",
+       "      <td>46</td>\n",
+       "      <td>other</td>\n",
+       "      <td>4501.01 (Alameda, CA)</td>\n",
+       "      <td>69970950706205725</td>\n",
+       "      <td>male</td>\n",
+       "      <td>2 (Tract 4501.01, Alameda, CA)</td>\n",
+       "      <td>California</td>\n",
+       "      <td>California</td>\n",
+       "      <td>white_not_hispanic_or_latino</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>core</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>39.0</td>\n",
+       "      <td>4486197526664593040</td>\n",
+       "      <td>2 (Tract 105, San Francisco, CA)</td>\n",
+       "      <td>non_retail_attraction</td>\n",
+       "      <td>in_person</td>\n",
+       "      <td>California</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>2 (Tract 105, San Francisco, CA)</td>\n",
+       "      <td>105 (San Francisco, CA)</td>\n",
+       "      <td>237966.0</td>\n",
+       "      <td>2 (Tract 4501.01, Alameda, CA)</td>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>one</td>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>home</td>\n",
+       "      <td>multiple_units</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>California</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>Alameda</td>\n",
+       "      <td>non_retail_attraction</td>\n",
+       "      <td>naics31_33</td>\n",
+       "      <td>renter</td>\n",
+       "      <td>unknown_fuel_type</td>\n",
+       "      <td>4501.01 (Alameda, CA)</td>\n",
+       "      <td>105 (San Francisco, CA)</td>\n",
+       "      <td>advanced_degree</td>\n",
+       "      <td>04:53:00</td>\n",
+       "      <td>237966.0</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>work</td>\n",
+       "      <td>multi_family</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>36.7</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>Alameda</td>\n",
+       "      <td>11699013211020046684</td>\n",
+       "      <td>05:39:20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>362910</th>\n",
+       "      <td>multi_family</td>\n",
+       "      <td>65</td>\n",
+       "      <td>english</td>\n",
+       "      <td>615.06 (San Francisco, CA)</td>\n",
+       "      <td>14710396768871133663</td>\n",
+       "      <td>female</td>\n",
+       "      <td>1 (Tract 615.06, San Francisco, CA)</td>\n",
+       "      <td>California</td>\n",
+       "      <td>California</td>\n",
+       "      <td>white_not_hispanic_or_latino</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>core</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>30.0</td>\n",
+       "      <td>3388798362605091248</td>\n",
+       "      <td>1 (Tract 3551.13, Contra Costa, CA)</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>in_person</td>\n",
+       "      <td>California</td>\n",
+       "      <td>Contra Costa</td>\n",
+       "      <td>1 (Tract 615.01, San Francisco, CA)</td>\n",
+       "      <td>3551.13 (Contra Costa, CA)</td>\n",
+       "      <td>237586.0</td>\n",
+       "      <td>1 (Tract 615.06, San Francisco, CA)</td>\n",
+       "      <td>walking</td>\n",
+       "      <td>one</td>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>home</td>\n",
+       "      <td>multiple_units</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>naics5151</td>\n",
+       "      <td>renter</td>\n",
+       "      <td>unknown_fuel_type</td>\n",
+       "      <td>615.06 (San Francisco, CA)</td>\n",
+       "      <td>615.01 (San Francisco, CA)</td>\n",
+       "      <td>bachelors_degree</td>\n",
+       "      <td>17:25:00</td>\n",
+       "      <td>77510.0</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>social</td>\n",
+       "      <td>mixed_use</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>33.7</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>14279596460102489210</td>\n",
+       "      <td>18:30:49</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>397490</th>\n",
+       "      <td>education</td>\n",
+       "      <td>53</td>\n",
+       "      <td>indo_european</td>\n",
+       "      <td>301.02 (San Francisco, CA)</td>\n",
+       "      <td>11603413512180790232</td>\n",
+       "      <td>male</td>\n",
+       "      <td>5 (Tract 4381, Alameda, CA)</td>\n",
+       "      <td>California</td>\n",
+       "      <td>California</td>\n",
+       "      <td>two_races_not_hispanic_or_latino</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>core</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>46.0</td>\n",
+       "      <td>17748416797468343771</td>\n",
+       "      <td>5 (Tract 4381, Alameda, CA)</td>\n",
+       "      <td>multi_family</td>\n",
+       "      <td>in_person</td>\n",
+       "      <td>California</td>\n",
+       "      <td>Alameda</td>\n",
+       "      <td>3 (Tract 301.02, San Francisco, CA)</td>\n",
+       "      <td>4381 (Alameda, CA)</td>\n",
+       "      <td>101548.0</td>\n",
+       "      <td>3 (Tract 301.02, San Francisco, CA)</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>two</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>work</td>\n",
+       "      <td>several_units</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>California</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>multi_family</td>\n",
+       "      <td>naics61</td>\n",
+       "      <td>owner</td>\n",
+       "      <td>other_non_bev</td>\n",
+       "      <td>4381 (Alameda, CA)</td>\n",
+       "      <td>301.02 (San Francisco, CA)</td>\n",
+       "      <td>some_college</td>\n",
+       "      <td>20:53:05</td>\n",
+       "      <td>71051.0</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>home</td>\n",
+       "      <td>education</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>34.1</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>Alameda</td>\n",
+       "      <td>9371860226741686287</td>\n",
+       "      <td>21:46:49</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>646286</th>\n",
+       "      <td>single_family</td>\n",
+       "      <td>42</td>\n",
+       "      <td>asian_pacific</td>\n",
+       "      <td>3851 (Contra Costa, CA)</td>\n",
+       "      <td>8856161571093041221</td>\n",
+       "      <td>female</td>\n",
+       "      <td>2 (Tract 3851, Contra Costa, CA)</td>\n",
+       "      <td>California</td>\n",
+       "      <td>California</td>\n",
+       "      <td>asian_not_hispanic_or_latino</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>core</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>61.0</td>\n",
+       "      <td>1096586971710081424</td>\n",
+       "      <td>1 (Tract 177, San Francisco, CA)</td>\n",
+       "      <td>retail</td>\n",
+       "      <td>unemployed_under_16_not_in_labor_force</td>\n",
+       "      <td>California</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>177 (San Francisco, CA)</td>\n",
+       "      <td>163758.0</td>\n",
+       "      <td>2 (Tract 3851, Contra Costa, CA)</td>\n",
+       "      <td>other_travel_mode</td>\n",
+       "      <td>two</td>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>home</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>Contra Costa</td>\n",
+       "      <td>mixed_use</td>\n",
+       "      <td>not_working</td>\n",
+       "      <td>owner</td>\n",
+       "      <td>unknown_fuel_type</td>\n",
+       "      <td>3851 (Contra Costa, CA)</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>high_school</td>\n",
+       "      <td>17:10:00</td>\n",
+       "      <td>11123.0</td>\n",
+       "      <td>not_in_labor_force</td>\n",
+       "      <td>eat</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>17.5</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>Contra Costa</td>\n",
+       "      <td>15224202816917079679</td>\n",
+       "      <td>17:52:23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>432031</th>\n",
+       "      <td>single_family</td>\n",
+       "      <td>30</td>\n",
+       "      <td>english</td>\n",
+       "      <td>3790 (Contra Costa, CA)</td>\n",
+       "      <td>11125850078941310816</td>\n",
+       "      <td>male</td>\n",
+       "      <td>1 (Tract 3790, Contra Costa, CA)</td>\n",
+       "      <td>California</td>\n",
+       "      <td>California</td>\n",
+       "      <td>white_not_hispanic_or_latino</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>core</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>58.0</td>\n",
+       "      <td>17878107943481256906</td>\n",
+       "      <td>3 (Tract 151, San Francisco, CA)</td>\n",
+       "      <td>office</td>\n",
+       "      <td>in_person</td>\n",
+       "      <td>California</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>3 (Tract 151, San Francisco, CA)</td>\n",
+       "      <td>151 (San Francisco, CA)</td>\n",
+       "      <td>191291.0</td>\n",
+       "      <td>1 (Tract 3790, Contra Costa, CA)</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>two</td>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>home</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>California</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Contra Costa</td>\n",
+       "      <td>mixed_use</td>\n",
+       "      <td>naics42</td>\n",
+       "      <td>owner</td>\n",
+       "      <td>unknown_fuel_type</td>\n",
+       "      <td>3790 (Contra Costa, CA)</td>\n",
+       "      <td>151 (San Francisco, CA)</td>\n",
+       "      <td>some_college</td>\n",
+       "      <td>13:50:00</td>\n",
+       "      <td>81981.0</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>work</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>Contra Costa</td>\n",
+       "      <td>17663033273047637228</td>\n",
+       "      <td>14:20:30</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       origin_building_use  trip_duration_minutes trip_taker_language  \\\n",
+       "199078        multi_family                     46               other   \n",
+       "362910        multi_family                     65             english   \n",
+       "397490           education                     53       indo_european   \n",
+       "646286       single_family                     42       asian_pacific   \n",
+       "432031       single_family                     30             english   \n",
+       "\n",
+       "                  origin_trct_2020 trip_taker_household_id trip_taker_sex  \\\n",
+       "199078       4501.01 (Alameda, CA)       69970950706205725           male   \n",
+       "362910  615.06 (San Francisco, CA)    14710396768871133663         female   \n",
+       "397490  301.02 (San Francisco, CA)    11603413512180790232           male   \n",
+       "646286     3851 (Contra Costa, CA)     8856161571093041221         female   \n",
+       "432031     3790 (Contra Costa, CA)    11125850078941310816           male   \n",
+       "\n",
+       "                  trip_taker_home_bgrp_2020 origin_st_2020  \\\n",
+       "199078       2 (Tract 4501.01, Alameda, CA)     California   \n",
+       "362910  1 (Tract 615.06, San Francisco, CA)     California   \n",
+       "397490          5 (Tract 4381, Alameda, CA)     California   \n",
+       "646286     2 (Tract 3851, Contra Costa, CA)     California   \n",
+       "432031     1 (Tract 3790, Contra Costa, CA)     California   \n",
+       "\n",
+       "       trip_taker_home_st_2020         trip_taker_race_ethnicity  \\\n",
+       "199078              California      white_not_hispanic_or_latino   \n",
+       "362910              California      white_not_hispanic_or_latino   \n",
+       "397490              California  two_races_not_hispanic_or_latino   \n",
+       "646286              California      asian_not_hispanic_or_latino   \n",
+       "432031              California      white_not_hispanic_or_latino   \n",
+       "\n",
+       "       transit_agency transit_route trip_taker_resident_type  \\\n",
+       "199078            NaN           NaN                     core   \n",
+       "362910            NaN           NaN                     core   \n",
+       "397490            NaN           NaN                     core   \n",
+       "646286            NaN           NaN                     core   \n",
+       "432031            NaN           NaN                     core   \n",
+       "\n",
+       "                vehicle_type  trip_taker_age           activity_id  \\\n",
+       "199078  unknown_vehicle_type            39.0   4486197526664593040   \n",
+       "362910  unknown_vehicle_type            30.0   3388798362605091248   \n",
+       "397490  unknown_vehicle_type            46.0  17748416797468343771   \n",
+       "646286  unknown_vehicle_type            61.0   1096586971710081424   \n",
+       "432031  unknown_vehicle_type            58.0  17878107943481256906   \n",
+       "\n",
+       "                      destination_bgrp_2020 destination_building_use  \\\n",
+       "199078     2 (Tract 105, San Francisco, CA)    non_retail_attraction   \n",
+       "362910  1 (Tract 3551.13, Contra Costa, CA)            single_family   \n",
+       "397490          5 (Tract 4381, Alameda, CA)             multi_family   \n",
+       "646286     1 (Tract 177, San Francisco, CA)                   retail   \n",
+       "432031     3 (Tract 151, San Francisco, CA)                   office   \n",
+       "\n",
+       "                                trip_taker_wfh destination_st_2020  \\\n",
+       "199078                               in_person          California   \n",
+       "362910                               in_person          California   \n",
+       "397490                               in_person          California   \n",
+       "646286  unemployed_under_16_not_in_labor_force          California   \n",
+       "432031                               in_person          California   \n",
+       "\n",
+       "       destination_cty_2020            trip_taker_work_bgrp_2020  \\\n",
+       "199078        San Francisco     2 (Tract 105, San Francisco, CA)   \n",
+       "362910         Contra Costa  1 (Tract 615.01, San Francisco, CA)   \n",
+       "397490              Alameda  3 (Tract 301.02, San Francisco, CA)   \n",
+       "646286        San Francisco   Does not have work/school location   \n",
+       "432031        San Francisco     3 (Tract 151, San Francisco, CA)   \n",
+       "\n",
+       "             destination_trct_2020  trip_taker_household_income  \\\n",
+       "199078     105 (San Francisco, CA)                     237966.0   \n",
+       "362910  3551.13 (Contra Costa, CA)                     237586.0   \n",
+       "397490          4381 (Alameda, CA)                     101548.0   \n",
+       "646286     177 (San Francisco, CA)                     163758.0   \n",
+       "432031     151 (San Francisco, CA)                     191291.0   \n",
+       "\n",
+       "                           origin_bgrp_2020 trip_taker_commute_mode  \\\n",
+       "199078       2 (Tract 4501.01, Alameda, CA)          public_transit   \n",
+       "362910  1 (Tract 615.06, San Francisco, CA)                 walking   \n",
+       "397490  3 (Tract 301.02, San Francisco, CA)            private_auto   \n",
+       "646286     2 (Tract 3851, Contra Costa, CA)       other_travel_mode   \n",
+       "432031     1 (Tract 3790, Contra Costa, CA)            private_auto   \n",
+       "\n",
+       "       trip_taker_available_vehicles    primary_mode previous_trip_purpose  \\\n",
+       "199078                           one  auto_passenger                  home   \n",
+       "362910                           one  auto_passenger                  home   \n",
+       "397490                           two    private_auto                  work   \n",
+       "646286                           two  auto_passenger                  home   \n",
+       "432031                           two  auto_passenger                  home   \n",
+       "\n",
+       "       trip_taker_building_type transit_submode  \\\n",
+       "199078           multiple_units             NaN   \n",
+       "362910           multiple_units             NaN   \n",
+       "397490            several_units             NaN   \n",
+       "646286            single_family             NaN   \n",
+       "432031            single_family             NaN   \n",
+       "\n",
+       "                   trip_taker_work_st_2020  trip_taker_household_size  \\\n",
+       "199078                          California                        4.0   \n",
+       "362910                          California                        2.0   \n",
+       "397490                          California                        4.0   \n",
+       "646286  Does not have work/school location                        4.0   \n",
+       "432031                          California                        3.0   \n",
+       "\n",
+       "       origin_cty_2020   destination_land_use trip_taker_industry  \\\n",
+       "199078         Alameda  non_retail_attraction          naics31_33   \n",
+       "362910   San Francisco          single_family           naics5151   \n",
+       "397490   San Francisco           multi_family             naics61   \n",
+       "646286    Contra Costa              mixed_use         not_working   \n",
+       "432031    Contra Costa              mixed_use             naics42   \n",
+       "\n",
+       "       trip_taker_tenure  vehicle_fuel_type   trip_taker_home_trct_2020  \\\n",
+       "199078            renter  unknown_fuel_type       4501.01 (Alameda, CA)   \n",
+       "362910            renter  unknown_fuel_type  615.06 (San Francisco, CA)   \n",
+       "397490             owner      other_non_bev          4381 (Alameda, CA)   \n",
+       "646286             owner  unknown_fuel_type     3851 (Contra Costa, CA)   \n",
+       "432031             owner  unknown_fuel_type     3790 (Contra Costa, CA)   \n",
+       "\n",
+       "                 trip_taker_work_trct_2020 trip_taker_education  \\\n",
+       "199078             105 (San Francisco, CA)      advanced_degree   \n",
+       "362910          615.01 (San Francisco, CA)     bachelors_degree   \n",
+       "397490          301.02 (San Francisco, CA)         some_college   \n",
+       "646286  Does not have work/school location          high_school   \n",
+       "432031             151 (San Francisco, CA)         some_college   \n",
+       "\n",
+       "       trip_start_time  trip_taker_individual_income  \\\n",
+       "199078        04:53:00                      237966.0   \n",
+       "362910        17:25:00                       77510.0   \n",
+       "397490        20:53:05                       71051.0   \n",
+       "646286        17:10:00                       11123.0   \n",
+       "432031        13:50:00                       81981.0   \n",
+       "\n",
+       "       trip_taker_employment_status trip_purpose origin_land_use  \\\n",
+       "199078                     employed         work    multi_family   \n",
+       "362910                     employed       social       mixed_use   \n",
+       "397490                     employed         home       education   \n",
+       "646286           not_in_labor_force          eat   single_family   \n",
+       "432031                     employed         work   single_family   \n",
+       "\n",
+       "                  trip_taker_work_cty_2020  trip_distance_miles  \\\n",
+       "199078                       San Francisco                 36.7   \n",
+       "362910                       San Francisco                 33.7   \n",
+       "397490                       San Francisco                 34.1   \n",
+       "646286  Does not have work/school location                 17.5   \n",
+       "432031                       San Francisco                 18.4   \n",
+       "\n",
+       "       trip_taker_school_grade_attending trip_taker_home_cty_2020  \\\n",
+       "199078              not_attending_school                  Alameda   \n",
+       "362910              not_attending_school            San Francisco   \n",
+       "397490              not_attending_school                  Alameda   \n",
+       "646286              not_attending_school             Contra Costa   \n",
+       "432031              not_attending_school             Contra Costa   \n",
+       "\n",
+       "        trip_taker_person_id trip_end_time  \n",
+       "199078  11699013211020046684      05:39:20  \n",
+       "362910  14279596460102489210      18:30:49  \n",
+       "397490   9371860226741686287      21:46:49  \n",
+       "646286  15224202816917079679      17:52:23  \n",
+       "432031  17663033273047637228      14:20:30  "
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips.sample(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e2199852-9b6e-46ca-86fd-abe71148d13f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "75945ef2-eab7-469a-baad-ee563d70c309",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong> Columns in Replica Trips Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong> Columns in Replica Trips Data</strong></h4>\"))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "1f3e4cbb-d211-40b1-b4bb-2c7cb43b33a9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['origin_building_use', 'trip_duration_minutes', 'trip_taker_language',\n",
+       "       'origin_trct_2020', 'trip_taker_household_id', 'trip_taker_sex',\n",
+       "       'trip_taker_home_bgrp_2020', 'origin_st_2020',\n",
+       "       'trip_taker_home_st_2020', 'trip_taker_race_ethnicity',\n",
+       "       'transit_agency', 'transit_route', 'trip_taker_resident_type',\n",
+       "       'vehicle_type', 'trip_taker_age', 'activity_id',\n",
+       "       'destination_bgrp_2020', 'destination_building_use', 'trip_taker_wfh',\n",
+       "       'destination_st_2020', 'destination_cty_2020',\n",
+       "       'trip_taker_work_bgrp_2020', 'destination_trct_2020',\n",
+       "       'trip_taker_household_income', 'origin_bgrp_2020',\n",
+       "       'trip_taker_commute_mode', 'trip_taker_available_vehicles',\n",
+       "       'primary_mode', 'previous_trip_purpose', 'trip_taker_building_type',\n",
+       "       'transit_submode', 'trip_taker_work_st_2020',\n",
+       "       'trip_taker_household_size', 'origin_cty_2020', 'destination_land_use',\n",
+       "       'trip_taker_industry', 'trip_taker_tenure', 'vehicle_fuel_type',\n",
+       "       'trip_taker_home_trct_2020', 'trip_taker_work_trct_2020',\n",
+       "       'trip_taker_education', 'trip_start_time',\n",
+       "       'trip_taker_individual_income', 'trip_taker_employment_status',\n",
+       "       'trip_purpose', 'origin_land_use', 'trip_taker_work_cty_2020',\n",
+       "       'trip_distance_miles', 'trip_taker_school_grade_attending',\n",
+       "       'trip_taker_home_cty_2020', 'trip_taker_person_id', 'trip_end_time'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e60fb5c7-a04b-48f3-8282-ca98a54dadd2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "92f9a5f4-08f1-43fc-ae01-c6bd404891d6",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "#### Data Exploration: Replica Trips\n",
+    "* Summarizing the data that we exported from Replica\n",
+    "* Existing visualizations in replica: \n",
+    "   * Primary Mode\n",
+    "   * Trip Purpose\n",
+    "   * Starting hour \n",
+    "   * Trip Duration/Distance\n",
+    "   * Origin Destination\n",
+    "   * Vehicle Fuel type\n",
+    "   * Transit Routes/Stops/Sub mode/Agency\n",
+    "   * Household Income\n",
+    "   * Race and Ethnicity\n",
+    "   * Private Auto Availability\n",
+    "   * Age\n",
+    "   * Employment/School Status\n",
+    "   \n",
+    "   "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "d7f3b44a-cd77-42e9-b0d8-7b9d228b37d5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trips = r_trips>>group_by(_.primary_mode)>>summarize(avg_trip_time = _.trip_duration_minutes.mean(),\n",
+    "                                                     number_trips = _.activity_id.nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "05893215-e993-44dc-9c4b-1aa7d94815cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-63b5ea120afb4438a948862bca6ef545.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-63b5ea120afb4438a948862bca6ef545.vega-embed details,\n",
+       "  #altair-viz-63b5ea120afb4438a948862bca6ef545.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-63b5ea120afb4438a948862bca6ef545\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-63b5ea120afb4438a948862bca6ef545\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-63b5ea120afb4438a948862bca6ef545\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-5ebbbb8d3f3ea3fc2a2c0aba4ca6c486\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"avg_trip_time\", \"scale\": {\"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"primary_mode\", \"type\": \"nominal\"}, {\"field\": \"avg_trip_time\", \"type\": \"quantitative\"}, {\"field\": \"number_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"primary_mode\", \"type\": \"nominal\"}, \"y\": {\"field\": \"avg_trip_time\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"Average Trip Time\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-5ebbbb8d3f3ea3fc2a2c0aba4ca6c486\": [{\"primary_mode\": \"auto_passenger\", \"avg_trip_time\": 49.55882961785474, \"number_trips\": 391291}, {\"primary_mode\": \"commercial\", \"avg_trip_time\": 37.51080104227957, \"number_trips\": 11897}, {\"primary_mode\": \"on_demand_auto\", \"avg_trip_time\": 34.715467665937, \"number_trips\": 26953}, {\"primary_mode\": \"private_auto\", \"avg_trip_time\": 59.57683606351334, \"number_trips\": 238690}, {\"primary_mode\": \"public_transit\", \"avg_trip_time\": 52.36283772584121, \"number_trips\": 6033}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(trips)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"primary_mode\"),\n",
+    "            y=alt.Y(\"avg_trip_time\"),\n",
+    "            color=alt.Color(\"avg_trip_time\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS)\n",
+    "            ), tooltip=trips.columns.tolist())\n",
+    "      .properties(title = \"Average Trip Time\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "65681a29-7f1b-42ed-9e0e-371a84a29cbd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-254a7bb15bf346d3b457213941cfda74.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-254a7bb15bf346d3b457213941cfda74.vega-embed details,\n",
+       "  #altair-viz-254a7bb15bf346d3b457213941cfda74.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-254a7bb15bf346d3b457213941cfda74\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-254a7bb15bf346d3b457213941cfda74\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-254a7bb15bf346d3b457213941cfda74\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-5ebbbb8d3f3ea3fc2a2c0aba4ca6c486\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"number_trips\", \"scale\": {\"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"primary_mode\", \"type\": \"nominal\"}, {\"field\": \"avg_trip_time\", \"type\": \"quantitative\"}, {\"field\": \"number_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"primary_mode\", \"type\": \"nominal\"}, \"y\": {\"field\": \"number_trips\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"Number of Trips\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-5ebbbb8d3f3ea3fc2a2c0aba4ca6c486\": [{\"primary_mode\": \"auto_passenger\", \"avg_trip_time\": 49.55882961785474, \"number_trips\": 391291}, {\"primary_mode\": \"commercial\", \"avg_trip_time\": 37.51080104227957, \"number_trips\": 11897}, {\"primary_mode\": \"on_demand_auto\", \"avg_trip_time\": 34.715467665937, \"number_trips\": 26953}, {\"primary_mode\": \"private_auto\", \"avg_trip_time\": 59.57683606351334, \"number_trips\": 238690}, {\"primary_mode\": \"public_transit\", \"avg_trip_time\": 52.36283772584121, \"number_trips\": 6033}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(trips)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"primary_mode\"),\n",
+    "            y=alt.Y(\"number_trips\"),\n",
+    "            color=alt.Color(\"number_trips\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,)\n",
+    "            ), tooltip=trips.columns.tolist())\n",
+    "      .properties(title=\"Number of Trips\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "0d60fe54-dc88-4570-8610-125b37b5917d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Length of Trips dataframe</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Length of Trips dataframe</strong></h4>\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "4f98abae-ae6b-4b4e-9427-b606a557582f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "674864"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(r_trips)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "55c6ff06-afed-45dc-b764-93188c2b9958",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Number of unique activity ids in data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Number of unique activity ids in data</strong></h4>\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "27c00872-5880-4464-84a5-e91423ce7895",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>number_trips</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>674864</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   number_trips\n",
+       "0        674864"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips>>summarize(number_trips = _.activity_id.nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "a20cbce8-e354-4aa3-99db-666a13576b5e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Number of unique trip taker ids</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Number of unique trip taker ids</strong></h4>\")) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "2def0aaf-9182-4393-8049-2dfb95749585",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>number_trips</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>309596</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   number_trips\n",
+       "0        309596"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips>>summarize(number_trips = _.trip_taker_person_id.nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "47fecd22-8276-48b8-9c74-d3a94906bbae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "race_ethnicity_by_mode = r_trips>>group_by(_.primary_mode)>>count(_.trip_taker_race_ethnicity)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "4cbeb867-916b-48aa-9949-d769fcd5af5a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Trip Taker Race and Ethnicity by Mode</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Trip Taker Race and Ethnicity by Mode</strong></h4>\")) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "5e895499-2142-432d-8402-c035f81326b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-6f264d3d3af446599b46fdb76492fb34.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-6f264d3d3af446599b46fdb76492fb34.vega-embed details,\n",
+       "  #altair-viz-6f264d3d3af446599b46fdb76492fb34.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-6f264d3d3af446599b46fdb76492fb34\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-6f264d3d3af446599b46fdb76492fb34\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-6f264d3d3af446599b46fdb76492fb34\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-bb29c74c9b2d9c3da4d3616767ebcb08\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"trip_taker_race_ethnicity\", \"scale\": {\"domain\": [\"aian_not_hispanic_or_latino\", \"asian_not_hispanic_or_latino\", \"black_not_hispanic_or_latino\", \"hispanic_or_latino_origin\", \"nhopi_not_hispanic_or_latino\", \"other_not_hispanic_or_latino\", \"two_races_not_hispanic_or_latino\", \"white_not_hispanic_or_latino\", NaN], \"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"primary_mode\", \"type\": \"nominal\"}, {\"field\": \"trip_taker_race_ethnicity\", \"type\": \"nominal\"}, {\"field\": \"n\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"primary_mode\", \"type\": \"nominal\"}, \"y\": {\"field\": \"n\", \"type\": \"quantitative\"}}, \"height\": 300, \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-bb29c74c9b2d9c3da4d3616767ebcb08\": [{\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"aian_not_hispanic_or_latino\", \"n\": 1017}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"asian_not_hispanic_or_latino\", \"n\": 98414}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"black_not_hispanic_or_latino\", \"n\": 33904}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"hispanic_or_latino_origin\", \"n\": 79083}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"nhopi_not_hispanic_or_latino\", \"n\": 2116}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"other_not_hispanic_or_latino\", \"n\": 2041}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"two_races_not_hispanic_or_latino\", \"n\": 15609}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"white_not_hispanic_or_latino\", \"n\": 135555}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": null, \"n\": 23552}, {\"primary_mode\": \"commercial\", \"trip_taker_race_ethnicity\": null, \"n\": 11897}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"aian_not_hispanic_or_latino\", \"n\": 100}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"asian_not_hispanic_or_latino\", \"n\": 6731}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"black_not_hispanic_or_latino\", \"n\": 2480}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"hispanic_or_latino_origin\", \"n\": 4489}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"nhopi_not_hispanic_or_latino\", \"n\": 79}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"other_not_hispanic_or_latino\", \"n\": 125}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"two_races_not_hispanic_or_latino\", \"n\": 1260}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"white_not_hispanic_or_latino\", \"n\": 9108}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": null, \"n\": 2581}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"aian_not_hispanic_or_latino\", \"n\": 630}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"asian_not_hispanic_or_latino\", \"n\": 59112}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"black_not_hispanic_or_latino\", \"n\": 20045}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"hispanic_or_latino_origin\", \"n\": 56404}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"nhopi_not_hispanic_or_latino\", \"n\": 1625}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"other_not_hispanic_or_latino\", \"n\": 1330}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"two_races_not_hispanic_or_latino\", \"n\": 9005}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"white_not_hispanic_or_latino\", \"n\": 84335}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": null, \"n\": 6204}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"aian_not_hispanic_or_latino\", \"n\": 32}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"asian_not_hispanic_or_latino\", \"n\": 1314}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"black_not_hispanic_or_latino\", \"n\": 693}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"hispanic_or_latino_origin\", \"n\": 1026}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"nhopi_not_hispanic_or_latino\", \"n\": 65}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"other_not_hispanic_or_latino\", \"n\": 33}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"two_races_not_hispanic_or_latino\", \"n\": 309}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"white_not_hispanic_or_latino\", \"n\": 2514}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": null, \"n\": 47}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(race_ethnicity_by_mode)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"primary_mode\"),\n",
+    "            y=alt.Y(\"n\"),\n",
+    "            color=alt.Color(\"trip_taker_race_ethnicity\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,\n",
+    "                                                                         domain=race_ethnicity_by_mode[\"trip_taker_race_ethnicity\"].unique().tolist())\n",
+    "            ),\n",
+    "            tooltip=race_ethnicity_by_mode.columns.tolist())\n",
+    "            \n",
+    "      .properties(\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "da3bbe59-9b06-471f-beb1-4762b8939600",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "500ad806-51ed-47e9-88a5-fc8a41edd7aa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<H4><strong>Transit Mode Splits</strong></H4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<H4><strong>Transit Mode Splits</strong></H4>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "d8cd6354-0433-4134-ad6e-9df92122cbd2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<strong>Looking at transit mode, need to alter the transit_agency col and transit_submode to get a better count.</strong>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<strong>Looking at transit mode, need to alter the transit_agency col and transit_submode to get a better count.</strong>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "261d7f48-f7c3-4ea7-a526-6f813ca16ede",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ptt_agency_count = (r_trips\n",
+    "#  >>filter(_.primary_mode==\"public_transit\")\n",
+    "#  >>group_by(_.primary_mode, _.transit_submode, _.transit_agency)\n",
+    "#  >>summarize(n =_.activity_id.nunique())\n",
+    "#  >>arrange(-_.n))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "e4516beb-8277-4fd4-aed1-23af65fc4a28",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ptt_agency_count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "727511b8-3141-40e4-b654-30aaae8200d9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Most common transit mode combinations</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Most common transit mode combinations</strong></h4>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "f3c31371-899f-4474-85b6-86e78e89209b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ptt_modes = (r_trips\n",
+    "#              >>filter(_.primary_mode ==\"public_transit\")\n",
+    "#              >>count(_.transit_submode)>>arrange(-_.n))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "657ff2f3-0d0d-419d-b3d5-512212897fb1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ptt_modes.head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "80daf7a1-b947-469c-b3b0-09d0302714b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##### unnesting the transit submode and agencies to get counts. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "edd81120-9756-4edb-b713-1586a9fd5021",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agencies_test, mode_test = _utils.get_tranist_agency_counts(r_trips, \"primary_mode\", \"transit_submode\", \"transit_agency\", \"activity_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "2025391f-537e-432a-a2f4-d2d6ce57af04",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>transit_submode</th>\n",
+       "      <th>transit_agency</th>\n",
+       "      <th>n</th>\n",
+       "      <th>agency_count</th>\n",
+       "      <th>n_modes_taken</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus</td>\n",
+       "      <td>AC TRANSIT</td>\n",
+       "      <td>2788</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus, bus</td>\n",
+       "      <td>San Francisco Municipal Transportation Agency, AC TRANSIT</td>\n",
+       "      <td>632</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus, bus</td>\n",
+       "      <td>AC TRANSIT, San Francisco Municipal Transportation Agency</td>\n",
+       "      <td>516</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus, bus</td>\n",
+       "      <td>AC TRANSIT, AC TRANSIT</td>\n",
+       "      <td>263</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus, light_rail</td>\n",
+       "      <td>AC TRANSIT, San Francisco Municipal Transportation Agency</td>\n",
+       "      <td>253</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>128</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>rail, bus</td>\n",
+       "      <td>Caltrain, SamTrans</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>130</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>rail, bus, bus</td>\n",
+       "      <td>Amtrak, AC TRANSIT, AC TRANSIT</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>133</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>rail, light_rail, bus</td>\n",
+       "      <td>Caltrain, San Francisco Municipal Transportation Agency, AC TRANSIT</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>136</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>rail, subway, bus, bus</td>\n",
+       "      <td>Caltrain, Bay Area Rapid Transit, San Francisco Municipal Transportation Agency, AC TRANSIT</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>141</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>subway, bus, bus, bus</td>\n",
+       "      <td>Bay Area Rapid Transit, San Francisco Municipal Transportation Agency, SolTrans, AC TRANSIT</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>144 rows × 6 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       primary_mode         transit_submode  \\\n",
+       "0    public_transit                     bus   \n",
+       "12   public_transit                bus, bus   \n",
+       "8    public_transit                bus, bus   \n",
+       "6    public_transit                bus, bus   \n",
+       "75   public_transit         bus, light_rail   \n",
+       "..              ...                     ...   \n",
+       "128  public_transit               rail, bus   \n",
+       "130  public_transit          rail, bus, bus   \n",
+       "133  public_transit   rail, light_rail, bus   \n",
+       "136  public_transit  rail, subway, bus, bus   \n",
+       "141  public_transit   subway, bus, bus, bus   \n",
+       "\n",
+       "                                                                                  transit_agency  \\\n",
+       "0                                                                                     AC TRANSIT   \n",
+       "12                                     San Francisco Municipal Transportation Agency, AC TRANSIT   \n",
+       "8                                      AC TRANSIT, San Francisco Municipal Transportation Agency   \n",
+       "6                                                                         AC TRANSIT, AC TRANSIT   \n",
+       "75                                     AC TRANSIT, San Francisco Municipal Transportation Agency   \n",
+       "..                                                                                           ...   \n",
+       "128                                                                           Caltrain, SamTrans   \n",
+       "130                                                               Amtrak, AC TRANSIT, AC TRANSIT   \n",
+       "133                          Caltrain, San Francisco Municipal Transportation Agency, AC TRANSIT   \n",
+       "136  Caltrain, Bay Area Rapid Transit, San Francisco Municipal Transportation Agency, AC TRANSIT   \n",
+       "141  Bay Area Rapid Transit, San Francisco Municipal Transportation Agency, SolTrans, AC TRANSIT   \n",
+       "\n",
+       "        n  agency_count  n_modes_taken  \n",
+       "0    2788             1              1  \n",
+       "12    632             2              2  \n",
+       "8     516             2              2  \n",
+       "6     263             1              2  \n",
+       "75    253             2              2  \n",
+       "..    ...           ...            ...  \n",
+       "128     1             2              2  \n",
+       "130     1             2              3  \n",
+       "133     1             3              3  \n",
+       "136     1             4              4  \n",
+       "141     1             4              4  \n",
+       "\n",
+       "[144 rows x 6 columns]"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agencies_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "589d2a23-b528-4de9-b6a0-a10f88a6da5c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "505f47b1-229a-4cd1-90b8-b83b4ccdd6c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "modes_count = agencies_test>>group_by(_.n_modes_taken)>>summarize(n_trips = _.n.sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "97746912-39f0-4c85-80d3-a00ed47922a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# modes_count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "5353a2e4-762d-4a27-8f32-267c2c55bb90",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-d0448c3bf1b743d384483ccd4230a0cb.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-d0448c3bf1b743d384483ccd4230a0cb.vega-embed details,\n",
+       "  #altair-viz-d0448c3bf1b743d384483ccd4230a0cb.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-d0448c3bf1b743d384483ccd4230a0cb\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-d0448c3bf1b743d384483ccd4230a0cb\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-d0448c3bf1b743d384483ccd4230a0cb\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-90a1080530cd4117ff7d3b9012be686f\"}, \"mark\": {\"type\": \"bar\", \"size\": 60}, \"encoding\": {\"color\": {\"field\": \"n_trips\", \"scale\": {\"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"title\": \"Number of Trips\", \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"n_modes_taken\", \"type\": \"quantitative\"}, {\"field\": \"n_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"n_modes_taken\", \"title\": \"Number of Modes Taken per Trip\", \"type\": \"quantitative\"}, \"y\": {\"field\": \"n_trips\", \"title\": \"Number of Trips\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"How Many Modes are Taken Per Trip\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-90a1080530cd4117ff7d3b9012be686f\": [{\"n_modes_taken\": 1, \"n_trips\": 3063}, {\"n_modes_taken\": 2, \"n_trips\": 2246}, {\"n_modes_taken\": 3, \"n_trips\": 644}, {\"n_modes_taken\": 4, \"n_trips\": 70}, {\"n_modes_taken\": 5, \"n_trips\": 9}, {\"n_modes_taken\": 6, \"n_trips\": 1}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart((modes_count))\n",
+    "        .mark_bar(size=60)\n",
+    "        .encode(\n",
+    "            x=alt.X(\"n_modes_taken\", title =\"Number of Modes Taken per Trip\"),\n",
+    "            y=alt.Y(\"n_trips\", title = \"Number of Trips\"),\n",
+    "            color=alt.Color(\"n_trips\", title = \"Number of Trips\",\n",
+    "                            scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS)),\n",
+    "            tooltip=modes_count.columns.tolist())\n",
+    "            \n",
+    "      .properties(title = \"How Many Modes are Taken Per Trip\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "fb8565b9-989a-459a-bede-433de30252e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ptt_agency_count>>group_by(_.agency_count)>>count(_.n_modes_taken)>>arrange(-_.n)\n",
+    "agency_mode_trips = agencies_test>>group_by(_.agency_count, _.n_modes_taken)>>summarize(ntrips=_.n.sum())>>arrange(-_.ntrips)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "b03dbe0a-a759-4fa9-849b-b31b318f86cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-c2416b9ea34b482fb0c0e90c8ebd3afc.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-c2416b9ea34b482fb0c0e90c8ebd3afc.vega-embed details,\n",
+       "  #altair-viz-c2416b9ea34b482fb0c0e90c8ebd3afc.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-c2416b9ea34b482fb0c0e90c8ebd3afc\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-c2416b9ea34b482fb0c0e90c8ebd3afc\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-c2416b9ea34b482fb0c0e90c8ebd3afc\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-e2a4538072fc13b1c4ad15dd231c083e\"}, \"mark\": {\"type\": \"circle\", \"size\": 100}, \"encoding\": {\"color\": {\"field\": \"ntrips\", \"scale\": {\"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"title\": \"Number of Trips\", \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"agency_count\", \"type\": \"quantitative\"}, {\"field\": \"n_modes_taken\", \"type\": \"quantitative\"}, {\"field\": \"ntrips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"agency_count\", \"title\": \"Number of Agencies\", \"type\": \"quantitative\"}, \"y\": {\"field\": \"n_modes_taken\", \"title\": \"Number of Modes Taken\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"How Many Modes are Taken Per Trip\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-e2a4538072fc13b1c4ad15dd231c083e\": [{\"agency_count\": 1, \"n_modes_taken\": 1, \"ntrips\": 3063}, {\"agency_count\": 2, \"n_modes_taken\": 2, \"ntrips\": 1658}, {\"agency_count\": 1, \"n_modes_taken\": 2, \"ntrips\": 588}, {\"agency_count\": 2, \"n_modes_taken\": 3, \"ntrips\": 411}, {\"agency_count\": 1, \"n_modes_taken\": 3, \"ntrips\": 146}, {\"agency_count\": 3, \"n_modes_taken\": 3, \"ntrips\": 87}, {\"agency_count\": 2, \"n_modes_taken\": 4, \"ntrips\": 27}, {\"agency_count\": 3, \"n_modes_taken\": 4, \"ntrips\": 23}, {\"agency_count\": 1, \"n_modes_taken\": 4, \"ntrips\": 16}, {\"agency_count\": 4, \"n_modes_taken\": 4, \"ntrips\": 4}, {\"agency_count\": 4, \"n_modes_taken\": 5, \"ntrips\": 4}, {\"agency_count\": 2, \"n_modes_taken\": 5, \"ntrips\": 2}, {\"agency_count\": 3, \"n_modes_taken\": 5, \"ntrips\": 2}, {\"agency_count\": 3, \"n_modes_taken\": 6, \"ntrips\": 1}, {\"agency_count\": 5, \"n_modes_taken\": 5, \"ntrips\": 1}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart((agency_mode_trips))\n",
+    "        .mark_circle(size=100)\n",
+    "        .encode(\n",
+    "            x=alt.X(\"agency_count\", title =\"Number of Agencies\"),\n",
+    "            y=alt.Y(\"n_modes_taken\", title = \"Number of Modes Taken\"),\n",
+    "            color=alt.Color(\"ntrips\", title = \"Number of Trips\",\n",
+    "                            scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS)),\n",
+    "            tooltip=agency_mode_trips.columns.tolist())\n",
+    "            \n",
+    "      .properties(title = \"How Many Modes are Taken Per Trip\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "91273d26-1fd1-42a1-b829-a77398c606fc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "6bd200d7-c0b9-4649-adf1-e025d216328b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##### Getting columns for each agency and counts "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "e8f5f457-ce9f-4bfb-99f6-82e6eb7d11f0",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "agency_list = _utils.get_list_of_agencies(agencies_test, \"transit_agency\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "f303acae-da1b-44a5-98b2-2f8f5b98f56a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Agencies Identified in Trips Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'Ac Transit',\n",
+       " 'Amtrak',\n",
+       " 'Bay Area Rapid Transit',\n",
+       " 'Caltrain',\n",
+       " 'Fairfield And Suisun Transit',\n",
+       " 'Marin Transit',\n",
+       " 'Nan',\n",
+       " 'Sacramento Regional Transit',\n",
+       " 'Samtrans',\n",
+       " 'San Francisco Bay Ferry',\n",
+       " 'San Francisco Municipal Transportation Agency',\n",
+       " 'San Joaquin Regional Transit District (Rtd)',\n",
+       " 'Santa Cruz Metro',\n",
+       " 'Soltrans',\n",
+       " 'The S',\n",
+       " 'Tri Delta Transit',\n",
+       " 'Vta'}"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Agencies Identified in Trips Data</strong></h4>\")) \n",
+    "\n",
+    "(agency_list)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d737409e-38b2-4aa9-8cac-4ad3b8e22294",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6d5ebb21-1aaf-4743-aa0a-feb58ed44da2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2de92f7b-2e28-4388-880f-9e34b8b603ea",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89479d3a-eeb5-491a-a064-49a77194109e",
+   "metadata": {},
+   "source": [
+    "##### Trying ChatGPT approach"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "bb062bcd-4322-4970-9115-7ea91ba7041c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = _utils.get_dummies_by_agency(agencies_test, \"transit_agency\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a011752-5211-40b4-a108-a8036fdbacce",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "97bc34c4-636f-46ca-a257-95e4af242584",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##### Identifying trips with one agency"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "46856b31-47ac-408c-903e-19d8b04283f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cols_to_keep = [\"transit_submode\",\"unique_agencies\", \"n\",\"n_modes_taken\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "2603e7e0-389a-49fb-93e9-5dc1d52c6012",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# chart = (alt.Chart(df)\n",
+    "#              .mark_circle(size=100)\n",
+    "#              .encode(\n",
+    "#                  x=alt.X(\"n_modes_taken\", title=\"Number of Modes taken\"),\n",
+    "#                  y=alt.Y(\"n\", title=\"Number of Trips\"),\n",
+    "#                  color = alt.Color(\"agency_count\", title=\"Number of Unique Agencies\",\n",
+    "#                                   scale=alt.Scale(\n",
+    "#                                       range=cp.CALITP_DIVERGING_COLORS,\n",
+    "#                                       domain=df[\"agency_count\"].unique().tolist())\n",
+    "#             ),\n",
+    "#             tooltip=cols_to_keep)\n",
+    "#         .properties(title = (\"Transit Trips Agency Breakdown\"), width=500,\n",
+    "#     height=300)\n",
+    "#         )\n",
+    "# chart                    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "149ed63c-436c-45fe-a526-5b1bf9f3d6fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# (df>>filter(_.agency_count==1)>>arrange(-_.n))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "7228c540-3033-4023-8145-91f8aee23eeb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-380995bda5714ecb9feaebb8761e522a.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-380995bda5714ecb9feaebb8761e522a.vega-embed details,\n",
+       "  #altair-viz-380995bda5714ecb9feaebb8761e522a.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-380995bda5714ecb9feaebb8761e522a\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-380995bda5714ecb9feaebb8761e522a\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-380995bda5714ecb9feaebb8761e522a\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-299268073d18cd8f04646fd199e0a650\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"n_modes_taken\", \"scale\": {\"range\": [\"#B9D6DF\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\", \"#0B405B\"]}, \"title\": \"Number of Trips\", \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"transit_submode\", \"type\": \"nominal\"}, {\"field\": \"unique_agencies\", \"type\": \"nominal\"}, {\"field\": \"n\", \"type\": \"quantitative\"}, {\"field\": \"n_modes_taken\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"unique_agencies\", \"title\": \"Agency\", \"type\": \"nominal\"}, \"y\": {\"field\": \"n\", \"title\": \"Number of Modes taken\", \"type\": \"quantitative\"}}, \"height\": 500, \"title\": \"Transit Trips With Only One Agency\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-299268073d18cd8f04646fd199e0a650\": [{\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus\", \"transit_agency\": \"AC TRANSIT\", \"n\": 2788, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 1, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"AC TRANSIT\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus\", \"transit_agency\": \"AC TRANSIT, AC TRANSIT\", \"n\": 263, \"agency_count\": 1, \"n_modes_taken\": 2, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 2, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"AC TRANSIT\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 234, \"agency_count\": 1, \"n_modes_taken\": 2, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 2, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency\", \"n\": 197, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 1, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 69, \"agency_count\": 1, \"n_modes_taken\": 3, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 3, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, light_rail\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 63, \"agency_count\": 1, \"n_modes_taken\": 2, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 2, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"light_rail, bus, bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 32, \"agency_count\": 1, \"n_modes_taken\": 3, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 3, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, light_rail\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 27, \"agency_count\": 1, \"n_modes_taken\": 3, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 3, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"light_rail\", \"transit_agency\": \"San Francisco Municipal Transportation Agency\", \"n\": 27, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 1, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"light_rail, bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 26, \"agency_count\": 1, \"n_modes_taken\": 2, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 2, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"nan\", \"transit_agency\": \"nan\", \"n\": 24, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 1, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"nan\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, bus, bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 9, \"agency_count\": 1, \"n_modes_taken\": 4, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 4, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, light_rail, bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 9, \"agency_count\": 1, \"n_modes_taken\": 3, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 3, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"rail\", \"transit_agency\": \"Caltrain\", \"n\": 8, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 1, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"Caltrain\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, bus\", \"transit_agency\": \"AC TRANSIT, AC TRANSIT, AC TRANSIT\", \"n\": 7, \"agency_count\": 1, \"n_modes_taken\": 3, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 3, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"AC TRANSIT\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus\", \"transit_agency\": \"VTA\", \"n\": 6, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 1, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"VTA\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus\", \"transit_agency\": \"Marin Transit\", \"n\": 4, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 1, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"Marin Transit\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"subway\", \"transit_agency\": \"Bay Area Rapid Transit\", \"n\": 4, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 1, \"Amtrak\": 0, \"unique_agencies\": \"Bay Area Rapid Transit\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus\", \"transit_agency\": \"SolTrans\", \"n\": 3, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 1, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"SolTrans\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, light_rail, bus, bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 3, \"agency_count\": 1, \"n_modes_taken\": 4, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 4, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus\", \"transit_agency\": \"SolTrans, SolTrans\", \"n\": 2, \"agency_count\": 1, \"n_modes_taken\": 2, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 2, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"SolTrans\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, bus, bus\", \"transit_agency\": \"AC TRANSIT, AC TRANSIT, AC TRANSIT, AC TRANSIT\", \"n\": 2, \"agency_count\": 1, \"n_modes_taken\": 4, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 4, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"AC TRANSIT\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus\", \"transit_agency\": \"SamTrans\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 1, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"SamTrans\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, bus, light_rail\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 4, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 4, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, cable_car\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 3, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 3, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, light_rail, bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 4, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 4, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"light_rail\", \"transit_agency\": \"VTA\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 1, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 0, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 1, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"VTA\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"light_rail, light_rail, bus\", \"transit_agency\": \"San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency, San Francisco Municipal Transportation Agency\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 3, \"Sacramento Regional Transit\": 0, \"SamTrans\": 0, \"nan\": 0, \"The S\": 0, \"San Francisco Municipal Transportation Agency\": 3, \"Caltrain\": 0, \"Marin Transit\": 0, \"Tri Delta Transit\": 0, \"Santa Cruz Metro\": 0, \"VTA\": 0, \"Fairfield and Suisun Transit\": 0, \"San Joaquin Regional Transit District (RTD)\": 0, \"SolTrans\": 0, \"San Francisco Bay Ferry\": 0, \"AC TRANSIT\": 0, \"Bay Area Rapid Transit\": 0, \"Amtrak\": 0, \"unique_agencies\": \"San Francisco Municipal Transportation Agency\"}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (alt.Chart((df>>filter(_.agency_count==1)))\n",
+    "             .mark_bar()\n",
+    "             .encode(\n",
+    "                 x=alt.X(\"unique_agencies\", title=\"Agency\"),\n",
+    "                 y=alt.Y(\"n\", title=\"Number of Modes taken\"),\n",
+    "                 color = alt.Color(\"n_modes_taken\", title=\"Number of Trips\",\n",
+    "                                  scale=alt.Scale(\n",
+    "                                      range=cp.CALITP_SEQUENTIAL_COLORS,)),\n",
+    "            tooltip=cols_to_keep)\n",
+    "        .properties(title = (\"Transit Trips With Only One Agency\"), width=800,\n",
+    "    height=500)\n",
+    "        )\n",
+    "chart           "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "60df338f-801f-49a1-a26f-0be5e03bddf3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Most Common Agency Combination</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>transit_agency</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>AC TRANSIT</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>San Francisco Municipal Transportation Agency, AC TRANSIT</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>AC TRANSIT, San Francisco Municipal Transportation Agency</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>AC TRANSIT, AC TRANSIT</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75</th>\n",
+       "      <td>AC TRANSIT, San Francisco Municipal Transportation Agency</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                               transit_agency\n",
+       "0                                                  AC TRANSIT\n",
+       "12  San Francisco Municipal Transportation Agency, AC TRANSIT\n",
+       "8   AC TRANSIT, San Francisco Municipal Transportation Agency\n",
+       "6                                      AC TRANSIT, AC TRANSIT\n",
+       "75  AC TRANSIT, San Francisco Municipal Transportation Agency"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Most Common Agency Combination</strong></h4>\")) \n",
+    "\n",
+    "(df>>arrange(-_.n)>>select(_.transit_agency)).head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "786394ef-be26-4e0d-94e7-35386d6d67c0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fd43ab95-0391-407b-b6b0-185034ba9528",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "8af03d60-4537-44d3-b82f-d857625e47c3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/jovyan/data-analyses/sb125_analyses/corridor_study/_utils.py:102: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.\n",
+      "  df_agencies['n_trips'] = df_agencies[list(df_agencies.columns)].sum(axis=1)\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_agencies = _utils.get_agencies_occurances(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "6951b590-cef8-44bd-b27d-0b18893609c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>agency</th>\n",
+       "      <th>n_trips</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Sacramento Regional Transit</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>SamTrans</td>\n",
+       "      <td>19</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>nan</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>The S</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>San Francisco Municipal Transportation Agency</td>\n",
+       "      <td>175</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Caltrain</td>\n",
+       "      <td>20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Marin Transit</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Tri Delta Transit</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Santa Cruz Metro</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>VTA</td>\n",
+       "      <td>16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Fairfield and Suisun Transit</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>San Joaquin Regional Transit District (RTD)</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>SolTrans</td>\n",
+       "      <td>29</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>San Francisco Bay Ferry</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>AC TRANSIT</td>\n",
+       "      <td>111</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>Bay Area Rapid Transit</td>\n",
+       "      <td>37</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>Amtrak</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                           agency  n_trips\n",
+       "0                     Sacramento Regional Transit        6\n",
+       "1                                        SamTrans       19\n",
+       "2                                             nan        1\n",
+       "3                                           The S        3\n",
+       "4   San Francisco Municipal Transportation Agency      175\n",
+       "5                                        Caltrain       20\n",
+       "6                                   Marin Transit        1\n",
+       "7                               Tri Delta Transit        1\n",
+       "8                                Santa Cruz Metro        1\n",
+       "9                                             VTA       16\n",
+       "10                   Fairfield and Suisun Transit        1\n",
+       "11    San Joaquin Regional Transit District (RTD)        0\n",
+       "12                                       SolTrans       29\n",
+       "13                        San Francisco Bay Ferry        3\n",
+       "14                                     AC TRANSIT      111\n",
+       "15                         Bay Area Rapid Transit       37\n",
+       "16                                         Amtrak       10"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_agencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "f98c76b9-b83f-42c3-aa12-702ade72ac38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tooltip_cols = [\"agency\", \"n_trips\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "f1267faf-e28c-4208-ae79-43b31f67f705",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# df_agencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "bf160b81-1bc2-4374-9529-6400252d5e4f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-03a0212e3b614752963371d9c39de252.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-03a0212e3b614752963371d9c39de252.vega-embed details,\n",
+       "  #altair-viz-03a0212e3b614752963371d9c39de252.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-03a0212e3b614752963371d9c39de252\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-03a0212e3b614752963371d9c39de252\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-03a0212e3b614752963371d9c39de252\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-c9f19226ae0e61f33c26fd111442784e\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"n_trips\", \"scale\": {\"range\": [\"#B9D6DF\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\", \"#0B405B\"]}, \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"agency\", \"type\": \"nominal\"}, {\"field\": \"n_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"agency\", \"title\": \"Agency Name\", \"type\": \"nominal\"}, \"y\": {\"field\": \"n_trips\", \"title\": \"Number of boardings reported for trips (One person taking two AC Transit trips will count as 2)\", \"type\": \"quantitative\"}}, \"height\": 500, \"title\": \"Number of Times an Agency was used for Trip taking over Bay Bridge\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-c9f19226ae0e61f33c26fd111442784e\": [{\"agency\": \"Sacramento Regional Transit\", \"n_trips\": 6}, {\"agency\": \"SamTrans\", \"n_trips\": 19}, {\"agency\": \"nan\", \"n_trips\": 1}, {\"agency\": \"The S\", \"n_trips\": 3}, {\"agency\": \"San Francisco Municipal Transportation Agency\", \"n_trips\": 175}, {\"agency\": \"Caltrain\", \"n_trips\": 20}, {\"agency\": \"Marin Transit\", \"n_trips\": 1}, {\"agency\": \"Tri Delta Transit\", \"n_trips\": 1}, {\"agency\": \"Santa Cruz Metro\", \"n_trips\": 1}, {\"agency\": \"VTA\", \"n_trips\": 16}, {\"agency\": \"Fairfield and Suisun Transit\", \"n_trips\": 1}, {\"agency\": \"San Joaquin Regional Transit District (RTD)\", \"n_trips\": 0}, {\"agency\": \"SolTrans\", \"n_trips\": 29}, {\"agency\": \"San Francisco Bay Ferry\", \"n_trips\": 3}, {\"agency\": \"AC TRANSIT\", \"n_trips\": 111}, {\"agency\": \"Bay Area Rapid Transit\", \"n_trips\": 37}, {\"agency\": \"Amtrak\", \"n_trips\": 10}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (alt.Chart(df_agencies)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"agency\", title = \"Agency Name\"),\n",
+    "            y=alt.Y(\"n_trips\", title= \"Number of boardings reported for trips (One person taking two AC Transit trips will count as 2)\"),\n",
+    "            color=alt.Color(\"n_trips\", scale=alt.Scale(range = cp.CALITP_SEQUENTIAL_COLORS)),\n",
+    "            tooltip = tooltip_cols)\n",
+    "      .properties(title = \"Number of Times an Agency was used for Trip taking over Bay Bridge\",\n",
+    "    width=800,\n",
+    "    height=500)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2b5b0cb2-465f-4e1f-83f4-7ae31396d012",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a59f170f-b2e0-41b3-ae7a-1ae4eca12596",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "16b45917-adc3-44d0-8d76-15ccd4083d26",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Trips by Resident Type</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Trips by Resident Type</strong></h4>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "5163926e-82bd-4c25-9486-45229d09a0d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trip_by_res_type = (r_trips\n",
+    " >>group_by(_.primary_mode,_.trip_taker_resident_type)\n",
+    " >>summarize(number_trips = _.activity_id.nunique())\n",
+    " >>arrange(_.primary_mode))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "636e7771-0ba7-42e9-af1d-e3e998ff8599",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>trip_taker_resident_type</th>\n",
+       "      <th>number_trips</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>core</td>\n",
+       "      <td>367739</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>visitor</td>\n",
+       "      <td>23552</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>commercial</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>11897</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>on_demand_auto</td>\n",
+       "      <td>core</td>\n",
+       "      <td>24372</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>on_demand_auto</td>\n",
+       "      <td>visitor</td>\n",
+       "      <td>2581</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>core</td>\n",
+       "      <td>232486</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>visitor</td>\n",
+       "      <td>6204</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>core</td>\n",
+       "      <td>5986</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>visitor</td>\n",
+       "      <td>47</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     primary_mode trip_taker_resident_type  number_trips\n",
+       "0  auto_passenger                     core        367739\n",
+       "1  auto_passenger                  visitor         23552\n",
+       "2      commercial                      NaN         11897\n",
+       "3  on_demand_auto                     core         24372\n",
+       "4  on_demand_auto                  visitor          2581\n",
+       "5    private_auto                     core        232486\n",
+       "6    private_auto                  visitor          6204\n",
+       "7  public_transit                     core          5986\n",
+       "8  public_transit                  visitor            47"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trip_by_res_type"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "90c5d683-91c5-4663-accd-4e45027a3e49",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-b68509580b814591ac9800977d683a7d.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-b68509580b814591ac9800977d683a7d.vega-embed details,\n",
+       "  #altair-viz-b68509580b814591ac9800977d683a7d.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-b68509580b814591ac9800977d683a7d\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-b68509580b814591ac9800977d683a7d\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-b68509580b814591ac9800977d683a7d\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-528534624f8069c35e0920aefe8f9b51\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"trip_taker_resident_type\", \"scale\": {\"domain\": [\"core\", \"visitor\", NaN], \"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"primary_mode\", \"type\": \"nominal\"}, {\"field\": \"trip_taker_resident_type\", \"type\": \"nominal\"}, {\"field\": \"number_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"primary_mode\", \"title\": \"Mode\", \"type\": \"nominal\"}, \"y\": {\"field\": \"number_trips\", \"title\": \"Number of Trips\", \"type\": \"quantitative\"}}, \"height\": 500, \"title\": \"Trips by Resident Type\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-528534624f8069c35e0920aefe8f9b51\": [{\"primary_mode\": \"auto_passenger\", \"trip_taker_resident_type\": \"core\", \"number_trips\": 367739}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_resident_type\": \"visitor\", \"number_trips\": 23552}, {\"primary_mode\": \"commercial\", \"trip_taker_resident_type\": null, \"number_trips\": 11897}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_resident_type\": \"core\", \"number_trips\": 24372}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_resident_type\": \"visitor\", \"number_trips\": 2581}, {\"primary_mode\": \"private_auto\", \"trip_taker_resident_type\": \"core\", \"number_trips\": 232486}, {\"primary_mode\": \"private_auto\", \"trip_taker_resident_type\": \"visitor\", \"number_trips\": 6204}, {\"primary_mode\": \"public_transit\", \"trip_taker_resident_type\": \"core\", \"number_trips\": 5986}, {\"primary_mode\": \"public_transit\", \"trip_taker_resident_type\": \"visitor\", \"number_trips\": 47}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(trip_by_res_type)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"primary_mode\", title = \"Mode\"),\n",
+    "            y=alt.Y(\"number_trips\", title = \"Number of Trips\"),\n",
+    "            color=alt.Color(\"trip_taker_resident_type\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,\n",
+    "                                                                         domain=trip_by_res_type[\"trip_taker_resident_type\"].unique().tolist())\n",
+    "            ),\n",
+    "            tooltip=trip_by_res_type.columns.tolist())\n",
+    "      .properties(title = \"Trips by Resident Type\",\n",
+    "    width=800,\n",
+    "    height=500)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f7b51fbb-8b87-4863-bcd9-50ed5047d7d6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "878c5c8e-18c3-456a-b641-67ad010f5101",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Unique Household Ids</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Unique Household Ids</strong></h4>\")) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "2a31bf27-ccc4-4ce3-8b6a-31dbd14caaf2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>trip_taker_household_id</th>\n",
+       "      <th>n</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>248686</th>\n",
+       "      <td></td>\n",
+       "      <td>27897</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>262322</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>16384</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>110604</th>\n",
+       "      <td>8194219563640751815</td>\n",
+       "      <td>28</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>82299</th>\n",
+       "      <td>6097771312917788596</td>\n",
+       "      <td>27</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>74914</th>\n",
+       "      <td>5552467881171814730</td>\n",
+       "      <td>22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>262312</th>\n",
+       "      <td>9988489366890220188</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>262316</th>\n",
+       "      <td>9991342309439330560</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>262317</th>\n",
+       "      <td>9992490903429866665</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>262318</th>\n",
+       "      <td>9992599661009943006</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>262319</th>\n",
+       "      <td>9993588483694519152</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>262323 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       trip_taker_household_id      n\n",
+       "248686                          27897\n",
+       "262322                     NaN  16384\n",
+       "110604     8194219563640751815     28\n",
+       "82299      6097771312917788596     27\n",
+       "74914      5552467881171814730     22\n",
+       "...                        ...    ...\n",
+       "262312     9988489366890220188      1\n",
+       "262316     9991342309439330560      1\n",
+       "262317     9992490903429866665      1\n",
+       "262318     9992599661009943006      1\n",
+       "262319     9993588483694519152      1\n",
+       "\n",
+       "[262323 rows x 2 columns]"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips>>count(_.trip_taker_household_id)>>arrange(-_.n)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "id": "eb9780a3-b996-45af-9cc3-b41629ec0e55",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Checking one household id</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Checking one household id</strong></h4>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "6fc3be54-b8dc-4cf8-893e-565ffa02934d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "28\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>origin_building_use</th>\n",
+       "      <th>trip_duration_minutes</th>\n",
+       "      <th>trip_taker_language</th>\n",
+       "      <th>origin_trct_2020</th>\n",
+       "      <th>trip_taker_household_id</th>\n",
+       "      <th>trip_taker_sex</th>\n",
+       "      <th>trip_taker_home_bgrp_2020</th>\n",
+       "      <th>origin_st_2020</th>\n",
+       "      <th>trip_taker_home_st_2020</th>\n",
+       "      <th>trip_taker_race_ethnicity</th>\n",
+       "      <th>transit_agency</th>\n",
+       "      <th>transit_route</th>\n",
+       "      <th>trip_taker_resident_type</th>\n",
+       "      <th>vehicle_type</th>\n",
+       "      <th>trip_taker_age</th>\n",
+       "      <th>activity_id</th>\n",
+       "      <th>destination_bgrp_2020</th>\n",
+       "      <th>destination_building_use</th>\n",
+       "      <th>trip_taker_wfh</th>\n",
+       "      <th>destination_st_2020</th>\n",
+       "      <th>destination_cty_2020</th>\n",
+       "      <th>trip_taker_work_bgrp_2020</th>\n",
+       "      <th>destination_trct_2020</th>\n",
+       "      <th>trip_taker_household_income</th>\n",
+       "      <th>origin_bgrp_2020</th>\n",
+       "      <th>trip_taker_commute_mode</th>\n",
+       "      <th>trip_taker_available_vehicles</th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>previous_trip_purpose</th>\n",
+       "      <th>trip_taker_building_type</th>\n",
+       "      <th>transit_submode</th>\n",
+       "      <th>trip_taker_work_st_2020</th>\n",
+       "      <th>trip_taker_household_size</th>\n",
+       "      <th>origin_cty_2020</th>\n",
+       "      <th>destination_land_use</th>\n",
+       "      <th>trip_taker_industry</th>\n",
+       "      <th>trip_taker_tenure</th>\n",
+       "      <th>vehicle_fuel_type</th>\n",
+       "      <th>trip_taker_home_trct_2020</th>\n",
+       "      <th>trip_taker_work_trct_2020</th>\n",
+       "      <th>trip_taker_education</th>\n",
+       "      <th>trip_start_time</th>\n",
+       "      <th>trip_taker_individual_income</th>\n",
+       "      <th>trip_taker_employment_status</th>\n",
+       "      <th>trip_purpose</th>\n",
+       "      <th>origin_land_use</th>\n",
+       "      <th>trip_taker_work_cty_2020</th>\n",
+       "      <th>trip_distance_miles</th>\n",
+       "      <th>trip_taker_school_grade_attending</th>\n",
+       "      <th>trip_taker_home_cty_2020</th>\n",
+       "      <th>trip_taker_person_id</th>\n",
+       "      <th>trip_end_time</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>594856</th>\n",
+       "      <td>single_family</td>\n",
+       "      <td>11</td>\n",
+       "      <td>indo_european</td>\n",
+       "      <td>179.03 (San Francisco, CA)</td>\n",
+       "      <td>8194219563640751815</td>\n",
+       "      <td>male</td>\n",
+       "      <td>1 (Tract 179.03, San Francisco, CA)</td>\n",
+       "      <td>California</td>\n",
+       "      <td>California</td>\n",
+       "      <td>white_not_hispanic_or_latino</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>core</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>27.0</td>\n",
+       "      <td>7878347104837895638</td>\n",
+       "      <td>3 (Tract 615.06, San Francisco, CA)</td>\n",
+       "      <td>retail</td>\n",
+       "      <td>remote</td>\n",
+       "      <td>California</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>1 (Tract 179.03, San Francisco, CA)</td>\n",
+       "      <td>615.06 (San Francisco, CA)</td>\n",
+       "      <td>1200990.0</td>\n",
+       "      <td>1 (Tract 179.03, San Francisco, CA)</td>\n",
+       "      <td>worked_from_home</td>\n",
+       "      <td>three_plus</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>home</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>California</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>mixed_use</td>\n",
+       "      <td>naics54</td>\n",
+       "      <td>renter</td>\n",
+       "      <td>other_non_bev</td>\n",
+       "      <td>179.03 (San Francisco, CA)</td>\n",
+       "      <td>179.03 (San Francisco, CA)</td>\n",
+       "      <td>bachelors_degree</td>\n",
+       "      <td>11:44:00</td>\n",
+       "      <td>218735.0</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>shop</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>14409692340574959811</td>\n",
+       "      <td>11:55:07</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       origin_building_use  trip_duration_minutes trip_taker_language  \\\n",
+       "594856       single_family                     11       indo_european   \n",
+       "\n",
+       "                  origin_trct_2020 trip_taker_household_id trip_taker_sex  \\\n",
+       "594856  179.03 (San Francisco, CA)     8194219563640751815           male   \n",
+       "\n",
+       "                  trip_taker_home_bgrp_2020 origin_st_2020  \\\n",
+       "594856  1 (Tract 179.03, San Francisco, CA)     California   \n",
+       "\n",
+       "       trip_taker_home_st_2020     trip_taker_race_ethnicity transit_agency  \\\n",
+       "594856              California  white_not_hispanic_or_latino            NaN   \n",
+       "\n",
+       "       transit_route trip_taker_resident_type          vehicle_type  \\\n",
+       "594856           NaN                     core  unknown_vehicle_type   \n",
+       "\n",
+       "        trip_taker_age          activity_id  \\\n",
+       "594856            27.0  7878347104837895638   \n",
+       "\n",
+       "                      destination_bgrp_2020 destination_building_use  \\\n",
+       "594856  3 (Tract 615.06, San Francisco, CA)                   retail   \n",
+       "\n",
+       "       trip_taker_wfh destination_st_2020 destination_cty_2020  \\\n",
+       "594856         remote          California        San Francisco   \n",
+       "\n",
+       "                  trip_taker_work_bgrp_2020       destination_trct_2020  \\\n",
+       "594856  1 (Tract 179.03, San Francisco, CA)  615.06 (San Francisco, CA)   \n",
+       "\n",
+       "        trip_taker_household_income                     origin_bgrp_2020  \\\n",
+       "594856                    1200990.0  1 (Tract 179.03, San Francisco, CA)   \n",
+       "\n",
+       "       trip_taker_commute_mode trip_taker_available_vehicles  primary_mode  \\\n",
+       "594856        worked_from_home                    three_plus  private_auto   \n",
+       "\n",
+       "       previous_trip_purpose trip_taker_building_type transit_submode  \\\n",
+       "594856                  home            single_family             NaN   \n",
+       "\n",
+       "       trip_taker_work_st_2020  trip_taker_household_size origin_cty_2020  \\\n",
+       "594856              California                       10.0   San Francisco   \n",
+       "\n",
+       "       destination_land_use trip_taker_industry trip_taker_tenure  \\\n",
+       "594856            mixed_use             naics54            renter   \n",
+       "\n",
+       "       vehicle_fuel_type   trip_taker_home_trct_2020  \\\n",
+       "594856     other_non_bev  179.03 (San Francisco, CA)   \n",
+       "\n",
+       "         trip_taker_work_trct_2020 trip_taker_education trip_start_time  \\\n",
+       "594856  179.03 (San Francisco, CA)     bachelors_degree        11:44:00   \n",
+       "\n",
+       "        trip_taker_individual_income trip_taker_employment_status  \\\n",
+       "594856                      218735.0                     employed   \n",
+       "\n",
+       "       trip_purpose origin_land_use trip_taker_work_cty_2020  \\\n",
+       "594856         shop   single_family            San Francisco   \n",
+       "\n",
+       "        trip_distance_miles trip_taker_school_grade_attending  \\\n",
+       "594856                  4.0              not_attending_school   \n",
+       "\n",
+       "       trip_taker_home_cty_2020  trip_taker_person_id trip_end_time  \n",
+       "594856            San Francisco  14409692340574959811      11:55:07  "
+      ]
+     },
+     "execution_count": 61,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "print(len(r_trips>>filter(_.trip_taker_household_id == 8194219563640751815)))\n",
+    "(r_trips>>filter(_.trip_taker_household_id == 8194219563640751815)).sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "4eccfdf8-429e-43df-899e-f7d77e051831",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>trip_taker_person_id</th>\n",
+       "      <th>trip_taker_age</th>\n",
+       "      <th>trip_taker_sex</th>\n",
+       "      <th>trip_taker_household_size</th>\n",
+       "      <th>n</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1325181746552868554</td>\n",
+       "      <td>22.0</td>\n",
+       "      <td>female</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2310331066900902679</td>\n",
+       "      <td>30.0</td>\n",
+       "      <td>female</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>4746831412975349070</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>female</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>10066255028734967962</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>male</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>11058477761487230854</td>\n",
+       "      <td>32.0</td>\n",
+       "      <td>male</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>12894946300265742193</td>\n",
+       "      <td>39.0</td>\n",
+       "      <td>male</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>14409692340574959811</td>\n",
+       "      <td>27.0</td>\n",
+       "      <td>male</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   trip_taker_person_id  trip_taker_age trip_taker_sex  \\\n",
+       "0   1325181746552868554            22.0         female   \n",
+       "1   2310331066900902679            30.0         female   \n",
+       "2   4746831412975349070            34.0         female   \n",
+       "3  10066255028734967962            28.0           male   \n",
+       "4  11058477761487230854            32.0           male   \n",
+       "5  12894946300265742193            39.0           male   \n",
+       "6  14409692340574959811            27.0           male   \n",
+       "\n",
+       "   trip_taker_household_size  n  \n",
+       "0                       10.0  6  \n",
+       "1                       10.0  6  \n",
+       "2                       10.0  2  \n",
+       "3                       10.0  4  \n",
+       "4                       10.0  2  \n",
+       "5                       10.0  2  \n",
+       "6                       10.0  6  "
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "## checking one household id\n",
+    "r_trips>>filter(_.trip_taker_household_id == 8194219563640751815)>>count(_.trip_taker_person_id, _.trip_taker_age,\n",
+    "                                                                         _.trip_taker_sex, _.trip_taker_household_size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c929c77d-0173-4a7d-be49-762349daf5cb",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ab226b47-4366-4fb9-aaae-e0aca760f9b3",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cd041141-2a65-45e8-a6ba-9b41cbffecbd",
+   "metadata": {},
+   "source": [
+    "#### Adding in Replica's People Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "dea31a60-e986-41e7-b31b-1e5403c9e041",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_483/1951040339.py:1: DtypeWarning: Columns (25) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+      "  r_ppl = to_snakecase(pd.read_csv(f\"{GCS_PATH}{replica_ppl}\"))\n"
+     ]
+    }
+   ],
+   "source": [
+    "r_ppl = to_snakecase(pd.read_csv(f\"{GCS_PATH}{replica_ppl}\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2cf7ed4b-7524-4e9a-858a-857fcf70950c",
+   "metadata": {},
+   "source": [
+    "replica people dataframe sample"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "42bc1220-b404-4aca-8214-43992c55163b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>person_id</th>\n",
+       "      <th>work_st_2020</th>\n",
+       "      <th>household_income</th>\n",
+       "      <th>resident_type</th>\n",
+       "      <th>language</th>\n",
+       "      <th>available_vehicles</th>\n",
+       "      <th>race_ethnicity</th>\n",
+       "      <th>education</th>\n",
+       "      <th>work_bgrp_2020</th>\n",
+       "      <th>wfh</th>\n",
+       "      <th>home_cty_2020</th>\n",
+       "      <th>home_trct_2020</th>\n",
+       "      <th>tenure</th>\n",
+       "      <th>industry</th>\n",
+       "      <th>work_trct_2020</th>\n",
+       "      <th>school_grade_attending</th>\n",
+       "      <th>building_type</th>\n",
+       "      <th>commute_mode</th>\n",
+       "      <th>employment_status</th>\n",
+       "      <th>work_cty_2020</th>\n",
+       "      <th>individual_income</th>\n",
+       "      <th>home_st_2020</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>household_size</th>\n",
+       "      <th>home_bgrp_2020</th>\n",
+       "      <th>household_id</th>\n",
+       "      <th>age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>237204</th>\n",
+       "      <td>16410964223051134474</td>\n",
+       "      <td>California</td>\n",
+       "      <td>120704.0</td>\n",
+       "      <td>core</td>\n",
+       "      <td>english</td>\n",
+       "      <td>three_plus</td>\n",
+       "      <td>white_not_hispanic_or_latino</td>\n",
+       "      <td>some_college</td>\n",
+       "      <td>3 (Tract 3211.01, Contra Costa, CA)</td>\n",
+       "      <td>employed_not_working</td>\n",
+       "      <td>Contra Costa</td>\n",
+       "      <td>3211.01 (Contra Costa, CA)</td>\n",
+       "      <td>owner</td>\n",
+       "      <td>naics812910</td>\n",
+       "      <td>3211.01 (Contra Costa, CA)</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>Contra Costa</td>\n",
+       "      <td>33528.0</td>\n",
+       "      <td>California</td>\n",
+       "      <td>male</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>4 (Tract 3211.01, Contra Costa, CA)</td>\n",
+       "      <td>503623235255197327</td>\n",
+       "      <td>30.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   person_id work_st_2020  household_income resident_type  \\\n",
+       "237204  16410964223051134474   California          120704.0          core   \n",
+       "\n",
+       "       language available_vehicles                race_ethnicity  \\\n",
+       "237204  english         three_plus  white_not_hispanic_or_latino   \n",
+       "\n",
+       "           education                       work_bgrp_2020  \\\n",
+       "237204  some_college  3 (Tract 3211.01, Contra Costa, CA)   \n",
+       "\n",
+       "                         wfh home_cty_2020              home_trct_2020 tenure  \\\n",
+       "237204  employed_not_working  Contra Costa  3211.01 (Contra Costa, CA)  owner   \n",
+       "\n",
+       "           industry              work_trct_2020 school_grade_attending  \\\n",
+       "237204  naics812910  3211.01 (Contra Costa, CA)   not_attending_school   \n",
+       "\n",
+       "        building_type  commute_mode employment_status work_cty_2020  \\\n",
+       "237204  single_family  private_auto          employed  Contra Costa   \n",
+       "\n",
+       "        individual_income home_st_2020   sex  household_size  \\\n",
+       "237204            33528.0   California  male             4.0   \n",
+       "\n",
+       "                             home_bgrp_2020        household_id   age  \n",
+       "237204  4 (Tract 3211.01, Contra Costa, CA)  503623235255197327  30.0  "
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_ppl.sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "id": "d2a1647f-ed67-4c33-a089-b72375323a7d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Number of Travelers by Resident Type: Replica People Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Number of Travelers by Resident Type: Replica People Data</strong></h4>\")) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "570daf6d-06b8-46e5-9664-a71c5a093073",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>resident_type</th>\n",
+       "      <th>_unique_ids</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>core</td>\n",
+       "      <td>278158</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>visitor</td>\n",
+       "      <td>23034</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  resident_type  _unique_ids\n",
+       "0          core       278158\n",
+       "1       visitor        23034"
+      ]
+     },
+     "execution_count": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_ppl>>group_by(_.resident_type)>>summarize(_unique_ids = _.person_id.nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "1483249f-602c-4805-bcc4-d55e018022ad",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Number of Travelers by Resident Type: Replica Trips Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Number of Travelers by Resident Type: Replica Trips Data</strong></h4>\")) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "5c1894f0-bd42-4014-89d4-6e8d43809319",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>trip_taker_resident_type</th>\n",
+       "      <th>_unique_ids</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>core</td>\n",
+       "      <td>282789</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>visitor</td>\n",
+       "      <td>26806</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  trip_taker_resident_type  _unique_ids\n",
+       "0                     core       282789\n",
+       "1                  visitor        26806\n",
+       "2                      NaN            1"
+      ]
+     },
+     "execution_count": 68,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips>>group_by(_.trip_taker_resident_type)>>summarize(_unique_ids = _.trip_taker_person_id.nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "id": "2f4b67bf-78ab-4aa8-bbb0-e382a8f78c9a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Traveler Demographics: Replica People Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Fitered for Core Residents"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>commute_mode</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>n_ppl</th>\n",
+       "      <th>avg_h_income</th>\n",
+       "      <th>avg_p_income</th>\n",
+       "      <th>avg_age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>female</td>\n",
+       "      <td>10908</td>\n",
+       "      <td>175717.982765</td>\n",
+       "      <td>70255.626054</td>\n",
+       "      <td>42.234507</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>male</td>\n",
+       "      <td>11605</td>\n",
+       "      <td>177241.394916</td>\n",
+       "      <td>82072.291685</td>\n",
+       "      <td>42.185523</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>biking</td>\n",
+       "      <td>female</td>\n",
+       "      <td>234</td>\n",
+       "      <td>248565.141026</td>\n",
+       "      <td>82592.418803</td>\n",
+       "      <td>36.085470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>biking</td>\n",
+       "      <td>male</td>\n",
+       "      <td>527</td>\n",
+       "      <td>219563.083491</td>\n",
+       "      <td>120152.859583</td>\n",
+       "      <td>38.426945</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>other_travel_mode</td>\n",
+       "      <td>female</td>\n",
+       "      <td>36176</td>\n",
+       "      <td>126129.721003</td>\n",
+       "      <td>21413.682939</td>\n",
+       "      <td>55.161599</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>other_travel_mode</td>\n",
+       "      <td>male</td>\n",
+       "      <td>26290</td>\n",
+       "      <td>116775.549106</td>\n",
+       "      <td>33563.078813</td>\n",
+       "      <td>54.328262</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>female</td>\n",
+       "      <td>45312</td>\n",
+       "      <td>186499.659406</td>\n",
+       "      <td>76492.005341</td>\n",
+       "      <td>42.626302</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>male</td>\n",
+       "      <td>59762</td>\n",
+       "      <td>190643.201265</td>\n",
+       "      <td>100712.386918</td>\n",
+       "      <td>42.872093</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>female</td>\n",
+       "      <td>22008</td>\n",
+       "      <td>193540.921347</td>\n",
+       "      <td>84074.072110</td>\n",
+       "      <td>41.921937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>male</td>\n",
+       "      <td>26480</td>\n",
+       "      <td>207838.001699</td>\n",
+       "      <td>125445.942485</td>\n",
+       "      <td>42.259290</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>walking</td>\n",
+       "      <td>female</td>\n",
+       "      <td>1332</td>\n",
+       "      <td>160144.725976</td>\n",
+       "      <td>63737.956456</td>\n",
+       "      <td>38.041291</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>walking</td>\n",
+       "      <td>male</td>\n",
+       "      <td>1494</td>\n",
+       "      <td>177570.705489</td>\n",
+       "      <td>100413.455154</td>\n",
+       "      <td>37.495315</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>worked_from_home</td>\n",
+       "      <td>female</td>\n",
+       "      <td>17409</td>\n",
+       "      <td>226232.999655</td>\n",
+       "      <td>97016.438853</td>\n",
+       "      <td>41.219829</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>worked_from_home</td>\n",
+       "      <td>male</td>\n",
+       "      <td>18621</td>\n",
+       "      <td>253921.717631</td>\n",
+       "      <td>137849.973686</td>\n",
+       "      <td>41.092208</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         commute_mode     sex  n_ppl   avg_h_income   avg_p_income    avg_age\n",
+       "0      auto_passenger  female  10908  175717.982765   70255.626054  42.234507\n",
+       "1      auto_passenger    male  11605  177241.394916   82072.291685  42.185523\n",
+       "2              biking  female    234  248565.141026   82592.418803  36.085470\n",
+       "3              biking    male    527  219563.083491  120152.859583  38.426945\n",
+       "4   other_travel_mode  female  36176  126129.721003   21413.682939  55.161599\n",
+       "5   other_travel_mode    male  26290  116775.549106   33563.078813  54.328262\n",
+       "6        private_auto  female  45312  186499.659406   76492.005341  42.626302\n",
+       "7        private_auto    male  59762  190643.201265  100712.386918  42.872093\n",
+       "8      public_transit  female  22008  193540.921347   84074.072110  41.921937\n",
+       "9      public_transit    male  26480  207838.001699  125445.942485  42.259290\n",
+       "10            walking  female   1332  160144.725976   63737.956456  38.041291\n",
+       "11            walking    male   1494  177570.705489  100413.455154  37.495315\n",
+       "12   worked_from_home  female  17409  226232.999655   97016.438853  41.219829\n",
+       "13   worked_from_home    male  18621  253921.717631  137849.973686  41.092208"
+      ]
+     },
+     "execution_count": 69,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Traveler Demographics: Replica People Data</strong></h4>\")) \n",
+    "display(HTML(\"Fitered for Core Residents\")) \n",
+    "(r_ppl\n",
+    " >>filter(_.home_bgrp_2020!=\"Visitor (no home location)\")\n",
+    " >>group_by(_.commute_mode, _.sex)\n",
+    " >>summarize(\n",
+    "     n_ppl = _.person_id.nunique(),\n",
+    "     avg_h_income = _.household_income.mean(),\n",
+    "     avg_p_income = _.individual_income.mean(),\n",
+    "     avg_age = _.age.mean())\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b0891b62-c968-4ea0-bd9b-753d299a5054",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "id": "2e4bd058-9c4d-4989-a5fc-db6cf6130bf2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Traveler Demographics: Replica Trips Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Fitered for Core Residents"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>trip_taker_sex</th>\n",
+       "      <th>n_ppl</th>\n",
+       "      <th>avg_h_income</th>\n",
+       "      <th>avg_p_income</th>\n",
+       "      <th>avg_age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>female</td>\n",
+       "      <td>99350</td>\n",
+       "      <td>173666.662228</td>\n",
+       "      <td>65104.398490</td>\n",
+       "      <td>45.064633</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>male</td>\n",
+       "      <td>105359</td>\n",
+       "      <td>187590.985442</td>\n",
+       "      <td>97296.509379</td>\n",
+       "      <td>43.991868</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>commercial</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>on_demand_auto</td>\n",
+       "      <td>female</td>\n",
+       "      <td>9051</td>\n",
+       "      <td>186226.833189</td>\n",
+       "      <td>79990.395102</td>\n",
+       "      <td>42.900399</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>on_demand_auto</td>\n",
+       "      <td>male</td>\n",
+       "      <td>10159</td>\n",
+       "      <td>202467.780725</td>\n",
+       "      <td>111915.392968</td>\n",
+       "      <td>42.436605</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>female</td>\n",
+       "      <td>68268</td>\n",
+       "      <td>174867.937251</td>\n",
+       "      <td>62299.064752</td>\n",
+       "      <td>45.316785</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>male</td>\n",
+       "      <td>75223</td>\n",
+       "      <td>182301.952228</td>\n",
+       "      <td>90322.373466</td>\n",
+       "      <td>44.265320</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>female</td>\n",
+       "      <td>2256</td>\n",
+       "      <td>186720.499643</td>\n",
+       "      <td>82496.554922</td>\n",
+       "      <td>39.104494</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>male</td>\n",
+       "      <td>2535</td>\n",
+       "      <td>205334.441232</td>\n",
+       "      <td>114041.914833</td>\n",
+       "      <td>38.312382</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     primary_mode trip_taker_sex   n_ppl   avg_h_income   avg_p_income  \\\n",
+       "0  auto_passenger         female   99350  173666.662228   65104.398490   \n",
+       "1  auto_passenger           male  105359  187590.985442   97296.509379   \n",
+       "2      commercial            NaN       1            NaN            NaN   \n",
+       "3  on_demand_auto         female    9051  186226.833189   79990.395102   \n",
+       "4  on_demand_auto           male   10159  202467.780725  111915.392968   \n",
+       "5    private_auto         female   68268  174867.937251   62299.064752   \n",
+       "6    private_auto           male   75223  182301.952228   90322.373466   \n",
+       "7  public_transit         female    2256  186720.499643   82496.554922   \n",
+       "8  public_transit           male    2535  205334.441232  114041.914833   \n",
+       "\n",
+       "     avg_age  \n",
+       "0  45.064633  \n",
+       "1  43.991868  \n",
+       "2        NaN  \n",
+       "3  42.900399  \n",
+       "4  42.436605  \n",
+       "5  45.316785  \n",
+       "6  44.265320  \n",
+       "7  39.104494  \n",
+       "8  38.312382  "
+      ]
+     },
+     "execution_count": 70,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Traveler Demographics: Replica Trips Data</strong></h4>\")) \n",
+    "display(HTML(\"Fitered for Core Residents\")) \n",
+    "(r_trips\n",
+    " >>filter(_.trip_taker_home_bgrp_2020!=\"Visitor (no home location)\")\n",
+    " >>group_by(_.primary_mode, _.trip_taker_sex)\n",
+    " >>summarize(\n",
+    "     n_ppl = _.trip_taker_person_id.nunique(),\n",
+    "     avg_h_income = _.trip_taker_household_income.mean(),\n",
+    "     avg_p_income = _.trip_taker_individual_income.mean(),\n",
+    "     avg_age = _.trip_taker_age.mean())\n",
+    ")\n",
+    "     "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "id": "7b637cdd-9560-4d31-bfeb-bffa6cbb55d2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "replica_people_demographics = (r_ppl\n",
+    " >>group_by(_.commute_mode, _.sex)\n",
+    " >>summarize(\n",
+    "     n_ppl = _.person_id.nunique(),\n",
+    "     avg_h_income = _.household_income.mean(),\n",
+    "     avg_p_income = _.individual_income.mean(),\n",
+    "     avg_age = _.age.mean())\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "bcaa0855-faf6-4eb0-aa8e-48cb3348baeb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>commute_mode</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>n_ppl</th>\n",
+       "      <th>avg_h_income</th>\n",
+       "      <th>avg_p_income</th>\n",
+       "      <th>avg_age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>female</td>\n",
+       "      <td>10908</td>\n",
+       "      <td>175717.982765</td>\n",
+       "      <td>70255.626054</td>\n",
+       "      <td>42.234507</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>male</td>\n",
+       "      <td>11605</td>\n",
+       "      <td>177241.394916</td>\n",
+       "      <td>82072.291685</td>\n",
+       "      <td>42.185523</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>biking</td>\n",
+       "      <td>female</td>\n",
+       "      <td>234</td>\n",
+       "      <td>248565.141026</td>\n",
+       "      <td>82592.418803</td>\n",
+       "      <td>36.085470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>biking</td>\n",
+       "      <td>male</td>\n",
+       "      <td>527</td>\n",
+       "      <td>219563.083491</td>\n",
+       "      <td>120152.859583</td>\n",
+       "      <td>38.426945</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>other_travel_mode</td>\n",
+       "      <td>female</td>\n",
+       "      <td>36176</td>\n",
+       "      <td>126129.721003</td>\n",
+       "      <td>21413.682939</td>\n",
+       "      <td>55.161599</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>other_travel_mode</td>\n",
+       "      <td>male</td>\n",
+       "      <td>26290</td>\n",
+       "      <td>116775.549106</td>\n",
+       "      <td>33563.078813</td>\n",
+       "      <td>54.328262</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>female</td>\n",
+       "      <td>45312</td>\n",
+       "      <td>186499.659406</td>\n",
+       "      <td>76492.005341</td>\n",
+       "      <td>42.626302</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>male</td>\n",
+       "      <td>59762</td>\n",
+       "      <td>190643.201265</td>\n",
+       "      <td>100712.386918</td>\n",
+       "      <td>42.872093</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>female</td>\n",
+       "      <td>22008</td>\n",
+       "      <td>193540.921347</td>\n",
+       "      <td>84074.072110</td>\n",
+       "      <td>41.921937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>male</td>\n",
+       "      <td>26480</td>\n",
+       "      <td>207838.001699</td>\n",
+       "      <td>125445.942485</td>\n",
+       "      <td>42.259290</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>walking</td>\n",
+       "      <td>female</td>\n",
+       "      <td>1332</td>\n",
+       "      <td>160144.725976</td>\n",
+       "      <td>63737.956456</td>\n",
+       "      <td>38.041291</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>walking</td>\n",
+       "      <td>male</td>\n",
+       "      <td>1494</td>\n",
+       "      <td>177570.705489</td>\n",
+       "      <td>100413.455154</td>\n",
+       "      <td>37.495315</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>worked_from_home</td>\n",
+       "      <td>female</td>\n",
+       "      <td>17409</td>\n",
+       "      <td>226232.999655</td>\n",
+       "      <td>97016.438853</td>\n",
+       "      <td>41.219829</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>worked_from_home</td>\n",
+       "      <td>male</td>\n",
+       "      <td>18621</td>\n",
+       "      <td>253921.717631</td>\n",
+       "      <td>137849.973686</td>\n",
+       "      <td>41.092208</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>23034</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         commute_mode     sex  n_ppl   avg_h_income   avg_p_income    avg_age\n",
+       "0      auto_passenger  female  10908  175717.982765   70255.626054  42.234507\n",
+       "1      auto_passenger    male  11605  177241.394916   82072.291685  42.185523\n",
+       "2              biking  female    234  248565.141026   82592.418803  36.085470\n",
+       "3              biking    male    527  219563.083491  120152.859583  38.426945\n",
+       "4   other_travel_mode  female  36176  126129.721003   21413.682939  55.161599\n",
+       "5   other_travel_mode    male  26290  116775.549106   33563.078813  54.328262\n",
+       "6        private_auto  female  45312  186499.659406   76492.005341  42.626302\n",
+       "7        private_auto    male  59762  190643.201265  100712.386918  42.872093\n",
+       "8      public_transit  female  22008  193540.921347   84074.072110  41.921937\n",
+       "9      public_transit    male  26480  207838.001699  125445.942485  42.259290\n",
+       "10            walking  female   1332  160144.725976   63737.956456  38.041291\n",
+       "11            walking    male   1494  177570.705489  100413.455154  37.495315\n",
+       "12   worked_from_home  female  17409  226232.999655   97016.438853  41.219829\n",
+       "13   worked_from_home    male  18621  253921.717631  137849.973686  41.092208\n",
+       "14                NaN     NaN  23034            NaN            NaN        NaN"
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "replica_people_demographics"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "id": "7f7c1066-c820-43d3-a68e-0dcdfc1dcdce",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-e495255148bd47c6bddc038286c78deb.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-e495255148bd47c6bddc038286c78deb.vega-embed details,\n",
+       "  #altair-viz-e495255148bd47c6bddc038286c78deb.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-e495255148bd47c6bddc038286c78deb\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-e495255148bd47c6bddc038286c78deb\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-e495255148bd47c6bddc038286c78deb\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-560f52f1a3d2154b0ba88a73dfa51e3d\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"commute_mode\", \"scale\": {\"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"commute_mode\", \"type\": \"nominal\"}, {\"field\": \"sex\", \"type\": \"nominal\"}, {\"field\": \"n_ppl\", \"type\": \"quantitative\"}, {\"field\": \"avg_h_income\", \"type\": \"quantitative\"}, {\"field\": \"avg_p_income\", \"type\": \"quantitative\"}, {\"field\": \"avg_age\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"commute_mode\", \"title\": \"Mode\", \"type\": \"nominal\"}, \"y\": {\"field\": \"n_ppl\", \"title\": \"Number of People\", \"type\": \"quantitative\"}}, \"height\": 500, \"title\": \"Trips by Resident Type\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-560f52f1a3d2154b0ba88a73dfa51e3d\": [{\"commute_mode\": \"auto_passenger\", \"sex\": \"female\", \"n_ppl\": 10908, \"avg_h_income\": 175717.98276494315, \"avg_p_income\": 70255.6260542721, \"avg_age\": 42.234506784011735}, {\"commute_mode\": \"auto_passenger\", \"sex\": \"male\", \"n_ppl\": 11605, \"avg_h_income\": 177241.39491598448, \"avg_p_income\": 82072.2916846187, \"avg_age\": 42.18552348125808}, {\"commute_mode\": \"biking\", \"sex\": \"female\", \"n_ppl\": 234, \"avg_h_income\": 248565.14102564103, \"avg_p_income\": 82592.4188034188, \"avg_age\": 36.085470085470085}, {\"commute_mode\": \"biking\", \"sex\": \"male\", \"n_ppl\": 527, \"avg_h_income\": 219563.0834914611, \"avg_p_income\": 120152.85958254269, \"avg_age\": 38.426944971537004}, {\"commute_mode\": \"other_travel_mode\", \"sex\": \"female\", \"n_ppl\": 36176, \"avg_h_income\": 126129.72100287484, \"avg_p_income\": 21413.68293896506, \"avg_age\": 55.16159885006634}, {\"commute_mode\": \"other_travel_mode\", \"sex\": \"male\", \"n_ppl\": 26290, \"avg_h_income\": 116775.549106124, \"avg_p_income\": 33563.07881323697, \"avg_age\": 54.32826169646253}, {\"commute_mode\": \"private_auto\", \"sex\": \"female\", \"n_ppl\": 45312, \"avg_h_income\": 186499.6594058969, \"avg_p_income\": 76492.00534074858, \"avg_age\": 42.626302083333336}, {\"commute_mode\": \"private_auto\", \"sex\": \"male\", \"n_ppl\": 59762, \"avg_h_income\": 190643.2012650179, \"avg_p_income\": 100712.3869181085, \"avg_age\": 42.872092634115326}, {\"commute_mode\": \"public_transit\", \"sex\": \"female\", \"n_ppl\": 22008, \"avg_h_income\": 193540.921346783, \"avg_p_income\": 84074.07211014177, \"avg_age\": 41.92193747728099}, {\"commute_mode\": \"public_transit\", \"sex\": \"male\", \"n_ppl\": 26480, \"avg_h_income\": 207838.00169939577, \"avg_p_income\": 125445.94248489426, \"avg_age\": 42.25929003021148}, {\"commute_mode\": \"walking\", \"sex\": \"female\", \"n_ppl\": 1332, \"avg_h_income\": 160144.72597597598, \"avg_p_income\": 63737.95645645646, \"avg_age\": 38.041291291291294}, {\"commute_mode\": \"walking\", \"sex\": \"male\", \"n_ppl\": 1494, \"avg_h_income\": 177570.70548862114, \"avg_p_income\": 100413.45515394914, \"avg_age\": 37.49531459170014}, {\"commute_mode\": \"worked_from_home\", \"sex\": \"female\", \"n_ppl\": 17409, \"avg_h_income\": 226232.9996553507, \"avg_p_income\": 97016.43885346659, \"avg_age\": 41.21982882417141}, {\"commute_mode\": \"worked_from_home\", \"sex\": \"male\", \"n_ppl\": 18621, \"avg_h_income\": 253921.71763063208, \"avg_p_income\": 137849.97368562376, \"avg_age\": 41.09220772246388}, {\"commute_mode\": null, \"sex\": null, \"n_ppl\": 23034, \"avg_h_income\": null, \"avg_p_income\": null, \"avg_age\": null}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 73,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(replica_people_demographics)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"commute_mode\", title = \"Mode\"),\n",
+    "            y=alt.Y(\"n_ppl\", title = \"Number of People\"),\n",
+    "            color=alt.Color(\"commute_mode\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS)),\n",
+    "            tooltip=replica_people_demographics.columns.tolist())\n",
+    "      .properties(title = \"Trips by Resident Type\",\n",
+    "    width=800,\n",
+    "    height=500)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a1dba8b5-7356-441f-8e6c-0f98e0f80c4c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "97f56b20-f299-43f5-bad4-2a42362962e2",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### Read in Streetlight Data: 2022"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "6f3cf136-7531-4b62-b050-169b7bd1c4ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "streetlight = \"streetlight_bay_bridge_corridor_study_corridor_study.csv\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "id": "47943ff0-2949-409b-a9ad-ca5efea3b52d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sl_data = to_snakecase(pd.read_csv(f\"{GCS_PATH}{streetlight}\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "id": "28fc95f8-5898-486f-81f3-f0ac7885431c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Streetlight Data Sample</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Streetlight Data Sample</strong></h4>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "id": "3398c3fa-856d-49a0-8d2d-7994f3f50df1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>data_periods</th>\n",
+       "      <th>mode_of_travel</th>\n",
+       "      <th>zone_id</th>\n",
+       "      <th>zone_name</th>\n",
+       "      <th>road_classification</th>\n",
+       "      <th>line_zone_length__miles_</th>\n",
+       "      <th>zone_is_pass_through</th>\n",
+       "      <th>zone_direction__degrees_</th>\n",
+       "      <th>zone_cardinal_direction</th>\n",
+       "      <th>zone_is_bi_direction</th>\n",
+       "      <th>day_type</th>\n",
+       "      <th>day_part</th>\n",
+       "      <th>average_daily_segment_traffic__stl_volume_</th>\n",
+       "      <th>avg_segment_speed__mph_</th>\n",
+       "      <th>avg_segment_travel_time__sec_</th>\n",
+       "      <th>free_flow_speed__mph_</th>\n",
+       "      <th>vehicle_miles_of_travel__stl_volume_</th>\n",
+       "      <th>travel_time_index</th>\n",
+       "      <th>congested_segment</th>\n",
+       "      <th>_85th_speed_percentile</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1411</th>\n",
+       "      <td>Jan 01, 2022 - Dec 31, 2022</td>\n",
+       "      <td>All Vehicles CVD Plus - StL All Vehicles Volume</td>\n",
+       "      <td>1130705657</td>\n",
+       "      <td>San Francisco – Oakland Bay Bridge / 52527662 / 1</td>\n",
+       "      <td>Motorway</td>\n",
+       "      <td>0.104</td>\n",
+       "      <td>yes</td>\n",
+       "      <td>40</td>\n",
+       "      <td>EAST</td>\n",
+       "      <td>no</td>\n",
+       "      <td>2: Weekend Day (Sa-Su)</td>\n",
+       "      <td>01: 12am (12am-1am)</td>\n",
+       "      <td>3029</td>\n",
+       "      <td>61</td>\n",
+       "      <td>7</td>\n",
+       "      <td>65.986</td>\n",
+       "      <td>314.44</td>\n",
+       "      <td>1.08</td>\n",
+       "      <td>False</td>\n",
+       "      <td>70</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     data_periods  \\\n",
+       "1411  Jan 01, 2022 - Dec 31, 2022   \n",
+       "\n",
+       "                                       mode_of_travel     zone_id  \\\n",
+       "1411  All Vehicles CVD Plus - StL All Vehicles Volume  1130705657   \n",
+       "\n",
+       "                                              zone_name road_classification  \\\n",
+       "1411  San Francisco – Oakland Bay Bridge / 52527662 / 1            Motorway   \n",
+       "\n",
+       "      line_zone_length__miles_ zone_is_pass_through  zone_direction__degrees_  \\\n",
+       "1411                     0.104                  yes                        40   \n",
+       "\n",
+       "     zone_cardinal_direction zone_is_bi_direction                day_type  \\\n",
+       "1411                    EAST                   no  2: Weekend Day (Sa-Su)   \n",
+       "\n",
+       "                 day_part  average_daily_segment_traffic__stl_volume_  \\\n",
+       "1411  01: 12am (12am-1am)                                        3029   \n",
+       "\n",
+       "      avg_segment_speed__mph_  avg_segment_travel_time__sec_  \\\n",
+       "1411                       61                              7   \n",
+       "\n",
+       "      free_flow_speed__mph_  vehicle_miles_of_travel__stl_volume_  \\\n",
+       "1411                 65.986                                314.44   \n",
+       "\n",
+       "      travel_time_index  congested_segment  _85th_speed_percentile  \n",
+       "1411               1.08              False                      70  "
+      ]
+     },
+     "execution_count": 77,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sl_data.sample()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a3d1c17-1d5b-4ddf-aac3-78b8156ceca4",
+   "metadata": {},
+   "source": [
+    "#### Data Explorations: Streetlight"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 78,
+   "id": "da10c3eb-31bd-437e-b546-82472d66f964",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<strong>Length of the Streetlight Data</strong>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "1710"
+      ]
+     },
+     "execution_count": 78,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<strong>Length of the Streetlight Data</strong>\")) \n",
+    "\n",
+    "len(sl_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "id": "5e403ce9-33bc-4453-9323-df46fad1f38a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sl_data>>count(_.zone_id, _.zone_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 80,
+   "id": "cd1ce590-2019-43f0-ba09-786520479ad8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>day_part</th>\n",
+       "      <th>n</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>00: All Day (12am-12am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>01: 12am (12am-1am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>02: Early AM (12am-6am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>03: 1am (1am-2am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>04: 2am (2am-3am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>05: 3am (3am-4am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>06: 4am (4am-5am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>07: 5am (5am-6am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>08: 6am (6am-7am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>09: Peak AM (6am-10am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>10: 7am (7am-8am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>11: 8am (8am-9am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>12: 9am (9am-10am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>13: 10am (10am-11am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>14: Mid-Day (10am-4pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>15: 11am (11am-12noon)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>16: 12pm (12noon-1pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>17: 1pm (1pm-2pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>18: 2pm (2pm-3pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>19: 3pm (3pm-4pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>20: 4pm (4pm-5pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>21: Peak PM (4pm-8pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>22: 5pm (5pm-6pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>23: 6pm (6pm-7pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>24: 7pm (7pm-8pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>25: 8pm (8pm-9pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>26: Late PM (8pm-12am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>27: 9pm (9pm-10pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>28: 10pm (10pm-11pm)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29</th>\n",
+       "      <td>29: 11pm (11pm-12am)</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   day_part  n\n",
+       "0   00: All Day (12am-12am)  3\n",
+       "1       01: 12am (12am-1am)  3\n",
+       "2   02: Early AM (12am-6am)  3\n",
+       "3         03: 1am (1am-2am)  3\n",
+       "4         04: 2am (2am-3am)  3\n",
+       "5         05: 3am (3am-4am)  3\n",
+       "6         06: 4am (4am-5am)  3\n",
+       "7         07: 5am (5am-6am)  3\n",
+       "8         08: 6am (6am-7am)  3\n",
+       "9    09: Peak AM (6am-10am)  3\n",
+       "10        10: 7am (7am-8am)  3\n",
+       "11        11: 8am (8am-9am)  3\n",
+       "12       12: 9am (9am-10am)  3\n",
+       "13     13: 10am (10am-11am)  3\n",
+       "14   14: Mid-Day (10am-4pm)  3\n",
+       "15   15: 11am (11am-12noon)  3\n",
+       "16    16: 12pm (12noon-1pm)  3\n",
+       "17        17: 1pm (1pm-2pm)  3\n",
+       "18        18: 2pm (2pm-3pm)  3\n",
+       "19        19: 3pm (3pm-4pm)  3\n",
+       "20        20: 4pm (4pm-5pm)  3\n",
+       "21    21: Peak PM (4pm-8pm)  3\n",
+       "22        22: 5pm (5pm-6pm)  3\n",
+       "23        23: 6pm (6pm-7pm)  3\n",
+       "24        24: 7pm (7pm-8pm)  3\n",
+       "25        25: 8pm (8pm-9pm)  3\n",
+       "26   26: Late PM (8pm-12am)  3\n",
+       "27       27: 9pm (9pm-10pm)  3\n",
+       "28     28: 10pm (10pm-11pm)  3\n",
+       "29     29: 11pm (11pm-12am)  3"
+      ]
+     },
+     "execution_count": 80,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sl_data>>filter(_.zone_id==1133975975)>>count(_.day_part)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5d362f46-cfe6-4d13-b3ea-67f491a66897",
+   "metadata": {},
+   "source": [
+    "* The data here shows that each segment is broken out into hour time slots and then also aggregated to peak time periods. moving forward we will look at the `All Day` for `day_part` and `All Days` for `day_type`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 81,
+   "id": "57c890a6-c667-4917-a090-b85f1aadcad7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sl_data_single_day = sl_data>>filter(_.day_part == '00: All Day (12am-12am)', _.day_type == '0: All Days (M-Su)')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 82,
+   "id": "0a059c82-c7c8-43b9-92a6-178b42101828",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# len(sl_data_single_day)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "id": "67213733-9905-42bd-912e-cf943cd66b40",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sl_data_single_day>>count(_.zone_id, _.zone_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 84,
+   "id": "2e497c77-91ef-490f-a288-abe4e2c740dc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sl_data_single_day>>filter(_.zone_id==1133975975)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 85,
+   "id": "28292f62-b2ab-46cb-ac08-b728facdfdc0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>data_periods</th>\n",
+       "      <th>mode_of_travel</th>\n",
+       "      <th>zone_id</th>\n",
+       "      <th>zone_name</th>\n",
+       "      <th>road_classification</th>\n",
+       "      <th>line_zone_length__miles_</th>\n",
+       "      <th>zone_is_pass_through</th>\n",
+       "      <th>zone_direction__degrees_</th>\n",
+       "      <th>zone_cardinal_direction</th>\n",
+       "      <th>zone_is_bi_direction</th>\n",
+       "      <th>day_type</th>\n",
+       "      <th>day_part</th>\n",
+       "      <th>average_daily_segment_traffic__stl_volume_</th>\n",
+       "      <th>avg_segment_speed__mph_</th>\n",
+       "      <th>avg_segment_travel_time__sec_</th>\n",
+       "      <th>free_flow_speed__mph_</th>\n",
+       "      <th>vehicle_miles_of_travel__stl_volume_</th>\n",
+       "      <th>travel_time_index</th>\n",
+       "      <th>congested_segment</th>\n",
+       "      <th>_85th_speed_percentile</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1440</th>\n",
+       "      <td>Jan 01, 2022 - Dec 31, 2022</td>\n",
+       "      <td>All Vehicles CVD Plus - StL All Vehicles Volume</td>\n",
+       "      <td>1132861884</td>\n",
+       "      <td>I 80 / 236348365 / 1</td>\n",
+       "      <td>Motorway</td>\n",
+       "      <td>0.006</td>\n",
+       "      <td>yes</td>\n",
+       "      <td>85</td>\n",
+       "      <td>EAST</td>\n",
+       "      <td>no</td>\n",
+       "      <td>0: All Days (M-Su)</td>\n",
+       "      <td>00: All Day (12am-12am)</td>\n",
+       "      <td>128581</td>\n",
+       "      <td>63</td>\n",
+       "      <td>2</td>\n",
+       "      <td>70.532</td>\n",
+       "      <td>725.2</td>\n",
+       "      <td>1.12</td>\n",
+       "      <td>False</td>\n",
+       "      <td>72</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>360</th>\n",
+       "      <td>Jan 01, 2022 - Dec 31, 2022</td>\n",
+       "      <td>All Vehicles CVD Plus - StL All Vehicles Volume</td>\n",
+       "      <td>1036056766</td>\n",
+       "      <td>San Francisco – Oakland Bay Bridge / 52721870 / 1</td>\n",
+       "      <td>Motorway</td>\n",
+       "      <td>0.073</td>\n",
+       "      <td>yes</td>\n",
+       "      <td>37</td>\n",
+       "      <td>EAST</td>\n",
+       "      <td>no</td>\n",
+       "      <td>0: All Days (M-Su)</td>\n",
+       "      <td>00: All Day (12am-12am)</td>\n",
+       "      <td>158493</td>\n",
+       "      <td>51</td>\n",
+       "      <td>5</td>\n",
+       "      <td>67.267</td>\n",
+       "      <td>11532.2</td>\n",
+       "      <td>1.32</td>\n",
+       "      <td>True</td>\n",
+       "      <td>66</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>270</th>\n",
+       "      <td>Jan 01, 2022 - Dec 31, 2022</td>\n",
+       "      <td>All Vehicles CVD Plus - StL All Vehicles Volume</td>\n",
+       "      <td>1032819756</td>\n",
+       "      <td>San Francisco – Oakland Bay Bridge / 11415208 / 1</td>\n",
+       "      <td>Motorway</td>\n",
+       "      <td>0.109</td>\n",
+       "      <td>yes</td>\n",
+       "      <td>220</td>\n",
+       "      <td>WEST</td>\n",
+       "      <td>no</td>\n",
+       "      <td>0: All Days (M-Su)</td>\n",
+       "      <td>00: All Day (12am-12am)</td>\n",
+       "      <td>132245</td>\n",
+       "      <td>49</td>\n",
+       "      <td>10</td>\n",
+       "      <td>68.596</td>\n",
+       "      <td>14450.0</td>\n",
+       "      <td>1.41</td>\n",
+       "      <td>True</td>\n",
+       "      <td>67</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     data_periods  \\\n",
+       "1440  Jan 01, 2022 - Dec 31, 2022   \n",
+       "360   Jan 01, 2022 - Dec 31, 2022   \n",
+       "270   Jan 01, 2022 - Dec 31, 2022   \n",
+       "\n",
+       "                                       mode_of_travel     zone_id  \\\n",
+       "1440  All Vehicles CVD Plus - StL All Vehicles Volume  1132861884   \n",
+       "360   All Vehicles CVD Plus - StL All Vehicles Volume  1036056766   \n",
+       "270   All Vehicles CVD Plus - StL All Vehicles Volume  1032819756   \n",
+       "\n",
+       "                                              zone_name road_classification  \\\n",
+       "1440                               I 80 / 236348365 / 1            Motorway   \n",
+       "360   San Francisco – Oakland Bay Bridge / 52721870 / 1            Motorway   \n",
+       "270   San Francisco – Oakland Bay Bridge / 11415208 / 1            Motorway   \n",
+       "\n",
+       "      line_zone_length__miles_ zone_is_pass_through  zone_direction__degrees_  \\\n",
+       "1440                     0.006                  yes                        85   \n",
+       "360                      0.073                  yes                        37   \n",
+       "270                      0.109                  yes                       220   \n",
+       "\n",
+       "     zone_cardinal_direction zone_is_bi_direction            day_type  \\\n",
+       "1440                    EAST                   no  0: All Days (M-Su)   \n",
+       "360                     EAST                   no  0: All Days (M-Su)   \n",
+       "270                     WEST                   no  0: All Days (M-Su)   \n",
+       "\n",
+       "                     day_part  average_daily_segment_traffic__stl_volume_  \\\n",
+       "1440  00: All Day (12am-12am)                                      128581   \n",
+       "360   00: All Day (12am-12am)                                      158493   \n",
+       "270   00: All Day (12am-12am)                                      132245   \n",
+       "\n",
+       "      avg_segment_speed__mph_  avg_segment_travel_time__sec_  \\\n",
+       "1440                       63                              2   \n",
+       "360                        51                              5   \n",
+       "270                        49                             10   \n",
+       "\n",
+       "      free_flow_speed__mph_  vehicle_miles_of_travel__stl_volume_  \\\n",
+       "1440                 70.532                                 725.2   \n",
+       "360                  67.267                               11532.2   \n",
+       "270                  68.596                               14450.0   \n",
+       "\n",
+       "      travel_time_index  congested_segment  _85th_speed_percentile  \n",
+       "1440               1.12              False                      72  \n",
+       "360                1.32               True                      66  \n",
+       "270                1.41               True                      67  "
+      ]
+     },
+     "execution_count": 85,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sl_data_single_day.sample(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 86,
+   "id": "14211b7a-38f9-4b55-b669-67fdae44aa80",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sl_data_single_day>>group_by(_.zone_cardinal_direction, _.day_type, _.day_part)>>summarize(avg_speed= _.avg_segment_speed__mph_.mean(),\n",
+    "#                                                                                           avg_travel_time = _.avg_segment_travel_time__sec_.mean(),\n",
+    "#                                                                                           avg_volume = _.average_daily_segment_traffic__stl_volume_.mean(),\n",
+    "#                                                                                           sum_volume = _.average_daily_segment_traffic__stl_volume_.sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 87,
+   "id": "778d58f0-25b7-4cf7-b60a-10e773055f48",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sl_peaks = (sl_data>>filter(\n",
+    "                            _.day_part != \"01: 12am (12am-1am)\",\n",
+    "                            _.day_part != \"03: 1am (1am-2am)\",\n",
+    "                            _.day_part != \"04: 2am (2am-3am)\",\n",
+    "                            _.day_part != \"05: 3am (3am-4am)\",\n",
+    "                            _.day_part != \"06: 4am (4am-5am)\",\n",
+    "                            _.day_part != \"07: 5am (5am-6am)\",\n",
+    "                            _.day_part != \"08: 6am (6am-7am)\",\n",
+    "                            _.day_part != \"10: 7am (7am-8am)\",\n",
+    "                            _.day_part != \"11: 8am (8am-9am)\",\n",
+    "                            _.day_part != \"12: 9am (9am-10am)\",\n",
+    "                            _.day_part != \"13: 10am (10am-11am)\",\n",
+    "                            _.day_part != \"15: 11am (11am-12noon)\",\n",
+    "                            _.day_part != \"16: 12pm (12noon-1pm)\",\n",
+    "                            _.day_part != \"17: 1pm (1pm-2pm)\",\n",
+    "                            _.day_part != \"18: 2pm (2pm-3pm)\",\n",
+    "                            _.day_part != \"19: 3pm (3pm-4pm)\",\n",
+    "                            _.day_part != \"20: 4pm (4pm-5pm)\",\n",
+    "                            _.day_part != \"22: 5pm (5pm-6pm)\",\n",
+    "                            _.day_part != \"23: 6pm (6pm-7pm)\",\n",
+    "                            _.day_part != \"24: 7pm (7pm-8pm)\",\n",
+    "                            _.day_part != \"25: 8pm (8pm-9pm)\",\n",
+    "                            _.day_part != \"27: 9pm (9pm-10pm)\",\n",
+    "                            _.day_part != \"28: 10pm (10pm-11pm)\",\n",
+    "                            _.day_part !=\"29: 11pm (11pm-12am)\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2f2fa572-8bb8-4b9f-a299-48df2b838c31",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "id": "29eab191-4eaa-445c-b444-49048135ef3b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sl_hourly = (sl_data>>filter(_.day_part != \"00: All Day (12am-12am)\",\n",
+    "                            _.day_part != \"02: Early AM (12am-6am)\",\n",
+    "                            _.day_part != \"09: Peak AM (6am-10am)\",\n",
+    "                            _.day_part != \"14: Mid-Day (10am-4pm)\",\n",
+    "                            _.day_part != \"21: Peak PM (4pm-8pm)\", _.day_part !=\"26: Late PM (8pm-12am)\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4cd2a638-cce1-4c94-8444-4aa4844bf7f0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "id": "896b63a9-b881-418a-ba40-dbea63f81614",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sl_peaks_agg = sl_peaks>>group_by(_.zone_cardinal_direction,\n",
+    "    _.day_type, _.day_part)>>summarize(avg_speed= _.avg_segment_speed__mph_.mean(),\n",
+    "                                                                                          avg_travel_time = _.avg_segment_travel_time__sec_.mean(),\n",
+    "                                                                                          avg_volume = _.average_daily_segment_traffic__stl_volume_.mean(),\n",
+    "                                                                                          sum_volume = _.average_daily_segment_traffic__stl_volume_.sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 90,
+   "id": "cac29684-36ac-488b-b2d1-044ab5ef86c0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sl_peaks_agg.sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 91,
+   "id": "eedc968c-8306-449a-a2e3-774719d8e256",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-68aabe7591654dc0aa82ad87e468f9cc.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-68aabe7591654dc0aa82ad87e468f9cc.vega-embed details,\n",
+       "  #altair-viz-68aabe7591654dc0aa82ad87e468f9cc.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-68aabe7591654dc0aa82ad87e468f9cc\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-68aabe7591654dc0aa82ad87e468f9cc\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-68aabe7591654dc0aa82ad87e468f9cc\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-88c9c9c3ca0b506afbfd3c98fc4bbbb7\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"zone_cardinal_direction\", \"scale\": {\"domain\": [\"EAST\", \"WEST\"], \"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"zone_cardinal_direction\", \"type\": \"nominal\"}, {\"field\": \"day_type\", \"type\": \"nominal\"}, {\"field\": \"day_part\", \"type\": \"nominal\"}, {\"field\": \"avg_speed\", \"type\": \"quantitative\"}, {\"field\": \"avg_travel_time\", \"type\": \"quantitative\"}, {\"field\": \"avg_volume\", \"type\": \"quantitative\"}, {\"field\": \"sum_volume\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"day_part\", \"type\": \"nominal\"}, \"y\": {\"field\": \"avg_speed\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"Average Speed by Direction by Day Part\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-88c9c9c3ca0b506afbfd3c98fc4bbbb7\": [{\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 55.9, \"avg_travel_time\": 32.6, \"avg_volume\": 139682.3, \"sum_volume\": 1396823}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 66.2, \"avg_travel_time\": 26.2, \"avg_volume\": 8431.8, \"sum_volume\": 84318}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 62.5, \"avg_travel_time\": 27.9, \"avg_volume\": 19938.0, \"sum_volume\": 199380}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 54.5, \"avg_travel_time\": 33.5, \"avg_volume\": 53138.4, \"sum_volume\": 531384}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 49.5, \"avg_travel_time\": 37.6, \"avg_volume\": 34933.0, \"sum_volume\": 349330}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 59.6, \"avg_travel_time\": 29.5, \"avg_volume\": 23240.7, \"sum_volume\": 232407}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 55.5, \"avg_travel_time\": 33.3, \"avg_volume\": 143069.3, \"sum_volume\": 1430693}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 66.5, \"avg_travel_time\": 26.0, \"avg_volume\": 7564.6, \"sum_volume\": 75646}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 62.0, \"avg_travel_time\": 28.3, \"avg_volume\": 21303.9, \"sum_volume\": 213039}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 53.5, \"avg_travel_time\": 34.6, \"avg_volume\": 55291.5, \"sum_volume\": 552915}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 49.1, \"avg_travel_time\": 38.3, \"avg_volume\": 35673.8, \"sum_volume\": 356738}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 60.0, \"avg_travel_time\": 29.2, \"avg_volume\": 23235.8, \"sum_volume\": 232358}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 57.3, \"avg_travel_time\": 30.8, \"avg_volume\": 131294.7, \"sum_volume\": 1312947}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 65.7, \"avg_travel_time\": 26.4, \"avg_volume\": 10579.4, \"sum_volume\": 105794}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 64.4, \"avg_travel_time\": 26.8, \"avg_volume\": 16556.2, \"sum_volume\": 165562}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 57.2, \"avg_travel_time\": 30.5, \"avg_volume\": 47807.3, \"sum_volume\": 478073}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 51.0, \"avg_travel_time\": 35.7, \"avg_volume\": 33098.7, \"sum_volume\": 330987}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 58.2, \"avg_travel_time\": 30.3, \"avg_volume\": 23252.7, \"sum_volume\": 232527}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 50.333333333333336, \"avg_travel_time\": 41.77777777777778, \"avg_volume\": 123029.77777777778, \"sum_volume\": 1107268}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 62.111111111111114, \"avg_travel_time\": 30.88888888888889, \"avg_volume\": 14892.888888888889, \"sum_volume\": 134036}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 43.888888888888886, \"avg_travel_time\": 46.22222222222222, \"avg_volume\": 30567.666666666668, \"sum_volume\": 275109}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 50.0, \"avg_travel_time\": 43.0, \"avg_volume\": 42606.22222222222, \"sum_volume\": 383456}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 45.888888888888886, \"avg_travel_time\": 47.666666666666664, \"avg_volume\": 22056.555555555555, \"sum_volume\": 198509}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 62.333333333333336, \"avg_travel_time\": 31.444444444444443, \"avg_volume\": 12906.444444444445, \"sum_volume\": 116158}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 50.888888888888886, \"avg_travel_time\": 41.22222222222222, \"avg_volume\": 127485.44444444444, \"sum_volume\": 1147369}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 61.333333333333336, \"avg_travel_time\": 31.444444444444443, \"avg_volume\": 17773.777777777777, \"sum_volume\": 159964}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 39.55555555555556, \"avg_travel_time\": 50.111111111111114, \"avg_volume\": 35295.444444444445, \"sum_volume\": 317659}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 53.44444444444444, \"avg_travel_time\": 39.888888888888886, \"avg_volume\": 41435.11111111111, \"sum_volume\": 372916}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 48.55555555555556, \"avg_travel_time\": 44.55555555555556, \"avg_volume\": 21333.88888888889, \"sum_volume\": 192005}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 63.666666666666664, \"avg_travel_time\": 30.22222222222222, \"avg_volume\": 11647.222222222223, \"sum_volume\": 104825}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 49.55555555555556, \"avg_travel_time\": 43.44444444444444, \"avg_volume\": 111996.88888888889, \"sum_volume\": 1007972}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 67.33333333333333, \"avg_travel_time\": 28.0, \"avg_volume\": 7759.111111111111, \"sum_volume\": 69832}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 64.22222222222223, \"avg_travel_time\": 29.77777777777778, \"avg_volume\": 18860.444444444445, \"sum_volume\": 169744}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 42.333333333333336, \"avg_travel_time\": 50.333333333333336, \"avg_volume\": 45505.88888888889, \"sum_volume\": 409553}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 40.22222222222222, \"avg_travel_time\": 54.22222222222222, \"avg_volume\": 23846.222222222223, \"sum_volume\": 214616}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 59.55555555555556, \"avg_travel_time\": 34.0, \"avg_volume\": 16025.0, \"sum_volume\": 144225}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 91,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(sl_peaks_agg)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"day_part\"),\n",
+    "            y=alt.Y(\"avg_speed\"),\n",
+    "            color=alt.Color(\"zone_cardinal_direction\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,\n",
+    "            domain=sl_peaks_agg[\"zone_cardinal_direction\"].unique().tolist())\n",
+    "            ),\n",
+    "            tooltip=sl_peaks_agg.columns.tolist(),\n",
+    "            )\n",
+    "      .properties(title = \"Average Speed by Direction by Day Part\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 92,
+   "id": "637afffc-560f-4485-985a-d6ee73dd65a7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-f9022beacde94c0f9a64a00f0abe4776.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-f9022beacde94c0f9a64a00f0abe4776.vega-embed details,\n",
+       "  #altair-viz-f9022beacde94c0f9a64a00f0abe4776.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-f9022beacde94c0f9a64a00f0abe4776\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-f9022beacde94c0f9a64a00f0abe4776\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-f9022beacde94c0f9a64a00f0abe4776\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-88c9c9c3ca0b506afbfd3c98fc4bbbb7\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"zone_cardinal_direction\", \"scale\": {\"domain\": [\"EAST\", \"WEST\"], \"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"zone_cardinal_direction\", \"type\": \"nominal\"}, {\"field\": \"day_type\", \"type\": \"nominal\"}, {\"field\": \"day_part\", \"type\": \"nominal\"}, {\"field\": \"avg_speed\", \"type\": \"quantitative\"}, {\"field\": \"avg_travel_time\", \"type\": \"quantitative\"}, {\"field\": \"avg_volume\", \"type\": \"quantitative\"}, {\"field\": \"sum_volume\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"day_part\", \"type\": \"nominal\"}, \"y\": {\"field\": \"sum_volume\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"Average Volume by Direction by Day Part\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-88c9c9c3ca0b506afbfd3c98fc4bbbb7\": [{\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 55.9, \"avg_travel_time\": 32.6, \"avg_volume\": 139682.3, \"sum_volume\": 1396823}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 66.2, \"avg_travel_time\": 26.2, \"avg_volume\": 8431.8, \"sum_volume\": 84318}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 62.5, \"avg_travel_time\": 27.9, \"avg_volume\": 19938.0, \"sum_volume\": 199380}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 54.5, \"avg_travel_time\": 33.5, \"avg_volume\": 53138.4, \"sum_volume\": 531384}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 49.5, \"avg_travel_time\": 37.6, \"avg_volume\": 34933.0, \"sum_volume\": 349330}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 59.6, \"avg_travel_time\": 29.5, \"avg_volume\": 23240.7, \"sum_volume\": 232407}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 55.5, \"avg_travel_time\": 33.3, \"avg_volume\": 143069.3, \"sum_volume\": 1430693}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 66.5, \"avg_travel_time\": 26.0, \"avg_volume\": 7564.6, \"sum_volume\": 75646}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 62.0, \"avg_travel_time\": 28.3, \"avg_volume\": 21303.9, \"sum_volume\": 213039}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 53.5, \"avg_travel_time\": 34.6, \"avg_volume\": 55291.5, \"sum_volume\": 552915}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 49.1, \"avg_travel_time\": 38.3, \"avg_volume\": 35673.8, \"sum_volume\": 356738}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 60.0, \"avg_travel_time\": 29.2, \"avg_volume\": 23235.8, \"sum_volume\": 232358}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 57.3, \"avg_travel_time\": 30.8, \"avg_volume\": 131294.7, \"sum_volume\": 1312947}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 65.7, \"avg_travel_time\": 26.4, \"avg_volume\": 10579.4, \"sum_volume\": 105794}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 64.4, \"avg_travel_time\": 26.8, \"avg_volume\": 16556.2, \"sum_volume\": 165562}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 57.2, \"avg_travel_time\": 30.5, \"avg_volume\": 47807.3, \"sum_volume\": 478073}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 51.0, \"avg_travel_time\": 35.7, \"avg_volume\": 33098.7, \"sum_volume\": 330987}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 58.2, \"avg_travel_time\": 30.3, \"avg_volume\": 23252.7, \"sum_volume\": 232527}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 50.333333333333336, \"avg_travel_time\": 41.77777777777778, \"avg_volume\": 123029.77777777778, \"sum_volume\": 1107268}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 62.111111111111114, \"avg_travel_time\": 30.88888888888889, \"avg_volume\": 14892.888888888889, \"sum_volume\": 134036}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 43.888888888888886, \"avg_travel_time\": 46.22222222222222, \"avg_volume\": 30567.666666666668, \"sum_volume\": 275109}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 50.0, \"avg_travel_time\": 43.0, \"avg_volume\": 42606.22222222222, \"sum_volume\": 383456}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 45.888888888888886, \"avg_travel_time\": 47.666666666666664, \"avg_volume\": 22056.555555555555, \"sum_volume\": 198509}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 62.333333333333336, \"avg_travel_time\": 31.444444444444443, \"avg_volume\": 12906.444444444445, \"sum_volume\": 116158}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 50.888888888888886, \"avg_travel_time\": 41.22222222222222, \"avg_volume\": 127485.44444444444, \"sum_volume\": 1147369}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 61.333333333333336, \"avg_travel_time\": 31.444444444444443, \"avg_volume\": 17773.777777777777, \"sum_volume\": 159964}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 39.55555555555556, \"avg_travel_time\": 50.111111111111114, \"avg_volume\": 35295.444444444445, \"sum_volume\": 317659}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 53.44444444444444, \"avg_travel_time\": 39.888888888888886, \"avg_volume\": 41435.11111111111, \"sum_volume\": 372916}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 48.55555555555556, \"avg_travel_time\": 44.55555555555556, \"avg_volume\": 21333.88888888889, \"sum_volume\": 192005}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"1: Weekday (M-F)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 63.666666666666664, \"avg_travel_time\": 30.22222222222222, \"avg_volume\": 11647.222222222223, \"sum_volume\": 104825}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"00: All Day (12am-12am)\", \"avg_speed\": 49.55555555555556, \"avg_travel_time\": 43.44444444444444, \"avg_volume\": 111996.88888888889, \"sum_volume\": 1007972}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"02: Early AM (12am-6am)\", \"avg_speed\": 67.33333333333333, \"avg_travel_time\": 28.0, \"avg_volume\": 7759.111111111111, \"sum_volume\": 69832}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"09: Peak AM (6am-10am)\", \"avg_speed\": 64.22222222222223, \"avg_travel_time\": 29.77777777777778, \"avg_volume\": 18860.444444444445, \"sum_volume\": 169744}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"14: Mid-Day (10am-4pm)\", \"avg_speed\": 42.333333333333336, \"avg_travel_time\": 50.333333333333336, \"avg_volume\": 45505.88888888889, \"sum_volume\": 409553}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"21: Peak PM (4pm-8pm)\", \"avg_speed\": 40.22222222222222, \"avg_travel_time\": 54.22222222222222, \"avg_volume\": 23846.222222222223, \"sum_volume\": 214616}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"2: Weekend Day (Sa-Su)\", \"day_part\": \"26: Late PM (8pm-12am)\", \"avg_speed\": 59.55555555555556, \"avg_travel_time\": 34.0, \"avg_volume\": 16025.0, \"sum_volume\": 144225}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 92,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(sl_peaks_agg)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"day_part\"),\n",
+    "            y=alt.Y(\"sum_volume\"),\n",
+    "            color=alt.Color(\"zone_cardinal_direction\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,\n",
+    "            domain=sl_peaks_agg[\"zone_cardinal_direction\"].unique().tolist())\n",
+    "            ),\n",
+    "            tooltip=sl_peaks_agg.columns.tolist(),\n",
+    "            )\n",
+    "      .properties(title = \"Average Volume by Direction by Day Part\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6dade438-083b-446d-b1f7-d1542a3e60e6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7d954475-9f22-418b-bb31-0ab9799a459e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 93,
+   "id": "b2eaa07a-2d05-4ed5-a405-a474500a643e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sl_hourly_agg = sl_hourly>>filter(_.day_type==\"0: All Days (M-Su)\")>>group_by(_.zone_cardinal_direction,\n",
+    "    _.day_type, _.day_part)>>summarize(avg_speed= _.avg_segment_speed__mph_.mean(),\n",
+    "                                                                                          avg_travel_time = _.avg_segment_travel_time__sec_.mean(),\n",
+    "                                                                                          avg_volume = _.average_daily_segment_traffic__stl_volume_.mean(),\n",
+    "                                                                                          sum_volume = _.average_daily_segment_traffic__stl_volume_.sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 94,
+   "id": "1ab3835d-5f8e-4721-9c29-7bd107bad334",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sl_hourly_agg.sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "10efa809-ec77-4127-aa62-a838dd005c7d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 95,
+   "id": "8cc145e6-b3d9-4b31-9a0d-270431ebf5fb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-ffb50d67a3244a5e9e746ed2b2d8a10b.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-ffb50d67a3244a5e9e746ed2b2d8a10b.vega-embed details,\n",
+       "  #altair-viz-ffb50d67a3244a5e9e746ed2b2d8a10b.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-ffb50d67a3244a5e9e746ed2b2d8a10b\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-ffb50d67a3244a5e9e746ed2b2d8a10b\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-ffb50d67a3244a5e9e746ed2b2d8a10b\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-3fba12efdf354b7883c43d7d9e4ce13e\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"zone_cardinal_direction\", \"scale\": {\"domain\": [\"EAST\", \"WEST\"], \"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"zone_cardinal_direction\", \"type\": \"nominal\"}, {\"field\": \"day_type\", \"type\": \"nominal\"}, {\"field\": \"day_part\", \"type\": \"nominal\"}, {\"field\": \"avg_speed\", \"type\": \"quantitative\"}, {\"field\": \"avg_travel_time\", \"type\": \"quantitative\"}, {\"field\": \"avg_volume\", \"type\": \"quantitative\"}, {\"field\": \"sum_volume\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"day_part\", \"type\": \"nominal\"}, \"y\": {\"field\": \"avg_speed\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"Average Speed by Hour\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-3fba12efdf354b7883c43d7d9e4ce13e\": [{\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"01: 12am (12am-1am)\", \"avg_speed\": 64.5, \"avg_travel_time\": 27.0, \"avg_volume\": 2452.6, \"sum_volume\": 24526}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"03: 1am (1am-2am)\", \"avg_speed\": 66.1, \"avg_travel_time\": 26.3, \"avg_volume\": 1498.1, \"sum_volume\": 14981}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"04: 2am (2am-3am)\", \"avg_speed\": 66.1, \"avg_travel_time\": 26.1, \"avg_volume\": 1143.3, \"sum_volume\": 11433}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"05: 3am (3am-4am)\", \"avg_speed\": 66.7, \"avg_travel_time\": 25.6, \"avg_volume\": 741.0, \"sum_volume\": 7410}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"06: 4am (4am-5am)\", \"avg_speed\": 67.8, \"avg_travel_time\": 25.4, \"avg_volume\": 919.5, \"sum_volume\": 9195}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"07: 5am (5am-6am)\", \"avg_speed\": 68.0, \"avg_travel_time\": 25.2, \"avg_volume\": 1677.1, \"sum_volume\": 16771}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"08: 6am (6am-7am)\", \"avg_speed\": 66.4, \"avg_travel_time\": 26.1, \"avg_volume\": 3067.0, \"sum_volume\": 30670}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"10: 7am (7am-8am)\", \"avg_speed\": 63.2, \"avg_travel_time\": 27.7, \"avg_volume\": 4861.4, \"sum_volume\": 48614}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"11: 8am (8am-9am)\", \"avg_speed\": 61.7, \"avg_travel_time\": 28.2, \"avg_volume\": 5791.7, \"sum_volume\": 57917}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"12: 9am (9am-10am)\", \"avg_speed\": 60.7, \"avg_travel_time\": 28.8, \"avg_volume\": 6218.1, \"sum_volume\": 62181}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"13: 10am (10am-11am)\", \"avg_speed\": 59.3, \"avg_travel_time\": 29.5, \"avg_volume\": 7218.6, \"sum_volume\": 72186}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"15: 11am (11am-12noon)\", \"avg_speed\": 58.2, \"avg_travel_time\": 30.2, \"avg_volume\": 8069.3, \"sum_volume\": 80693}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"16: 12pm (12noon-1pm)\", \"avg_speed\": 57.5, \"avg_travel_time\": 31.7, \"avg_volume\": 8800.3, \"sum_volume\": 88003}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"17: 1pm (1pm-2pm)\", \"avg_speed\": 54.8, \"avg_travel_time\": 33.6, \"avg_volume\": 9318.9, \"sum_volume\": 93189}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"18: 2pm (2pm-3pm)\", \"avg_speed\": 51.1, \"avg_travel_time\": 36.3, \"avg_volume\": 9952.8, \"sum_volume\": 99528}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"19: 3pm (3pm-4pm)\", \"avg_speed\": 48.5, \"avg_travel_time\": 38.6, \"avg_volume\": 9778.9, \"sum_volume\": 97789}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"20: 4pm (4pm-5pm)\", \"avg_speed\": 48.0, \"avg_travel_time\": 39.4, \"avg_volume\": 9494.3, \"sum_volume\": 94943}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"22: 5pm (5pm-6pm)\", \"avg_speed\": 47.4, \"avg_travel_time\": 39.5, \"avg_volume\": 9071.2, \"sum_volume\": 90712}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"23: 6pm (6pm-7pm)\", \"avg_speed\": 49.0, \"avg_travel_time\": 37.6, \"avg_volume\": 8538.1, \"sum_volume\": 85381}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"24: 7pm (7pm-8pm)\", \"avg_speed\": 54.2, \"avg_travel_time\": 33.3, \"avg_volume\": 7829.4, \"sum_volume\": 78294}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"25: 8pm (8pm-9pm)\", \"avg_speed\": 57.7, \"avg_travel_time\": 30.9, \"avg_volume\": 6893.2, \"sum_volume\": 68932}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"27: 9pm (9pm-10pm)\", \"avg_speed\": 59.3, \"avg_travel_time\": 29.4, \"avg_volume\": 6383.5, \"sum_volume\": 63835}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"28: 10pm (10pm-11pm)\", \"avg_speed\": 59.9, \"avg_travel_time\": 29.1, \"avg_volume\": 5889.8, \"sum_volume\": 58898}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"29: 11pm (11pm-12am)\", \"avg_speed\": 61.9, \"avg_travel_time\": 28.2, \"avg_volume\": 4074.1, \"sum_volume\": 40741}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"01: 12am (12am-1am)\", \"avg_speed\": 66.66666666666667, \"avg_travel_time\": 28.444444444444443, \"avg_volume\": 1057.6666666666667, \"sum_volume\": 9519}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"03: 1am (1am-2am)\", \"avg_speed\": 66.77777777777777, \"avg_travel_time\": 28.444444444444443, \"avg_volume\": 754.4444444444445, \"sum_volume\": 6790}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"04: 2am (2am-3am)\", \"avg_speed\": 67.88888888888889, \"avg_travel_time\": 27.555555555555557, \"avg_volume\": 817.5555555555555, \"sum_volume\": 7358}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"05: 3am (3am-4am)\", \"avg_speed\": 68.11111111111111, \"avg_travel_time\": 27.88888888888889, \"avg_volume\": 1291.4444444444443, \"sum_volume\": 11623}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"06: 4am (4am-5am)\", \"avg_speed\": 68.55555555555556, \"avg_travel_time\": 27.666666666666668, \"avg_volume\": 3400.1111111111113, \"sum_volume\": 30601}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"07: 5am (5am-6am)\", \"avg_speed\": 56.888888888888886, \"avg_travel_time\": 34.111111111111114, \"avg_volume\": 7571.666666666667, \"sum_volume\": 68145}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"08: 6am (6am-7am)\", \"avg_speed\": 45.22222222222222, \"avg_travel_time\": 43.55555555555556, \"avg_volume\": 7902.555555555556, \"sum_volume\": 71123}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"10: 7am (7am-8am)\", \"avg_speed\": 40.888888888888886, \"avg_travel_time\": 48.55555555555556, \"avg_volume\": 7073.111111111111, \"sum_volume\": 63658}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"11: 8am (8am-9am)\", \"avg_speed\": 43.22222222222222, \"avg_travel_time\": 47.55555555555556, \"avg_volume\": 7499.333333333333, \"sum_volume\": 67494}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"12: 9am (9am-10am)\", \"avg_speed\": 45.77777777777778, \"avg_travel_time\": 46.111111111111114, \"avg_volume\": 8092.444444444444, \"sum_volume\": 72832}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"13: 10am (10am-11am)\", \"avg_speed\": 47.111111111111114, \"avg_travel_time\": 44.666666666666664, \"avg_volume\": 8061.0, \"sum_volume\": 72549}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"15: 11am (11am-12noon)\", \"avg_speed\": 48.333333333333336, \"avg_travel_time\": 44.888888888888886, \"avg_volume\": 7662.555555555556, \"sum_volume\": 68963}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"16: 12pm (12noon-1pm)\", \"avg_speed\": 50.55555555555556, \"avg_travel_time\": 42.666666666666664, \"avg_volume\": 7071.222222222223, \"sum_volume\": 63641}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"17: 1pm (1pm-2pm)\", \"avg_speed\": 52.22222222222222, \"avg_travel_time\": 40.55555555555556, \"avg_volume\": 6757.0, \"sum_volume\": 60813}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"18: 2pm (2pm-3pm)\", \"avg_speed\": 51.666666666666664, \"avg_travel_time\": 41.44444444444444, \"avg_volume\": 6702.555555555556, \"sum_volume\": 60323}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"19: 3pm (3pm-4pm)\", \"avg_speed\": 51.0, \"avg_travel_time\": 43.111111111111114, \"avg_volume\": 6351.555555555556, \"sum_volume\": 57164}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"20: 4pm (4pm-5pm)\", \"avg_speed\": 47.0, \"avg_travel_time\": 47.666666666666664, \"avg_volume\": 6174.555555555556, \"sum_volume\": 55571}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"22: 5pm (5pm-6pm)\", \"avg_speed\": 39.888888888888886, \"avg_travel_time\": 54.22222222222222, \"avg_volume\": 5875.222222222223, \"sum_volume\": 52877}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"23: 6pm (6pm-7pm)\", \"avg_speed\": 43.0, \"avg_travel_time\": 51.55555555555556, \"avg_volume\": 5412.222222222223, \"sum_volume\": 48710}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"24: 7pm (7pm-8pm)\", \"avg_speed\": 56.111111111111114, \"avg_travel_time\": 37.888888888888886, \"avg_volume\": 4594.777777777777, \"sum_volume\": 41353}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"25: 8pm (8pm-9pm)\", \"avg_speed\": 60.77777777777778, \"avg_travel_time\": 33.111111111111114, \"avg_volume\": 4138.444444444444, \"sum_volume\": 37246}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"27: 9pm (9pm-10pm)\", \"avg_speed\": 61.55555555555556, \"avg_travel_time\": 31.88888888888889, \"avg_volume\": 3718.777777777778, \"sum_volume\": 33469}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"28: 10pm (10pm-11pm)\", \"avg_speed\": 63.333333333333336, \"avg_travel_time\": 30.666666666666668, \"avg_volume\": 3115.0, \"sum_volume\": 28035}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"29: 11pm (11pm-12am)\", \"avg_speed\": 65.33333333333333, \"avg_travel_time\": 29.22222222222222, \"avg_volume\": 1934.4444444444443, \"sum_volume\": 17410}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 95,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(sl_hourly_agg)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"day_part\"),\n",
+    "            y=alt.Y(\"avg_speed\"),\n",
+    "            color=alt.Color(\"zone_cardinal_direction\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,\n",
+    "            domain=sl_hourly_agg[\"zone_cardinal_direction\"].unique().tolist())\n",
+    "            ),\n",
+    "            tooltip=sl_hourly_agg.columns.tolist(),\n",
+    "            )\n",
+    "      .properties(title = \"Average Speed by Hour\", \n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "id": "b54b867c-d073-4280-bfd3-2fa5bd387016",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-78fddf293e8c4401bfe80dcfd747c67f.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-78fddf293e8c4401bfe80dcfd747c67f.vega-embed details,\n",
+       "  #altair-viz-78fddf293e8c4401bfe80dcfd747c67f.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-78fddf293e8c4401bfe80dcfd747c67f\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-78fddf293e8c4401bfe80dcfd747c67f\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-78fddf293e8c4401bfe80dcfd747c67f\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-3fba12efdf354b7883c43d7d9e4ce13e\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"zone_cardinal_direction\", \"scale\": {\"domain\": [\"EAST\", \"WEST\"], \"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"zone_cardinal_direction\", \"type\": \"nominal\"}, {\"field\": \"day_type\", \"type\": \"nominal\"}, {\"field\": \"day_part\", \"type\": \"nominal\"}, {\"field\": \"avg_speed\", \"type\": \"quantitative\"}, {\"field\": \"avg_travel_time\", \"type\": \"quantitative\"}, {\"field\": \"avg_volume\", \"type\": \"quantitative\"}, {\"field\": \"sum_volume\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"day_part\", \"type\": \"nominal\"}, \"y\": {\"field\": \"sum_volume\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"Total Volume by Hour\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-3fba12efdf354b7883c43d7d9e4ce13e\": [{\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"01: 12am (12am-1am)\", \"avg_speed\": 64.5, \"avg_travel_time\": 27.0, \"avg_volume\": 2452.6, \"sum_volume\": 24526}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"03: 1am (1am-2am)\", \"avg_speed\": 66.1, \"avg_travel_time\": 26.3, \"avg_volume\": 1498.1, \"sum_volume\": 14981}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"04: 2am (2am-3am)\", \"avg_speed\": 66.1, \"avg_travel_time\": 26.1, \"avg_volume\": 1143.3, \"sum_volume\": 11433}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"05: 3am (3am-4am)\", \"avg_speed\": 66.7, \"avg_travel_time\": 25.6, \"avg_volume\": 741.0, \"sum_volume\": 7410}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"06: 4am (4am-5am)\", \"avg_speed\": 67.8, \"avg_travel_time\": 25.4, \"avg_volume\": 919.5, \"sum_volume\": 9195}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"07: 5am (5am-6am)\", \"avg_speed\": 68.0, \"avg_travel_time\": 25.2, \"avg_volume\": 1677.1, \"sum_volume\": 16771}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"08: 6am (6am-7am)\", \"avg_speed\": 66.4, \"avg_travel_time\": 26.1, \"avg_volume\": 3067.0, \"sum_volume\": 30670}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"10: 7am (7am-8am)\", \"avg_speed\": 63.2, \"avg_travel_time\": 27.7, \"avg_volume\": 4861.4, \"sum_volume\": 48614}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"11: 8am (8am-9am)\", \"avg_speed\": 61.7, \"avg_travel_time\": 28.2, \"avg_volume\": 5791.7, \"sum_volume\": 57917}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"12: 9am (9am-10am)\", \"avg_speed\": 60.7, \"avg_travel_time\": 28.8, \"avg_volume\": 6218.1, \"sum_volume\": 62181}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"13: 10am (10am-11am)\", \"avg_speed\": 59.3, \"avg_travel_time\": 29.5, \"avg_volume\": 7218.6, \"sum_volume\": 72186}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"15: 11am (11am-12noon)\", \"avg_speed\": 58.2, \"avg_travel_time\": 30.2, \"avg_volume\": 8069.3, \"sum_volume\": 80693}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"16: 12pm (12noon-1pm)\", \"avg_speed\": 57.5, \"avg_travel_time\": 31.7, \"avg_volume\": 8800.3, \"sum_volume\": 88003}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"17: 1pm (1pm-2pm)\", \"avg_speed\": 54.8, \"avg_travel_time\": 33.6, \"avg_volume\": 9318.9, \"sum_volume\": 93189}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"18: 2pm (2pm-3pm)\", \"avg_speed\": 51.1, \"avg_travel_time\": 36.3, \"avg_volume\": 9952.8, \"sum_volume\": 99528}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"19: 3pm (3pm-4pm)\", \"avg_speed\": 48.5, \"avg_travel_time\": 38.6, \"avg_volume\": 9778.9, \"sum_volume\": 97789}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"20: 4pm (4pm-5pm)\", \"avg_speed\": 48.0, \"avg_travel_time\": 39.4, \"avg_volume\": 9494.3, \"sum_volume\": 94943}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"22: 5pm (5pm-6pm)\", \"avg_speed\": 47.4, \"avg_travel_time\": 39.5, \"avg_volume\": 9071.2, \"sum_volume\": 90712}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"23: 6pm (6pm-7pm)\", \"avg_speed\": 49.0, \"avg_travel_time\": 37.6, \"avg_volume\": 8538.1, \"sum_volume\": 85381}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"24: 7pm (7pm-8pm)\", \"avg_speed\": 54.2, \"avg_travel_time\": 33.3, \"avg_volume\": 7829.4, \"sum_volume\": 78294}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"25: 8pm (8pm-9pm)\", \"avg_speed\": 57.7, \"avg_travel_time\": 30.9, \"avg_volume\": 6893.2, \"sum_volume\": 68932}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"27: 9pm (9pm-10pm)\", \"avg_speed\": 59.3, \"avg_travel_time\": 29.4, \"avg_volume\": 6383.5, \"sum_volume\": 63835}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"28: 10pm (10pm-11pm)\", \"avg_speed\": 59.9, \"avg_travel_time\": 29.1, \"avg_volume\": 5889.8, \"sum_volume\": 58898}, {\"zone_cardinal_direction\": \"EAST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"29: 11pm (11pm-12am)\", \"avg_speed\": 61.9, \"avg_travel_time\": 28.2, \"avg_volume\": 4074.1, \"sum_volume\": 40741}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"01: 12am (12am-1am)\", \"avg_speed\": 66.66666666666667, \"avg_travel_time\": 28.444444444444443, \"avg_volume\": 1057.6666666666667, \"sum_volume\": 9519}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"03: 1am (1am-2am)\", \"avg_speed\": 66.77777777777777, \"avg_travel_time\": 28.444444444444443, \"avg_volume\": 754.4444444444445, \"sum_volume\": 6790}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"04: 2am (2am-3am)\", \"avg_speed\": 67.88888888888889, \"avg_travel_time\": 27.555555555555557, \"avg_volume\": 817.5555555555555, \"sum_volume\": 7358}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"05: 3am (3am-4am)\", \"avg_speed\": 68.11111111111111, \"avg_travel_time\": 27.88888888888889, \"avg_volume\": 1291.4444444444443, \"sum_volume\": 11623}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"06: 4am (4am-5am)\", \"avg_speed\": 68.55555555555556, \"avg_travel_time\": 27.666666666666668, \"avg_volume\": 3400.1111111111113, \"sum_volume\": 30601}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"07: 5am (5am-6am)\", \"avg_speed\": 56.888888888888886, \"avg_travel_time\": 34.111111111111114, \"avg_volume\": 7571.666666666667, \"sum_volume\": 68145}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"08: 6am (6am-7am)\", \"avg_speed\": 45.22222222222222, \"avg_travel_time\": 43.55555555555556, \"avg_volume\": 7902.555555555556, \"sum_volume\": 71123}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"10: 7am (7am-8am)\", \"avg_speed\": 40.888888888888886, \"avg_travel_time\": 48.55555555555556, \"avg_volume\": 7073.111111111111, \"sum_volume\": 63658}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"11: 8am (8am-9am)\", \"avg_speed\": 43.22222222222222, \"avg_travel_time\": 47.55555555555556, \"avg_volume\": 7499.333333333333, \"sum_volume\": 67494}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"12: 9am (9am-10am)\", \"avg_speed\": 45.77777777777778, \"avg_travel_time\": 46.111111111111114, \"avg_volume\": 8092.444444444444, \"sum_volume\": 72832}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"13: 10am (10am-11am)\", \"avg_speed\": 47.111111111111114, \"avg_travel_time\": 44.666666666666664, \"avg_volume\": 8061.0, \"sum_volume\": 72549}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"15: 11am (11am-12noon)\", \"avg_speed\": 48.333333333333336, \"avg_travel_time\": 44.888888888888886, \"avg_volume\": 7662.555555555556, \"sum_volume\": 68963}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"16: 12pm (12noon-1pm)\", \"avg_speed\": 50.55555555555556, \"avg_travel_time\": 42.666666666666664, \"avg_volume\": 7071.222222222223, \"sum_volume\": 63641}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"17: 1pm (1pm-2pm)\", \"avg_speed\": 52.22222222222222, \"avg_travel_time\": 40.55555555555556, \"avg_volume\": 6757.0, \"sum_volume\": 60813}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"18: 2pm (2pm-3pm)\", \"avg_speed\": 51.666666666666664, \"avg_travel_time\": 41.44444444444444, \"avg_volume\": 6702.555555555556, \"sum_volume\": 60323}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"19: 3pm (3pm-4pm)\", \"avg_speed\": 51.0, \"avg_travel_time\": 43.111111111111114, \"avg_volume\": 6351.555555555556, \"sum_volume\": 57164}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"20: 4pm (4pm-5pm)\", \"avg_speed\": 47.0, \"avg_travel_time\": 47.666666666666664, \"avg_volume\": 6174.555555555556, \"sum_volume\": 55571}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"22: 5pm (5pm-6pm)\", \"avg_speed\": 39.888888888888886, \"avg_travel_time\": 54.22222222222222, \"avg_volume\": 5875.222222222223, \"sum_volume\": 52877}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"23: 6pm (6pm-7pm)\", \"avg_speed\": 43.0, \"avg_travel_time\": 51.55555555555556, \"avg_volume\": 5412.222222222223, \"sum_volume\": 48710}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"24: 7pm (7pm-8pm)\", \"avg_speed\": 56.111111111111114, \"avg_travel_time\": 37.888888888888886, \"avg_volume\": 4594.777777777777, \"sum_volume\": 41353}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"25: 8pm (8pm-9pm)\", \"avg_speed\": 60.77777777777778, \"avg_travel_time\": 33.111111111111114, \"avg_volume\": 4138.444444444444, \"sum_volume\": 37246}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"27: 9pm (9pm-10pm)\", \"avg_speed\": 61.55555555555556, \"avg_travel_time\": 31.88888888888889, \"avg_volume\": 3718.777777777778, \"sum_volume\": 33469}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"28: 10pm (10pm-11pm)\", \"avg_speed\": 63.333333333333336, \"avg_travel_time\": 30.666666666666668, \"avg_volume\": 3115.0, \"sum_volume\": 28035}, {\"zone_cardinal_direction\": \"WEST\", \"day_type\": \"0: All Days (M-Su)\", \"day_part\": \"29: 11pm (11pm-12am)\", \"avg_speed\": 65.33333333333333, \"avg_travel_time\": 29.22222222222222, \"avg_volume\": 1934.4444444444443, \"sum_volume\": 17410}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 96,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(sl_hourly_agg)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"day_part\"),\n",
+    "            y=alt.Y(\"sum_volume\"),\n",
+    "            color=alt.Color(\"zone_cardinal_direction\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,\n",
+    "            domain=sl_hourly_agg[\"zone_cardinal_direction\"].unique().tolist())\n",
+    "            ),\n",
+    "            tooltip=sl_hourly_agg.columns.tolist(),\n",
+    "            )\n",
+    "      .properties(title = \"Total Volume by Hour\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cd1987e0-957e-4b30-a940-86f3c9c0fd39",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "76157cad-aeda-4ba4-9f98-77c677e6b6c6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bfe9e847-b78f-4e81-b735-708df21764a0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "006dfcc5-bf3f-4a33-a654-601fbb232b71",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ecded8d2-70ae-4a9a-8592-cc5e9b9cd8df",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5d007800-e20a-4991-b99d-f6cf74521b05",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bbc819b1-0dfc-46be-90bd-b136263dc22c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/sb125_analyses/corridor_study/data_downloads_skirball.ipynb b/sb125_analyses/corridor_study/data_downloads_skirball.ipynb
new file mode 100644
index 000000000..268ec1842
--- /dev/null
+++ b/sb125_analyses/corridor_study/data_downloads_skirball.ipynb
@@ -0,0 +1,4459 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "82a53f1d-2622-4cb0-bfdd-36ceec652215",
+   "metadata": {},
+   "source": [
+    "# SB1 Big Data Downloads: I-405 Skirball\n",
+    "An analysis into the corridor analysis data downloads from Streetlight and Replica"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "45233485-2055-499a-a89e-fc154fd56e63",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_516/2202862553.py:12: DeprecationWarning: Importing display from IPython.core.display is deprecated since IPython 7.14, please import from IPython display\n",
+      "  from IPython.core.display import display\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from siuba import *\n",
+    "import ast\n",
+    "\n",
+    "\n",
+    "from calitp_data_analysis.sql import to_snakecase\n",
+    "\n",
+    "import altair as alt\n",
+    "from calitp_data_analysis import calitp_color_palette as cp\n",
+    "\n",
+    "from IPython.display import Markdown, HTML, display_html, display\n",
+    "from IPython.core.display import display\n",
+    "\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9e5db6b9-2add-42e7-b820-1b075dc3bbcc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dla_utils import _dla_utils"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "c0ea35c1-246d-4356-ad1c-83fe9cc437ff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import _utils"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "651aae92-5188-4676-8e5f-3c040f77077c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pd.set_option('display.max_columns', 500)\n",
+    "pd.set_option('display.max_colwidth', 100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "af402da0-0b03-4c71-a1af-19f97f67cef1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "GCS_PATH = \"gs://calitp-analytics-data/data-analyses/sb125/corridor_study_data/\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "71c1deda-8e83-45d8-a0f5-20b36b7051c0",
+   "metadata": {},
+   "source": [
+    "### Read in Replica Data Spring 2023"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "0e5c1b44-c981-4a9a-b6ea-e1cb2a7a279e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "replica_trips = \"replica-405_skirball-05_24_24-trips_dataset.csv\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a9f14685-0953-4b1d-a636-882230fef1d5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "cb3dea26-4e6d-4dc7-acc8-27b899a0a537",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_516/2643890524.py:1: DtypeWarning: Columns (18,19,20,25,26,28,29,30,31,33,36,38,39,40,41,42,43) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+      "  r_trips = to_snakecase(pd.read_csv(f\"{GCS_PATH}{replica_trips}\"))\n"
+     ]
+    }
+   ],
+   "source": [
+    "r_trips = to_snakecase(pd.read_csv(f\"{GCS_PATH}{replica_trips}\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ca697494-b872-4de8-afd9-c538a455364c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong> Sample of data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong> Sample of data</strong></h4>\"))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "4713b1a5-ccac-4e1b-8552-850285cad53e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>activity_id</th>\n",
+       "      <th>origin_bgrp_2020</th>\n",
+       "      <th>origin_trct_2020</th>\n",
+       "      <th>origin_cty_2020</th>\n",
+       "      <th>origin_st_2020</th>\n",
+       "      <th>destination_bgrp_2020</th>\n",
+       "      <th>destination_trct_2020</th>\n",
+       "      <th>destination_cty_2020</th>\n",
+       "      <th>destination_st_2020</th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>trip_purpose</th>\n",
+       "      <th>previous_trip_purpose</th>\n",
+       "      <th>trip_start_time</th>\n",
+       "      <th>trip_end_time</th>\n",
+       "      <th>trip_duration_minutes</th>\n",
+       "      <th>trip_distance_miles</th>\n",
+       "      <th>vehicle_type</th>\n",
+       "      <th>vehicle_fuel_type</th>\n",
+       "      <th>transit_submode</th>\n",
+       "      <th>transit_agency</th>\n",
+       "      <th>transit_route</th>\n",
+       "      <th>origin_land_use</th>\n",
+       "      <th>origin_building_use</th>\n",
+       "      <th>destination_land_use</th>\n",
+       "      <th>destination_building_use</th>\n",
+       "      <th>trip_taker_person_id</th>\n",
+       "      <th>trip_taker_household_id</th>\n",
+       "      <th>trip_taker_age</th>\n",
+       "      <th>trip_taker_sex</th>\n",
+       "      <th>trip_taker_race_ethnicity</th>\n",
+       "      <th>trip_taker_employment_status</th>\n",
+       "      <th>trip_taker_wfh</th>\n",
+       "      <th>trip_taker_individual_income</th>\n",
+       "      <th>trip_taker_commute_mode</th>\n",
+       "      <th>trip_taker_household_size</th>\n",
+       "      <th>trip_taker_household_income</th>\n",
+       "      <th>trip_taker_available_vehicles</th>\n",
+       "      <th>trip_taker_resident_type</th>\n",
+       "      <th>trip_taker_industry</th>\n",
+       "      <th>trip_taker_building_type</th>\n",
+       "      <th>trip_taker_school_grade_attending</th>\n",
+       "      <th>trip_taker_education</th>\n",
+       "      <th>trip_taker_tenure</th>\n",
+       "      <th>trip_taker_language</th>\n",
+       "      <th>trip_taker_home_bgrp_2020</th>\n",
+       "      <th>trip_taker_home_trct_2020</th>\n",
+       "      <th>trip_taker_home_cty_2020</th>\n",
+       "      <th>trip_taker_home_st_2020</th>\n",
+       "      <th>trip_taker_work_bgrp_2020</th>\n",
+       "      <th>trip_taker_work_trct_2020</th>\n",
+       "      <th>trip_taker_work_cty_2020</th>\n",
+       "      <th>trip_taker_work_st_2020</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>257013</th>\n",
+       "      <td>9302896571626397264</td>\n",
+       "      <td>2 (Tract 2169.02, Los Angeles, CA)</td>\n",
+       "      <td>2169.02 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>1 (Tract 1281.02, Los Angeles, CA)</td>\n",
+       "      <td>1281.02 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>home</td>\n",
+       "      <td>social</td>\n",
+       "      <td>12:17:00</td>\n",
+       "      <td>12:50:00</td>\n",
+       "      <td>33</td>\n",
+       "      <td>18.90</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>other_non_bev</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>multi_family</td>\n",
+       "      <td>multi_family</td>\n",
+       "      <td>7579849294298285797</td>\n",
+       "      <td>9607203881269597076</td>\n",
+       "      <td>33.00</td>\n",
+       "      <td>male</td>\n",
+       "      <td>white_not_hispanic_or_latino</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>in_person</td>\n",
+       "      <td>59,218.00</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>3.00</td>\n",
+       "      <td>184,761.00</td>\n",
+       "      <td>two</td>\n",
+       "      <td>core</td>\n",
+       "      <td>naics23</td>\n",
+       "      <td>several_units</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>some_college</td>\n",
+       "      <td>renter</td>\n",
+       "      <td>english</td>\n",
+       "      <td>1 (Tract 1281.02, Los Angeles, CA)</td>\n",
+       "      <td>1281.02 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>1 (Tract 2171.01, Los Angeles, CA)</td>\n",
+       "      <td>2171.01 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>366384</th>\n",
+       "      <td>10044791123655181857</td>\n",
+       "      <td>2 (Tract 5033.01, Los Angeles, CA)</td>\n",
+       "      <td>5033.01 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2 (Tract 2622, Los Angeles, CA)</td>\n",
+       "      <td>2622 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>home</td>\n",
+       "      <td>social</td>\n",
+       "      <td>12:55:16</td>\n",
+       "      <td>13:57:55</td>\n",
+       "      <td>62</td>\n",
+       "      <td>35.70</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>unknown_fuel_type</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>1348767672027219422</td>\n",
+       "      <td>14444669387201913369</td>\n",
+       "      <td>27.00</td>\n",
+       "      <td>female</td>\n",
+       "      <td>black_not_hispanic_or_latino</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>in_person</td>\n",
+       "      <td>94,986.00</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>2.00</td>\n",
+       "      <td>94,986.00</td>\n",
+       "      <td>three_plus</td>\n",
+       "      <td>core</td>\n",
+       "      <td>naics61</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>advanced_degree</td>\n",
+       "      <td>owner</td>\n",
+       "      <td>english</td>\n",
+       "      <td>2 (Tract 2622, Los Angeles, CA)</td>\n",
+       "      <td>2622 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2 (Tract 1397.01, Los Angeles, CA)</td>\n",
+       "      <td>1397.01 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>404087</th>\n",
+       "      <td>8025058747789155362</td>\n",
+       "      <td>1 (Tract 2623.03, Los Angeles, CA)</td>\n",
+       "      <td>2623.03 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2 (Tract 1041.03, Los Angeles, CA)</td>\n",
+       "      <td>1041.03 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>home</td>\n",
+       "      <td>social</td>\n",
+       "      <td>13:39:16</td>\n",
+       "      <td>14:19:59</td>\n",
+       "      <td>40</td>\n",
+       "      <td>21.00</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>other_non_bev</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>15874717675890836160</td>\n",
+       "      <td>5139820635381915520</td>\n",
+       "      <td>52.00</td>\n",
+       "      <td>female</td>\n",
+       "      <td>hispanic_or_latino_origin</td>\n",
+       "      <td>not_in_labor_force</td>\n",
+       "      <td>unemployed_under_16_not_in_labor_force</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>other_travel_mode</td>\n",
+       "      <td>13.00</td>\n",
+       "      <td>115,058.00</td>\n",
+       "      <td>three_plus</td>\n",
+       "      <td>core</td>\n",
+       "      <td>not_working</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>k_12</td>\n",
+       "      <td>owner</td>\n",
+       "      <td>spanish</td>\n",
+       "      <td>2 (Tract 1041.03, Los Angeles, CA)</td>\n",
+       "      <td>1041.03 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>213866</th>\n",
+       "      <td>7281458345523096603</td>\n",
+       "      <td>1 (Tract 1375.01, Los Angeles, CA)</td>\n",
+       "      <td>1375.01 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>3 (Tract 7014.02, Los Angeles, CA)</td>\n",
+       "      <td>7014.02 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>work</td>\n",
+       "      <td>home</td>\n",
+       "      <td>06:32:00</td>\n",
+       "      <td>07:14:10</td>\n",
+       "      <td>42</td>\n",
+       "      <td>21.40</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>unknown_fuel_type</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>mixed_use</td>\n",
+       "      <td>healthcare</td>\n",
+       "      <td>6116471627154071969</td>\n",
+       "      <td>7757742330168392134</td>\n",
+       "      <td>34.00</td>\n",
+       "      <td>male</td>\n",
+       "      <td>white_not_hispanic_or_latino</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>in_person</td>\n",
+       "      <td>129,138.00</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>2.00</td>\n",
+       "      <td>129,138.00</td>\n",
+       "      <td>two</td>\n",
+       "      <td>core</td>\n",
+       "      <td>naics622110</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>advanced_degree</td>\n",
+       "      <td>renter</td>\n",
+       "      <td>indo_european</td>\n",
+       "      <td>1 (Tract 1375.01, Los Angeles, CA)</td>\n",
+       "      <td>1375.01 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>3 (Tract 7014.02, Los Angeles, CA)</td>\n",
+       "      <td>7014.02 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>403783</th>\n",
+       "      <td>16782161229821888706</td>\n",
+       "      <td>3 (Tract 7028.01, Los Angeles, CA)</td>\n",
+       "      <td>7028.01 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2 (Tract 1066.04, Los Angeles, CA)</td>\n",
+       "      <td>1066.04 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>home</td>\n",
+       "      <td>shop</td>\n",
+       "      <td>16:58:00</td>\n",
+       "      <td>18:02:01</td>\n",
+       "      <td>64</td>\n",
+       "      <td>23.40</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>unknown_fuel_type</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>office</td>\n",
+       "      <td>office</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>14388114560565293720</td>\n",
+       "      <td>4788446096359409371</td>\n",
+       "      <td>88.00</td>\n",
+       "      <td>male</td>\n",
+       "      <td>hispanic_or_latino_origin</td>\n",
+       "      <td>not_in_labor_force</td>\n",
+       "      <td>unemployed_under_16_not_in_labor_force</td>\n",
+       "      <td>26,495.00</td>\n",
+       "      <td>other_travel_mode</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>26,495.00</td>\n",
+       "      <td>zero</td>\n",
+       "      <td>core</td>\n",
+       "      <td>not_working</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>k_12</td>\n",
+       "      <td>renter</td>\n",
+       "      <td>spanish</td>\n",
+       "      <td>2 (Tract 1066.04, Los Angeles, CA)</td>\n",
+       "      <td>1066.04 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "      <td>Does not have work/school location</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                 activity_id                    origin_bgrp_2020  \\\n",
+       "257013   9302896571626397264  2 (Tract 2169.02, Los Angeles, CA)   \n",
+       "366384  10044791123655181857  2 (Tract 5033.01, Los Angeles, CA)   \n",
+       "404087   8025058747789155362  1 (Tract 2623.03, Los Angeles, CA)   \n",
+       "213866   7281458345523096603  1 (Tract 1375.01, Los Angeles, CA)   \n",
+       "403783  16782161229821888706  3 (Tract 7028.01, Los Angeles, CA)   \n",
+       "\n",
+       "                 origin_trct_2020         origin_cty_2020 origin_st_2020  \\\n",
+       "257013  2169.02 (Los Angeles, CA)  Los Angeles County, CA     California   \n",
+       "366384  5033.01 (Los Angeles, CA)  Los Angeles County, CA     California   \n",
+       "404087  2623.03 (Los Angeles, CA)  Los Angeles County, CA     California   \n",
+       "213866  1375.01 (Los Angeles, CA)  Los Angeles County, CA     California   \n",
+       "403783  7028.01 (Los Angeles, CA)  Los Angeles County, CA     California   \n",
+       "\n",
+       "                     destination_bgrp_2020      destination_trct_2020  \\\n",
+       "257013  1 (Tract 1281.02, Los Angeles, CA)  1281.02 (Los Angeles, CA)   \n",
+       "366384     2 (Tract 2622, Los Angeles, CA)     2622 (Los Angeles, CA)   \n",
+       "404087  2 (Tract 1041.03, Los Angeles, CA)  1041.03 (Los Angeles, CA)   \n",
+       "213866  3 (Tract 7014.02, Los Angeles, CA)  7014.02 (Los Angeles, CA)   \n",
+       "403783  2 (Tract 1066.04, Los Angeles, CA)  1066.04 (Los Angeles, CA)   \n",
+       "\n",
+       "          destination_cty_2020 destination_st_2020    primary_mode  \\\n",
+       "257013  Los Angeles County, CA          California    private_auto   \n",
+       "366384  Los Angeles County, CA          California  auto_passenger   \n",
+       "404087  Los Angeles County, CA          California    private_auto   \n",
+       "213866  Los Angeles County, CA          California  auto_passenger   \n",
+       "403783  Los Angeles County, CA          California  auto_passenger   \n",
+       "\n",
+       "       trip_purpose previous_trip_purpose trip_start_time trip_end_time  \\\n",
+       "257013         home                social        12:17:00      12:50:00   \n",
+       "366384         home                social        12:55:16      13:57:55   \n",
+       "404087         home                social        13:39:16      14:19:59   \n",
+       "213866         work                  home        06:32:00      07:14:10   \n",
+       "403783         home                  shop        16:58:00      18:02:01   \n",
+       "\n",
+       "        trip_duration_minutes  trip_distance_miles          vehicle_type  \\\n",
+       "257013                     33                18.90  unknown_vehicle_type   \n",
+       "366384                     62                35.70  unknown_vehicle_type   \n",
+       "404087                     40                21.00  unknown_vehicle_type   \n",
+       "213866                     42                21.40  unknown_vehicle_type   \n",
+       "403783                     64                23.40  unknown_vehicle_type   \n",
+       "\n",
+       "        vehicle_fuel_type transit_submode transit_agency transit_route  \\\n",
+       "257013      other_non_bev             NaN            NaN           NaN   \n",
+       "366384  unknown_fuel_type             NaN            NaN           NaN   \n",
+       "404087      other_non_bev             NaN            NaN           NaN   \n",
+       "213866  unknown_fuel_type             NaN            NaN           NaN   \n",
+       "403783  unknown_fuel_type             NaN            NaN           NaN   \n",
+       "\n",
+       "       origin_land_use origin_building_use destination_land_use  \\\n",
+       "257013   single_family       single_family         multi_family   \n",
+       "366384   single_family       single_family        single_family   \n",
+       "404087   single_family       single_family        single_family   \n",
+       "213866   single_family       single_family            mixed_use   \n",
+       "403783          office              office        single_family   \n",
+       "\n",
+       "       destination_building_use  trip_taker_person_id trip_taker_household_id  \\\n",
+       "257013             multi_family   7579849294298285797     9607203881269597076   \n",
+       "366384            single_family   1348767672027219422    14444669387201913369   \n",
+       "404087            single_family  15874717675890836160     5139820635381915520   \n",
+       "213866               healthcare   6116471627154071969     7757742330168392134   \n",
+       "403783            single_family  14388114560565293720     4788446096359409371   \n",
+       "\n",
+       "        trip_taker_age trip_taker_sex     trip_taker_race_ethnicity  \\\n",
+       "257013           33.00           male  white_not_hispanic_or_latino   \n",
+       "366384           27.00         female  black_not_hispanic_or_latino   \n",
+       "404087           52.00         female     hispanic_or_latino_origin   \n",
+       "213866           34.00           male  white_not_hispanic_or_latino   \n",
+       "403783           88.00           male     hispanic_or_latino_origin   \n",
+       "\n",
+       "       trip_taker_employment_status                          trip_taker_wfh  \\\n",
+       "257013                     employed                               in_person   \n",
+       "366384                     employed                               in_person   \n",
+       "404087           not_in_labor_force  unemployed_under_16_not_in_labor_force   \n",
+       "213866                     employed                               in_person   \n",
+       "403783           not_in_labor_force  unemployed_under_16_not_in_labor_force   \n",
+       "\n",
+       "        trip_taker_individual_income trip_taker_commute_mode  \\\n",
+       "257013                     59,218.00            private_auto   \n",
+       "366384                     94,986.00            private_auto   \n",
+       "404087                          0.00       other_travel_mode   \n",
+       "213866                    129,138.00            private_auto   \n",
+       "403783                     26,495.00       other_travel_mode   \n",
+       "\n",
+       "        trip_taker_household_size  trip_taker_household_income  \\\n",
+       "257013                       3.00                   184,761.00   \n",
+       "366384                       2.00                    94,986.00   \n",
+       "404087                      13.00                   115,058.00   \n",
+       "213866                       2.00                   129,138.00   \n",
+       "403783                       1.00                    26,495.00   \n",
+       "\n",
+       "       trip_taker_available_vehicles trip_taker_resident_type  \\\n",
+       "257013                           two                     core   \n",
+       "366384                    three_plus                     core   \n",
+       "404087                    three_plus                     core   \n",
+       "213866                           two                     core   \n",
+       "403783                          zero                     core   \n",
+       "\n",
+       "       trip_taker_industry trip_taker_building_type  \\\n",
+       "257013             naics23            several_units   \n",
+       "366384             naics61            single_family   \n",
+       "404087         not_working            single_family   \n",
+       "213866         naics622110            single_family   \n",
+       "403783         not_working            single_family   \n",
+       "\n",
+       "       trip_taker_school_grade_attending trip_taker_education  \\\n",
+       "257013              not_attending_school         some_college   \n",
+       "366384              not_attending_school      advanced_degree   \n",
+       "404087              not_attending_school                 k_12   \n",
+       "213866              not_attending_school      advanced_degree   \n",
+       "403783              not_attending_school                 k_12   \n",
+       "\n",
+       "       trip_taker_tenure trip_taker_language  \\\n",
+       "257013            renter             english   \n",
+       "366384             owner             english   \n",
+       "404087             owner             spanish   \n",
+       "213866            renter       indo_european   \n",
+       "403783            renter             spanish   \n",
+       "\n",
+       "                 trip_taker_home_bgrp_2020  trip_taker_home_trct_2020  \\\n",
+       "257013  1 (Tract 1281.02, Los Angeles, CA)  1281.02 (Los Angeles, CA)   \n",
+       "366384     2 (Tract 2622, Los Angeles, CA)     2622 (Los Angeles, CA)   \n",
+       "404087  2 (Tract 1041.03, Los Angeles, CA)  1041.03 (Los Angeles, CA)   \n",
+       "213866  1 (Tract 1375.01, Los Angeles, CA)  1375.01 (Los Angeles, CA)   \n",
+       "403783  2 (Tract 1066.04, Los Angeles, CA)  1066.04 (Los Angeles, CA)   \n",
+       "\n",
+       "       trip_taker_home_cty_2020 trip_taker_home_st_2020  \\\n",
+       "257013   Los Angeles County, CA              California   \n",
+       "366384   Los Angeles County, CA              California   \n",
+       "404087   Los Angeles County, CA              California   \n",
+       "213866   Los Angeles County, CA              California   \n",
+       "403783   Los Angeles County, CA              California   \n",
+       "\n",
+       "                 trip_taker_work_bgrp_2020  \\\n",
+       "257013  1 (Tract 2171.01, Los Angeles, CA)   \n",
+       "366384  2 (Tract 1397.01, Los Angeles, CA)   \n",
+       "404087  Does not have work/school location   \n",
+       "213866  3 (Tract 7014.02, Los Angeles, CA)   \n",
+       "403783  Does not have work/school location   \n",
+       "\n",
+       "                 trip_taker_work_trct_2020  \\\n",
+       "257013           2171.01 (Los Angeles, CA)   \n",
+       "366384           1397.01 (Los Angeles, CA)   \n",
+       "404087  Does not have work/school location   \n",
+       "213866           7014.02 (Los Angeles, CA)   \n",
+       "403783  Does not have work/school location   \n",
+       "\n",
+       "                  trip_taker_work_cty_2020             trip_taker_work_st_2020  \n",
+       "257013              Los Angeles County, CA                          California  \n",
+       "366384              Los Angeles County, CA                          California  \n",
+       "404087  Does not have work/school location  Does not have work/school location  \n",
+       "213866              Los Angeles County, CA                          California  \n",
+       "403783  Does not have work/school location  Does not have work/school location  "
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips.sample(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e2199852-9b6e-46ca-86fd-abe71148d13f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "75945ef2-eab7-469a-baad-ee563d70c309",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong> Columns in Replica Trips Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong> Columns in Replica Trips Data</strong></h4>\"))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "1f3e4cbb-d211-40b1-b4bb-2c7cb43b33a9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['activity_id', 'origin_bgrp_2020', 'origin_trct_2020',\n",
+       "       'origin_cty_2020', 'origin_st_2020', 'destination_bgrp_2020',\n",
+       "       'destination_trct_2020', 'destination_cty_2020', 'destination_st_2020',\n",
+       "       'primary_mode', 'trip_purpose', 'previous_trip_purpose',\n",
+       "       'trip_start_time', 'trip_end_time', 'trip_duration_minutes',\n",
+       "       'trip_distance_miles', 'vehicle_type', 'vehicle_fuel_type',\n",
+       "       'transit_submode', 'transit_agency', 'transit_route', 'origin_land_use',\n",
+       "       'origin_building_use', 'destination_land_use',\n",
+       "       'destination_building_use', 'trip_taker_person_id',\n",
+       "       'trip_taker_household_id', 'trip_taker_age', 'trip_taker_sex',\n",
+       "       'trip_taker_race_ethnicity', 'trip_taker_employment_status',\n",
+       "       'trip_taker_wfh', 'trip_taker_individual_income',\n",
+       "       'trip_taker_commute_mode', 'trip_taker_household_size',\n",
+       "       'trip_taker_household_income', 'trip_taker_available_vehicles',\n",
+       "       'trip_taker_resident_type', 'trip_taker_industry',\n",
+       "       'trip_taker_building_type', 'trip_taker_school_grade_attending',\n",
+       "       'trip_taker_education', 'trip_taker_tenure', 'trip_taker_language',\n",
+       "       'trip_taker_home_bgrp_2020', 'trip_taker_home_trct_2020',\n",
+       "       'trip_taker_home_cty_2020', 'trip_taker_home_st_2020',\n",
+       "       'trip_taker_work_bgrp_2020', 'trip_taker_work_trct_2020',\n",
+       "       'trip_taker_work_cty_2020', 'trip_taker_work_st_2020'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e60fb5c7-a04b-48f3-8282-ca98a54dadd2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "92f9a5f4-08f1-43fc-ae01-c6bd404891d6",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "#### Data Exploration: Replica Trips\n",
+    "* Summarizing the data that we exported from Replica\n",
+    "* Existing visualizations in replica: \n",
+    "   * Primary Mode\n",
+    "   * Trip Purpose\n",
+    "   * Starting hour \n",
+    "   * Trip Duration/Distance\n",
+    "   * Origin Destination\n",
+    "   * Vehicle Fuel type\n",
+    "   * Transit Routes/Stops/Sub mode/Agency\n",
+    "   * Household Income\n",
+    "   * Race and Ethnicity\n",
+    "   * Private Auto Availability\n",
+    "   * Age\n",
+    "   * Employment/School Status\n",
+    "   \n",
+    "   "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "c191620c-cef4-446a-bf6b-e17222f47ab6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# def basic_bar_chart(df, x_col, y_col, color_col):\n",
+    "\n",
+    "#     chart = (alt.Chart(df)\n",
+    "#              .mark_bar()\n",
+    "#              .encode(\n",
+    "#                  x=alt.X(x_col, title=labeling(x_col)),\n",
+    "#                  y=alt.Y(y_col, title=labeling(y_col)),\n",
+    "#                  color = (alt.Color(color_col,\n",
+    "#                                   scale=alt.Scale(\n",
+    "#                                       range=cp.CALITP_CATEGORY_BRIGHT_COLORS),\n",
+    "#                                       legend=alt.Legend(title=(labeling(color_col)), symbolLimit=10)\n",
+    "#                                   )),\n",
+    "#                  tooltip=[alt.Tooltip(x_col, title=labeling(x_col)),\n",
+    "#                           alt.Tooltip(y_col, title=labeling(y_col))]\n",
+    "#                                    )\n",
+    "#             )\n",
+    "\n",
+    "#     chart=styleguide.preset_chart_config(chart)\n",
+    "#     chart = add_tooltip(chart, labeling(x_col), labeling(y_col))\n",
+    "#     return chart"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "d7f3b44a-cd77-42e9-b0d8-7b9d228b37d5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trips = r_trips>>group_by(_.primary_mode)>>summarize(avg_trip_time = _.trip_duration_minutes.mean(),\n",
+    "                                                     number_trips = _.activity_id.nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "3c77c803-9ecb-4cb4-9d1d-d7e2fa5d4074",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 5 entries, 0 to 4\n",
+      "Data columns (total 3 columns):\n",
+      " #   Column         Non-Null Count  Dtype  \n",
+      "---  ------         --------------  -----  \n",
+      " 0   primary_mode   5 non-null      object \n",
+      " 1   avg_trip_time  5 non-null      float64\n",
+      " 2   number_trips   5 non-null      int64  \n",
+      "dtypes: float64(1), int64(1), object(1)\n",
+      "memory usage: 248.0+ bytes\n"
+     ]
+    }
+   ],
+   "source": [
+    "trips.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "05893215-e993-44dc-9c4b-1aa7d94815cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-2f001b15f40f4ae18927ce230f65cac2.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-2f001b15f40f4ae18927ce230f65cac2.vega-embed details,\n",
+       "  #altair-viz-2f001b15f40f4ae18927ce230f65cac2.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-2f001b15f40f4ae18927ce230f65cac2\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-2f001b15f40f4ae18927ce230f65cac2\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-2f001b15f40f4ae18927ce230f65cac2\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-e02771658aa3b3b9ff937e4bbfcb41ba\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"avg_trip_time\", \"scale\": {\"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"primary_mode\", \"type\": \"nominal\"}, {\"field\": \"avg_trip_time\", \"type\": \"quantitative\"}, {\"field\": \"number_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"primary_mode\", \"type\": \"nominal\"}, \"y\": {\"field\": \"avg_trip_time\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"Average Trip Time\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-e02771658aa3b3b9ff937e4bbfcb41ba\": [{\"primary_mode\": \"auto_passenger\", \"avg_trip_time\": 112.61406824507749, \"number_trips\": 145505}, {\"primary_mode\": \"commercial\", \"avg_trip_time\": 43.71912546779594, \"number_trips\": 10154}, {\"primary_mode\": \"on_demand_auto\", \"avg_trip_time\": 41.548600105652405, \"number_trips\": 3786}, {\"primary_mode\": \"private_auto\", \"avg_trip_time\": 79.92043592264831, \"number_trips\": 305100}, {\"primary_mode\": \"public_transit\", \"avg_trip_time\": 104.36544549977386, \"number_trips\": 2211}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(trips)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"primary_mode\"),\n",
+    "            y=alt.Y(\"avg_trip_time\"),\n",
+    "            color=alt.Color(\"avg_trip_time\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS)\n",
+    "            ), tooltip=trips.columns.tolist())\n",
+    "      .properties(title = \"Average Trip Time\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "65681a29-7f1b-42ed-9e0e-371a84a29cbd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-44a2a04a922b4ee0beb94784c391de4c.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-44a2a04a922b4ee0beb94784c391de4c.vega-embed details,\n",
+       "  #altair-viz-44a2a04a922b4ee0beb94784c391de4c.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-44a2a04a922b4ee0beb94784c391de4c\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-44a2a04a922b4ee0beb94784c391de4c\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-44a2a04a922b4ee0beb94784c391de4c\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-e02771658aa3b3b9ff937e4bbfcb41ba\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"number_trips\", \"scale\": {\"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"primary_mode\", \"type\": \"nominal\"}, {\"field\": \"avg_trip_time\", \"type\": \"quantitative\"}, {\"field\": \"number_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"primary_mode\", \"type\": \"nominal\"}, \"y\": {\"field\": \"number_trips\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"Number of Trips\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-e02771658aa3b3b9ff937e4bbfcb41ba\": [{\"primary_mode\": \"auto_passenger\", \"avg_trip_time\": 112.61406824507749, \"number_trips\": 145505}, {\"primary_mode\": \"commercial\", \"avg_trip_time\": 43.71912546779594, \"number_trips\": 10154}, {\"primary_mode\": \"on_demand_auto\", \"avg_trip_time\": 41.548600105652405, \"number_trips\": 3786}, {\"primary_mode\": \"private_auto\", \"avg_trip_time\": 79.92043592264831, \"number_trips\": 305100}, {\"primary_mode\": \"public_transit\", \"avg_trip_time\": 104.36544549977386, \"number_trips\": 2211}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(trips)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"primary_mode\"),\n",
+    "            y=alt.Y(\"number_trips\"),\n",
+    "            color=alt.Color(\"number_trips\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,)\n",
+    "            ), tooltip=trips.columns.tolist())\n",
+    "      .properties(title=\"Number of Trips\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "0d60fe54-dc88-4570-8610-125b37b5917d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Length of Trips dataframe</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Length of Trips dataframe</strong></h4>\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "4f98abae-ae6b-4b4e-9427-b606a557582f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "466756"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(r_trips)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "55c6ff06-afed-45dc-b764-93188c2b9958",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Number of unique activity ids in data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Number of unique activity ids in data</strong></h4>\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "27c00872-5880-4464-84a5-e91423ce7895",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>number_trips</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>466756</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   number_trips\n",
+       "0        466756"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips>>summarize(number_trips = _.activity_id.nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "a20cbce8-e354-4aa3-99db-666a13576b5e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Number of unique trip taker ids</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Number of unique trip taker ids</strong></h4>\")) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "2def0aaf-9182-4393-8049-2dfb95749585",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>number_trips</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>281798</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   number_trips\n",
+       "0        281798"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips>>summarize(number_trips = _.trip_taker_person_id.nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "47fecd22-8276-48b8-9c74-d3a94906bbae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "race_ethnicity_by_mode = r_trips>>group_by(_.primary_mode)>>count(_.trip_taker_race_ethnicity)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "4cbeb867-916b-48aa-9949-d769fcd5af5a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Trip Taker Race and Ethnicity by Mode</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Trip Taker Race and Ethnicity by Mode</strong></h4>\")) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "5e895499-2142-432d-8402-c035f81326b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-33b313dee3e74b4d831c22fe203709dc.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-33b313dee3e74b4d831c22fe203709dc.vega-embed details,\n",
+       "  #altair-viz-33b313dee3e74b4d831c22fe203709dc.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-33b313dee3e74b4d831c22fe203709dc\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-33b313dee3e74b4d831c22fe203709dc\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-33b313dee3e74b4d831c22fe203709dc\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-a66a70d85b32c8dcb3d5a3f0cef4541c\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"trip_taker_race_ethnicity\", \"scale\": {\"domain\": [\"aian_not_hispanic_or_latino\", \"asian_not_hispanic_or_latino\", \"black_not_hispanic_or_latino\", \"hispanic_or_latino_origin\", \"nhopi_not_hispanic_or_latino\", \"other_not_hispanic_or_latino\", \"two_races_not_hispanic_or_latino\", \"white_not_hispanic_or_latino\", NaN], \"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"primary_mode\", \"type\": \"nominal\"}, {\"field\": \"trip_taker_race_ethnicity\", \"type\": \"nominal\"}, {\"field\": \"n\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"primary_mode\", \"type\": \"nominal\"}, \"y\": {\"field\": \"n\", \"type\": \"quantitative\"}}, \"height\": 300, \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-a66a70d85b32c8dcb3d5a3f0cef4541c\": [{\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"aian_not_hispanic_or_latino\", \"n\": 170}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"asian_not_hispanic_or_latino\", \"n\": 14465}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"black_not_hispanic_or_latino\", \"n\": 7077}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"hispanic_or_latino_origin\", \"n\": 41505}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"nhopi_not_hispanic_or_latino\", \"n\": 166}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"other_not_hispanic_or_latino\", \"n\": 816}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"two_races_not_hispanic_or_latino\", \"n\": 4434}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": \"white_not_hispanic_or_latino\", \"n\": 48054}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_race_ethnicity\": null, \"n\": 28818}, {\"primary_mode\": \"commercial\", \"trip_taker_race_ethnicity\": null, \"n\": 10154}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"aian_not_hispanic_or_latino\", \"n\": 5}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"asian_not_hispanic_or_latino\", \"n\": 369}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"black_not_hispanic_or_latino\", \"n\": 196}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"hispanic_or_latino_origin\", \"n\": 1122}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"nhopi_not_hispanic_or_latino\", \"n\": 5}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"other_not_hispanic_or_latino\", \"n\": 24}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"two_races_not_hispanic_or_latino\", \"n\": 102}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": \"white_not_hispanic_or_latino\", \"n\": 1368}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_race_ethnicity\": null, \"n\": 595}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"aian_not_hispanic_or_latino\", \"n\": 401}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"asian_not_hispanic_or_latino\", \"n\": 36971}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"black_not_hispanic_or_latino\", \"n\": 17876}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"hispanic_or_latino_origin\", \"n\": 107307}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"nhopi_not_hispanic_or_latino\", \"n\": 558}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"other_not_hispanic_or_latino\", \"n\": 1752}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"two_races_not_hispanic_or_latino\", \"n\": 9192}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": \"white_not_hispanic_or_latino\", \"n\": 120648}, {\"primary_mode\": \"private_auto\", \"trip_taker_race_ethnicity\": null, \"n\": 10395}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"asian_not_hispanic_or_latino\", \"n\": 270}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"black_not_hispanic_or_latino\", \"n\": 134}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"hispanic_or_latino_origin\", \"n\": 1186}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"nhopi_not_hispanic_or_latino\", \"n\": 1}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"other_not_hispanic_or_latino\", \"n\": 12}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"two_races_not_hispanic_or_latino\", \"n\": 54}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": \"white_not_hispanic_or_latino\", \"n\": 498}, {\"primary_mode\": \"public_transit\", \"trip_taker_race_ethnicity\": null, \"n\": 56}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(race_ethnicity_by_mode)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"primary_mode\"),\n",
+    "            y=alt.Y(\"n\"),\n",
+    "            color=alt.Color(\"trip_taker_race_ethnicity\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,\n",
+    "                                                                         domain=race_ethnicity_by_mode[\"trip_taker_race_ethnicity\"].unique().tolist())\n",
+    "            ),\n",
+    "            tooltip=race_ethnicity_by_mode.columns.tolist())\n",
+    "            \n",
+    "      .properties(\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "da3bbe59-9b06-471f-beb1-4762b8939600",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "500ad806-51ed-47e9-88a5-fc8a41edd7aa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<H4><strong>Transit Mode Splits</strong></H4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<H4><strong>Transit Mode Splits</strong></H4>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "d8cd6354-0433-4134-ad6e-9df92122cbd2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<strong>Looking at transit mode, need to alter the transit_agency col and transit_submode to get a better count.</strong>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<strong>Looking at transit mode, need to alter the transit_agency col and transit_submode to get a better count.</strong>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "261d7f48-f7c3-4ea7-a526-6f813ca16ede",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ptt_agency_count = (r_trips\n",
+    "#  >>filter(_.primary_mode==\"public_transit\")\n",
+    "#  >>group_by(_.primary_mode, _.transit_submode, _.transit_agency)\n",
+    "#  >>summarize(n =_.activity_id.nunique())\n",
+    "#  >>arrange(-_.n))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "e4516beb-8277-4fd4-aed1-23af65fc4a28",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ptt_agency_count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "727511b8-3141-40e4-b654-30aaae8200d9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Most common transit mode combinations</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Most common transit mode combinations</strong></h4>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f3c31371-899f-4474-85b6-86e78e89209b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "657ff2f3-0d0d-419d-b3d5-512212897fb1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ptt_modes.head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "80daf7a1-b947-469c-b3b0-09d0302714b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##### unnesting the transit submode and agencies to get counts. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "edd81120-9756-4edb-b713-1586a9fd5021",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>activity_id</th>\n",
+       "      <th>origin_bgrp_2020</th>\n",
+       "      <th>origin_trct_2020</th>\n",
+       "      <th>origin_cty_2020</th>\n",
+       "      <th>origin_st_2020</th>\n",
+       "      <th>destination_bgrp_2020</th>\n",
+       "      <th>destination_trct_2020</th>\n",
+       "      <th>destination_cty_2020</th>\n",
+       "      <th>destination_st_2020</th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>trip_purpose</th>\n",
+       "      <th>previous_trip_purpose</th>\n",
+       "      <th>trip_start_time</th>\n",
+       "      <th>trip_end_time</th>\n",
+       "      <th>trip_duration_minutes</th>\n",
+       "      <th>trip_distance_miles</th>\n",
+       "      <th>vehicle_type</th>\n",
+       "      <th>vehicle_fuel_type</th>\n",
+       "      <th>transit_submode</th>\n",
+       "      <th>transit_agency</th>\n",
+       "      <th>transit_route</th>\n",
+       "      <th>origin_land_use</th>\n",
+       "      <th>origin_building_use</th>\n",
+       "      <th>destination_land_use</th>\n",
+       "      <th>destination_building_use</th>\n",
+       "      <th>trip_taker_person_id</th>\n",
+       "      <th>trip_taker_household_id</th>\n",
+       "      <th>trip_taker_age</th>\n",
+       "      <th>trip_taker_sex</th>\n",
+       "      <th>trip_taker_race_ethnicity</th>\n",
+       "      <th>trip_taker_employment_status</th>\n",
+       "      <th>trip_taker_wfh</th>\n",
+       "      <th>trip_taker_individual_income</th>\n",
+       "      <th>trip_taker_commute_mode</th>\n",
+       "      <th>trip_taker_household_size</th>\n",
+       "      <th>trip_taker_household_income</th>\n",
+       "      <th>trip_taker_available_vehicles</th>\n",
+       "      <th>trip_taker_resident_type</th>\n",
+       "      <th>trip_taker_industry</th>\n",
+       "      <th>trip_taker_building_type</th>\n",
+       "      <th>trip_taker_school_grade_attending</th>\n",
+       "      <th>trip_taker_education</th>\n",
+       "      <th>trip_taker_tenure</th>\n",
+       "      <th>trip_taker_language</th>\n",
+       "      <th>trip_taker_home_bgrp_2020</th>\n",
+       "      <th>trip_taker_home_trct_2020</th>\n",
+       "      <th>trip_taker_home_cty_2020</th>\n",
+       "      <th>trip_taker_home_st_2020</th>\n",
+       "      <th>trip_taker_work_bgrp_2020</th>\n",
+       "      <th>trip_taker_work_trct_2020</th>\n",
+       "      <th>trip_taker_work_cty_2020</th>\n",
+       "      <th>trip_taker_work_st_2020</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>61898</th>\n",
+       "      <td>7706952349763026875</td>\n",
+       "      <td>2 (Tract 1111, Los Angeles, CA)</td>\n",
+       "      <td>1111 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>1 (Tract 2060.51, Los Angeles, CA)</td>\n",
+       "      <td>2060.51 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>work</td>\n",
+       "      <td>home</td>\n",
+       "      <td>05:35:00</td>\n",
+       "      <td>07:53:14</td>\n",
+       "      <td>138</td>\n",
+       "      <td>29.80</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>unknown_fuel_type</td>\n",
+       "      <td>bus, bus</td>\n",
+       "      <td>LADOTMVN, Metro - Los Angeles</td>\n",
+       "      <td>CE573, Metro Rapid Line</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>retail</td>\n",
+       "      <td>retail</td>\n",
+       "      <td>15982840578351068133</td>\n",
+       "      <td>16243967259505879865</td>\n",
+       "      <td>48.00</td>\n",
+       "      <td>male</td>\n",
+       "      <td>hispanic_or_latino_origin</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>in_person</td>\n",
+       "      <td>46,903.00</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>5.00</td>\n",
+       "      <td>88,596.00</td>\n",
+       "      <td>zero</td>\n",
+       "      <td>core</td>\n",
+       "      <td>naics56</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>high_school</td>\n",
+       "      <td>renter</td>\n",
+       "      <td>spanish</td>\n",
+       "      <td>2 (Tract 1111, Los Angeles, CA)</td>\n",
+       "      <td>1111 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>1 (Tract 2060.51, Los Angeles, CA)</td>\n",
+       "      <td>2060.51 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               activity_id                 origin_bgrp_2020  \\\n",
+       "61898  7706952349763026875  2 (Tract 1111, Los Angeles, CA)   \n",
+       "\n",
+       "             origin_trct_2020         origin_cty_2020 origin_st_2020  \\\n",
+       "61898  1111 (Los Angeles, CA)  Los Angeles County, CA     California   \n",
+       "\n",
+       "                    destination_bgrp_2020      destination_trct_2020  \\\n",
+       "61898  1 (Tract 2060.51, Los Angeles, CA)  2060.51 (Los Angeles, CA)   \n",
+       "\n",
+       "         destination_cty_2020 destination_st_2020    primary_mode  \\\n",
+       "61898  Los Angeles County, CA          California  public_transit   \n",
+       "\n",
+       "      trip_purpose previous_trip_purpose trip_start_time trip_end_time  \\\n",
+       "61898         work                  home        05:35:00      07:53:14   \n",
+       "\n",
+       "       trip_duration_minutes  trip_distance_miles          vehicle_type  \\\n",
+       "61898                    138                29.80  unknown_vehicle_type   \n",
+       "\n",
+       "       vehicle_fuel_type transit_submode                 transit_agency  \\\n",
+       "61898  unknown_fuel_type        bus, bus  LADOTMVN, Metro - Los Angeles   \n",
+       "\n",
+       "                 transit_route origin_land_use origin_building_use  \\\n",
+       "61898  CE573, Metro Rapid Line   single_family       single_family   \n",
+       "\n",
+       "      destination_land_use destination_building_use  trip_taker_person_id  \\\n",
+       "61898               retail                   retail  15982840578351068133   \n",
+       "\n",
+       "      trip_taker_household_id  trip_taker_age trip_taker_sex  \\\n",
+       "61898    16243967259505879865           48.00           male   \n",
+       "\n",
+       "       trip_taker_race_ethnicity trip_taker_employment_status trip_taker_wfh  \\\n",
+       "61898  hispanic_or_latino_origin                     employed      in_person   \n",
+       "\n",
+       "       trip_taker_individual_income trip_taker_commute_mode  \\\n",
+       "61898                     46,903.00            private_auto   \n",
+       "\n",
+       "       trip_taker_household_size  trip_taker_household_income  \\\n",
+       "61898                       5.00                    88,596.00   \n",
+       "\n",
+       "      trip_taker_available_vehicles trip_taker_resident_type  \\\n",
+       "61898                          zero                     core   \n",
+       "\n",
+       "      trip_taker_industry trip_taker_building_type  \\\n",
+       "61898             naics56            single_family   \n",
+       "\n",
+       "      trip_taker_school_grade_attending trip_taker_education  \\\n",
+       "61898              not_attending_school          high_school   \n",
+       "\n",
+       "      trip_taker_tenure trip_taker_language        trip_taker_home_bgrp_2020  \\\n",
+       "61898            renter             spanish  2 (Tract 1111, Los Angeles, CA)   \n",
+       "\n",
+       "      trip_taker_home_trct_2020 trip_taker_home_cty_2020  \\\n",
+       "61898    1111 (Los Angeles, CA)   Los Angeles County, CA   \n",
+       "\n",
+       "      trip_taker_home_st_2020           trip_taker_work_bgrp_2020  \\\n",
+       "61898              California  1 (Tract 2060.51, Los Angeles, CA)   \n",
+       "\n",
+       "       trip_taker_work_trct_2020 trip_taker_work_cty_2020  \\\n",
+       "61898  2060.51 (Los Angeles, CA)   Los Angeles County, CA   \n",
+       "\n",
+       "      trip_taker_work_st_2020  \n",
+       "61898              California  "
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "(r_trips>>filter(_.primary_mode==\"public_transit\")).sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2025391f-537e-432a-a2f4-d2d6ce57af04",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1af1d8ca-813c-44bc-ab93-c35bb11f0ea5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "eb27ab6b-6244-406f-b41a-55503a77521a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agencies_test, mode_test = _utils.get_tranist_agency_counts(r_trips, \"primary_mode\", \"transit_submode\", \"transit_agency\", \"activity_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "92ed5077-3524-4c39-8cf4-bf1b7922da2a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>transit_submode</th>\n",
+       "      <th>transit_agency</th>\n",
+       "      <th>n</th>\n",
+       "      <th>agency_count</th>\n",
+       "      <th>n_modes_taken</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus, bus</td>\n",
+       "      <td>Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "      <td>501</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>57</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus, bus, bus</td>\n",
+       "      <td>Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "      <td>375</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus, bus, bus</td>\n",
+       "      <td>Big Blue Bus, Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "      <td>192</td>\n",
+       "      <td>2</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus, bus</td>\n",
+       "      <td>Big Blue Bus, Metro - Los Angeles</td>\n",
+       "      <td>171</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>bus</td>\n",
+       "      <td>Metro - Los Angeles</td>\n",
+       "      <td>145</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>118</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>rail, bus, bus, bus</td>\n",
+       "      <td>Amtrak, Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>119</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>rail, bus, bus, rail</td>\n",
+       "      <td>Amtrak, Big Blue Bus, Metro - Los Angeles, Amtrak</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>120</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>rail, bus, light_rail, bus</td>\n",
+       "      <td>Amtrak, Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>121</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>subway, bus</td>\n",
+       "      <td>Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>122</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>subway, bus, bus</td>\n",
+       "      <td>Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>123 rows × 6 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       primary_mode             transit_submode  \\\n",
+       "15   public_transit                    bus, bus   \n",
+       "57   public_transit               bus, bus, bus   \n",
+       "27   public_transit               bus, bus, bus   \n",
+       "5    public_transit                    bus, bus   \n",
+       "1    public_transit                         bus   \n",
+       "..              ...                         ...   \n",
+       "118  public_transit         rail, bus, bus, bus   \n",
+       "119  public_transit        rail, bus, bus, rail   \n",
+       "120  public_transit  rail, bus, light_rail, bus   \n",
+       "121  public_transit                 subway, bus   \n",
+       "122  public_transit            subway, bus, bus   \n",
+       "\n",
+       "                                                            transit_agency  \\\n",
+       "15                                Metro - Los Angeles, Metro - Los Angeles   \n",
+       "57           Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles   \n",
+       "27                  Big Blue Bus, Metro - Los Angeles, Metro - Los Angeles   \n",
+       "5                                        Big Blue Bus, Metro - Los Angeles   \n",
+       "1                                                      Metro - Los Angeles   \n",
+       "..                                                                     ...   \n",
+       "118  Amtrak, Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles   \n",
+       "119                      Amtrak, Big Blue Bus, Metro - Los Angeles, Amtrak   \n",
+       "120  Amtrak, Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles   \n",
+       "121                               Metro - Los Angeles, Metro - Los Angeles   \n",
+       "122          Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles   \n",
+       "\n",
+       "       n  agency_count  n_modes_taken  \n",
+       "15   501             1              2  \n",
+       "57   375             1              3  \n",
+       "27   192             2              3  \n",
+       "5    171             2              2  \n",
+       "1    145             1              1  \n",
+       "..   ...           ...            ...  \n",
+       "118    1             2              4  \n",
+       "119    1             3              4  \n",
+       "120    1             2              4  \n",
+       "121    1             1              2  \n",
+       "122    1             1              3  \n",
+       "\n",
+       "[123 rows x 6 columns]"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agencies_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "0cd5c4f6-116a-41a9-b67c-d4146994ee36",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>transit_submode</th>\n",
+       "      <th>n</th>\n",
+       "      <th>n_modes_taken</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>bus, bus, bus</td>\n",
+       "      <td>855</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>bus, bus</td>\n",
+       "      <td>842</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>bus</td>\n",
+       "      <td>163</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>bus, light_rail, bus</td>\n",
+       "      <td>124</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>bus, bus, bus, bus</td>\n",
+       "      <td>85</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>light_rail, bus</td>\n",
+       "      <td>56</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>light_rail, bus, bus</td>\n",
+       "      <td>24</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>bus, light_rail, bus, bus</td>\n",
+       "      <td>18</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>light_rail, light_rail, bus</td>\n",
+       "      <td>12</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>bus, bus, subway</td>\n",
+       "      <td>7</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>bus, light_rail, light_rail, bus</td>\n",
+       "      <td>7</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>rail, bus, bus</td>\n",
+       "      <td>5</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>bus, bus, light_rail</td>\n",
+       "      <td>2</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>light_rail, bus, bus, bus</td>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>rail, bus, bus, bus</td>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>bus, bus, light_rail, bus</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>bus, light_rail</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>bus, rail</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>rail, bus, bus, rail</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>rail, bus, light_rail, bus</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>subway, bus</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>subway, bus, bus</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     transit_submode    n  n_modes_taken\n",
+       "2                      bus, bus, bus  855              3\n",
+       "1                           bus, bus  842              2\n",
+       "0                                bus  163              1\n",
+       "8               bus, light_rail, bus  124              3\n",
+       "3                 bus, bus, bus, bus   85              4\n",
+       "12                   light_rail, bus   56              2\n",
+       "13              light_rail, bus, bus   24              3\n",
+       "9          bus, light_rail, bus, bus   18              4\n",
+       "15       light_rail, light_rail, bus   12              3\n",
+       "6                   bus, bus, subway    7              3\n",
+       "10  bus, light_rail, light_rail, bus    7              4\n",
+       "16                    rail, bus, bus    5              3\n",
+       "4               bus, bus, light_rail    2              3\n",
+       "14         light_rail, bus, bus, bus    2              4\n",
+       "17               rail, bus, bus, bus    2              4\n",
+       "5          bus, bus, light_rail, bus    1              4\n",
+       "7                    bus, light_rail    1              2\n",
+       "11                         bus, rail    1              2\n",
+       "18              rail, bus, bus, rail    1              4\n",
+       "19        rail, bus, light_rail, bus    1              4\n",
+       "20                       subway, bus    1              2\n",
+       "21                  subway, bus, bus    1              3"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mode_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3d93bd0e-f30d-4a53-9077-25818eef0cf7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "cb12d509-d786-458c-894a-193c80666bb6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## This line of code gets all agencies listed, even if agency is named twice. \n",
+    "## Need code that counts the unique agencies\n",
+    "#ptt_agency_count['agency_count'] = ptt_agency_count.transit_agency.apply(lambda x: len(x.split(\", \")))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0b628473-3842-44df-bbe0-9e17a1e250f7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "589d2a23-b528-4de9-b6a0-a10f88a6da5c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "505f47b1-229a-4cd1-90b8-b83b4ccdd6c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "modes_count = agencies_test>>group_by(_.n_modes_taken)>>summarize(n_trips = _.n.sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "97746912-39f0-4c85-80d3-a00ed47922a8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>n_modes_taken</th>\n",
+       "      <th>n_trips</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>163</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>901</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>1030</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>117</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   n_modes_taken  n_trips\n",
+       "0              1      163\n",
+       "1              2      901\n",
+       "2              3     1030\n",
+       "3              4      117"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modes_count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "5353a2e4-762d-4a27-8f32-267c2c55bb90",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-16ed8bc70e8949d799ea0dfb3ebdf7e1.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-16ed8bc70e8949d799ea0dfb3ebdf7e1.vega-embed details,\n",
+       "  #altair-viz-16ed8bc70e8949d799ea0dfb3ebdf7e1.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-16ed8bc70e8949d799ea0dfb3ebdf7e1\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-16ed8bc70e8949d799ea0dfb3ebdf7e1\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-16ed8bc70e8949d799ea0dfb3ebdf7e1\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-f92214c4a7adf96c9fa24e974acacdca\"}, \"mark\": {\"type\": \"bar\", \"size\": 60}, \"encoding\": {\"color\": {\"field\": \"n_trips\", \"scale\": {\"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"title\": \"Number of Trips\", \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"n_modes_taken\", \"type\": \"quantitative\"}, {\"field\": \"n_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"n_modes_taken\", \"title\": \"Number of Modes Taken per Trip\", \"type\": \"quantitative\"}, \"y\": {\"field\": \"n_trips\", \"title\": \"Number of Trips\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"How Many Modes are Taken Per Trip\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-f92214c4a7adf96c9fa24e974acacdca\": [{\"n_modes_taken\": 1, \"n_trips\": 163}, {\"n_modes_taken\": 2, \"n_trips\": 901}, {\"n_modes_taken\": 3, \"n_trips\": 1030}, {\"n_modes_taken\": 4, \"n_trips\": 117}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart((modes_count))\n",
+    "        .mark_bar(size=60)\n",
+    "        .encode(\n",
+    "            x=alt.X(\"n_modes_taken\", title =\"Number of Modes Taken per Trip\"),\n",
+    "            y=alt.Y(\"n_trips\", title = \"Number of Trips\"),\n",
+    "            color=alt.Color(\"n_trips\", title = \"Number of Trips\",\n",
+    "                            scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS)),\n",
+    "            tooltip=modes_count.columns.tolist())\n",
+    "            \n",
+    "      .properties(title = \"How Many Modes are Taken Per Trip\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "71d43883-c5fe-4dff-9084-41426c399cec",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "68cafc15-d68a-49ea-9e03-48bbcb6513d5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "fb8565b9-989a-459a-bede-433de30252e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agency_mode_trips = agencies_test>>group_by(_.agency_count, _.n_modes_taken)>>summarize(ntrips=_.n.sum())>>arrange(-_.ntrips)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "b03dbe0a-a759-4fa9-849b-b31b318f86cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-2230ce87e122408986f300fc7edb0a63.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-2230ce87e122408986f300fc7edb0a63.vega-embed details,\n",
+       "  #altair-viz-2230ce87e122408986f300fc7edb0a63.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-2230ce87e122408986f300fc7edb0a63\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-2230ce87e122408986f300fc7edb0a63\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-2230ce87e122408986f300fc7edb0a63\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-45edf6f3ff5ac7fde669ffec06507a88\"}, \"mark\": {\"type\": \"circle\", \"size\": 100}, \"encoding\": {\"color\": {\"field\": \"ntrips\", \"scale\": {\"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"title\": \"Number of Trips\", \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"agency_count\", \"type\": \"quantitative\"}, {\"field\": \"n_modes_taken\", \"type\": \"quantitative\"}, {\"field\": \"ntrips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"agency_count\", \"title\": \"Number of Agencies\", \"type\": \"quantitative\"}, \"y\": {\"field\": \"n_modes_taken\", \"title\": \"Number of Modes Taken\", \"type\": \"quantitative\"}}, \"height\": 300, \"title\": \"How Many Modes are Taken Per Trip\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-45edf6f3ff5ac7fde669ffec06507a88\": [{\"agency_count\": 1, \"n_modes_taken\": 2, \"ntrips\": 561}, {\"agency_count\": 1, \"n_modes_taken\": 3, \"ntrips\": 509}, {\"agency_count\": 2, \"n_modes_taken\": 3, \"ntrips\": 438}, {\"agency_count\": 2, \"n_modes_taken\": 2, \"ntrips\": 340}, {\"agency_count\": 1, \"n_modes_taken\": 1, \"ntrips\": 163}, {\"agency_count\": 3, \"n_modes_taken\": 3, \"ntrips\": 83}, {\"agency_count\": 2, \"n_modes_taken\": 4, \"ntrips\": 59}, {\"agency_count\": 1, \"n_modes_taken\": 4, \"ntrips\": 45}, {\"agency_count\": 3, \"n_modes_taken\": 4, \"ntrips\": 13}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart((agency_mode_trips))\n",
+    "        .mark_circle(size=100)\n",
+    "        .encode(\n",
+    "            x=alt.X(\"agency_count\", title =\"Number of Agencies\"),\n",
+    "            y=alt.Y(\"n_modes_taken\", title = \"Number of Modes Taken\"),\n",
+    "            color=alt.Color(\"ntrips\", title = \"Number of Trips\",\n",
+    "                            scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS)),\n",
+    "            tooltip=agency_mode_trips.columns.tolist())\n",
+    "            \n",
+    "      .properties(title = \"How Many Modes are Taken Per Trip\",\n",
+    "    width=800,\n",
+    "    height=300)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "91273d26-1fd1-42a1-b829-a77398c606fc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "6bd200d7-c0b9-4649-adf1-e025d216328b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##### Getting columns for each agency and counts "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ebb28116-cc54-43ce-ac77-9dc9e798d58a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2c39646f-7503-4c96-a594-5bbe5960d9f0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "e8f5f457-ce9f-4bfb-99f6-82e6eb7d11f0",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# ptt_agency_count['transit_agency'].unique().tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5c1af5bd-c08e-472e-9b71-aac3c29ceb71",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "3c399936-bc62-491c-b71d-89a861e02fc7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agency_list = _utils.get_list_of_agencies(agencies_test, \"transit_agency\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "416d16f0-3128-4857-9136-69f0403ce5cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# len(agency_list)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "f303acae-da1b-44a5-98b2-2f8f5b98f56a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Agencies Identified in Trips Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'Amtrak',\n",
+       " 'Avta',\n",
+       " 'Beach Cities Transit-City Of Redondo Beach',\n",
+       " 'Big Blue Bus',\n",
+       " 'Culver Citybus',\n",
+       " 'Foothill Transit',\n",
+       " 'Gtrans',\n",
+       " 'La Go Bus',\n",
+       " 'Ladot126',\n",
+       " 'Ladotdt',\n",
+       " 'Ladotmvn',\n",
+       " 'Ladotmvs',\n",
+       " 'Long Beach Transit',\n",
+       " 'Metro - Los Angeles',\n",
+       " 'Metrolink Trains',\n",
+       " 'Santa Clarita Transit'}"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Agencies Identified in Trips Data</strong></h4>\")) \n",
+    "\n",
+    "(agency_list)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b121b63-083b-4898-9eb1-cb919698d9ca",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "34eada82-1f1c-4411-8dd4-3bb71b0ddb16",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "71af6e25-52b0-45e9-ba2b-a00a670e3010",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "### making a copy of the ptt_agency_count\n",
+    "# df = r_trips.copy()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5bdc0792-219c-4877-880c-cd7d84db2303",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2de92f7b-2e28-4388-880f-9e34b8b603ea",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89479d3a-eeb5-491a-a064-49a77194109e",
+   "metadata": {},
+   "source": [
+    "##### Trying ChatGPT approach"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "bd6f46a5-404f-41eb-9fd8-4600451e6d20",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# agency_indv_count = (df>>filter(_.primary_mode==\"public_transit\")>>select(_.transit_agency))\n",
+    "# agency_indv_count['transit_agency'] = agency_indv_count['transit_agency'].astype(str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "33c93185-2e76-4257-840e-c7634f3cae05",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# agency_indv_count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a50d438-a9c1-4ade-8a38-0e17227dac09",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "045be8fb-d8fd-4019-8282-df53602b122b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "efc4eb07-c0f9-4bc2-87bb-cac95f606657",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = _utils.get_dummies_by_agency(agencies_test, \"transit_agency\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ca4b0345-f196-40cc-8b26-f42abb58f199",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "97bc34c4-636f-46ca-a257-95e4af242584",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##### Identifying trips with one agency"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "46856b31-47ac-408c-903e-19d8b04283f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cols_to_keep = [\"transit_submode\",\"unique_agencies\", \"n\",\"n_modes_taken\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "2603e7e0-389a-49fb-93e9-5dc1d52c6012",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# chart = (alt.Chart(df)\n",
+    "#              .mark_circle(size=100)\n",
+    "#              .encode(\n",
+    "#                  x=alt.X(\"n_modes_taken\", title=\"Number of Modes taken\"),\n",
+    "#                  y=alt.Y(\"n\", title=\"Number of Trips\"),\n",
+    "#                  color = alt.Color(\"agency_count\", title=\"Number of Unique Agencies\",\n",
+    "#                                   scale=alt.Scale(\n",
+    "#                                       range=cp.CALITP_DIVERGING_COLORS,\n",
+    "#                                       domain=df[\"agency_count\"].unique().tolist())\n",
+    "#             ),\n",
+    "#             tooltip=cols_to_keep)\n",
+    "#         .properties(title = (\"Transit Trips Agency Breakdown\"), width=500,\n",
+    "#     height=300)\n",
+    "#         )\n",
+    "# chart                    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "149ed63c-436c-45fe-a526-5b1bf9f3d6fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# (df>>filter(_.agency_count==1)>>arrange(-_.n))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d400fa0e-2bb1-4d8a-9a63-6865afe33897",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "7228c540-3033-4023-8145-91f8aee23eeb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-cef0b9ddc57f4ddbb8b34aac08e67194.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-cef0b9ddc57f4ddbb8b34aac08e67194.vega-embed details,\n",
+       "  #altair-viz-cef0b9ddc57f4ddbb8b34aac08e67194.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-cef0b9ddc57f4ddbb8b34aac08e67194\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-cef0b9ddc57f4ddbb8b34aac08e67194\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-cef0b9ddc57f4ddbb8b34aac08e67194\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-a895a14dba8cc38710f07dfb5ccab89f\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"n_modes_taken\", \"scale\": {\"range\": [\"#B9D6DF\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\", \"#0B405B\"]}, \"title\": \"Number of Trips\", \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"transit_submode\", \"type\": \"nominal\"}, {\"field\": \"unique_agencies\", \"type\": \"nominal\"}, {\"field\": \"n\", \"type\": \"quantitative\"}, {\"field\": \"n_modes_taken\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"unique_agencies\", \"title\": \"Agency\", \"type\": \"nominal\"}, \"y\": {\"field\": \"n\", \"title\": \"Number of Modes taken\", \"type\": \"quantitative\"}}, \"height\": 500, \"title\": \"Transit Trips With Only One Agency\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-a895a14dba8cc38710f07dfb5ccab89f\": [{\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles\", \"n\": 501, \"agency_count\": 1, \"n_modes_taken\": 2, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 2, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 375, \"agency_count\": 1, \"n_modes_taken\": 3, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 3, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus\", \"transit_agency\": \"Metro - Los Angeles\", \"n\": 145, \"agency_count\": 1, \"n_modes_taken\": 1, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 1, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, light_rail, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 93, \"agency_count\": 1, \"n_modes_taken\": 3, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 3, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"light_rail, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles\", \"n\": 55, \"agency_count\": 1, \"n_modes_taken\": 2, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 2, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, bus, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 33, \"agency_count\": 1, \"n_modes_taken\": 4, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 4, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"light_rail, bus, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 19, \"agency_count\": 1, \"n_modes_taken\": 3, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 3, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus\", \"transit_agency\": \"LADOTMVN\", \"n\": 16, \"agency_count\": 1, \"n_modes_taken\": 1, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 1, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 0, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"LADOTMVN\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"light_rail, light_rail, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 12, \"agency_count\": 1, \"n_modes_taken\": 3, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 3, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, light_rail, bus, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 10, \"agency_count\": 1, \"n_modes_taken\": 4, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 4, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, subway\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 6, \"agency_count\": 1, \"n_modes_taken\": 3, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 3, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus\", \"transit_agency\": \"Santa Clarita Transit, Santa Clarita Transit\", \"n\": 3, \"agency_count\": 1, \"n_modes_taken\": 2, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 0, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 2, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Santa Clarita Transit\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus\", \"transit_agency\": \"Santa Clarita Transit\", \"n\": 2, \"agency_count\": 1, \"n_modes_taken\": 1, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 0, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 1, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Santa Clarita Transit\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, bus\", \"transit_agency\": \"Santa Clarita Transit, Santa Clarita Transit, Santa Clarita Transit\", \"n\": 2, \"agency_count\": 1, \"n_modes_taken\": 3, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 0, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 3, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Santa Clarita Transit\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus\", \"transit_agency\": \"LADOTMVN, LADOTMVN\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 2, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 2, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 0, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"LADOTMVN\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, light_rail\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 3, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 3, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"bus, bus, light_rail, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 4, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 4, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"light_rail, bus, bus, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 4, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 4, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"subway, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 2, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 2, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}, {\"primary_mode\": \"public_transit\", \"transit_submode\": \"subway, bus, bus\", \"transit_agency\": \"Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\", \"n\": 1, \"agency_count\": 1, \"n_modes_taken\": 3, \"Foothill Transit\": 0, \"LADOTMVS\": 0, \"LADOTMVN\": 0, \"AVTA\": 0, \"Beach Cities Transit-City of Redondo Beach\": 0, \"Metro - Los Angeles\": 3, \"Long Beach Transit\": 0, \"LADOT126\": 0, \"Santa Clarita Transit\": 0, \"Metrolink Trains\": 0, \"LADOTDT\": 0, \"Culver CityBus\": 0, \"GTrans\": 0, \"Amtrak\": 0, \"LA Go Bus\": 0, \"Big Blue Bus\": 0, \"unique_agencies\": \"Metro - Los Angeles\"}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (alt.Chart((df>>filter(_.agency_count==1)))\n",
+    "             .mark_bar()\n",
+    "             .encode(\n",
+    "                 x=alt.X(\"unique_agencies\", title=\"Agency\"),\n",
+    "                 y=alt.Y(\"n\", title=\"Number of Modes taken\"),\n",
+    "                 color = alt.Color(\"n_modes_taken\", title=\"Number of Trips\",\n",
+    "                                  scale=alt.Scale(\n",
+    "                                      range=cp.CALITP_SEQUENTIAL_COLORS,)),\n",
+    "            tooltip=cols_to_keep)\n",
+    "        .properties(title = (\"Transit Trips With Only One Agency\"), width=800,\n",
+    "    height=500)\n",
+    "        )\n",
+    "chart           "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "60df338f-801f-49a1-a26f-0be5e03bddf3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Most Common Agency Combination</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>transit_agency</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>57</th>\n",
+       "      <td>Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>Big Blue Bus, Metro - Los Angeles, Metro - Los Angeles</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Big Blue Bus, Metro - Los Angeles</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Metro - Los Angeles</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                   transit_agency\n",
+       "15                       Metro - Los Angeles, Metro - Los Angeles\n",
+       "57  Metro - Los Angeles, Metro - Los Angeles, Metro - Los Angeles\n",
+       "27         Big Blue Bus, Metro - Los Angeles, Metro - Los Angeles\n",
+       "5                               Big Blue Bus, Metro - Los Angeles\n",
+       "1                                             Metro - Los Angeles"
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Most Common Agency Combination</strong></h4>\")) \n",
+    "\n",
+    "(df>>arrange(-_.n)>>select(_.transit_agency)).head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "786394ef-be26-4e0d-94e7-35386d6d67c0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fd43ab95-0391-407b-b6b0-185034ba9528",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "febd910a-2f1d-4b99-bb3b-76adb11f0b63",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "96b794f2-bcfd-4afb-9ce5-8793c15fe199",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/jovyan/data-analyses/sb125_analyses/corridor_study/_utils.py:102: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.\n",
+      "  df_agencies['n_trips'] = df_agencies[list(df_agencies.columns)].sum(axis=1)\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_agencies = _utils.get_agencies_occurances(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "80cbffde-6686-4921-b543-84e52f97a0c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>agency</th>\n",
+       "      <th>n_trips</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Foothill Transit</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>LADOTMVS</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>LADOTMVN</td>\n",
+       "      <td>54</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>AVTA</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Beach Cities Transit-City of Redondo Beach</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Metro - Los Angeles</td>\n",
+       "      <td>195</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Long Beach Transit</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>LADOT126</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Santa Clarita Transit</td>\n",
+       "      <td>28</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Metrolink Trains</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>LADOTDT</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>Culver CityBus</td>\n",
+       "      <td>28</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>GTrans</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>Amtrak</td>\n",
+       "      <td>8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>LA Go Bus</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>Big Blue Bus</td>\n",
+       "      <td>37</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                        agency  n_trips\n",
+       "0                             Foothill Transit        1\n",
+       "1                                     LADOTMVS        4\n",
+       "2                                     LADOTMVN       54\n",
+       "3                                         AVTA        4\n",
+       "4   Beach Cities Transit-City of Redondo Beach        2\n",
+       "5                          Metro - Los Angeles      195\n",
+       "6                           Long Beach Transit        1\n",
+       "7                                     LADOT126        4\n",
+       "8                        Santa Clarita Transit       28\n",
+       "9                             Metrolink Trains        1\n",
+       "10                                     LADOTDT        3\n",
+       "11                              Culver CityBus       28\n",
+       "12                                      GTrans        1\n",
+       "13                                      Amtrak        8\n",
+       "14                                   LA Go Bus        1\n",
+       "15                                Big Blue Bus       37"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_agencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "id": "f98c76b9-b83f-42c3-aa12-702ade72ac38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tooltip_cols = [\"agency\", \"n_trips\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "bf160b81-1bc2-4374-9529-6400252d5e4f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-ed27324385954076b4e0a27a81eef8aa.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-ed27324385954076b4e0a27a81eef8aa.vega-embed details,\n",
+       "  #altair-viz-ed27324385954076b4e0a27a81eef8aa.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-ed27324385954076b4e0a27a81eef8aa\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-ed27324385954076b4e0a27a81eef8aa\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-ed27324385954076b4e0a27a81eef8aa\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-42b0ff3c2e3eaea341f1d9c4293fedf1\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"n_trips\", \"scale\": {\"range\": [\"#B9D6DF\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\", \"#0B405B\"]}, \"type\": \"quantitative\"}, \"tooltip\": [{\"field\": \"agency\", \"type\": \"nominal\"}, {\"field\": \"n_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"agency\", \"title\": \"Agency Name\", \"type\": \"nominal\"}, \"y\": {\"field\": \"n_trips\", \"title\": \"Number of boardings reported for trips (One person taking two LA Metro trips will count as 2)\", \"type\": \"quantitative\"}}, \"height\": 500, \"title\": \"Number of Times an Agency was used for Trip Taking\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-42b0ff3c2e3eaea341f1d9c4293fedf1\": [{\"agency\": \"Foothill Transit\", \"n_trips\": 1}, {\"agency\": \"LADOTMVS\", \"n_trips\": 4}, {\"agency\": \"LADOTMVN\", \"n_trips\": 54}, {\"agency\": \"AVTA\", \"n_trips\": 4}, {\"agency\": \"Beach Cities Transit-City of Redondo Beach\", \"n_trips\": 2}, {\"agency\": \"Metro - Los Angeles\", \"n_trips\": 195}, {\"agency\": \"Long Beach Transit\", \"n_trips\": 1}, {\"agency\": \"LADOT126\", \"n_trips\": 4}, {\"agency\": \"Santa Clarita Transit\", \"n_trips\": 28}, {\"agency\": \"Metrolink Trains\", \"n_trips\": 1}, {\"agency\": \"LADOTDT\", \"n_trips\": 3}, {\"agency\": \"Culver CityBus\", \"n_trips\": 28}, {\"agency\": \"GTrans\", \"n_trips\": 1}, {\"agency\": \"Amtrak\", \"n_trips\": 8}, {\"agency\": \"LA Go Bus\", \"n_trips\": 1}, {\"agency\": \"Big Blue Bus\", \"n_trips\": 37}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 61,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (alt.Chart(df_agencies)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"agency\", title = \"Agency Name\"),\n",
+    "            y=alt.Y(\"n_trips\", title= \"Number of boardings reported for trips (One person taking two LA Metro trips will count as 2)\"),\n",
+    "            color=alt.Color(\"n_trips\", scale=alt.Scale(range = cp.CALITP_SEQUENTIAL_COLORS)),\n",
+    "            tooltip = tooltip_cols)\n",
+    "      .properties(title = \"Number of Times an Agency was used for Trip Taking\",\n",
+    "    width=800,\n",
+    "    height=500)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a59f170f-b2e0-41b3-ae7a-1ae4eca12596",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "16b45917-adc3-44d0-8d76-15ccd4083d26",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Trips by Resident Type</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Trips by Resident Type</strong></h4>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "5163926e-82bd-4c25-9486-45229d09a0d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trip_by_res_type = (r_trips\n",
+    " >>group_by(_.primary_mode,_.trip_taker_resident_type)\n",
+    " >>summarize(number_trips = _.activity_id.nunique())\n",
+    " >>arrange(_.primary_mode))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "636e7771-0ba7-42e9-af1d-e3e998ff8599",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>trip_taker_resident_type</th>\n",
+       "      <th>number_trips</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>core</td>\n",
+       "      <td>116685</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>donut</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>visitor</td>\n",
+       "      <td>28818</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>commercial</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>10154</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>on_demand_auto</td>\n",
+       "      <td>core</td>\n",
+       "      <td>3191</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>on_demand_auto</td>\n",
+       "      <td>visitor</td>\n",
+       "      <td>595</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>core</td>\n",
+       "      <td>294704</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>donut</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>visitor</td>\n",
+       "      <td>10394</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>core</td>\n",
+       "      <td>2155</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>visitor</td>\n",
+       "      <td>56</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      primary_mode trip_taker_resident_type  number_trips\n",
+       "0   auto_passenger                     core        116685\n",
+       "1   auto_passenger                    donut             2\n",
+       "2   auto_passenger                  visitor         28818\n",
+       "3       commercial                      NaN         10154\n",
+       "4   on_demand_auto                     core          3191\n",
+       "5   on_demand_auto                  visitor           595\n",
+       "6     private_auto                     core        294704\n",
+       "7     private_auto                    donut             1\n",
+       "8     private_auto                  visitor         10394\n",
+       "9     private_auto                      NaN             1\n",
+       "10  public_transit                     core          2155\n",
+       "11  public_transit                  visitor            56"
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trip_by_res_type"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "id": "90c5d683-91c5-4663-accd-4e45027a3e49",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "  #altair-viz-b5eb8bbcdcad4751a775bacd2396e6e4.vega-embed {\n",
+       "    width: 100%;\n",
+       "    display: flex;\n",
+       "  }\n",
+       "\n",
+       "  #altair-viz-b5eb8bbcdcad4751a775bacd2396e6e4.vega-embed details,\n",
+       "  #altair-viz-b5eb8bbcdcad4751a775bacd2396e6e4.vega-embed details summary {\n",
+       "    position: relative;\n",
+       "  }\n",
+       "</style>\n",
+       "<div id=\"altair-viz-b5eb8bbcdcad4751a775bacd2396e6e4\"></div>\n",
+       "<script type=\"text/javascript\">\n",
+       "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
+       "  (function(spec, embedOpt){\n",
+       "    let outputDiv = document.currentScript.previousElementSibling;\n",
+       "    if (outputDiv.id !== \"altair-viz-b5eb8bbcdcad4751a775bacd2396e6e4\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-b5eb8bbcdcad4751a775bacd2396e6e4\");\n",
+       "    }\n",
+       "    const paths = {\n",
+       "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
+       "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
+       "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm/vega-lite@5.14.1?noext\",\n",
+       "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm/vega-embed@6?noext\",\n",
+       "    };\n",
+       "\n",
+       "    function maybeLoadScript(lib, version) {\n",
+       "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
+       "      return (VEGA_DEBUG[key] == version) ?\n",
+       "        Promise.resolve(paths[lib]) :\n",
+       "        new Promise(function(resolve, reject) {\n",
+       "          var s = document.createElement('script');\n",
+       "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+       "          s.async = true;\n",
+       "          s.onload = () => {\n",
+       "            VEGA_DEBUG[key] = version;\n",
+       "            return resolve(paths[lib]);\n",
+       "          };\n",
+       "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+       "          s.src = paths[lib];\n",
+       "        });\n",
+       "    }\n",
+       "\n",
+       "    function showError(err) {\n",
+       "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+       "      throw err;\n",
+       "    }\n",
+       "\n",
+       "    function displayChart(vegaEmbed) {\n",
+       "      vegaEmbed(outputDiv, spec, embedOpt)\n",
+       "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+       "    }\n",
+       "\n",
+       "    if(typeof define === \"function\" && define.amd) {\n",
+       "      requirejs.config({paths});\n",
+       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "    } else {\n",
+       "      maybeLoadScript(\"vega\", \"5\")\n",
+       "        .then(() => maybeLoadScript(\"vega-lite\", \"5.14.1\"))\n",
+       "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
+       "        .catch(showError)\n",
+       "        .then(() => displayChart(vegaEmbed));\n",
+       "    }\n",
+       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"data\": {\"name\": \"data-98adfad59e1a2bdb6885e749a6848056\"}, \"mark\": {\"type\": \"bar\"}, \"encoding\": {\"color\": {\"field\": \"trip_taker_resident_type\", \"scale\": {\"domain\": [\"core\", \"donut\", \"visitor\", NaN], \"range\": [\"#E16B26\", \"#EB9F3C\", \"#f6e7e1\", \"#8CBCCB\", \"#2EA8CE\", \"#136C97\"]}, \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"primary_mode\", \"type\": \"nominal\"}, {\"field\": \"trip_taker_resident_type\", \"type\": \"nominal\"}, {\"field\": \"number_trips\", \"type\": \"quantitative\"}], \"x\": {\"field\": \"primary_mode\", \"title\": \"Mode\", \"type\": \"nominal\"}, \"y\": {\"field\": \"number_trips\", \"title\": \"Number of Trips\", \"type\": \"quantitative\"}}, \"height\": 500, \"title\": \"Trips by Resident Type\", \"width\": 800, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.14.1.json\", \"datasets\": {\"data-98adfad59e1a2bdb6885e749a6848056\": [{\"primary_mode\": \"auto_passenger\", \"trip_taker_resident_type\": \"core\", \"number_trips\": 116685}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_resident_type\": \"donut\", \"number_trips\": 2}, {\"primary_mode\": \"auto_passenger\", \"trip_taker_resident_type\": \"visitor\", \"number_trips\": 28818}, {\"primary_mode\": \"commercial\", \"trip_taker_resident_type\": null, \"number_trips\": 10154}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_resident_type\": \"core\", \"number_trips\": 3191}, {\"primary_mode\": \"on_demand_auto\", \"trip_taker_resident_type\": \"visitor\", \"number_trips\": 595}, {\"primary_mode\": \"private_auto\", \"trip_taker_resident_type\": \"core\", \"number_trips\": 294704}, {\"primary_mode\": \"private_auto\", \"trip_taker_resident_type\": \"donut\", \"number_trips\": 1}, {\"primary_mode\": \"private_auto\", \"trip_taker_resident_type\": \"visitor\", \"number_trips\": 10394}, {\"primary_mode\": \"private_auto\", \"trip_taker_resident_type\": null, \"number_trips\": 1}, {\"primary_mode\": \"public_transit\", \"trip_taker_resident_type\": \"core\", \"number_trips\": 2155}, {\"primary_mode\": \"public_transit\", \"trip_taker_resident_type\": \"visitor\", \"number_trips\": 56}]}}, {\"mode\": \"vega-lite\"});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "alt.Chart(...)"
+      ]
+     },
+     "execution_count": 65,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chart = (\n",
+    "        alt.Chart(trip_by_res_type)\n",
+    "        .mark_bar()\n",
+    "        .encode(\n",
+    "            x=alt.X(\"primary_mode\", title = \"Mode\"),\n",
+    "            y=alt.Y(\"number_trips\", title = \"Number of Trips\"),\n",
+    "            color=alt.Color(\"trip_taker_resident_type\", scale=alt.Scale(range = cp.CALITP_DIVERGING_COLORS,\n",
+    "                                                                         domain=trip_by_res_type[\"trip_taker_resident_type\"].unique().tolist())\n",
+    "            ),\n",
+    "            tooltip=trip_by_res_type.columns.tolist())\n",
+    "      .properties(title = \"Trips by Resident Type\",\n",
+    "    width=800,\n",
+    "    height=500)\n",
+    "        )\n",
+    "chart "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f7b51fbb-8b87-4863-bcd9-50ed5047d7d6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "878c5c8e-18c3-456a-b641-67ad010f5101",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Unique Household Ids</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Unique Household Ids</strong></h4>\")) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "2a31bf27-ccc4-4ce3-8b6a-31dbd14caaf2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>trip_taker_household_id</th>\n",
+       "      <th>n</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>160790</th>\n",
+       "      <td></td>\n",
+       "      <td>33634</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>267303</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>16384</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>79436</th>\n",
+       "      <td>9146817053558612433</td>\n",
+       "      <td>16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23626</th>\n",
+       "      <td>2709972826117271852</td>\n",
+       "      <td>15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30303</th>\n",
+       "      <td>3488167635549658463</td>\n",
+       "      <td>14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>267296</th>\n",
+       "      <td>9999130854496671765</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>267299</th>\n",
+       "      <td>999930961444594419</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>267300</th>\n",
+       "      <td>9999534358623422158</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>267301</th>\n",
+       "      <td>9999886348099258237</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>267302</th>\n",
+       "      <td>9999902755724147714</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>267304 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       trip_taker_household_id      n\n",
+       "160790                          33634\n",
+       "267303                     NaN  16384\n",
+       "79436      9146817053558612433     16\n",
+       "23626      2709972826117271852     15\n",
+       "30303      3488167635549658463     14\n",
+       "...                        ...    ...\n",
+       "267296     9999130854496671765      1\n",
+       "267299      999930961444594419      1\n",
+       "267300     9999534358623422158      1\n",
+       "267301     9999886348099258237      1\n",
+       "267302     9999902755724147714      1\n",
+       "\n",
+       "[267304 rows x 2 columns]"
+      ]
+     },
+     "execution_count": 67,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips>>count(_.trip_taker_household_id)>>arrange(-_.n)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "eb9780a3-b996-45af-9cc3-b41629ec0e55",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Checking one household id</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Checking one household id</strong></h4>\")) \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "id": "6fc3be54-b8dc-4cf8-893e-565ffa02934d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "16\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>activity_id</th>\n",
+       "      <th>origin_bgrp_2020</th>\n",
+       "      <th>origin_trct_2020</th>\n",
+       "      <th>origin_cty_2020</th>\n",
+       "      <th>origin_st_2020</th>\n",
+       "      <th>destination_bgrp_2020</th>\n",
+       "      <th>destination_trct_2020</th>\n",
+       "      <th>destination_cty_2020</th>\n",
+       "      <th>destination_st_2020</th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>trip_purpose</th>\n",
+       "      <th>previous_trip_purpose</th>\n",
+       "      <th>trip_start_time</th>\n",
+       "      <th>trip_end_time</th>\n",
+       "      <th>trip_duration_minutes</th>\n",
+       "      <th>trip_distance_miles</th>\n",
+       "      <th>vehicle_type</th>\n",
+       "      <th>vehicle_fuel_type</th>\n",
+       "      <th>transit_submode</th>\n",
+       "      <th>transit_agency</th>\n",
+       "      <th>transit_route</th>\n",
+       "      <th>origin_land_use</th>\n",
+       "      <th>origin_building_use</th>\n",
+       "      <th>destination_land_use</th>\n",
+       "      <th>destination_building_use</th>\n",
+       "      <th>trip_taker_person_id</th>\n",
+       "      <th>trip_taker_household_id</th>\n",
+       "      <th>trip_taker_age</th>\n",
+       "      <th>trip_taker_sex</th>\n",
+       "      <th>trip_taker_race_ethnicity</th>\n",
+       "      <th>trip_taker_employment_status</th>\n",
+       "      <th>trip_taker_wfh</th>\n",
+       "      <th>trip_taker_individual_income</th>\n",
+       "      <th>trip_taker_commute_mode</th>\n",
+       "      <th>trip_taker_household_size</th>\n",
+       "      <th>trip_taker_household_income</th>\n",
+       "      <th>trip_taker_available_vehicles</th>\n",
+       "      <th>trip_taker_resident_type</th>\n",
+       "      <th>trip_taker_industry</th>\n",
+       "      <th>trip_taker_building_type</th>\n",
+       "      <th>trip_taker_school_grade_attending</th>\n",
+       "      <th>trip_taker_education</th>\n",
+       "      <th>trip_taker_tenure</th>\n",
+       "      <th>trip_taker_language</th>\n",
+       "      <th>trip_taker_home_bgrp_2020</th>\n",
+       "      <th>trip_taker_home_trct_2020</th>\n",
+       "      <th>trip_taker_home_cty_2020</th>\n",
+       "      <th>trip_taker_home_st_2020</th>\n",
+       "      <th>trip_taker_work_bgrp_2020</th>\n",
+       "      <th>trip_taker_work_trct_2020</th>\n",
+       "      <th>trip_taker_work_cty_2020</th>\n",
+       "      <th>trip_taker_work_st_2020</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>304389</th>\n",
+       "      <td>11797067000884676673</td>\n",
+       "      <td>1 (Tract 7010, Los Angeles, CA)</td>\n",
+       "      <td>7010 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>1 (Tract 2623.01, Los Angeles, CA)</td>\n",
+       "      <td>2623.01 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>home</td>\n",
+       "      <td>work</td>\n",
+       "      <td>18:33:00</td>\n",
+       "      <td>18:55:47</td>\n",
+       "      <td>22</td>\n",
+       "      <td>10.00</td>\n",
+       "      <td>unknown_vehicle_type</td>\n",
+       "      <td>unknown_fuel_type</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>office</td>\n",
+       "      <td>office</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>8423484308586815884</td>\n",
+       "      <td>9146817053558612433</td>\n",
+       "      <td>32.00</td>\n",
+       "      <td>female</td>\n",
+       "      <td>asian_not_hispanic_or_latino</td>\n",
+       "      <td>employed</td>\n",
+       "      <td>in_person</td>\n",
+       "      <td>17,261.00</td>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>11.00</td>\n",
+       "      <td>318,660.00</td>\n",
+       "      <td>three_plus</td>\n",
+       "      <td>core</td>\n",
+       "      <td>naics812199</td>\n",
+       "      <td>single_family</td>\n",
+       "      <td>not_attending_school</td>\n",
+       "      <td>some_college</td>\n",
+       "      <td>owner</td>\n",
+       "      <td>asian_pacific</td>\n",
+       "      <td>1 (Tract 2623.01, Los Angeles, CA)</td>\n",
+       "      <td>2623.01 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "      <td>1 (Tract 7010, Los Angeles, CA)</td>\n",
+       "      <td>7010 (Los Angeles, CA)</td>\n",
+       "      <td>Los Angeles County, CA</td>\n",
+       "      <td>California</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                 activity_id                 origin_bgrp_2020  \\\n",
+       "304389  11797067000884676673  1 (Tract 7010, Los Angeles, CA)   \n",
+       "\n",
+       "              origin_trct_2020         origin_cty_2020 origin_st_2020  \\\n",
+       "304389  7010 (Los Angeles, CA)  Los Angeles County, CA     California   \n",
+       "\n",
+       "                     destination_bgrp_2020      destination_trct_2020  \\\n",
+       "304389  1 (Tract 2623.01, Los Angeles, CA)  2623.01 (Los Angeles, CA)   \n",
+       "\n",
+       "          destination_cty_2020 destination_st_2020    primary_mode  \\\n",
+       "304389  Los Angeles County, CA          California  auto_passenger   \n",
+       "\n",
+       "       trip_purpose previous_trip_purpose trip_start_time trip_end_time  \\\n",
+       "304389         home                  work        18:33:00      18:55:47   \n",
+       "\n",
+       "        trip_duration_minutes  trip_distance_miles          vehicle_type  \\\n",
+       "304389                     22                10.00  unknown_vehicle_type   \n",
+       "\n",
+       "        vehicle_fuel_type transit_submode transit_agency transit_route  \\\n",
+       "304389  unknown_fuel_type             NaN            NaN           NaN   \n",
+       "\n",
+       "       origin_land_use origin_building_use destination_land_use  \\\n",
+       "304389          office              office        single_family   \n",
+       "\n",
+       "       destination_building_use trip_taker_person_id trip_taker_household_id  \\\n",
+       "304389            single_family  8423484308586815884     9146817053558612433   \n",
+       "\n",
+       "        trip_taker_age trip_taker_sex     trip_taker_race_ethnicity  \\\n",
+       "304389           32.00         female  asian_not_hispanic_or_latino   \n",
+       "\n",
+       "       trip_taker_employment_status trip_taker_wfh  \\\n",
+       "304389                     employed      in_person   \n",
+       "\n",
+       "        trip_taker_individual_income trip_taker_commute_mode  \\\n",
+       "304389                     17,261.00            private_auto   \n",
+       "\n",
+       "        trip_taker_household_size  trip_taker_household_income  \\\n",
+       "304389                      11.00                   318,660.00   \n",
+       "\n",
+       "       trip_taker_available_vehicles trip_taker_resident_type  \\\n",
+       "304389                    three_plus                     core   \n",
+       "\n",
+       "       trip_taker_industry trip_taker_building_type  \\\n",
+       "304389         naics812199            single_family   \n",
+       "\n",
+       "       trip_taker_school_grade_attending trip_taker_education  \\\n",
+       "304389              not_attending_school         some_college   \n",
+       "\n",
+       "       trip_taker_tenure trip_taker_language  \\\n",
+       "304389             owner       asian_pacific   \n",
+       "\n",
+       "                 trip_taker_home_bgrp_2020  trip_taker_home_trct_2020  \\\n",
+       "304389  1 (Tract 2623.01, Los Angeles, CA)  2623.01 (Los Angeles, CA)   \n",
+       "\n",
+       "       trip_taker_home_cty_2020 trip_taker_home_st_2020  \\\n",
+       "304389   Los Angeles County, CA              California   \n",
+       "\n",
+       "              trip_taker_work_bgrp_2020 trip_taker_work_trct_2020  \\\n",
+       "304389  1 (Tract 7010, Los Angeles, CA)    7010 (Los Angeles, CA)   \n",
+       "\n",
+       "       trip_taker_work_cty_2020 trip_taker_work_st_2020  \n",
+       "304389   Los Angeles County, CA              California  "
+      ]
+     },
+     "execution_count": 69,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "print(len(r_trips>>filter(_.trip_taker_household_id == 9146817053558612433)))\n",
+    "(r_trips>>filter(_.trip_taker_household_id == 9146817053558612433)).sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "id": "4eccfdf8-429e-43df-899e-f7d77e051831",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>trip_taker_person_id</th>\n",
+       "      <th>trip_taker_age</th>\n",
+       "      <th>trip_taker_sex</th>\n",
+       "      <th>trip_taker_household_size</th>\n",
+       "      <th>n</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>4508016952300979367</td>\n",
+       "      <td>25.00</td>\n",
+       "      <td>female</td>\n",
+       "      <td>11.00</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>4736398356956282212</td>\n",
+       "      <td>38.00</td>\n",
+       "      <td>female</td>\n",
+       "      <td>11.00</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>8423484308586815884</td>\n",
+       "      <td>32.00</td>\n",
+       "      <td>female</td>\n",
+       "      <td>11.00</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12395012647665989305</td>\n",
+       "      <td>21.00</td>\n",
+       "      <td>female</td>\n",
+       "      <td>11.00</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>14673592671547908751</td>\n",
+       "      <td>18.00</td>\n",
+       "      <td>female</td>\n",
+       "      <td>11.00</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>16545634957747565398</td>\n",
+       "      <td>49.00</td>\n",
+       "      <td>female</td>\n",
+       "      <td>11.00</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>16684115452596066816</td>\n",
+       "      <td>53.00</td>\n",
+       "      <td>male</td>\n",
+       "      <td>11.00</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   trip_taker_person_id  trip_taker_age trip_taker_sex  \\\n",
+       "0   4508016952300979367           25.00         female   \n",
+       "1   4736398356956282212           38.00         female   \n",
+       "2   8423484308586815884           32.00         female   \n",
+       "3  12395012647665989305           21.00         female   \n",
+       "4  14673592671547908751           18.00         female   \n",
+       "5  16545634957747565398           49.00         female   \n",
+       "6  16684115452596066816           53.00           male   \n",
+       "\n",
+       "   trip_taker_household_size  n  \n",
+       "0                      11.00  5  \n",
+       "1                      11.00  2  \n",
+       "2                      11.00  2  \n",
+       "3                      11.00  1  \n",
+       "4                      11.00  4  \n",
+       "5                      11.00  1  \n",
+       "6                      11.00  1  "
+      ]
+     },
+     "execution_count": 70,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "## checking one household id\n",
+    "r_trips>>filter(_.trip_taker_household_id == 9146817053558612433)>>count(_.trip_taker_person_id, _.trip_taker_age,\n",
+    "                                                                         _.trip_taker_sex, _.trip_taker_household_size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c929c77d-0173-4a7d-be49-762349daf5cb",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ab226b47-4366-4fb9-aaae-e0aca760f9b3",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "id": "1483249f-602c-4805-bcc4-d55e018022ad",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Number of Travelers by Resident Type: Replica Trips Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Number of Travelers by Resident Type: Replica Trips Data</strong></h4>\")) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "5c1894f0-bd42-4014-89d4-6e8d43809319",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>trip_taker_resident_type</th>\n",
+       "      <th>_unique_ids</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>core</td>\n",
+       "      <td>246597</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>donut</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>visitor</td>\n",
+       "      <td>35198</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  trip_taker_resident_type  _unique_ids\n",
+       "0                     core       246597\n",
+       "1                    donut            2\n",
+       "2                  visitor        35198\n",
+       "3                      NaN            1"
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r_trips>>group_by(_.trip_taker_resident_type)>>summarize(_unique_ids = _.trip_taker_person_id.nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b0891b62-c968-4ea0-bd9b-753d299a5054",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "id": "2e4bd058-9c4d-4989-a5fc-db6cf6130bf2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4><strong>Traveler Demographics: Replica Trips Data</strong></h4>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Fitered for Core Residents"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>primary_mode</th>\n",
+       "      <th>trip_taker_sex</th>\n",
+       "      <th>n_ppl</th>\n",
+       "      <th>avg_h_income</th>\n",
+       "      <th>avg_p_income</th>\n",
+       "      <th>avg_age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>female</td>\n",
+       "      <td>44266</td>\n",
+       "      <td>162,899.90</td>\n",
+       "      <td>57,807.91</td>\n",
+       "      <td>43.65</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>auto_passenger</td>\n",
+       "      <td>male</td>\n",
+       "      <td>43836</td>\n",
+       "      <td>173,439.46</td>\n",
+       "      <td>87,237.70</td>\n",
+       "      <td>42.86</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>commercial</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>on_demand_auto</td>\n",
+       "      <td>female</td>\n",
+       "      <td>1560</td>\n",
+       "      <td>181,325.52</td>\n",
+       "      <td>58,599.19</td>\n",
+       "      <td>46.58</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>on_demand_auto</td>\n",
+       "      <td>male</td>\n",
+       "      <td>1532</td>\n",
+       "      <td>181,278.14</td>\n",
+       "      <td>92,035.74</td>\n",
+       "      <td>43.23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>female</td>\n",
+       "      <td>90634</td>\n",
+       "      <td>167,383.19</td>\n",
+       "      <td>62,989.92</td>\n",
+       "      <td>43.79</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>male</td>\n",
+       "      <td>99967</td>\n",
+       "      <td>174,477.16</td>\n",
+       "      <td>94,470.93</td>\n",
+       "      <td>43.81</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>private_auto</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>female</td>\n",
+       "      <td>927</td>\n",
+       "      <td>81,553.45</td>\n",
+       "      <td>39,058.57</td>\n",
+       "      <td>42.90</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>public_transit</td>\n",
+       "      <td>male</td>\n",
+       "      <td>979</td>\n",
+       "      <td>97,733.91</td>\n",
+       "      <td>44,295.90</td>\n",
+       "      <td>39.82</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     primary_mode trip_taker_sex  n_ppl  avg_h_income  avg_p_income  avg_age\n",
+       "0  auto_passenger         female  44266    162,899.90     57,807.91    43.65\n",
+       "1  auto_passenger           male  43836    173,439.46     87,237.70    42.86\n",
+       "2      commercial            NaN      1           NaN           NaN      NaN\n",
+       "3  on_demand_auto         female   1560    181,325.52     58,599.19    46.58\n",
+       "4  on_demand_auto           male   1532    181,278.14     92,035.74    43.23\n",
+       "5    private_auto         female  90634    167,383.19     62,989.92    43.79\n",
+       "6    private_auto           male  99967    174,477.16     94,470.93    43.81\n",
+       "7    private_auto            NaN      1           NaN           NaN      NaN\n",
+       "8  public_transit         female    927     81,553.45     39,058.57    42.90\n",
+       "9  public_transit           male    979     97,733.91     44,295.90    39.82"
+      ]
+     },
+     "execution_count": 73,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "display(HTML(\"<h4><strong>Traveler Demographics: Replica Trips Data</strong></h4>\")) \n",
+    "display(HTML(\"Fitered for Core Residents\")) \n",
+    "(r_trips\n",
+    " >>filter(_.trip_taker_home_bgrp_2020!=\"Visitor (no home location)\")\n",
+    " >>group_by(_.primary_mode, _.trip_taker_sex)\n",
+    " >>summarize(\n",
+    "     n_ppl = _.trip_taker_person_id.nunique(),\n",
+    "     avg_h_income = _.trip_taker_household_income.mean(),\n",
+    "     avg_p_income = _.trip_taker_individual_income.mean(),\n",
+    "     avg_age = _.trip_taker_age.mean())\n",
+    ")\n",
+    "     "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a1dba8b5-7356-441f-8e6c-0f98e0f80c4c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aa84cc8c-8b17-41b6-abdf-c8397ef1e706",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "101bbd51-38b9-4791-8119-f0dc3002b6a6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bbc819b1-0dfc-46be-90bd-b136263dc22c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}