Merge pull request #436 from cal-itp/tircp_cleanup

TIRCP

Author: amandaha8

consolidated_app/utilities.py

@@ -3,10 +3,8 @@
 from calitp import *
 from plotnine import *
 import intake
-from shared_utils import geography_utils
 
 import altair as alt
-import altair_saver
 from shared_utils import geography_utils
 from shared_utils import altair_utils
 from shared_utils import calitp_color_palette as cp

tircp/A7_zev.py

@@ -2,13 +2,7 @@
 from calitp import *
 import A1_data_prep
 
-from plotnine import *
-import intake
-from shared_utils import geography_utils
-
 import altair as alt
-import altair_saver
-from shared_utils import geography_utils
 from shared_utils import altair_utils
 from shared_utils import calitp_color_palette as cp
 from shared_utils import styleguide
@@ -28,20 +22,21 @@ def grab_zev_count(df, description_col: str):
     # Replace numbers that are written out into integers
     df[description_col] = (
         df[description_col]
-        .str.replace("seven", "7")
         .str.replace("two", "2")
         .str.replace("three", "3")
         .str.replace("four", "4")
         .str.replace("five", "5")
         .str.replace("six", "6")
+        .str.replace("seven", "7")
         .str.replace("eight", "8")
+        .str.replace("nine", "9")
         .str.replace("eleven", "11")
         .str.replace("fifteen", "15")
         .str.replace("twenty", "20")
     )
 
     # Extract numbers from description into a new column
-    # cast as float, fill in zeroes
+    # cast as float, fill in NA with 0
     df["number_of_zev"] = (
         df[description_col].str.extract("(\d+)").astype("float64").fillna(0)
     )
@@ -67,11 +62,6 @@ def grab_zev_count(df, description_col: str):
 """
 Summary table for ZEV
 """
-# Format numbers to currency in uuu8
-#def currency_format(df, col_name: str):
- #   df[col_name] = "$" + (df[col_name].astype(float)).round(0).astype(str)
-  #  return df
-
 def zev_summary(
     df_zev,
     df_all_projects,
@@ -130,7 +120,6 @@ def labeling(word):
     return word
 
 ### Bar chart with interactive tooltip: x_col and y_col will show up ### 
-### This function only returns a chart, doesn't save
 def basic_bar_chart(df, x_col, y_col, colorcol, chart_title=''):
     if chart_title == "":
         chart_title = (f"{labeling(x_col)} by {labeling(y_col)}")
@@ -150,7 +139,6 @@ def basic_bar_chart(df, x_col, y_col, colorcol, chart_title=''):
     )
 
     chart=styleguide.preset_chart_config(chart)
-    # chart.save(f"./bar_{chart_title}.png")
     return chart
 
 

tircp/README.md

@@ -0,0 +1,21 @@
+# TIRCP 
+
+**TIRCP**, The Transit and Intercity Rail Capital Program (TIRCP) was created by Senate Bill (SB) 862 (Chapter 36, Statutes of 2014) and modified by 9 (Chapter 710, Statutes of 2015), to provide grants from the Greenhouse Gas Reduction Fund (GGRF) to fund transformative capital improvements that will modernize California’s intercity, commuter, and urban rail systems, and bus and ferry transit systems to significantly reduce emissions of greenhouse gases, vehicle miles traveled, and congestion. [Source](https://dot.ca.gov/programs/rail-and-mass-transportation/transit-and-intercity-rail-capital-program)
+
+## Sections
+
+### [Presentations](./presentations/):
+1. [CTC Presentation](./presentations/Interim_Expenditures_Solution.ipynb): Notebook for CTC presentation.
+2. [Interim Expenditures](./presentations/Interim_Expenditures_Solution.ipynb): Notebook that takes expenditures data from InfoAdvantage and merges it with TIRCP data on Project ID. This was prepared for an internal PMP presentation.
+
+### [Zero Emission Vehicles]:
+1. [ZEV LCTOP TIRCP](./zev_lctop_tircp.ipynb): Notebook that estimates the number, type (LRV versus bus), and funding amount for purchasing ZEV through the LCTOP and TIRCP programs. The associated functions are under A7_zev.py.
+3. [ZEV Charts](./zev_charts): The saved charts from the notebook. 
+
+
+### [Other]:
+1. [Tableau](./A2_tableau.py): This script prepares the Excel workbook that serves as the data source for the TIRCP Tableau dashboard. 
+2. [Semiannual Report](./A3_semiannual_report.py): This script automates the Semiannual Report that summarizes how TIRCP projects have progressed.
+3. [Program Allocation Plan](./A4_program_allocation_plan.py): This script automates the Program Allocation Plan that is submitted every few months to show how funds are scheduled to be allocated. 
+4. [Crosswalks](./A5_crosswalks.py): There are manual portions of cleaning up this data and all the crosswalks are located here. 
+5. [Full Script](./A6_full_script.py): A function that builds the first three reports and saves them to GCS. 

tircp/zev_lctop_tircp.ipynb

@@ -288,24 +288,44 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4aa9c044-945e-4c17-ab5b-8cf3ca0393ec",
+   "id": "a6cf9006-2654-4b6d-8726-82f3e41ffe20",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Function for comparing total funding amount versus total estimated expense\n",
-    "def funding_vs_expenses(df):\n",
-    "    if df[\"total_project_request_99314_+_99313\"] == df[\"total_project_cost\"]:\n",
+    "def funding_vs_expenses(row):\n",
+    "    if row[\"total_project_request_99314_+_99313\"] == row[\"total_project_cost\"]:\n",
     "        return \"Fully funded\"\n",
-    "    if df[\"total_project_cost\"] == 0:\n",
+    "    if row[\"total_project_cost\"] == 0:\n",
     "        return \"No project cost info, just 0\"\n",
-    "    elif df[\"total_project_request_99314_+_99313\"] > df[\"total_project_cost\"]:\n",
+    "    elif row[\"total_project_request_99314_+_99313\"] > row[\"total_project_cost\"]:\n",
     "        return \"Funding exceeds total expenses\"\n",
-    "    elif df[\"total_project_request_99314_+_99313\"] < df[\"total_project_cost\"]:\n",
+    "    elif row[\"total_project_request_99314_+_99313\"] < row[\"total_project_cost\"]:\n",
     "        return \"Not fully funded\"\n",
     "    else:\n",
     "        return \"Not fully funded\""
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4d5c6f83-8acd-4976-ad05-5f288aeb81db",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lctop3['fully_funded'] = df_lctop3.apply(lambda x: funding_vs_expenses(x), axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "383bfa38-758f-441f-9ed7-9760a3127a0d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Apply function to determine if a project is fully funded or not\n",
+    "df_lctop3['fully_funded'] = df_lctop3.apply(funding_vs_expenses, axis=1)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -501,7 +521,7 @@
    },
    "outputs": [],
    "source": [
-    "# df_tircp_zev"
+    "# df_tircp_zev.head(5)"
    ]
   },
   {
@@ -553,7 +573,7 @@
     "\n",
     "# Open the workbook in a dictionary\n",
     "dict_df1 = pd.read_excel(\n",
-    "    \"gs://calitp-analytics-data/data-analyses/tircp/LCTOP_TIRCP_manual_ZEV_count.xlsx\",\n",
+    "    \"gs://calitp-analytics-data/data-analyses/tircp/LCTOP_TIRCP_ZEV_manual.xlsx\",\n",
     "    sheet_name=sheets_list,\n",
     ")"
    ]
@@ -570,6 +590,16 @@
     "tircp_clean = to_snakecase(dict_df1.get(\"tircp\"))"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3a75d4eb-4eb2-475f-af81-99138a599e30",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tircp_clean.head(2)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "c6ba5966-b1e0-4b07-8718-d573764de145",