dublin_bikes_algo.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "3b88c663",
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "import pandas as pd\n",
    "from datetime import datetime as dt\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.linear_model import LinearRegression"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e66c040b",
   "metadata": {},
   "source": [
    "- imported the data file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "aaacdf47",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "number of rows and columns: (168300, 5)\n"
     ]
    }
   ],
   "source": [
    "bikes = pd.read_csv(r\"C:\\Users\\benea\\Downloads\\dynamic.csv\")\n",
    "\n",
    "print(\"number of rows and columns:\", bikes.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "9da4d373",
   "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>time</th>\n",
       "      <th>number</th>\n",
       "      <th>stands_available</th>\n",
       "      <th>bikes_available</th>\n",
       "      <th>status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2022-03-22 00:00:11</td>\n",
       "      <td>30</td>\n",
       "      <td>16</td>\n",
       "      <td>4</td>\n",
       "      <td>OPEN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2022-03-22 00:00:11</td>\n",
       "      <td>42</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>OPEN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2022-03-22 00:00:11</td>\n",
       "      <td>54</td>\n",
       "      <td>10</td>\n",
       "      <td>23</td>\n",
       "      <td>OPEN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2022-03-22 00:00:11</td>\n",
       "      <td>108</td>\n",
       "      <td>14</td>\n",
       "      <td>21</td>\n",
       "      <td>OPEN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2022-03-22 00:00:12</td>\n",
       "      <td>6</td>\n",
       "      <td>17</td>\n",
       "      <td>3</td>\n",
       "      <td>OPEN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  time  number  stands_available  bikes_available status\n",
       "0  2022-03-22 00:00:11      30                16                4   OPEN\n",
       "1  2022-03-22 00:00:11      42                 0               30   OPEN\n",
       "2  2022-03-22 00:00:11      54                10               23   OPEN\n",
       "3  2022-03-22 00:00:11     108                14               21   OPEN\n",
       "4  2022-03-22 00:00:12       6                17                3   OPEN"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bikes.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "d50a0cf7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "number of rows and columns: (2054, 16)\n"
     ]
    }
   ],
   "source": [
    "weather = pd.read_csv(r\"C:\\Users\\benea\\Downloads\\current_weather.csv\")\n",
    "\n",
    "print(\"number of rows and columns:\", weather.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "335e4b82",
   "metadata": {},
   "source": [
    "- Analysed the data format."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "b9c47659",
   "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>dt</th>\n",
       "      <th>sunrise</th>\n",
       "      <th>sunset</th>\n",
       "      <th>temp</th>\n",
       "      <th>feels_like</th>\n",
       "      <th>pressure</th>\n",
       "      <th>humidity</th>\n",
       "      <th>uvi</th>\n",
       "      <th>clouds</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>wind_gusts</th>\n",
       "      <th>wind_dir</th>\n",
       "      <th>rain</th>\n",
       "      <th>snow</th>\n",
       "      <th>description</th>\n",
       "      <th>icon</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2049</th>\n",
       "      <td>2022-03-27 13:36:41</td>\n",
       "      <td>2022-03-27 06:10:53</td>\n",
       "      <td>2022-03-27 18:49:52</td>\n",
       "      <td>12.89</td>\n",
       "      <td>12.19</td>\n",
       "      <td>1031</td>\n",
       "      <td>75</td>\n",
       "      <td>0.00</td>\n",
       "      <td>20</td>\n",
       "      <td>3.60</td>\n",
       "      <td>0.0</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>few clouds</td>\n",
       "      <td>02d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2050</th>\n",
       "      <td>2022-03-27 13:41:42</td>\n",
       "      <td>2022-03-27 06:10:53</td>\n",
       "      <td>2022-03-27 18:49:52</td>\n",
       "      <td>12.89</td>\n",
       "      <td>12.19</td>\n",
       "      <td>1031</td>\n",
       "      <td>75</td>\n",
       "      <td>2.36</td>\n",
       "      <td>20</td>\n",
       "      <td>3.60</td>\n",
       "      <td>0.0</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>few clouds</td>\n",
       "      <td>02d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2051</th>\n",
       "      <td>2022-03-27 13:46:43</td>\n",
       "      <td>2022-03-27 06:10:53</td>\n",
       "      <td>2022-03-27 18:49:52</td>\n",
       "      <td>12.75</td>\n",
       "      <td>12.04</td>\n",
       "      <td>1031</td>\n",
       "      <td>75</td>\n",
       "      <td>2.36</td>\n",
       "      <td>20</td>\n",
       "      <td>4.12</td>\n",
       "      <td>0.0</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>few clouds</td>\n",
       "      <td>02d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2052</th>\n",
       "      <td>2022-03-27 13:51:43</td>\n",
       "      <td>2022-03-27 06:10:53</td>\n",
       "      <td>2022-03-27 18:49:52</td>\n",
       "      <td>12.75</td>\n",
       "      <td>12.04</td>\n",
       "      <td>1030</td>\n",
       "      <td>75</td>\n",
       "      <td>0.00</td>\n",
       "      <td>20</td>\n",
       "      <td>4.12</td>\n",
       "      <td>0.0</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>few clouds</td>\n",
       "      <td>02d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2053</th>\n",
       "      <td>2022-03-27 13:56:44</td>\n",
       "      <td>2022-03-27 06:10:53</td>\n",
       "      <td>2022-03-27 18:49:52</td>\n",
       "      <td>12.72</td>\n",
       "      <td>12.01</td>\n",
       "      <td>1030</td>\n",
       "      <td>75</td>\n",
       "      <td>0.00</td>\n",
       "      <td>20</td>\n",
       "      <td>4.12</td>\n",
       "      <td>0.0</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>few clouds</td>\n",
       "      <td>02d</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                       dt              sunrise               sunset   temp  \\\n",
       "2049  2022-03-27 13:36:41  2022-03-27 06:10:53  2022-03-27 18:49:52  12.89   \n",
       "2050  2022-03-27 13:41:42  2022-03-27 06:10:53  2022-03-27 18:49:52  12.89   \n",
       "2051  2022-03-27 13:46:43  2022-03-27 06:10:53  2022-03-27 18:49:52  12.75   \n",
       "2052  2022-03-27 13:51:43  2022-03-27 06:10:53  2022-03-27 18:49:52  12.75   \n",
       "2053  2022-03-27 13:56:44  2022-03-27 06:10:53  2022-03-27 18:49:52  12.72   \n",
       "\n",
       "      feels_like  pressure  humidity   uvi  clouds  wind_speed  wind_gusts  \\\n",
       "2049       12.19      1031        75  0.00      20        3.60         0.0   \n",
       "2050       12.19      1031        75  2.36      20        3.60         0.0   \n",
       "2051       12.04      1031        75  2.36      20        4.12         0.0   \n",
       "2052       12.04      1030        75  0.00      20        4.12         0.0   \n",
       "2053       12.01      1030        75  0.00      20        4.12         0.0   \n",
       "\n",
       "      wind_dir  rain  snow description icon  \n",
       "2049        40     0     0  few clouds  02d  \n",
       "2050        40     0     0  few clouds  02d  \n",
       "2051        60     0     0  few clouds  02d  \n",
       "2052        60     0     0  few clouds  02d  \n",
       "2053        60     0     0  few clouds  02d  "
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather.tail(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "db5da739",
   "metadata": {},
   "source": [
    "- Checked for null values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "da685716",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dt             0\n",
       "sunrise        0\n",
       "sunset         0\n",
       "temp           0\n",
       "feels_like     0\n",
       "pressure       0\n",
       "humidity       0\n",
       "uvi            0\n",
       "clouds         0\n",
       "wind_speed     0\n",
       "wind_gusts     0\n",
       "wind_dir       0\n",
       "rain           0\n",
       "snow           0\n",
       "description    0\n",
       "icon           0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "ddc1cc9f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "time                0\n",
       "number              0\n",
       "stands_available    0\n",
       "bikes_available     0\n",
       "status              0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bikes.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f857fd78",
   "metadata": {},
   "source": [
    "- Checked for duplicates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "07bc95c7",
   "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>dt</th>\n",
       "      <th>sunrise</th>\n",
       "      <th>sunset</th>\n",
       "      <th>temp</th>\n",
       "      <th>feels_like</th>\n",
       "      <th>pressure</th>\n",
       "      <th>humidity</th>\n",
       "      <th>uvi</th>\n",
       "      <th>clouds</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>wind_gusts</th>\n",
       "      <th>wind_dir</th>\n",
       "      <th>rain</th>\n",
       "      <th>snow</th>\n",
       "      <th>description</th>\n",
       "      <th>icon</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [dt, sunrise, sunset, temp, feels_like, pressure, humidity, uvi, clouds, wind_speed, wind_gusts, wind_dir, rain, snow, description, icon]\n",
       "Index: []"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather[weather.duplicated()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "8cd43831",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dt             0\n",
       "sunrise        0\n",
       "sunset         0\n",
       "temp           0\n",
       "feels_like     0\n",
       "pressure       0\n",
       "humidity       0\n",
       "uvi            0\n",
       "clouds         0\n",
       "wind_speed     0\n",
       "wind_gusts     0\n",
       "wind_dir       0\n",
       "rain           0\n",
       "snow           0\n",
       "description    0\n",
       "icon           0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather[weather.duplicated(['dt'])].count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "de394a2e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "time                0\n",
       "number              0\n",
       "stands_available    0\n",
       "bikes_available     0\n",
       "status              0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bikes[bikes.duplicated()].count()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f6d90abc",
   "metadata": {},
   "source": [
    "- Altered data types to prepare for modelling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "4b4baced",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "time                object\n",
       "number               int64\n",
       "stands_available     int64\n",
       "bikes_available      int64\n",
       "status              object\n",
       "dtype: object"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bikes.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "3143d5b3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "time                datetime64[ns]\n",
       "number                       int64\n",
       "stands_available             int64\n",
       "bikes_available              int64\n",
       "status                    category\n",
       "dtype: object"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bikes['time'] = pd.to_datetime(bikes['time'])\n",
    "bikes['status'] = bikes['status'].astype('category')\n",
    "\n",
    "bikes.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "b23da6c3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dt              object\n",
       "sunrise         object\n",
       "sunset          object\n",
       "temp           float64\n",
       "feels_like     float64\n",
       "pressure         int64\n",
       "humidity         int64\n",
       "uvi            float64\n",
       "clouds           int64\n",
       "wind_speed     float64\n",
       "wind_gusts     float64\n",
       "wind_dir         int64\n",
       "rain             int64\n",
       "snow             int64\n",
       "description     object\n",
       "icon            object\n",
       "dtype: object"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "95faea0c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dt             datetime64[ns]\n",
       "sunrise                object\n",
       "sunset                 object\n",
       "temp                  float64\n",
       "feels_like            float64\n",
       "pressure                int64\n",
       "humidity                int64\n",
       "uvi                   float64\n",
       "clouds                  int64\n",
       "wind_speed            float64\n",
       "wind_gusts            float64\n",
       "wind_dir                int64\n",
       "rain                 category\n",
       "snow                    int64\n",
       "description          category\n",
       "icon                 category\n",
       "dtype: object"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather['dt'] = pd.to_datetime(weather['dt'])\n",
    "weather['description'] = weather['description'].astype('category')\n",
    "weather['icon'] = weather['icon'].astype('category')\n",
    "weather['rain'] = weather['rain'].astype('category')\n",
    "\n",
    "\n",
    "weather.dtypes\n",
    "#didn't bother changing the irrelelvant columns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb5e1d9c",
   "metadata": {},
   "source": [
    "- Merged the two data frames on the time value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "6e35ac14",
   "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>time</th>\n",
       "      <th>sunrise</th>\n",
       "      <th>sunset</th>\n",
       "      <th>temp</th>\n",
       "      <th>feels_like</th>\n",
       "      <th>pressure</th>\n",
       "      <th>humidity</th>\n",
       "      <th>uvi</th>\n",
       "      <th>clouds</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>wind_gusts</th>\n",
       "      <th>wind_dir</th>\n",
       "      <th>rain</th>\n",
       "      <th>snow</th>\n",
       "      <th>description</th>\n",
       "      <th>icon</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2022-03-15 23:25:00</td>\n",
       "      <td>2022-03-15 06:40:05</td>\n",
       "      <td>2022-03-15 18:28:05</td>\n",
       "      <td>9.03</td>\n",
       "      <td>6.32</td>\n",
       "      <td>1015</td>\n",
       "      <td>80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>75</td>\n",
       "      <td>5.14</td>\n",
       "      <td>0.0</td>\n",
       "      <td>210</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>broken clouds</td>\n",
       "      <td>04n</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2022-03-15 23:25:00</td>\n",
       "      <td>2022-03-15 06:40:05</td>\n",
       "      <td>2022-03-15 18:28:05</td>\n",
       "      <td>9.03</td>\n",
       "      <td>6.32</td>\n",
       "      <td>1015</td>\n",
       "      <td>80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>75</td>\n",
       "      <td>5.14</td>\n",
       "      <td>0.0</td>\n",
       "      <td>210</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>broken clouds</td>\n",
       "      <td>04n</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2022-03-15 23:30:00</td>\n",
       "      <td>2022-03-15 06:40:05</td>\n",
       "      <td>2022-03-15 18:28:05</td>\n",
       "      <td>9.09</td>\n",
       "      <td>6.40</td>\n",
       "      <td>1015</td>\n",
       "      <td>80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>75</td>\n",
       "      <td>5.14</td>\n",
       "      <td>0.0</td>\n",
       "      <td>210</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>broken clouds</td>\n",
       "      <td>04n</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2022-03-15 23:35:00</td>\n",
       "      <td>2022-03-15 06:40:05</td>\n",
       "      <td>2022-03-15 18:28:05</td>\n",
       "      <td>9.19</td>\n",
       "      <td>6.52</td>\n",
       "      <td>1015</td>\n",
       "      <td>80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>75</td>\n",
       "      <td>5.14</td>\n",
       "      <td>0.0</td>\n",
       "      <td>210</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>broken clouds</td>\n",
       "      <td>04n</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2022-03-15 23:40:00</td>\n",
       "      <td>2022-03-15 06:40:05</td>\n",
       "      <td>2022-03-15 18:28:05</td>\n",
       "      <td>9.19</td>\n",
       "      <td>6.52</td>\n",
       "      <td>1015</td>\n",
       "      <td>80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>75</td>\n",
       "      <td>5.14</td>\n",
       "      <td>0.0</td>\n",
       "      <td>210</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>broken clouds</td>\n",
       "      <td>04n</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 time              sunrise               sunset  temp  \\\n",
       "0 2022-03-15 23:25:00  2022-03-15 06:40:05  2022-03-15 18:28:05  9.03   \n",
       "1 2022-03-15 23:25:00  2022-03-15 06:40:05  2022-03-15 18:28:05  9.03   \n",
       "2 2022-03-15 23:30:00  2022-03-15 06:40:05  2022-03-15 18:28:05  9.09   \n",
       "3 2022-03-15 23:35:00  2022-03-15 06:40:05  2022-03-15 18:28:05  9.19   \n",
       "4 2022-03-15 23:40:00  2022-03-15 06:40:05  2022-03-15 18:28:05  9.19   \n",
       "\n",
       "   feels_like  pressure  humidity  uvi  clouds  wind_speed  wind_gusts  \\\n",
       "0        6.32      1015        80  0.0      75        5.14         0.0   \n",
       "1        6.32      1015        80  0.0      75        5.14         0.0   \n",
       "2        6.40      1015        80  0.0      75        5.14         0.0   \n",
       "3        6.52      1015        80  0.0      75        5.14         0.0   \n",
       "4        6.52      1015        80  0.0      75        5.14         0.0   \n",
       "\n",
       "   wind_dir rain  snow    description icon  \n",
       "0       210    0     0  broken clouds  04n  \n",
       "1       210    0     0  broken clouds  04n  \n",
       "2       210    0     0  broken clouds  04n  \n",
       "3       210    0     0  broken clouds  04n  \n",
       "4       210    0     0  broken clouds  04n  "
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#must merge the 2 data frames at the datetime columns\n",
    "#times wont be exactly the same so must round them\n",
    "#date time format is the same in each\n",
    "#rounding all to neares 5 minutes so join is easier\n",
    "\n",
    "bikes[\"time\"] = bikes[\"time\"].dt.round(\"5min\")\n",
    "\n",
    "weather[\"dt\"] = weather[\"dt\"].dt.round(\"5min\")\n",
    "\n",
    "weather.rename(columns = {'dt':'time'}, inplace = True)\n",
    "\n",
    "\n",
    "weather.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "d5ec6c20",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(167596, 20)\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>time</th>\n",
       "      <th>number</th>\n",
       "      <th>stands_available</th>\n",
       "      <th>bikes_available</th>\n",
       "      <th>status</th>\n",
       "      <th>sunrise</th>\n",
       "      <th>sunset</th>\n",
       "      <th>temp</th>\n",
       "      <th>feels_like</th>\n",
       "      <th>pressure</th>\n",
       "      <th>humidity</th>\n",
       "      <th>uvi</th>\n",
       "      <th>clouds</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>wind_gusts</th>\n",
       "      <th>wind_dir</th>\n",
       "      <th>rain</th>\n",
       "      <th>snow</th>\n",
       "      <th>description</th>\n",
       "      <th>icon</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>25906</th>\n",
       "      <td>2022-03-22 20:40:00</td>\n",
       "      <td>29</td>\n",
       "      <td>14</td>\n",
       "      <td>15</td>\n",
       "      <td>OPEN</td>\n",
       "      <td>2022-03-22 06:23:04</td>\n",
       "      <td>2022-03-22 18:40:50</td>\n",
       "      <td>8.75</td>\n",
       "      <td>6.96</td>\n",
       "      <td>1026</td>\n",
       "      <td>87</td>\n",
       "      <td>0.00</td>\n",
       "      <td>20</td>\n",
       "      <td>3.09</td>\n",
       "      <td>0.0</td>\n",
       "      <td>110</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>few clouds</td>\n",
       "      <td>02n</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98805</th>\n",
       "      <td>2022-03-25 06:55:00</td>\n",
       "      <td>36</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>OPEN</td>\n",
       "      <td>2022-03-25 06:15:45</td>\n",
       "      <td>2022-03-25 18:46:15</td>\n",
       "      <td>8.45</td>\n",
       "      <td>8.45</td>\n",
       "      <td>1031</td>\n",
       "      <td>89</td>\n",
       "      <td>0.00</td>\n",
       "      <td>75</td>\n",
       "      <td>0.51</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>broken clouds</td>\n",
       "      <td>04d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84994</th>\n",
       "      <td>2022-03-24 20:00:00</td>\n",
       "      <td>31</td>\n",
       "      <td>3</td>\n",
       "      <td>17</td>\n",
       "      <td>OPEN</td>\n",
       "      <td>2022-03-24 06:18:11</td>\n",
       "      <td>2022-03-24 18:44:27</td>\n",
       "      <td>9.67</td>\n",
       "      <td>9.23</td>\n",
       "      <td>1030</td>\n",
       "      <td>79</td>\n",
       "      <td>0.00</td>\n",
       "      <td>20</td>\n",
       "      <td>1.54</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>few clouds</td>\n",
       "      <td>02n</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>165489</th>\n",
       "      <td>2022-03-27 12:15:00</td>\n",
       "      <td>44</td>\n",
       "      <td>23</td>\n",
       "      <td>7</td>\n",
       "      <td>OPEN</td>\n",
       "      <td>2022-03-27 06:10:53</td>\n",
       "      <td>2022-03-27 18:49:52</td>\n",
       "      <td>12.55</td>\n",
       "      <td>11.85</td>\n",
       "      <td>1031</td>\n",
       "      <td>76</td>\n",
       "      <td>2.85</td>\n",
       "      <td>20</td>\n",
       "      <td>4.02</td>\n",
       "      <td>0.0</td>\n",
       "      <td>70</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>few clouds</td>\n",
       "      <td>02d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>151234</th>\n",
       "      <td>2022-03-27 00:55:00</td>\n",
       "      <td>67</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>OPEN</td>\n",
       "      <td>2022-03-27 06:10:53</td>\n",
       "      <td>2022-03-27 18:49:52</td>\n",
       "      <td>6.94</td>\n",
       "      <td>5.14</td>\n",
       "      <td>1034</td>\n",
       "      <td>83</td>\n",
       "      <td>0.00</td>\n",
       "      <td>20</td>\n",
       "      <td>2.57</td>\n",
       "      <td>0.0</td>\n",
       "      <td>90</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>few clouds</td>\n",
       "      <td>02n</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      time  number  stands_available  bikes_available status  \\\n",
       "25906  2022-03-22 20:40:00      29                14               15   OPEN   \n",
       "98805  2022-03-25 06:55:00      36                40                0   OPEN   \n",
       "84994  2022-03-24 20:00:00      31                 3               17   OPEN   \n",
       "165489 2022-03-27 12:15:00      44                23                7   OPEN   \n",
       "151234 2022-03-27 00:55:00      67                 0               40   OPEN   \n",
       "\n",
       "                    sunrise               sunset   temp  feels_like  pressure  \\\n",
       "25906   2022-03-22 06:23:04  2022-03-22 18:40:50   8.75        6.96      1026   \n",
       "98805   2022-03-25 06:15:45  2022-03-25 18:46:15   8.45        8.45      1031   \n",
       "84994   2022-03-24 06:18:11  2022-03-24 18:44:27   9.67        9.23      1030   \n",
       "165489  2022-03-27 06:10:53  2022-03-27 18:49:52  12.55       11.85      1031   \n",
       "151234  2022-03-27 06:10:53  2022-03-27 18:49:52   6.94        5.14      1034   \n",
       "\n",
       "        humidity   uvi  clouds  wind_speed  wind_gusts  wind_dir rain  snow  \\\n",
       "25906         87  0.00      20        3.09         0.0       110    0     0   \n",
       "98805         89  0.00      75        0.51         0.0         0    0     0   \n",
       "84994         79  0.00      20        1.54         0.0        10    0     0   \n",
       "165489        76  2.85      20        4.02         0.0        70    0     0   \n",
       "151234        83  0.00      20        2.57         0.0        90    0     0   \n",
       "\n",
       "          description icon  \n",
       "25906      few clouds  02n  \n",
       "98805   broken clouds  04d  \n",
       "84994      few clouds  02n  \n",
       "165489     few clouds  02d  \n",
       "151234     few clouds  02n  "
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.merge(bikes,weather,on=\"time\")\n",
    "df = df.sample(frac=1)\n",
    "print(df.shape)\n",
    "df.tail(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "4a4796ba",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "bikes_available     0.995817\n",
       "clouds                   NaN\n",
       "description              NaN\n",
       "feels_like               NaN\n",
       "humidity                 NaN\n",
       "icon                     NaN\n",
       "number              0.995817\n",
       "pressure                 NaN\n",
       "rain                     NaN\n",
       "snow                     NaN\n",
       "stands_available    0.995817\n",
       "status              0.995817\n",
       "sunrise                  NaN\n",
       "sunset                   NaN\n",
       "temp                     NaN\n",
       "time                0.995817\n",
       "uvi                      NaN\n",
       "wind_dir                 NaN\n",
       "wind_gusts               NaN\n",
       "wind_speed               NaN\n",
       "dtype: float64"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.count() / bikes.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "592a2021",
   "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>time</th>\n",
       "      <th>number</th>\n",
       "      <th>stands_available</th>\n",
       "      <th>bikes_available</th>\n",
       "      <th>status</th>\n",
       "      <th>sunrise</th>\n",
       "      <th>sunset</th>\n",
       "      <th>temp</th>\n",
       "      <th>feels_like</th>\n",
       "      <th>pressure</th>\n",
       "      <th>humidity</th>\n",
       "      <th>uvi</th>\n",
       "      <th>clouds</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>wind_gusts</th>\n",
       "      <th>wind_dir</th>\n",
       "      <th>rain</th>\n",
       "      <th>snow</th>\n",
       "      <th>description</th>\n",
       "      <th>icon</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>61686</th>\n",
       "      <td>2022-03-24 01:15:00</td>\n",
       "      <td>11</td>\n",
       "      <td>22</td>\n",
       "      <td>8</td>\n",
       "      <td>OPEN</td>\n",
       "      <td>2022-03-24 06:18:11</td>\n",
       "      <td>2022-03-24 18:44:27</td>\n",
       "      <td>9.86</td>\n",
       "      <td>8.98</td>\n",
       "      <td>1029</td>\n",
       "      <td>79</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>2.06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>290</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>clear sky</td>\n",
       "      <td>01n</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>92884</th>\n",
       "      <td>2022-03-25 02:15:00</td>\n",
       "      <td>24</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "      <td>OPEN</td>\n",
       "      <td>2022-03-25 06:15:45</td>\n",
       "      <td>2022-03-25 18:46:15</td>\n",
       "      <td>7.94</td>\n",
       "      <td>6.74</td>\n",
       "      <td>1031</td>\n",
       "      <td>86</td>\n",
       "      <td>0.00</td>\n",
       "      <td>40</td>\n",
       "      <td>2.06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>310</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>scattered clouds</td>\n",
       "      <td>03n</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76939</th>\n",
       "      <td>2022-03-24 13:30:00</td>\n",
       "      <td>109</td>\n",
       "      <td>22</td>\n",
       "      <td>7</td>\n",
       "      <td>OPEN</td>\n",
       "      <td>2022-03-24 06:18:11</td>\n",
       "      <td>2022-03-24 18:44:27</td>\n",
       "      <td>15.71</td>\n",
       "      <td>14.88</td>\n",
       "      <td>1029</td>\n",
       "      <td>59</td>\n",
       "      <td>3.33</td>\n",
       "      <td>0</td>\n",
       "      <td>3.60</td>\n",
       "      <td>0.0</td>\n",
       "      <td>220</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>clear sky</td>\n",
       "      <td>01d</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     time  number  stands_available  bikes_available status  \\\n",
       "61686 2022-03-24 01:15:00      11                22                8   OPEN   \n",
       "92884 2022-03-25 02:15:00      24                 9               11   OPEN   \n",
       "76939 2022-03-24 13:30:00     109                22                7   OPEN   \n",
       "\n",
       "                   sunrise               sunset   temp  feels_like  pressure  \\\n",
       "61686  2022-03-24 06:18:11  2022-03-24 18:44:27   9.86        8.98      1029   \n",
       "92884  2022-03-25 06:15:45  2022-03-25 18:46:15   7.94        6.74      1031   \n",
       "76939  2022-03-24 06:18:11  2022-03-24 18:44:27  15.71       14.88      1029   \n",
       "\n",
       "       humidity   uvi  clouds  wind_speed  wind_gusts  wind_dir rain  snow  \\\n",
       "61686        79  0.00       0        2.06         0.0       290    0     0   \n",
       "92884        86  0.00      40        2.06         0.0       310    0     0   \n",
       "76939        59  3.33       0        3.60         0.0       220    0     0   \n",
       "\n",
       "            description icon  \n",
       "61686         clear sky  01n  \n",
       "92884  scattered clouds  03n  \n",
       "76939         clear sky  01d  "
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eb138797",
   "metadata": {},
   "source": [
    "- Split the time and date into two seperate columns.\n",
    "- converted them to integer formats to be analysed in the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "0f330669",
   "metadata": {},
   "outputs": [],
   "source": [
    "import datetime as dt\n",
    "\n",
    "df['day'] = df.time.dt.day_name()\n",
    "df['day'] = pd.factorize(df['day'], sort=True)[0]\n",
    "df.tail\n",
    "\n",
    "df['time'] = df.time.values.astype(np.int64) // 10 ** 10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "6b5258a9",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop(columns=[\"pressure\", \"sunset\", \"sunrise\", \"status\", \"description\", \"icon\", \"uvi\", \"wind_gusts\", \"snow\", \"feels_like\", \"wind_dir\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "ff15fa43",
   "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>time</th>\n",
       "      <th>number</th>\n",
       "      <th>stands_available</th>\n",
       "      <th>bikes_available</th>\n",
       "      <th>temp</th>\n",
       "      <th>humidity</th>\n",
       "      <th>clouds</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>rain</th>\n",
       "      <th>day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>61686</th>\n",
       "      <td>164808450</td>\n",
       "      <td>11</td>\n",
       "      <td>22</td>\n",
       "      <td>8</td>\n",
       "      <td>9.86</td>\n",
       "      <td>79</td>\n",
       "      <td>0</td>\n",
       "      <td>2.06</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>92884</th>\n",
       "      <td>164817450</td>\n",
       "      <td>24</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "      <td>7.94</td>\n",
       "      <td>86</td>\n",
       "      <td>40</td>\n",
       "      <td>2.06</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76939</th>\n",
       "      <td>164812860</td>\n",
       "      <td>109</td>\n",
       "      <td>22</td>\n",
       "      <td>7</td>\n",
       "      <td>15.71</td>\n",
       "      <td>59</td>\n",
       "      <td>0</td>\n",
       "      <td>3.60</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64870</th>\n",
       "      <td>164809380</td>\n",
       "      <td>68</td>\n",
       "      <td>34</td>\n",
       "      <td>6</td>\n",
       "      <td>9.61</td>\n",
       "      <td>79</td>\n",
       "      <td>0</td>\n",
       "      <td>2.06</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>88532</th>\n",
       "      <td>164816190</td>\n",
       "      <td>72</td>\n",
       "      <td>3</td>\n",
       "      <td>28</td>\n",
       "      <td>9.35</td>\n",
       "      <td>85</td>\n",
       "      <td>75</td>\n",
       "      <td>1.03</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>136785</th>\n",
       "      <td>164830080</td>\n",
       "      <td>40</td>\n",
       "      <td>6</td>\n",
       "      <td>14</td>\n",
       "      <td>15.47</td>\n",
       "      <td>57</td>\n",
       "      <td>20</td>\n",
       "      <td>4.63</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54099</th>\n",
       "      <td>164806290</td>\n",
       "      <td>90</td>\n",
       "      <td>38</td>\n",
       "      <td>2</td>\n",
       "      <td>12.38</td>\n",
       "      <td>68</td>\n",
       "      <td>75</td>\n",
       "      <td>2.06</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60088</th>\n",
       "      <td>164807970</td>\n",
       "      <td>12</td>\n",
       "      <td>12</td>\n",
       "      <td>8</td>\n",
       "      <td>9.17</td>\n",
       "      <td>79</td>\n",
       "      <td>0</td>\n",
       "      <td>2.06</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16600</th>\n",
       "      <td>164795460</td>\n",
       "      <td>40</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>15.60</td>\n",
       "      <td>65</td>\n",
       "      <td>20</td>\n",
       "      <td>6.17</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134505</th>\n",
       "      <td>164829450</td>\n",
       "      <td>17</td>\n",
       "      <td>3</td>\n",
       "      <td>17</td>\n",
       "      <td>14.34</td>\n",
       "      <td>65</td>\n",
       "      <td>20</td>\n",
       "      <td>3.09</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>123513</th>\n",
       "      <td>164826270</td>\n",
       "      <td>91</td>\n",
       "      <td>7</td>\n",
       "      <td>23</td>\n",
       "      <td>6.10</td>\n",
       "      <td>84</td>\n",
       "      <td>20</td>\n",
       "      <td>1.54</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>154751</th>\n",
       "      <td>164835270</td>\n",
       "      <td>63</td>\n",
       "      <td>10</td>\n",
       "      <td>25</td>\n",
       "      <td>7.13</td>\n",
       "      <td>83</td>\n",
       "      <td>20</td>\n",
       "      <td>2.06</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99236</th>\n",
       "      <td>164819280</td>\n",
       "      <td>76</td>\n",
       "      <td>17</td>\n",
       "      <td>21</td>\n",
       "      <td>9.02</td>\n",
       "      <td>89</td>\n",
       "      <td>75</td>\n",
       "      <td>0.51</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131642</th>\n",
       "      <td>164828640</td>\n",
       "      <td>112</td>\n",
       "      <td>7</td>\n",
       "      <td>23</td>\n",
       "      <td>10.84</td>\n",
       "      <td>82</td>\n",
       "      <td>20</td>\n",
       "      <td>2.57</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32268</th>\n",
       "      <td>164799990</td>\n",
       "      <td>78</td>\n",
       "      <td>21</td>\n",
       "      <td>19</td>\n",
       "      <td>9.58</td>\n",
       "      <td>61</td>\n",
       "      <td>0</td>\n",
       "      <td>2.57</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133500</th>\n",
       "      <td>164829180</td>\n",
       "      <td>18</td>\n",
       "      <td>15</td>\n",
       "      <td>15</td>\n",
       "      <td>13.39</td>\n",
       "      <td>72</td>\n",
       "      <td>20</td>\n",
       "      <td>2.57</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>140239</th>\n",
       "      <td>164831100</td>\n",
       "      <td>55</td>\n",
       "      <td>25</td>\n",
       "      <td>11</td>\n",
       "      <td>14.78</td>\n",
       "      <td>51</td>\n",
       "      <td>0</td>\n",
       "      <td>4.63</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97524</th>\n",
       "      <td>164818770</td>\n",
       "      <td>88</td>\n",
       "      <td>23</td>\n",
       "      <td>7</td>\n",
       "      <td>8.39</td>\n",
       "      <td>89</td>\n",
       "      <td>75</td>\n",
       "      <td>1.54</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>150132</th>\n",
       "      <td>164833950</td>\n",
       "      <td>90</td>\n",
       "      <td>39</td>\n",
       "      <td>0</td>\n",
       "      <td>7.72</td>\n",
       "      <td>83</td>\n",
       "      <td>16</td>\n",
       "      <td>0.89</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>121337</th>\n",
       "      <td>164825640</td>\n",
       "      <td>66</td>\n",
       "      <td>26</td>\n",
       "      <td>14</td>\n",
       "      <td>6.53</td>\n",
       "      <td>85</td>\n",
       "      <td>20</td>\n",
       "      <td>1.54</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             time  number  stands_available  bikes_available   temp  humidity  \\\n",
       "61686   164808450      11                22                8   9.86        79   \n",
       "92884   164817450      24                 9               11   7.94        86   \n",
       "76939   164812860     109                22                7  15.71        59   \n",
       "64870   164809380      68                34                6   9.61        79   \n",
       "88532   164816190      72                 3               28   9.35        85   \n",
       "136785  164830080      40                 6               14  15.47        57   \n",
       "54099   164806290      90                38                2  12.38        68   \n",
       "60088   164807970      12                12                8   9.17        79   \n",
       "16600   164795460      40                 9               12  15.60        65   \n",
       "134505  164829450      17                 3               17  14.34        65   \n",
       "123513  164826270      91                 7               23   6.10        84   \n",
       "154751  164835270      63                10               25   7.13        83   \n",
       "99236   164819280      76                17               21   9.02        89   \n",
       "131642  164828640     112                 7               23  10.84        82   \n",
       "32268   164799990      78                21               19   9.58        61   \n",
       "133500  164829180      18                15               15  13.39        72   \n",
       "140239  164831100      55                25               11  14.78        51   \n",
       "97524   164818770      88                23                7   8.39        89   \n",
       "150132  164833950      90                39                0   7.72        83   \n",
       "121337  164825640      66                26               14   6.53        85   \n",
       "\n",
       "        clouds  wind_speed rain  day  \n",
       "61686        0        2.06    0    3  \n",
       "92884       40        2.06    0    0  \n",
       "76939        0        3.60    0    3  \n",
       "64870        0        2.06    0    3  \n",
       "88532       75        1.03    0    3  \n",
       "136785      20        4.63    0    1  \n",
       "54099       75        2.06    0    5  \n",
       "60088        0        2.06    0    5  \n",
       "16600       20        6.17    0    4  \n",
       "134505      20        3.09    0    1  \n",
       "123513      20        1.54    0    1  \n",
       "154751      20        2.06    0    2  \n",
       "99236       75        0.51    0    0  \n",
       "131642      20        2.57    0    1  \n",
       "32268        0        2.57    0    5  \n",
       "133500      20        2.57    0    1  \n",
       "140239       0        4.63    0    1  \n",
       "97524       75        1.54    0    0  \n",
       "150132      16        0.89    0    2  \n",
       "121337      20        1.54    0    1  "
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "513149e0",
   "metadata": {},
   "source": [
    "- Tested it with and without a few different columns and found it was most accurate with just time, as counterintuitive as that may seem.\n",
    "- Chose to leave in the rain and day data as it may have been that the test set sample would not reflect the ability of the model to factor in these variables. The accuracy score was only fractionally reduced anyway."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "17f9b7be",
   "metadata": {},
   "source": [
    "- Split the data into input and output sets.\n",
    "- Split those sets into training and testing sets."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "83659e60",
   "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</th>\n",
       "      <th>stands_available</th>\n",
       "      <th>bikes_available</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>165489</th>\n",
       "      <td>44</td>\n",
       "      <td>23</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>151234</th>\n",
       "      <td>67</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        number  stands_available  bikes_available\n",
       "165489      44                23                7\n",
       "151234      67                 0               40"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#date time format is the same in each\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "x = df.drop(columns=[\"bikes_available\", \"stands_available\", \"wind_speed\", \"humidity\", \"clouds\", \"temp\"])\n",
    "y = df.drop(columns=[\"wind_speed\", \"humidity\", \"clouds\", \"rain\", \"temp\", \"time\", \"day\"])\n",
    "\n",
    "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)\n",
    "y.tail(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "ce352bea",
   "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>time</th>\n",
       "      <th>number</th>\n",
       "      <th>rain</th>\n",
       "      <th>day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>25906</th>\n",
       "      <td>164798160</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98805</th>\n",
       "      <td>164819130</td>\n",
       "      <td>36</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84994</th>\n",
       "      <td>164815200</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>165489</th>\n",
       "      <td>164838330</td>\n",
       "      <td>44</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>151234</th>\n",
       "      <td>164834250</td>\n",
       "      <td>67</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             time  number rain  day\n",
       "25906   164798160      29    0    4\n",
       "98805   164819130      36    0    0\n",
       "84994   164815200      31    0    3\n",
       "165489  164838330      44    0    2\n",
       "151234  164834250      67    0    2"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.tail(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "d8eac1bd",
   "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</th>\n",
       "      <th>stands_available</th>\n",
       "      <th>bikes_available</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>29528</th>\n",
       "      <td>64</td>\n",
       "      <td>25</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45967</th>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21983</th>\n",
       "      <td>63</td>\n",
       "      <td>26</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       number  stands_available  bikes_available\n",
       "29528      64                25               15\n",
       "45967       9                 3               20\n",
       "21983      63                26                9"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test.tail(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7fba3e23",
   "metadata": {},
   "source": [
    "- Created an array to hold the station numbers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "3e2123cb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "110"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.number.nunique()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "id": "ec3590cd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117]\n"
     ]
    }
   ],
   "source": [
    "stations = x.number.unique()\n",
    "stations = sorted(stations)\n",
    "print(stations)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "81ab66c1",
   "metadata": {},
   "source": [
    "We initially experimented with a Linear Regression model but decided it was unsuitable for predicting as it didn't return a rounded integer value and additionally was more difficult to evaluate than a Decision Tree model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "b89c014a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "12.04632609675507\n"
     ]
    }
   ],
   "source": [
    "model = LinearRegression()\n",
    "\n",
    "y_train_b = y_train['bikes_available'] \n",
    "y_test_b = y_test['bikes_available']\n",
    "\n",
    "\n",
    "model.fit(x_train, y_train_b)\n",
    "\n",
    "predictions = model.predict(x_test)\n",
    "\n",
    "print(predictions[70])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "76da26f1",
   "metadata": {},
   "source": [
    "# IMPORTANT BIT"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "801a5200",
   "metadata": {},
   "source": [
    "- Used Decision Tree model to predict the bikes and stands available.\n",
    "- The loop allowed an easy saving of the pickle files and printed out the accuracy score for each station.\n",
    "- To get a broad overview of the accuracy we created a demo model that would show the overall accuracy of the model. \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "9e35e475",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy score for station number 2: 0.7947019867549668\n",
      "accuracy score for station number 3: 0.6983606557377049\n",
      "accuracy score for station number 4: 0.7788778877887789\n",
      "accuracy score for station number 5: 0.6044303797468354\n",
      "accuracy score for station number 6: 0.7635135135135135\n",
      "accuracy score for station number 7: 0.8456973293768546\n",
      "accuracy score for station number 8: 0.6765676567656765\n",
      "accuracy score for station number 9: 0.5774193548387097\n",
      "accuracy score for station number 10: 0.7266666666666667\n",
      "accuracy score for station number 11: 0.8122866894197952\n",
      "accuracy score for station number 12: 0.7864768683274022\n",
      "accuracy score for station number 13: 0.8827361563517915\n",
      "accuracy score for station number 15: 0.8717948717948718\n",
      "accuracy score for station number 16: 0.8289473684210527\n",
      "accuracy score for station number 17: 0.8312883435582822\n",
      "accuracy score for station number 18: 0.6464968152866242\n",
      "accuracy score for station number 19: 0.6064516129032258\n",
      "accuracy score for station number 21: 0.7542662116040956\n",
      "accuracy score for station number 22: 0.7152777777777778\n",
      "accuracy score for station number 23: 0.7192429022082019\n",
      "accuracy score for station number 24: 0.6676923076923077\n",
      "accuracy score for station number 25: 0.8631921824104235\n",
      "accuracy score for station number 26: 0.7922535211267606\n",
      "accuracy score for station number 27: 0.6990291262135923\n",
      "accuracy score for station number 28: 0.8041237113402062\n",
      "accuracy score for station number 29: 0.6755952380952381\n",
      "accuracy score for station number 30: 0.819935691318328\n",
      "accuracy score for station number 31: 0.6103896103896104\n",
      "accuracy score for station number 32: 0.6755852842809364\n",
      "accuracy score for station number 33: 0.5236593059936908\n",
      "accuracy score for station number 34: 0.6054421768707483\n",
      "accuracy score for station number 36: 0.7333333333333333\n",
      "accuracy score for station number 37: 0.9122807017543859\n",
      "accuracy score for station number 38: 0.6490683229813664\n",
      "accuracy score for station number 39: 0.7287581699346405\n",
      "accuracy score for station number 40: 0.7118055555555556\n",
      "accuracy score for station number 41: 0.8838709677419355\n",
      "accuracy score for station number 42: 0.6883116883116883\n",
      "accuracy score for station number 43: 0.6446540880503144\n",
      "accuracy score for station number 44: 0.6949152542372882\n",
      "accuracy score for station number 45: 0.7887788778877888\n",
      "accuracy score for station number 47: 0.8459119496855346\n",
      "accuracy score for station number 48: 0.7517241379310344\n",
      "accuracy score for station number 49: 0.6819484240687679\n",
      "accuracy score for station number 50: 0.7027027027027027\n",
      "accuracy score for station number 51: 0.7628865979381443\n",
      "accuracy score for station number 52: 0.7508896797153025\n",
      "accuracy score for station number 53: 0.8810975609756098\n",
      "accuracy score for station number 54: 0.8355704697986577\n",
      "accuracy score for station number 55: 0.9122137404580153\n",
      "accuracy score for station number 56: 0.697452229299363\n",
      "accuracy score for station number 57: 0.8928571428571429\n",
      "accuracy score for station number 58: 0.6989966555183946\n",
      "accuracy score for station number 59: 0.8443708609271523\n",
      "accuracy score for station number 60: 0.677115987460815\n",
      "accuracy score for station number 61: 0.8741721854304636\n",
      "accuracy score for station number 62: 0.875\n",
      "accuracy score for station number 63: 0.8338762214983714\n",
      "accuracy score for station number 64: 0.729903536977492\n",
      "accuracy score for station number 65: 0.8018867924528302\n",
      "accuracy score for station number 66: 0.6181229773462783\n",
      "accuracy score for station number 67: 0.6167247386759582\n",
      "accuracy score for station number 68: 0.6199376947040498\n",
      "accuracy score for station number 69: 0.5259515570934256\n",
      "accuracy score for station number 71: 0.8081761006289309\n",
      "accuracy score for station number 72: 0.6996805111821086\n",
      "accuracy score for station number 73: 0.765079365079365\n",
      "accuracy score for station number 74: 0.7616099071207431\n",
      "accuracy score for station number 75: 0.7525083612040134\n",
      "accuracy score for station number 76: 0.8138686131386861\n",
      "accuracy score for station number 77: 0.7305194805194806\n",
      "accuracy score for station number 78: 0.8142857142857143\n",
      "accuracy score for station number 79: 0.8776758409785933\n",
      "accuracy score for station number 80: 0.7784810126582279\n",
      "accuracy score for station number 82: 0.9039735099337748\n",
      "accuracy score for station number 83: 0.7821428571428571\n",
      "accuracy score for station number 84: 0.8013937282229965\n",
      "accuracy score for station number 85: 0.8432055749128919\n",
      "accuracy score for station number 86: 0.7175324675324676\n",
      "accuracy score for station number 87: 0.8281786941580757\n",
      "accuracy score for station number 88: 0.7620689655172413\n",
      "accuracy score for station number 89: 0.9290322580645162\n",
      "accuracy score for station number 90: 0.7138364779874213\n",
      "accuracy score for station number 91: 0.6917808219178082\n",
      "accuracy score for station number 92: 0.718213058419244\n",
      "accuracy score for station number 93: 0.941358024691358\n",
      "accuracy score for station number 94: 0.9966666666666667\n",
      "accuracy score for station number 95: 0.7129629629629629\n",
      "accuracy score for station number 96: 0.9114285714285715\n",
      "accuracy score for station number 97: 0.735191637630662\n",
      "accuracy score for station number 98: 0.8036253776435045\n",
      "accuracy score for station number 99: 0.8528428093645485\n",
      "accuracy score for station number 100: 0.7834394904458599\n",
      "accuracy score for station number 101: 0.7660818713450293\n",
      "accuracy score for station number 102: 0.9151943462897526\n",
      "accuracy score for station number 103: 0.8295081967213115\n",
      "accuracy score for station number 104: 0.9580645161290322\n",
      "accuracy score for station number 105: 0.8927444794952681\n",
      "accuracy score for station number 106: 0.8235294117647058\n",
      "accuracy score for station number 107: 0.7759197324414716\n",
      "accuracy score for station number 108: 0.82\n",
      "accuracy score for station number 109: 0.8238993710691824\n",
      "accuracy score for station number 110: 0.8316498316498316\n",
      "accuracy score for station number 111: 0.7335526315789473\n",
      "accuracy score for station number 112: 0.6702508960573477\n",
      "accuracy score for station number 113: 0.9025974025974026\n",
      "accuracy score for station number 114: 0.7220338983050848\n",
      "accuracy score for station number 115: 0.7195571955719557\n",
      "accuracy score for station number 116: 0.9094202898550725\n",
      "accuracy score for station number 117: 0.9156626506024096\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "import joblib\n",
    "import pickle\n",
    "\n",
    "\n",
    "model = DecisionTreeClassifier()\n",
    "\n",
    "for i in stations:\n",
    "    temp_x = x_train.loc[x_train['number'] == i] #assigning by the station number\n",
    "    temp_y = y_train.loc[y_train['number'] == i]\n",
    "    \n",
    "    temp_test_x = x_test.loc[x_test['number'] == i]\n",
    "    temp_test_y = y_test.loc[y_test['number'] == i]\n",
    "    \n",
    "    temp_y = temp_y['bikes_available'] #removing station number from output\n",
    "    temp_test_y = temp_test_y['bikes_available'] #removing station number from output\n",
    "    \n",
    "    \n",
    "    model.fit(temp_x, temp_y) \n",
    "    \n",
    "    filename = f\"bike_predict_station_{i}.pkl\"\n",
    "    pickle.dump(model,open(filename, 'wb'))\n",
    "    \n",
    "    \n",
    "    predictions = model.predict(temp_test_x)\n",
    "    score = accuracy_score(temp_test_y, predictions)\n",
    "    print(f\"accuracy score for station number {i}: {score}\")\n",
    "\n",
    "        \n",
    "        \n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "b9378240",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7702863961813843"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# code for singular algorithm\n",
    "\n",
    "y_train_b = y_train['bikes_available'] \n",
    "y_test_b = y_test['bikes_available']\n",
    "\n",
    "\n",
    "model.fit(x_train, y_train_b)\n",
    "\n",
    "predictions = model.predict(x_test)\n",
    "\n",
    "score = accuracy_score(y_test_b, predictions)\n",
    "score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "id": "4a859891",
   "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>time</th>\n",
       "      <th>number</th>\n",
       "      <th>rain</th>\n",
       "      <th>day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>29528</th>\n",
       "      <td>164799180</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45967</th>\n",
       "      <td>164803950</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21983</th>\n",
       "      <td>164797050</td>\n",
       "      <td>63</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            time  number rain  day\n",
       "29528  164799180      64    0    4\n",
       "45967  164803950       9    0    5\n",
       "21983  164797050      63    0    4"
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test.tail(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "id": "6a914639",
   "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</th>\n",
       "      <th>stands_available</th>\n",
       "      <th>bikes_available</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>29528</th>\n",
       "      <td>64</td>\n",
       "      <td>25</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45967</th>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21983</th>\n",
       "      <td>63</td>\n",
       "      <td>26</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       number  stands_available  bikes_available\n",
       "29528      64                25               15\n",
       "45967       9                 3               20\n",
       "21983      63                26                9"
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test.tail(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "id": "c1a8c159",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy score for station number 2: 0.7947019867549668\n",
      "accuracy score for station number 3: 0.6950819672131148\n",
      "accuracy score for station number 4: 0.7854785478547854\n",
      "accuracy score for station number 5: 0.6044303797468354\n",
      "accuracy score for station number 6: 0.7668918918918919\n",
      "accuracy score for station number 7: 0.8456973293768546\n",
      "accuracy score for station number 8: 0.6732673267326733\n",
      "accuracy score for station number 9: 0.5741935483870968\n",
      "accuracy score for station number 10: 0.7266666666666667\n",
      "accuracy score for station number 11: 0.8122866894197952\n",
      "accuracy score for station number 12: 0.7864768683274022\n",
      "accuracy score for station number 13: 0.8827361563517915\n",
      "accuracy score for station number 15: 0.8717948717948718\n",
      "accuracy score for station number 16: 0.8289473684210527\n",
      "accuracy score for station number 17: 0.8282208588957055\n",
      "accuracy score for station number 18: 0.643312101910828\n",
      "accuracy score for station number 19: 0.6064516129032258\n",
      "accuracy score for station number 21: 0.7679180887372014\n",
      "accuracy score for station number 22: 0.7118055555555556\n",
      "accuracy score for station number 23: 0.7192429022082019\n",
      "accuracy score for station number 24: 0.6676923076923077\n",
      "accuracy score for station number 25: 0.8631921824104235\n",
      "accuracy score for station number 26: 0.7922535211267606\n",
      "accuracy score for station number 27: 0.6990291262135923\n",
      "accuracy score for station number 28: 0.8041237113402062\n",
      "accuracy score for station number 29: 0.6785714285714286\n",
      "accuracy score for station number 30: 0.819935691318328\n",
      "accuracy score for station number 31: 0.6071428571428571\n",
      "accuracy score for station number 32: 0.6655518394648829\n",
      "accuracy score for station number 33: 0.526813880126183\n",
      "accuracy score for station number 34: 0.608843537414966\n",
      "accuracy score for station number 36: 0.7365079365079366\n",
      "accuracy score for station number 37: 0.9157894736842105\n",
      "accuracy score for station number 38: 0.6490683229813664\n",
      "accuracy score for station number 39: 0.7254901960784313\n",
      "accuracy score for station number 40: 0.7118055555555556\n",
      "accuracy score for station number 41: 0.8838709677419355\n",
      "accuracy score for station number 42: 0.6883116883116883\n",
      "accuracy score for station number 43: 0.6352201257861635\n",
      "accuracy score for station number 44: 0.6949152542372882\n",
      "accuracy score for station number 45: 0.7854785478547854\n",
      "accuracy score for station number 47: 0.8427672955974843\n",
      "accuracy score for station number 48: 0.7586206896551724\n",
      "accuracy score for station number 49: 0.6819484240687679\n",
      "accuracy score for station number 50: 0.7027027027027027\n",
      "accuracy score for station number 51: 0.7663230240549829\n",
      "accuracy score for station number 52: 0.7508896797153025\n",
      "accuracy score for station number 53: 0.8810975609756098\n",
      "accuracy score for station number 54: 0.8389261744966443\n",
      "accuracy score for station number 55: 0.9122137404580153\n",
      "accuracy score for station number 56: 0.6942675159235668\n",
      "accuracy score for station number 57: 0.8928571428571429\n",
      "accuracy score for station number 58: 0.6989966555183946\n",
      "accuracy score for station number 59: 0.8410596026490066\n",
      "accuracy score for station number 60: 0.677115987460815\n",
      "accuracy score for station number 61: 0.8708609271523179\n",
      "accuracy score for station number 62: 0.875\n",
      "accuracy score for station number 63: 0.8371335504885994\n",
      "accuracy score for station number 64: 0.729903536977492\n",
      "accuracy score for station number 65: 0.8018867924528302\n",
      "accuracy score for station number 66: 0.6148867313915858\n",
      "accuracy score for station number 67: 0.6167247386759582\n",
      "accuracy score for station number 68: 0.6199376947040498\n",
      "accuracy score for station number 69: 0.5224913494809689\n",
      "accuracy score for station number 71: 0.8050314465408805\n",
      "accuracy score for station number 72: 0.6996805111821086\n",
      "accuracy score for station number 73: 0.765079365079365\n",
      "accuracy score for station number 74: 0.7616099071207431\n",
      "accuracy score for station number 75: 0.7491638795986622\n",
      "accuracy score for station number 76: 0.8138686131386861\n",
      "accuracy score for station number 77: 0.7305194805194806\n",
      "accuracy score for station number 78: 0.8142857142857143\n",
      "accuracy score for station number 79: 0.8807339449541285\n",
      "accuracy score for station number 80: 0.7784810126582279\n",
      "accuracy score for station number 82: 0.9072847682119205\n",
      "accuracy score for station number 83: 0.7821428571428571\n",
      "accuracy score for station number 84: 0.7979094076655052\n",
      "accuracy score for station number 85: 0.8432055749128919\n",
      "accuracy score for station number 86: 0.7175324675324676\n",
      "accuracy score for station number 87: 0.8247422680412371\n",
      "accuracy score for station number 88: 0.7655172413793103\n",
      "accuracy score for station number 89: 0.9290322580645162\n",
      "accuracy score for station number 90: 0.7138364779874213\n",
      "accuracy score for station number 91: 0.6917808219178082\n",
      "accuracy score for station number 92: 0.718213058419244\n",
      "accuracy score for station number 93: 0.941358024691358\n",
      "accuracy score for station number 94: 0.9933333333333333\n",
      "accuracy score for station number 95: 0.7129629629629629\n",
      "accuracy score for station number 96: 0.9114285714285715\n",
      "accuracy score for station number 97: 0.735191637630662\n",
      "accuracy score for station number 98: 0.8006042296072508\n",
      "accuracy score for station number 99: 0.8528428093645485\n",
      "accuracy score for station number 100: 0.7802547770700637\n",
      "accuracy score for station number 101: 0.7660818713450293\n",
      "accuracy score for station number 102: 0.9151943462897526\n",
      "accuracy score for station number 103: 0.8295081967213115\n",
      "accuracy score for station number 104: 0.9548387096774194\n",
      "accuracy score for station number 105: 0.889589905362776\n",
      "accuracy score for station number 106: 0.8235294117647058\n",
      "accuracy score for station number 107: 0.7759197324414716\n",
      "accuracy score for station number 108: 0.82\n",
      "accuracy score for station number 109: 0.8207547169811321\n",
      "accuracy score for station number 110: 0.8316498316498316\n",
      "accuracy score for station number 111: 0.7335526315789473\n",
      "accuracy score for station number 112: 0.6702508960573477\n",
      "accuracy score for station number 113: 0.8993506493506493\n",
      "accuracy score for station number 114: 0.7220338983050848\n",
      "accuracy score for station number 115: 0.7195571955719557\n",
      "accuracy score for station number 116: 0.9094202898550725\n",
      "accuracy score for station number 117: 0.9156626506024096\n"
     ]
    }
   ],
   "source": [
    "\n",
    "model2 = DecisionTreeClassifier()\n",
    "\n",
    "for i in stations:\n",
    "    temp_x = x_train.loc[x_train['number'] == i] #assigning by the station number\n",
    "    temp_y = y_train.loc[y_train['number'] == i]\n",
    "    \n",
    "    temp_test_x = x_test.loc[x_test['number'] == i]\n",
    "    temp_test_y = y_test.loc[y_test['number'] == i]\n",
    "    \n",
    "    temp_y = temp_y['stands_available'] #removing station number from output\n",
    "    temp_test_y = temp_test_y['stands_available'] #removing station number from output\n",
    "    \n",
    "    \n",
    "    model2.fit(temp_x, temp_y) \n",
    "    \n",
    "    filename = f\"space_predict_station_{i}.pkl\"\n",
    "    pickle.dump(model2,open(filename, 'wb'))\n",
    "    \n",
    "    \n",
    "    predictions = model2.predict(temp_test_x)\n",
    "    score = accuracy_score(temp_test_y, predictions)\n",
    "    print(f\"accuracy score for station number {i}: {score}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "id": "4582fd9b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "             time  number rain  day\n",
      "75512   164812440      41    0    3\n",
      "51282   164805450      96    0    5\n",
      "139975  164831010       3    0    1\n",
      "131647  164828640      84    0    1\n",
      "105615  164821110      69    0    0\n",
      "...           ...     ...  ...  ...\n",
      "24770   164797830      69    0    4\n",
      "28801   164799000      63    0    4\n",
      "29528   164799180      64    0    4\n",
      "45967   164803950       9    0    5\n",
      "21983   164797050      63    0    4\n",
      "\n",
      "[33520 rows x 4 columns]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.7692124105011933"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#old code for singular algorithm\n",
    "\n",
    "y_train_s = y_train['stands_available'] \n",
    "y_test_s = y_test['stands_available']\n",
    "\n",
    "print(x_test)\n",
    "\n",
    "model2.fit(x_train, y_train_s)\n",
    "\n",
    "predictions = model2.predict(x_test)\n",
    "\n",
    "score = accuracy_score(y_test_s, predictions)\n",
    "score"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "23d95b09",
   "metadata": {},
   "source": [
    "- Plot to display accuracy of the model through a graph. Dots on the blue line indicate that the guess was exactly correct."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "id": "a41df8fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x1080 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# source: https://stackoverflow.com/questions/58410187/how-to-plot-predicted-values-vs-the-true-value\n",
    "\n",
    "plt.figure(figsize=(15,15))\n",
    "plt.scatter(y_test_s, predictions, c='crimson')\n",
    "plt.yscale('log')\n",
    "plt.xscale('log')\n",
    "\n",
    "p1 = max(max(predictions), max(y_test_s))\n",
    "p2 = min(min(predictions), min(y_test_s))\n",
    "plt.plot([p1, p2], [p1, p2], 'b-')\n",
    "plt.xlabel('True Values', fontsize=15)\n",
    "plt.ylabel('Predictions', fontsize=15)\n",
    "plt.axis('equal')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f1310622",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}