multinomial-regressionmodel.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 205,
   "id": "5654b7d7-df65-4cf4-8688-c79866637e7c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 207,
   "id": "ea8c96a5-ae07-42a8-8ec1-65ede225b1a4",
   "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>date</th>\n",
       "      <th>road_name</th>\n",
       "      <th>location</th>\n",
       "      <th>suburb</th>\n",
       "      <th>speed_limit</th>\n",
       "      <th>direction</th>\n",
       "      <th>time</th>\n",
       "      <th>Light_Vehicles</th>\n",
       "      <th>Light_Vehicles_with_Trailer</th>\n",
       "      <th>Two_Axle_Trucks_Buses</th>\n",
       "      <th>...</th>\n",
       "      <th>status_id</th>\n",
       "      <th>seg_descr</th>\n",
       "      <th>poly_area</th>\n",
       "      <th>gisid</th>\n",
       "      <th>street_id</th>\n",
       "      <th>seg_part</th>\n",
       "      <th>Geo Shape x</th>\n",
       "      <th>Geo Shape y</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2014-10-11</td>\n",
       "      <td>Wolseley Parade</td>\n",
       "      <td>North East Of Derby Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>16:00</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>4.093996</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Wolseley Parade between Bellair Street and Der...</td>\n",
       "      <td>5235</td>\n",
       "      <td>2301</td>\n",
       "      <td>1186</td>\n",
       "      <td>1</td>\n",
       "      <td>144.928291</td>\n",
       "      <td>-37.796994</td>\n",
       "      <td>-37.796238</td>\n",
       "      <td>144.929383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2014-10-11</td>\n",
       "      <td>Wolseley Parade</td>\n",
       "      <td>North East Of Derby Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>17:00</td>\n",
       "      <td>42.000000</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>4.093996</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Wolseley Parade between Bellair Street and Der...</td>\n",
       "      <td>5235</td>\n",
       "      <td>2301</td>\n",
       "      <td>1186</td>\n",
       "      <td>1</td>\n",
       "      <td>144.928291</td>\n",
       "      <td>-37.796994</td>\n",
       "      <td>-37.796238</td>\n",
       "      <td>144.929383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2014-10-11</td>\n",
       "      <td>Wolseley Parade</td>\n",
       "      <td>North East Of Derby Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>18:00</td>\n",
       "      <td>33.000000</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Wolseley Parade between Bellair Street and Der...</td>\n",
       "      <td>5235</td>\n",
       "      <td>2301</td>\n",
       "      <td>1186</td>\n",
       "      <td>1</td>\n",
       "      <td>144.928291</td>\n",
       "      <td>-37.796994</td>\n",
       "      <td>-37.796238</td>\n",
       "      <td>144.929383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2014-11-11</td>\n",
       "      <td>Wolseley Parade</td>\n",
       "      <td>North East Of Derby Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>2:00</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>4.093996</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Wolseley Parade between Bellair Street and Der...</td>\n",
       "      <td>5235</td>\n",
       "      <td>2301</td>\n",
       "      <td>1186</td>\n",
       "      <td>1</td>\n",
       "      <td>144.928291</td>\n",
       "      <td>-37.796994</td>\n",
       "      <td>-37.796238</td>\n",
       "      <td>144.929383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2014-11-11</td>\n",
       "      <td>Wolseley Parade</td>\n",
       "      <td>North East Of Derby Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>4:00</td>\n",
       "      <td>86.177384</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>4.093996</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Wolseley Parade between Bellair Street and Der...</td>\n",
       "      <td>5235</td>\n",
       "      <td>2301</td>\n",
       "      <td>1186</td>\n",
       "      <td>1</td>\n",
       "      <td>144.928291</td>\n",
       "      <td>-37.796994</td>\n",
       "      <td>-37.796238</td>\n",
       "      <td>144.929383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63115</th>\n",
       "      <td>2014-11-13</td>\n",
       "      <td>Tennyson Street</td>\n",
       "      <td>South West Of Southey Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>12:00</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Tennyson Street between Southey Street and Ard...</td>\n",
       "      <td>1574</td>\n",
       "      <td>2289</td>\n",
       "      <td>1119</td>\n",
       "      <td>1</td>\n",
       "      <td>144.930478</td>\n",
       "      <td>-37.797832</td>\n",
       "      <td>-37.798036</td>\n",
       "      <td>144.929982</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63116</th>\n",
       "      <td>2014-11-13</td>\n",
       "      <td>Tennyson Street</td>\n",
       "      <td>South West Of Southey Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>13:00</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>4.093996</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Tennyson Street between Southey Street and Ard...</td>\n",
       "      <td>1574</td>\n",
       "      <td>2289</td>\n",
       "      <td>1119</td>\n",
       "      <td>1</td>\n",
       "      <td>144.930478</td>\n",
       "      <td>-37.797832</td>\n",
       "      <td>-37.798036</td>\n",
       "      <td>144.929982</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63117</th>\n",
       "      <td>2014-11-13</td>\n",
       "      <td>Tennyson Street</td>\n",
       "      <td>South West Of Southey Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>14:00</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Tennyson Street between Southey Street and Ard...</td>\n",
       "      <td>1574</td>\n",
       "      <td>2289</td>\n",
       "      <td>1119</td>\n",
       "      <td>1</td>\n",
       "      <td>144.930478</td>\n",
       "      <td>-37.797832</td>\n",
       "      <td>-37.798036</td>\n",
       "      <td>144.929982</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63118</th>\n",
       "      <td>2014-11-13</td>\n",
       "      <td>Tennyson Street</td>\n",
       "      <td>South West Of Southey Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>16:00</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Tennyson Street between Southey Street and Ard...</td>\n",
       "      <td>1574</td>\n",
       "      <td>2289</td>\n",
       "      <td>1119</td>\n",
       "      <td>1</td>\n",
       "      <td>144.930478</td>\n",
       "      <td>-37.797832</td>\n",
       "      <td>-37.798036</td>\n",
       "      <td>144.929982</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63119</th>\n",
       "      <td>2014-11-13</td>\n",
       "      <td>Tennyson Street</td>\n",
       "      <td>South West Of Southey Street</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>50</td>\n",
       "      <td>W</td>\n",
       "      <td>19:00</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>0.386506</td>\n",
       "      <td>4.093996</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>Tennyson Street between Southey Street and Ard...</td>\n",
       "      <td>1574</td>\n",
       "      <td>2289</td>\n",
       "      <td>1119</td>\n",
       "      <td>1</td>\n",
       "      <td>144.930478</td>\n",
       "      <td>-37.797832</td>\n",
       "      <td>-37.798036</td>\n",
       "      <td>144.929982</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>63120 rows × 39 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             date        road_name                      location      suburb  \\\n",
       "0      2014-10-11  Wolseley Parade    North East Of Derby Street  Kensington   \n",
       "1      2014-10-11  Wolseley Parade    North East Of Derby Street  Kensington   \n",
       "2      2014-10-11  Wolseley Parade    North East Of Derby Street  Kensington   \n",
       "3      2014-11-11  Wolseley Parade    North East Of Derby Street  Kensington   \n",
       "4      2014-11-11  Wolseley Parade    North East Of Derby Street  Kensington   \n",
       "...           ...              ...                           ...         ...   \n",
       "63115  2014-11-13  Tennyson Street  South West Of Southey Street  Kensington   \n",
       "63116  2014-11-13  Tennyson Street  South West Of Southey Street  Kensington   \n",
       "63117  2014-11-13  Tennyson Street  South West Of Southey Street  Kensington   \n",
       "63118  2014-11-13  Tennyson Street  South West Of Southey Street  Kensington   \n",
       "63119  2014-11-13  Tennyson Street  South West Of Southey Street  Kensington   \n",
       "\n",
       "       speed_limit direction   time  Light_Vehicles  \\\n",
       "0               50         W  16:00       24.000000   \n",
       "1               50         W  17:00       42.000000   \n",
       "2               50         W  18:00       33.000000   \n",
       "3               50         W   2:00        3.000000   \n",
       "4               50         W   4:00       86.177384   \n",
       "...            ...       ...    ...             ...   \n",
       "63115           50         W  12:00        4.000000   \n",
       "63116           50         W  13:00        6.000000   \n",
       "63117           50         W  14:00        6.000000   \n",
       "63118           50         W  16:00        8.000000   \n",
       "63119           50         W  19:00        7.000000   \n",
       "\n",
       "       Light_Vehicles_with_Trailer  Two_Axle_Trucks_Buses  ...  status_id  \\\n",
       "0                         0.386506               4.093996  ...          2   \n",
       "1                         0.386506               4.093996  ...          2   \n",
       "2                         0.386506               1.000000  ...          2   \n",
       "3                         0.386506               4.093996  ...          2   \n",
       "4                         0.386506               4.093996  ...          2   \n",
       "...                            ...                    ...  ...        ...   \n",
       "63115                     0.386506               1.000000  ...          2   \n",
       "63116                     0.386506               4.093996  ...          2   \n",
       "63117                     0.386506               1.000000  ...          2   \n",
       "63118                     0.386506               1.000000  ...          2   \n",
       "63119                     0.386506               4.093996  ...          2   \n",
       "\n",
       "                                               seg_descr  poly_area  gisid  \\\n",
       "0      Wolseley Parade between Bellair Street and Der...       5235   2301   \n",
       "1      Wolseley Parade between Bellair Street and Der...       5235   2301   \n",
       "2      Wolseley Parade between Bellair Street and Der...       5235   2301   \n",
       "3      Wolseley Parade between Bellair Street and Der...       5235   2301   \n",
       "4      Wolseley Parade between Bellair Street and Der...       5235   2301   \n",
       "...                                                  ...        ...    ...   \n",
       "63115  Tennyson Street between Southey Street and Ard...       1574   2289   \n",
       "63116  Tennyson Street between Southey Street and Ard...       1574   2289   \n",
       "63117  Tennyson Street between Southey Street and Ard...       1574   2289   \n",
       "63118  Tennyson Street between Southey Street and Ard...       1574   2289   \n",
       "63119  Tennyson Street between Southey Street and Ard...       1574   2289   \n",
       "\n",
       "       street_id  seg_part  Geo Shape x  Geo Shape y   Latitude   Longitude  \n",
       "0           1186         1   144.928291   -37.796994 -37.796238  144.929383  \n",
       "1           1186         1   144.928291   -37.796994 -37.796238  144.929383  \n",
       "2           1186         1   144.928291   -37.796994 -37.796238  144.929383  \n",
       "3           1186         1   144.928291   -37.796994 -37.796238  144.929383  \n",
       "4           1186         1   144.928291   -37.796994 -37.796238  144.929383  \n",
       "...          ...       ...          ...          ...        ...         ...  \n",
       "63115       1119         1   144.930478   -37.797832 -37.798036  144.929982  \n",
       "63116       1119         1   144.930478   -37.797832 -37.798036  144.929982  \n",
       "63117       1119         1   144.930478   -37.797832 -37.798036  144.929982  \n",
       "63118       1119         1   144.930478   -37.797832 -37.798036  144.929982  \n",
       "63119       1119         1   144.930478   -37.797832 -37.798036  144.929982  \n",
       "\n",
       "[63120 rows x 39 columns]"
      ]
     },
     "execution_count": 207,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "file_path = \"/Users/hnineikhaing/Desktop/cleaned_merged_data.csv\"\n",
    "df= pd.read_csv(file_path)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "id": "06028a2d-ad6d-4a5f-951c-5395d0f899d3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 63120 entries, 0 to 63119\n",
      "Data columns (total 39 columns):\n",
      " #   Column                           Non-Null Count  Dtype  \n",
      "---  ------                           --------------  -----  \n",
      " 0   date                             63120 non-null  object \n",
      " 1   road_name                        63120 non-null  object \n",
      " 2   location                         63120 non-null  object \n",
      " 3   suburb                           63120 non-null  object \n",
      " 4   speed_limit                      63120 non-null  int64  \n",
      " 5   direction                        63120 non-null  object \n",
      " 6   time                             63120 non-null  object \n",
      " 7   Light_Vehicles                   63120 non-null  float64\n",
      " 8   Light_Vehicles_with_Trailer      63120 non-null  float64\n",
      " 9   Two_Axle_Trucks_Buses            63120 non-null  float64\n",
      " 10  Three_Axle_Trucks_Buses          63120 non-null  float64\n",
      " 11  Four_Axle_Trucks                 63120 non-null  float64\n",
      " 12  Three_Axle_Articulated_Vehicles  63120 non-null  float64\n",
      " 13  Four_Axle_Articulated_Vehicles   63120 non-null  float64\n",
      " 14  Five_Axle_Articulated_Vehicles   63120 non-null  float64\n",
      " 15  Six_Axle_Articulated_Vehicles    63120 non-null  float64\n",
      " 16  B_Double_Trucks                  63120 non-null  float64\n",
      " 17  Double_Road_Trains               63120 non-null  float64\n",
      " 18  Triple_Road_Trains               63120 non-null  float64\n",
      " 19  Unknown_Vehicles                 63120 non-null  float64\n",
      " 20  Motorcycles                      63120 non-null  float64\n",
      " 21  Bicycles                         63120 non-null  float64\n",
      " 22  average_speed                    63120 non-null  float64\n",
      " 23  85th_percentile_speed            63120 non-null  float64\n",
      " 24  maximum_speed                    63120 non-null  float64\n",
      " 25  road_segment                     63120 non-null  int64  \n",
      " 26  seg_id                           63120 non-null  int64  \n",
      " 27  str_type                         63120 non-null  object \n",
      " 28  dtupdate                         63120 non-null  int64  \n",
      " 29  status_id                        63120 non-null  int64  \n",
      " 30  seg_descr                        63120 non-null  object \n",
      " 31  poly_area                        63120 non-null  int64  \n",
      " 32  gisid                            63120 non-null  int64  \n",
      " 33  street_id                        63120 non-null  int64  \n",
      " 34  seg_part                         63120 non-null  int64  \n",
      " 35  Geo Shape x                      63120 non-null  float64\n",
      " 36  Geo Shape y                      63120 non-null  float64\n",
      " 37  Latitude                         63120 non-null  float64\n",
      " 38  Longitude                        63120 non-null  float64\n",
      "dtypes: float64(22), int64(9), object(8)\n",
      "memory usage: 18.8+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "id": "f1eeb510-8156-43a4-95ca-e200aaf9a5ff",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   light_vehicle_ratio  heavy_vehicle_ratio\n",
      "0             0.711139             0.153454\n",
      "1             0.810571             0.100632\n",
      "2             0.830548             0.053940\n",
      "3             0.254774             0.395894\n",
      "4             0.897318             0.054549\n"
     ]
    }
   ],
   "source": [
    "# Sum all vehicles to get the total vehicle count\n",
    "df['total_vehicles'] = df[\n",
    "    ['Light_Vehicles', 'Light_Vehicles_with_Trailer', 'Two_Axle_Trucks_Buses', \n",
    "     'Three_Axle_Trucks_Buses', 'Four_Axle_Trucks', 'Three_Axle_Articulated_Vehicles', \n",
    "     'Four_Axle_Articulated_Vehicles', 'Five_Axle_Articulated_Vehicles', \n",
    "     'Six_Axle_Articulated_Vehicles', 'B_Double_Trucks', 'Double_Road_Trains', \n",
    "     'Triple_Road_Trains', 'Unknown_Vehicles', 'Motorcycles', 'Bicycles']\n",
    "].sum(axis=1)\n",
    "\n",
    "# Calculate the proportion of light vehicles\n",
    "df['light_vehicle_ratio'] = (df['Light_Vehicles'] + df['Light_Vehicles_with_Trailer']) / df['total_vehicles']\n",
    "\n",
    "# Calculate the proportion of heavy vehicles\n",
    "df['heavy_vehicle_ratio'] = (\n",
    "    df['Two_Axle_Trucks_Buses'] + df['Three_Axle_Trucks_Buses'] + df['Four_Axle_Trucks'] +\n",
    "    df['Three_Axle_Articulated_Vehicles'] + df['Four_Axle_Articulated_Vehicles'] +\n",
    "    df['Five_Axle_Articulated_Vehicles'] + df['Six_Axle_Articulated_Vehicles'] +\n",
    "    df['B_Double_Trucks'] + df['Double_Road_Trains'] + df['Triple_Road_Trains']\n",
    ") / df['total_vehicles']\n",
    "\n",
    "# Display the first few rows to verify\n",
    "print(df[['light_vehicle_ratio', 'heavy_vehicle_ratio']].head())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "id": "5974a3f7-2eef-4228-ad8f-6b81c3b99732",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "vehicle_composition\n",
      "Light Traffic    36371\n",
      "Mixed Traffic    26248\n",
      "Heavy Traffic      501\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# Function to categorize vehicle composition based on the ratios\n",
    "def categorize_composition(row):\n",
    "    if row['heavy_vehicle_ratio'] > 0.5:\n",
    "        return 'Heavy Traffic'\n",
    "    elif row['light_vehicle_ratio'] > 0.7:\n",
    "        return 'Light Traffic'\n",
    "    else:\n",
    "        return 'Mixed Traffic'\n",
    "\n",
    "# Apply the function to create the vehicle_composition column\n",
    "df['vehicle_composition'] = df.apply(categorize_composition, axis=1)\n",
    "\n",
    "# Check the distribution of the new column\n",
    "print(df['vehicle_composition'].value_counts())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "id": "bd1d6b9b-540f-4315-8076-86ba757b2db3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   light_vehicle_ratio  heavy_vehicle_ratio vehicle_composition\n",
      "0             0.711139             0.153454       Light Traffic\n",
      "1             0.810571             0.100632       Light Traffic\n",
      "2             0.830548             0.053940       Light Traffic\n",
      "3             0.254774             0.395894       Mixed Traffic\n",
      "4             0.897318             0.054549       Light Traffic\n",
      "Vehicle Composition Distribution (%):\n",
      "vehicle_composition\n",
      "Light Traffic    57.621990\n",
      "Mixed Traffic    41.584284\n",
      "Heavy Traffic     0.793726\n",
      "Name: proportion, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# Display a few rows to verify the vehicle_composition\n",
    "print(df[['light_vehicle_ratio', 'heavy_vehicle_ratio', 'vehicle_composition']].head())\n",
    "\n",
    "# Analyze the distribution of vehicle composition categories\n",
    "vehicle_composition_distribution = df['vehicle_composition'].value_counts(normalize=True) * 100\n",
    "print(\"Vehicle Composition Distribution (%):\")\n",
    "print(vehicle_composition_distribution)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "id": "4dd26e82-3300-4520-9684-58c644f363c1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "speed_limit        int64\n",
      "average_speed    float64\n",
      "Latitude         float64\n",
      "Longitude        float64\n",
      "road_name         object\n",
      "location          object\n",
      "suburb            object\n",
      "direction         object\n",
      "dtype: object\n"
     ]
    }
   ],
   "source": [
    "# Defining the features$\n",
    "features = ['speed_limit', 'average_speed', 'Latitude', 'Longitude', 'road_name', 'location', 'suburb', 'direction']\n",
    "\n",
    "# Creating Target variable\n",
    "target = 'vehicle_composition'\n",
    "\n",
    "# Checking the data types of features and handle any categorical variables\n",
    "print(df[features].dtypes)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "id": "847d160d-3e87-4247-9fce-ecd150b5955b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Features shape: (63120, 267)\n",
      "Target shape: (63120,)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.preprocessing import OneHotEncoder\n",
    "\n",
    "# Identify categorical and numerical features\n",
    "categorical_features = ['road_name', 'location', 'suburb', 'direction']\n",
    "numerical_features = ['speed_limit', 'average_speed', 'Latitude', 'Longitude']\n",
    "\n",
    "# Apply OneHotEncoder to categorical features\n",
    "encoder = OneHotEncoder(drop='first', sparse_output=False)\n",
    "encoded_features = encoder.fit_transform(df[categorical_features])\n",
    "\n",
    "# Combine numerical and encoded categorical features\n",
    "import numpy as np\n",
    "X = np.hstack((df[numerical_features].values, encoded_features))\n",
    "\n",
    "# Target variable\n",
    "y = df[target].values\n",
    "\n",
    "# Check the shapes of X and y\n",
    "print(f'Features shape: {X.shape}')\n",
    "print(f'Target shape: {y.shape}')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 156,
   "id": "0dcc7bf4-8df8-4882-89de-cf0fe9d3a943",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training features shape: (50496, 267)\n",
      "Testing features shape: (12624, 267)\n",
      "Training target shape: (50496,)\n",
      "Testing target shape: (12624,)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# Split the data into training (80%) and testing (20%) sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Verify the shapes of the splits\n",
    "print(f'Training features shape: {X_train.shape}')\n",
    "print(f'Testing features shape: {X_test.shape}')\n",
    "print(f'Training target shape: {y_train.shape}')\n",
    "print(f'Testing target shape: {y_test.shape}')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 158,
   "id": "1ab4c4ee-88c1-4395-b5a4-516b4c46f3c7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model coefficients: [[-1.29143794e-02 -1.02636459e-01 -9.61018285e-04  1.78700919e-02\n",
      "  -5.04055401e-01  7.70790862e-01 -4.22595490e-01 -3.71932187e-01\n",
      "   1.05854103e+00 -2.73297730e-01  8.29981193e-01 -7.43464292e-01\n",
      "   1.07497842e-01 -3.75356170e-01  2.25379531e-01  3.35771679e-01\n",
      "  -4.03624785e-01 -1.32412141e-01 -7.25124845e-01  3.15507719e-01\n",
      "   1.16788306e+00  8.76561881e-01  6.69653892e-01 -4.11646868e-01\n",
      "   4.50978767e-01  7.57857306e-01 -5.95933850e-02  1.02069832e+00\n",
      "   8.60230930e-02  9.27632997e-01  6.63152971e-01 -5.76403648e-01\n",
      "  -1.26949129e-01 -2.53384210e-01  6.66063795e-01 -1.72233627e-01\n",
      "  -1.11136425e+00  5.38419122e-01  7.99587912e-01 -4.77300224e-01\n",
      "  -8.66035443e-01  3.89273784e-01 -5.88488705e-01 -3.46729224e-01\n",
      "  -4.90963544e-01 -2.19184968e-01 -4.78570194e-01 -3.99925939e-01\n",
      "   1.16245218e-01 -1.00302477e+00 -4.89814450e-01 -2.00615811e-01\n",
      "   7.84936200e-01  2.55055944e-01  6.00188541e-01  3.76957439e-01\n",
      "   9.40339671e-02  1.02681375e+00 -1.12360483e+00 -4.57768891e-02\n",
      "  -1.81948466e-01  5.50988148e-01 -5.89602213e-01 -7.52353998e-02\n",
      "  -3.66825287e-01 -8.91510525e-01 -8.50739351e-01 -4.95903746e-01\n",
      "  -4.67667610e-01 -5.54904819e-01 -2.31892537e-02  2.69904710e-01\n",
      "   2.69762235e-01 -5.31287801e-01  7.95074904e-01 -6.64754197e-02\n",
      "  -2.49388979e-01 -2.05501832e-01  5.86475093e-01 -4.80276351e-01\n",
      "   4.29554306e-01  2.29768457e-01  5.29291367e-01  3.03944677e-01\n",
      "   9.55432327e-01  8.41999230e-01 -3.35474288e-01 -6.53485784e-01\n",
      "   7.61854696e-01 -9.63135319e-02  4.47791263e-01  4.39794411e-02\n",
      "   3.16758707e-01  9.08996518e-01 -3.14543036e-01 -5.56695300e-02\n",
      "  -1.26424937e-01 -5.57967312e-01 -1.76975993e-01  3.90751723e-01\n",
      "  -1.03843862e-01 -2.90049999e-01 -8.22853849e-01  1.17461330e+00\n",
      "  -2.42315450e-01  3.26394804e-01 -3.80131688e-01 -1.33510061e-01\n",
      "  -6.92629409e-01 -1.07173348e+00 -1.73325320e-01 -4.28166144e-01\n",
      "   4.39794411e-02  7.48222861e-01 -7.73700390e-02 -3.29739874e-03\n",
      "  -9.63135319e-02  2.55055944e-01 -4.08703327e-01  7.12648004e-01\n",
      "   4.26390441e-01 -1.07204666e+00 -1.95738010e-01 -6.92629409e-01\n",
      "  -1.76402975e-01 -3.35474288e-01  3.70204752e-02  3.57706894e-01\n",
      "   3.76957439e-01 -1.26949129e-01  9.88609087e-02 -1.63854315e-01\n",
      "  -2.97130652e-01 -1.78963406e-01  3.15507719e-01  6.69653892e-01\n",
      "  -6.53485784e-01 -3.89805067e-01 -5.40034993e-01 -2.76262394e-01\n",
      "  -3.80131688e-01 -5.54904819e-01 -1.26424937e-01  7.68243437e-01\n",
      "   2.69762235e-01 -9.32330348e-01  6.41513844e-01 -3.82640346e-01\n",
      "   6.62993787e-01  7.84936200e-01  8.12168049e-01 -3.86100290e-01\n",
      "  -3.39024554e-01 -1.72233627e-01 -5.96006617e-01 -3.50374665e-01\n",
      "   9.40339671e-02 -8.77744748e-02 -5.65841404e-01 -5.26420632e-01\n",
      "  -1.04629670e-01 -3.51694980e-01 -2.24708667e-01  2.63787103e-01\n",
      "  -6.45568268e-01  2.25379531e-01 -2.53384210e-01 -7.15495688e-02\n",
      "  -7.33799762e-01 -8.34242359e-01 -5.95933850e-02 -2.96433217e-01\n",
      "  -1.39157681e-01  3.35771679e-01 -1.53680736e-01 -2.31892537e-02\n",
      "   7.75523811e-01 -9.59298478e-02 -4.53902081e-01 -9.45934354e-01\n",
      "  -1.73068630e-01  2.74335372e-01 -2.48098342e-02 -3.20311959e-01\n",
      "   3.80940594e-01 -7.74063576e-01 -8.36649977e-01  5.19877167e-01\n",
      "  -8.13398855e-02 -2.39383459e-01 -3.66825287e-01  8.93204918e-02\n",
      "   2.69904710e-01 -1.44145522e-01  1.08318444e-01 -1.33510061e-01\n",
      "  -2.05501832e-01  1.67223520e+00 -4.65657137e-02  4.29554306e-01\n",
      "  -5.57967312e-01  4.81664839e-01 -3.15298148e-01  4.02527254e-01\n",
      "  -1.68668060e-01  1.83062744e-01 -1.65667016e-01  5.08158793e-01\n",
      "  -1.11237994e+00  5.86475093e-01 -1.32412141e-01  1.05854103e+00\n",
      "  -5.71139145e-01 -3.73941131e-01 -3.74718325e-01  7.76140954e-01\n",
      "  -8.81590778e-01 -6.28538709e-01 -1.00302477e+00  5.50988148e-01\n",
      "   1.11528111e+00 -1.42492580e-01  5.50093552e-01  1.64370537e+00\n",
      "   1.56481446e+00 -8.26230390e-02 -7.39316729e-01  7.27078281e-01\n",
      "   1.09431954e+00 -7.36212171e-02 -2.44369105e-01 -2.38598587e-02\n",
      "  -3.46729224e-01  2.68779398e-01  3.89273784e-01 -4.80276351e-01\n",
      "   9.27632997e-01  2.29768457e-01  4.76720197e-01  4.47791263e-01\n",
      "  -7.21899568e-01 -7.56483799e-02 -4.57768891e-02 -3.75356170e-01\n",
      "  -2.90049999e-01 -1.07032733e+00 -1.30055139e-01 -4.03624785e-01\n",
      "   1.54267140e-01  1.21323930e+00  4.50978767e-01  6.59724264e-01\n",
      "   1.43877474e+00  5.38419122e-01  4.47791263e-01  1.11376793e-01\n",
      "  -3.65264565e-01 -5.74712674e-01 -8.06831203e-01  2.75912403e-01\n",
      "   4.12951953e-04 -2.89951975e-01 -4.99744666e-01  4.99141779e-01\n",
      "   1.39210158e-01 -1.52491543e-02 -2.02195100e-02]\n",
      " [ 2.96980644e-02  7.68544877e-02 -2.74077758e-03 -2.21415987e-02\n",
      "   4.01828162e-01 -5.20183890e-01  6.87152905e-02  3.48266758e-01\n",
      "  -1.34103824e+00  6.69167206e-01 -6.53448480e-01  4.88305706e-01\n",
      "  -4.29947446e-01 -2.44503050e-01  1.56387200e-01 -4.91528373e-01\n",
      "   4.77152135e-01  4.04097998e-02  8.61360835e-01 -3.96913562e-02\n",
      "  -8.89863303e-01 -4.86640309e-01 -5.12053570e-01  6.39335218e-02\n",
      "  -2.58062642e-01 -5.91548816e-01 -4.32490162e-01 -1.37155989e+00\n",
      "  -8.73615291e-02 -3.81002748e-01 -8.99266852e-03  1.48822293e+00\n",
      "   9.42925529e-01 -8.47666195e-02 -3.37820744e-01  6.33181444e-01\n",
      "   1.03257714e+00  4.48260884e-03 -7.31852566e-01  5.10200633e-01\n",
      "   9.60820368e-01 -5.06025644e-01  1.20564354e-01 -2.43550695e-01\n",
      "   2.38382598e-01  5.20348133e-02  1.17654358e+00  2.77486490e-01\n",
      "  -1.71543732e-01  1.29914683e+00  3.93368566e-01  1.05607313e-01\n",
      "  -8.80999797e-01 -2.98730016e-01 -9.06874574e-01 -1.37016255e-01\n",
      "   1.93674921e-01 -1.77577670e+00  3.48199181e-01  4.25565382e-01\n",
      "   7.14099890e-01 -3.97125452e-01 -4.07459797e-01  2.94348493e-02\n",
      "  -1.10389056e-01  7.03836821e-01  4.91074834e-01  1.18390571e-01\n",
      "   2.77738718e-01  7.43364627e-01  8.78050923e-02 -2.53384895e-01\n",
      "  -2.03756922e-01  3.53156873e-01 -6.97494082e-01 -3.83633568e-01\n",
      "   1.39137860e+00 -1.95058898e-01 -2.40079890e-01 -1.50404207e-01\n",
      "  -4.59016275e-01 -1.64845137e-02 -7.18694923e-01 -2.80480556e-01\n",
      "  -7.68367667e-01 -4.48168391e-01 -3.50335761e-01  2.63506076e-02\n",
      "  -5.16071251e-01  2.41982172e-02 -3.05603835e-01 -3.72915378e-01\n",
      "   4.85410388e-02 -7.59182619e-01  1.50718812e+00 -2.03944819e-01\n",
      "  -6.61489132e-02  3.68669695e-01  8.27162511e-01  5.55247192e-02\n",
      "   4.69641128e-01 -3.95402121e-01  1.13304398e-01 -1.12312061e+00\n",
      "   1.26679121e+00 -2.85092187e-01  1.11479722e-02  3.25706850e-01\n",
      "   3.34466844e-01  6.22935495e-01 -2.57012937e-01  1.69844159e-01\n",
      "  -3.72915378e-01 -6.22033623e-01  1.91859879e-01  1.95834433e-02\n",
      "   2.41982172e-02 -2.98730016e-01 -1.45661844e-02 -2.65914371e-01\n",
      "  -5.01086983e-01  3.82251529e-01 -2.16041924e-01  3.34466844e-01\n",
      "  -2.79046960e-01 -3.50335761e-01  1.89156312e-01 -4.07061530e-01\n",
      "  -1.37016255e-01  9.42925529e-01 -1.22294907e-01  2.16713401e-01\n",
      "   1.96381738e-01  7.36836500e-01 -3.96913562e-02 -5.12053570e-01\n",
      "   2.63506076e-02  6.79859012e-02  7.52546465e-01  3.53467220e-01\n",
      "   1.11479722e-02  7.43364627e-01 -6.61489132e-02 -3.26326313e-01\n",
      "  -2.03756922e-01  5.82173661e-01 -5.01930060e-01  8.14324014e-01\n",
      "  -3.93776344e-01 -8.80999797e-01 -6.40860333e-01  2.28686501e-01\n",
      "   6.32674334e-01  6.33181444e-01  1.11250686e+00 -6.29474148e-02\n",
      "   1.93674921e-01  3.89598135e-01  6.64281268e-01  2.78859901e-01\n",
      "   2.67685249e-01  8.58829817e-01  6.29393116e-01 -3.44337209e-01\n",
      "   1.14016150e-01  1.56387200e-01 -8.47666195e-02 -3.73488363e-01\n",
      "   2.80213280e-01  1.32648812e-01 -4.32490162e-01 -1.65555502e-01\n",
      "   1.27954738e-02 -4.91528373e-01  4.64775577e-01  8.78050923e-02\n",
      "  -8.31801959e-01  3.62219561e-01  4.99023510e-01  4.16895739e-01\n",
      "  -2.45698340e-01 -1.56657883e-01 -3.37206037e-02  5.66761801e-01\n",
      "  -3.05564359e-01  7.94189911e-01  5.45970048e-01  3.65521968e-01\n",
      "  -1.72060397e-02  3.17449192e-01 -1.10389056e-01 -1.06944972e-01\n",
      "  -2.53384895e-01  6.12387675e-01 -1.60313995e-01  3.25706850e-01\n",
      "  -1.95058898e-01 -1.28912610e+00  4.88682819e-01 -4.59016275e-01\n",
      "   3.68669695e-01 -1.77786226e-02  3.18461548e-01  4.12627640e-02\n",
      "   4.01481957e-01 -4.41172951e-01  2.30276036e-01  1.99970031e-02\n",
      "   3.90545685e-01 -2.40079890e-01  4.04097998e-02 -1.34103824e+00\n",
      "   1.47825420e-01 -1.51405624e-01  6.68388664e-02 -4.63775829e-01\n",
      "   2.95265112e-01  4.69430496e-01  1.29914683e+00 -3.97125452e-01\n",
      "  -4.85710513e-01  2.07396982e-01 -8.77446196e-01 -2.33382601e-01\n",
      "  -1.61751568e+00  5.05202314e-01  4.68323578e-01 -1.50009512e-01\n",
      "  -9.56831252e-01 -4.14728635e-01  5.54461470e-01  1.65859281e-01\n",
      "  -2.43550695e-01 -8.75545372e-01 -5.06025644e-01 -1.50404207e-01\n",
      "  -3.81002748e-01 -1.64845137e-02 -8.98330502e-01 -3.05603835e-01\n",
      "  -6.34369486e-03 -3.93551282e-02  4.25565382e-01 -2.44503050e-01\n",
      "  -3.95402121e-01  5.94762682e-01  7.99483443e-01  4.77152135e-01\n",
      "   7.65595455e-02 -9.13718051e-01 -2.58062642e-01 -9.09860306e-01\n",
      "  -6.75637872e-01  4.48260884e-03 -3.05603835e-01 -1.76094140e-01\n",
      "   6.97919426e-02  1.28398682e-02  7.95576044e-01 -3.73506082e-01\n",
      "   2.84983471e-01  1.14559805e-01  3.75081507e-01 -3.76023741e-01\n",
      "  -7.01979938e-02  4.07026118e-02 -8.58954733e-02]\n",
      " [-1.67836850e-02  2.57819709e-02  3.70179586e-03  4.27150688e-03\n",
      "   1.02227239e-01 -2.50606972e-01  3.53880200e-01  2.36654290e-02\n",
      "   2.82497206e-01 -3.95869476e-01 -1.76532713e-01  2.55158586e-01\n",
      "   3.22449604e-01  6.19859220e-01 -3.81766731e-01  1.55756694e-01\n",
      "  -7.35273498e-02  9.20023416e-02 -1.36235991e-01 -2.75816363e-01\n",
      "  -2.78019754e-01 -3.89921572e-01 -1.57600322e-01  3.47713347e-01\n",
      "  -1.92916126e-01 -1.66308490e-01  4.92083547e-01  3.50861568e-01\n",
      "   1.33843609e-03 -5.46630248e-01 -6.54160302e-01 -9.11819286e-01\n",
      "  -8.15976400e-01  3.38150829e-01 -3.28243051e-01 -4.60947818e-01\n",
      "   7.87871132e-02 -5.42901731e-01 -6.77353464e-02 -3.29004090e-02\n",
      "  -9.47849250e-02  1.16751860e-01  4.67924351e-01  5.90279919e-01\n",
      "   2.52580945e-01  1.67150155e-01 -6.97973381e-01  1.22439449e-01\n",
      "   5.52985136e-02 -2.96122058e-01  9.64458836e-02  9.50084980e-02\n",
      "   9.60635969e-02  4.36740726e-02  3.06686033e-01 -2.39941184e-01\n",
      "  -2.87708889e-01  7.48962949e-01  7.75405649e-01 -3.79788493e-01\n",
      "  -5.32151424e-01 -1.53862696e-01  9.97062010e-01  4.58005505e-02\n",
      "   4.77214343e-01  1.87673704e-01  3.59664517e-01  3.77513174e-01\n",
      "   1.89928892e-01 -1.88459808e-01 -6.46158386e-02 -1.65198146e-02\n",
      "  -6.60053128e-02  1.78130928e-01 -9.75808217e-02  4.50108988e-01\n",
      "  -1.14198962e+00  4.00560730e-01 -3.46395203e-01  6.30680558e-01\n",
      "   2.94619684e-02 -2.13283943e-01  1.89403556e-01 -2.34641211e-02\n",
      "  -1.87064661e-01 -3.93830839e-01  6.85810049e-01  6.27135176e-01\n",
      "  -2.45783445e-01  7.21153148e-02 -1.42187427e-01  3.28935937e-01\n",
      "  -3.65299746e-01 -1.49813900e-01 -1.19264509e+00  2.59614349e-01\n",
      "   1.92573850e-01  1.89297617e-01 -6.50186518e-01 -4.46276442e-01\n",
      "  -3.65797266e-01  6.85452120e-01  7.09549451e-01 -5.14926964e-02\n",
      "  -1.02447576e+00 -4.13026170e-02  3.68983716e-01 -1.92196790e-01\n",
      "   3.58162566e-01  4.48797984e-01  4.30338257e-01  2.58321985e-01\n",
      "   3.28935937e-01 -1.26189238e-01 -1.14489840e-01 -1.62860446e-02\n",
      "   7.21153148e-02  4.36740726e-02  4.23269511e-01 -4.46733633e-01\n",
      "   7.46965416e-02  6.89795127e-01  4.11779933e-01  3.58162566e-01\n",
      "   4.55449935e-01  6.85810049e-01 -2.26176787e-01  4.93546362e-02\n",
      "  -2.39941184e-01 -8.15976400e-01  2.34339984e-02 -5.28590863e-02\n",
      "   1.00748914e-01 -5.57873094e-01 -2.75816363e-01 -1.57600322e-01\n",
      "   6.27135176e-01  3.21819166e-01 -2.12511472e-01 -7.72048262e-02\n",
      "   3.68983716e-01 -1.88459808e-01  1.92573850e-01 -4.41917123e-01\n",
      "  -6.60053128e-02  3.50156687e-01 -1.39583783e-01 -4.31683668e-01\n",
      "  -2.69217444e-01  9.60635969e-02 -1.71307716e-01  1.57413789e-01\n",
      "  -2.93649780e-01 -4.60947818e-01 -5.16500238e-01  4.13322080e-01\n",
      "  -2.87708889e-01 -3.01823660e-01 -9.84398639e-02  2.47560732e-01\n",
      "  -1.63055579e-01 -5.07134837e-01 -4.04684449e-01  8.05501062e-02\n",
      "   5.31552119e-01 -3.81766731e-01  3.38150829e-01  4.45037932e-01\n",
      "   4.53586483e-01  7.01593547e-01  4.92083547e-01  4.61988720e-01\n",
      "   1.26362207e-01  1.55756694e-01 -3.11094841e-01 -6.46158386e-02\n",
      "   5.62781484e-02 -2.66289713e-01 -4.51214293e-02  5.29038616e-01\n",
      "   4.18766970e-01 -1.17677488e-01  5.85304379e-02 -2.46449842e-01\n",
      "  -7.53762351e-02 -2.01263354e-02  2.90679929e-01 -8.85399135e-01\n",
      "   9.85459252e-02 -7.80657323e-02  4.77214343e-01  1.76244807e-02\n",
      "  -1.65198146e-02 -4.68242153e-01  5.19955514e-02 -1.92196790e-01\n",
      "   4.00560730e-01 -3.83109094e-01 -4.42117105e-01  2.94619684e-02\n",
      "   1.89297617e-01 -4.63886216e-01 -3.16339923e-03 -4.43790018e-01\n",
      "  -2.32813898e-01  2.58110207e-01 -6.46090208e-02 -5.28155796e-01\n",
      "   7.21834250e-01 -3.46395203e-01  9.20023416e-02  2.82497206e-01\n",
      "   4.23313725e-01  5.25346755e-01  3.07879459e-01 -3.12365125e-01\n",
      "   5.86325665e-01  1.59108213e-01 -2.96122058e-01 -1.53862696e-01\n",
      "  -6.29570602e-01 -6.49044021e-02  3.27352644e-01 -1.41032277e+00\n",
      "   5.27012251e-02 -4.22579275e-01  2.70993151e-01 -5.77068770e-01\n",
      "  -1.37488284e-01  4.88349852e-01 -3.10092366e-01 -1.41999422e-01\n",
      "   5.90279919e-01  6.06765974e-01  1.16751860e-01  6.30680558e-01\n",
      "  -5.46630248e-01 -2.13283943e-01  4.21610306e-01 -1.42187427e-01\n",
      "   7.28243263e-01  1.15003508e-01 -3.79788493e-01  6.19859220e-01\n",
      "   6.85452120e-01  4.75564646e-01 -6.69428303e-01 -7.35273498e-02\n",
      "  -2.30826686e-01 -2.99521248e-01 -1.92916126e-01  2.50136042e-01\n",
      "  -7.63136867e-01 -5.42901731e-01 -1.42187427e-01  6.47173475e-02\n",
      "   2.95472622e-01  5.61872806e-01  1.12551590e-02  9.75936792e-02\n",
      "  -2.85396423e-01  1.75392170e-01  1.24663159e-01 -1.23118038e-01\n",
      "  -6.90121643e-02 -2.54534574e-02  1.06114983e-01]]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/anaconda3/lib/python3.12/site-packages/sklearn/linear_model/_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "# Initialize the multinomial logistic regression model\n",
    "model = LogisticRegression(multi_class='multinomial', solver='lbfgs', max_iter=1000, class_weight='balanced')\n",
    "# Train the model\n",
    "model.fit(X_train, y_train)\n",
    "\n",
    "print(\"Model coefficients:\", model.coef_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "id": "569cdd71-2dac-46fc-aa05-8b1509c4b3d8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Predict vehicle compositions on the test set\n",
    "y_pred = model.predict(X_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "id": "33569f26-7462-4345-8d28-be95a7f30ebc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-7 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-7 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-7 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-7 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-7 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-7 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-7 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-7 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-7 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-7 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-7 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(max_iter=1000, multi_class=&#x27;multinomial&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" checked><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;LogisticRegression<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>LogisticRegression(max_iter=1000, multi_class=&#x27;multinomial&#x27;)</pre></div> </div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression(max_iter=1000, multi_class='multinomial')"
      ]
     },
     "execution_count": 162,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# Initialize the scaler\n",
    "scaler = StandardScaler()\n",
    "\n",
    "# Scale the training and testing data\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "# Re-train the logistic regression model on the scaled data\n",
    "model = LogisticRegression(multi_class='multinomial', solver='lbfgs', max_iter=1000)\n",
    "model.fit(X_train_scaled, y_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "id": "eb2df7e4-b1a8-4753-84f8-7fe71e830f4d",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "Heavy Traffic       0.03      0.81      0.07        97\n",
      "Light Traffic       0.80      0.67      0.73      7240\n",
      "Mixed Traffic       0.63      0.50      0.56      5287\n",
      "\n",
      "     accuracy                           0.60     12624\n",
      "    macro avg       0.49      0.66      0.45     12624\n",
      " weighted avg       0.72      0.60      0.65     12624\n",
      "\n",
      "Confusion Matrix:\n",
      "[[  79    9    9]\n",
      " [ 808 4861 1571]\n",
      " [1388 1242 2657]]\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report, confusion_matrix\n",
    "\n",
    "# Print the classification report\n",
    "print(\"Classification Report:\")\n",
    "print(classification_report(y_test, y_pred))\n",
    "\n",
    "# Print the confusion matrix\n",
    "print(\"Confusion Matrix:\")\n",
    "print(confusion_matrix(y_test, y_pred))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "id": "9bd37374-ec66-400d-afb8-3fbcfcf25b78",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "# Generate the confusion matrix\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "# Plot the heatmap\n",
    "plt.figure(figsize=(8, 6))\n",
    "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=model.classes_, yticklabels=model.classes_)\n",
    "plt.ylabel('Actual')\n",
    "plt.xlabel('Predicted')\n",
    "plt.title('Confusion Matrix')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "id": "d132bb26-57b1-4ab0-b011-1ea7d1021572",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross-validation scores: [0.73376238 0.73561739 0.73730072 0.73848896 0.73631053]\n",
      "Average cross-validation score: 0.7362959944078377\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "# Perform 5-fold cross-validation on the scaled data\n",
    "cv_scores = cross_val_score(model, X_train_scaled, y_train, cv=5)\n",
    "\n",
    "# Print cross-validation scores\n",
    "print(\"Cross-validation scores:\", cv_scores)\n",
    "print(\"Average cross-validation score:\", np.mean(cv_scores))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "id": "d149303b-a08a-43c0-ae11-ad6d663adebd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Heavy Traffic  Light Traffic  Mixed Traffic Actual Composition\n",
      "0       0.000002       0.863961       0.136036      Mixed Traffic\n",
      "1       0.000042       0.895697       0.104262      Light Traffic\n",
      "2       0.000043       0.999952       0.000005      Light Traffic\n",
      "3       0.000046       0.728718       0.271236      Mixed Traffic\n",
      "4       0.000013       0.999984       0.000003      Light Traffic\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Take a subset of the test data (first 5 rows for demonstration)\n",
    "subset = X_test_scaled[:5]\n",
    "actual_compositions = y_test[:5]\n",
    "\n",
    "# Predict the probability distribution for each vehicle composition\n",
    "predicted_probs = model.predict_proba(subset)\n",
    "\n",
    "# Create a DataFrame to display the results\n",
    "probs_df = pd.DataFrame(predicted_probs, columns=model.classes_)\n",
    "probs_df['Actual Composition'] = actual_compositions\n",
    "\n",
    "# Display the probability distribution along with actual classes\n",
    "print(probs_df)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "id": "d8e01f98-ec56-4615-a89b-b9df4b2045ea",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Heavy Traffic  Light Traffic  Mixed Traffic Actual Composition\n",
      "0       0.066570       0.333368       0.600062      Mixed Traffic\n",
      "1       0.000029       0.194368       0.805604      Mixed Traffic\n",
      "2       0.000087       0.189673       0.810241      Mixed Traffic\n",
      "3       0.000046       0.550835       0.449119      Light Traffic\n",
      "4       0.000100       0.844199       0.155702      Light Traffic\n"
     ]
    }
   ],
   "source": [
    "# Testing on rows 10 to 15 of the test set\n",
    "subset = X_test_scaled[10:15]\n",
    "actual_compositions = y_test[10:15]\n",
    "\n",
    "# Predict the probability distribution for this subset\n",
    "predicted_probs = model.predict_proba(subset)\n",
    "\n",
    "# Create a DataFrame to display the results\n",
    "probs_df = pd.DataFrame(predicted_probs, columns=model.classes_)\n",
    "probs_df['Actual Composition'] = actual_compositions\n",
    "\n",
    "# Display the probability distribution along with actual classes\n",
    "print(probs_df)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 186,
   "id": "3a83bd48-df75-464b-a2c6-0db99577d8e8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Heavy Traffic  Light Traffic  Mixed Traffic Actual Composition\n",
      "0       0.028757       0.148906       0.822337      Mixed Traffic\n",
      "1       0.000012       0.975957       0.024031      Light Traffic\n",
      "2       0.010151       0.656182       0.333668      Light Traffic\n",
      "3       0.006916       0.374662       0.618422      Light Traffic\n",
      "4       0.002019       0.634784       0.363197      Light Traffic\n"
     ]
    }
   ],
   "source": [
    "# Testing on the last 5 rows of the test set\n",
    "subset = X_test_scaled[-5:]\n",
    "actual_compositions = y_test[-5:]\n",
    "\n",
    "# Predict the probability distribution for this subset\n",
    "predicted_probs = model.predict_proba(subset)\n",
    "\n",
    "# Create a DataFrame to display the results\n",
    "probs_df = pd.DataFrame(predicted_probs, columns=model.classes_)\n",
    "probs_df['Actual Composition'] = actual_compositions\n",
    "\n",
    "# Display the probability distribution along with actual classes\n",
    "print(probs_df)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 195,
   "id": "5cfff985-5fa1-47e8-91e3-605be32d794e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example new data (replace with actual values for each feature)\n",
    "# [speed_limit, average_speed, latitude, longitude, light_vehicle_ratio, heavy_vehicle_ratio]\n",
    "new_data = [[60, 50, -37.814, 144.963, 0.4, 0.2]]  # Example of a new traffic scenario\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 213,
   "id": "7f4c73ae-42dd-44ef-aead-0e062c8c24a4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['date', 'road_name', 'location', 'suburb', 'speed_limit', 'direction',\n",
      "       'time', 'Light_Vehicles', 'Light_Vehicles_with_Trailer',\n",
      "       'Two_Axle_Trucks_Buses', 'Three_Axle_Trucks_Buses', 'Four_Axle_Trucks',\n",
      "       'Three_Axle_Articulated_Vehicles', 'Four_Axle_Articulated_Vehicles',\n",
      "       'Five_Axle_Articulated_Vehicles', 'Six_Axle_Articulated_Vehicles',\n",
      "       'B_Double_Trucks', 'Double_Road_Trains', 'Triple_Road_Trains',\n",
      "       'Unknown_Vehicles', 'Motorcycles', 'Bicycles', 'average_speed',\n",
      "       '85th_percentile_speed', 'maximum_speed', 'road_segment', 'seg_id',\n",
      "       'str_type', 'dtupdate', 'status_id', 'seg_descr', 'poly_area', 'gisid',\n",
      "       'street_id', 'seg_part', 'Geo Shape x', 'Geo Shape y', 'Latitude',\n",
      "       'Longitude'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "# Print all the columns in the DataFrame\n",
    "print(df.columns)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 217,
   "id": "a1f1b07d-6872-4853-b342-397a273c94be",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example: Recreate 'vehicle_composition' based on some conditions (adjust to your case)\n",
    "# You may have defined vehicle composition based on traffic types or a combination of vehicle columns.\n",
    "df['vehicle_composition'] = pd.cut(df['average_speed'], \n",
    "                                   bins=[0, 30, 60, 100], \n",
    "                                   labels=['Heavy Traffic', 'Mixed Traffic', 'Light Traffic'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 233,
   "id": "e55f9498-325c-4a36-b292-0fd7765c4796",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Test predictions on a subset of test data\n",
    "subset = X_test_scaled[10:15]  # Testing on a small subset\n",
    "actual_compositions = y_test[10:15]  # This is likely a numpy array or list, so no need for `.values`\n",
    "\n",
    "# Predict the probability distribution for this subset\n",
    "predicted_probs = model.predict_proba(subset)\n",
    "\n",
    "# Create a DataFrame to display the results\n",
    "probs_df = pd.DataFrame(predicted_probs, columns=model.classes_)\n",
    "probs_df['Actual Composition'] = actual_compositions  # No need for .values\n",
    "\n",
    "# Visualize the probability distribution for each row\n",
    "for i in range(len(probs_df)):\n",
    "    probs_df.iloc[i, :-1].plot(kind='bar', figsize=(8, 4))\n",
    "    plt.title(f'Predicted Probabilities for Row {i+1} - Actual: {probs_df[\"Actual Composition\"].iloc[i]}')\n",
    "    plt.ylabel('Probability')\n",
    "    plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 235,
   "id": "9e198392-6428-4d41-a9d2-b99af3617a2c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "               precision    recall  f1-score   support\n",
      "\n",
      "Heavy Traffic       1.00      0.01      0.02        97\n",
      "Light Traffic       0.76      0.79      0.77      7240\n",
      "Mixed Traffic       0.69      0.66      0.67      5287\n",
      "\n",
      "     accuracy                           0.73     12624\n",
      "    macro avg       0.81      0.49      0.49     12624\n",
      " weighted avg       0.73      0.73      0.72     12624\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "\n",
    "# Print classification report\n",
    "print(classification_report(y_test, model.predict(X_test_scaled), target_names=model.classes_))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 255,
   "id": "f3b1ce36-7b3c-41b4-aa6d-486e9f8c250a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Heavy Traffic  Light Traffic  Mixed Traffic Actual Composition\n",
      "0       0.000062       0.361548       0.638390      Light Traffic\n",
      "1       0.004132       0.274873       0.720995      Light Traffic\n",
      "2       0.000125       0.372711       0.627165      Mixed Traffic\n",
      "3       0.000049       0.945645       0.054305      Light Traffic\n",
      "4       0.027270       0.337151       0.635579      Mixed Traffic\n"
     ]
    }
   ],
   "source": [
    "# Testing on rows 50 to 55 of the test set\n",
    "subset = X_test_scaled[50:55]\n",
    "actual_compositions = y_test[50:55]\n",
    "\n",
    "# Predict the probability distribution for this subset\n",
    "predicted_probs = model.predict_proba(subset)\n",
    "\n",
    "# Create a DataFrame to display the results\n",
    "probs_df = pd.DataFrame(predicted_probs, columns=model.classes_)\n",
    "probs_df['Actual Composition'] = actual_compositions\n",
    "\n",
    "# Display the probability distribution along with actual classes\n",
    "print(probs_df)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 247,
   "id": "214e85ee-f97f-44fe-ba71-47773b4b2c32",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df.drop(columns=['vehicle_composition'])  # where 'target_column' is the name of your target variable\n",
    "y = df['vehicle_composition']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 249,
   "id": "d0494be3-04ef-4f63-b3b4-7c6457a3dc83",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['date', 'road_name', 'location', 'suburb', 'speed_limit', 'direction',\n",
      "       'time', 'Light_Vehicles', 'Light_Vehicles_with_Trailer',\n",
      "       'Two_Axle_Trucks_Buses', 'Three_Axle_Trucks_Buses', 'Four_Axle_Trucks',\n",
      "       'Three_Axle_Articulated_Vehicles', 'Four_Axle_Articulated_Vehicles',\n",
      "       'Five_Axle_Articulated_Vehicles', 'Six_Axle_Articulated_Vehicles',\n",
      "       'B_Double_Trucks', 'Double_Road_Trains', 'Triple_Road_Trains',\n",
      "       'Unknown_Vehicles', 'Motorcycles', 'Bicycles', 'average_speed',\n",
      "       '85th_percentile_speed', 'maximum_speed', 'road_segment', 'seg_id',\n",
      "       'str_type', 'dtupdate', 'status_id', 'seg_descr', 'poly_area', 'gisid',\n",
      "       'street_id', 'seg_part', 'Geo Shape x', 'Geo Shape y', 'Latitude',\n",
      "       'Longitude'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(X.columns)  # Assuming X is the unscaled feature set\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "924ad2f7-32fa-404f-b2e1-e048ca9c7afe",
   "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}