poisson_regression.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "4867383b",
   "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>holiday</th>\n",
       "      <th>workingday</th>\n",
       "      <th>weathersit</th>\n",
       "      <th>temp</th>\n",
       "      <th>atemp</th>\n",
       "      <th>hum</th>\n",
       "      <th>windspeed</th>\n",
       "      <th>cnt</th>\n",
       "      <th>season_fall</th>\n",
       "      <th>season_spring</th>\n",
       "      <th>season_summer</th>\n",
       "      <th>season_winter</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.344167</td>\n",
       "      <td>0.363625</td>\n",
       "      <td>0.805833</td>\n",
       "      <td>0.160446</td>\n",
       "      <td>985</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.363478</td>\n",
       "      <td>0.353739</td>\n",
       "      <td>0.696087</td>\n",
       "      <td>0.248539</td>\n",
       "      <td>801</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.196364</td>\n",
       "      <td>0.189405</td>\n",
       "      <td>0.437273</td>\n",
       "      <td>0.248309</td>\n",
       "      <td>1349</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>0.212122</td>\n",
       "      <td>0.590435</td>\n",
       "      <td>0.160296</td>\n",
       "      <td>1562</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.226957</td>\n",
       "      <td>0.229270</td>\n",
       "      <td>0.436957</td>\n",
       "      <td>0.186900</td>\n",
       "      <td>1600</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>726</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0.254167</td>\n",
       "      <td>0.226642</td>\n",
       "      <td>0.652917</td>\n",
       "      <td>0.350133</td>\n",
       "      <td>2114</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>727</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0.253333</td>\n",
       "      <td>0.255046</td>\n",
       "      <td>0.590000</td>\n",
       "      <td>0.155471</td>\n",
       "      <td>3095</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>728</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.253333</td>\n",
       "      <td>0.242400</td>\n",
       "      <td>0.752917</td>\n",
       "      <td>0.124383</td>\n",
       "      <td>1341</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>729</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.255833</td>\n",
       "      <td>0.231700</td>\n",
       "      <td>0.483333</td>\n",
       "      <td>0.350754</td>\n",
       "      <td>1796</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>730</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0.215833</td>\n",
       "      <td>0.223487</td>\n",
       "      <td>0.577500</td>\n",
       "      <td>0.154846</td>\n",
       "      <td>2729</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>731 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     holiday  workingday  weathersit      temp     atemp       hum  windspeed  \\\n",
       "0          0           0           2  0.344167  0.363625  0.805833   0.160446   \n",
       "1          0           0           2  0.363478  0.353739  0.696087   0.248539   \n",
       "2          0           1           1  0.196364  0.189405  0.437273   0.248309   \n",
       "3          0           1           1  0.200000  0.212122  0.590435   0.160296   \n",
       "4          0           1           1  0.226957  0.229270  0.436957   0.186900   \n",
       "..       ...         ...         ...       ...       ...       ...        ...   \n",
       "726        0           1           2  0.254167  0.226642  0.652917   0.350133   \n",
       "727        0           1           2  0.253333  0.255046  0.590000   0.155471   \n",
       "728        0           0           2  0.253333  0.242400  0.752917   0.124383   \n",
       "729        0           0           1  0.255833  0.231700  0.483333   0.350754   \n",
       "730        0           1           2  0.215833  0.223487  0.577500   0.154846   \n",
       "\n",
       "      cnt  season_fall  season_spring  season_summer  season_winter  \n",
       "0     985            0              1              0              0  \n",
       "1     801            0              1              0              0  \n",
       "2    1349            0              1              0              0  \n",
       "3    1562            0              1              0              0  \n",
       "4    1600            0              1              0              0  \n",
       "..    ...          ...            ...            ...            ...  \n",
       "726  2114            0              1              0              0  \n",
       "727  3095            0              1              0              0  \n",
       "728  1341            0              1              0              0  \n",
       "729  1796            0              1              0              0  \n",
       "730  2729            0              1              0              0  \n",
       "\n",
       "[731 rows x 12 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Loading Data\n",
    "\n",
    "import pandas as pd\n",
    "\n",
    "bike_sharing_data = pd.read_csv('bike_sharing_data.csv')\n",
    "\n",
    "bike_sharing_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "28ac43bb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Training Model\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score, explained_variance_score\n",
    "from sklearn.linear_model import PoissonRegressor\n",
    "\n",
    "features = bike_sharing_data.drop(columns=['cnt'])\n",
    "target  = bike_sharing_data['cnt']\n",
    "\n",
    "features_train, features_test, target_train, target_test = train_test_split(features, target, test_size=0.2, random_state=42)\n",
    "\n",
    "poisson_regressor = PoissonRegressor(max_iter=1000)\n",
    "\n",
    "poisson_regressor.fit(features, target)\n",
    "\n",
    "predictions = poisson_regressor.predict(features)\n",
    "\n",
    "mse = mean_squared_error(target, predictions)\n",
    "rmse = np.sqrt(mse)\n",
    "mae = mean_absolute_error(target, predictions)\n",
    "r2 = r2_score(target, predictions)\n",
    "explained_variance = explained_variance_score(target, predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "641e811c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Squared Error (MSE): 1852055.4621398125\n",
      "Root Mean Squared Error (RMSE): 1360.9024440200747\n",
      "Mean Absolute Error (MAE): 1153.1959722820134\n",
      "R-squared (R2): 0.5058094351492075\n",
      "Explained Variance Score: 0.5058094351492861\n"
     ]
    }
   ],
   "source": [
    "# Printing Stats\n",
    "\n",
    "print(f\"Mean Squared Error (MSE): {mse}\")\n",
    "print(f\"Root Mean Squared Error (RMSE): {rmse}\")\n",
    "print(f\"Mean Absolute Error (MAE): {mae}\")\n",
    "print(f\"R-squared (R2): {r2}\")\n",
    "print(f\"Explained Variance Score: {explained_variance}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "809c5062",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Printing Feature contribution in prediction\n",
    "\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "features_list = features.columns.tolist()\n",
    "coefficients = poisson_regressor.coef_\n",
    "\n",
    "feature_importance_df = pd.DataFrame({\n",
    "    'Feature': features_list,\n",
    "    'Coefficient': coefficients\n",
    "})\n",
    "\n",
    "feature_importance_df['Importance'] = feature_importance_df['Coefficient'].abs()\n",
    "feature_importance_df = feature_importance_df.sort_values(by='Importance', ascending=False)\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.barplot(x='Importance', y='Feature', data=feature_importance_df.head(10))\n",
    "plt.title('Top 10 Important Features from Poisson Regression')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "264ad181",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Saving Trained Model\n",
    "import pickle\n",
    "\n",
    "with open('./models/poissons_model_regression.pkl', 'wb') as file:\n",
    "    pickle.dump(poisson_regressor, file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "376faaa3",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}