Linear regression model.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rLAVbovG8m4u"
      },
      "source": [
        "# **Importing required libraries**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "id": "yCg79xud-jHy"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.pipeline import Pipeline\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score\n",
        "from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor\n",
        "from xgboost import XGBRegressor\n",
        "from sklearn.linear_model import LinearRegression, Lasso, Ridge\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "from sklearn.compose import ColumnTransformer\n",
        "import pickle"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Loading & Splitting the data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 132
        },
        "id": "u7G9ieGO8mYv",
        "outputId": "7abb8860-f967-42ee-ff42-30c81e3948fb"
      },
      "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>latitude</th>\n",
              "      <th>longitude</th>\n",
              "      <th>year</th>\n",
              "      <th>season_categorical</th>\n",
              "      <th>pricetype_binary</th>\n",
              "      <th>month_categorical</th>\n",
              "      <th>commodities_categorical</th>\n",
              "      <th>adjusted_price</th>\n",
              "      <th>month_sin</th>\n",
              "      <th>month_cos</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>64216</th>\n",
              "      <td>13.062665</td>\n",
              "      <td>11.171371</td>\n",
              "      <td>2023</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>6</td>\n",
              "      <td>31</td>\n",
              "      <td>224.488083</td>\n",
              "      <td>1.220000e-16</td>\n",
              "      <td>-1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>64217</th>\n",
              "      <td>13.062665</td>\n",
              "      <td>11.171371</td>\n",
              "      <td>2023</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>6</td>\n",
              "      <td>35</td>\n",
              "      <td>203.507889</td>\n",
              "      <td>1.220000e-16</td>\n",
              "      <td>-1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>64218</th>\n",
              "      <td>13.062665</td>\n",
              "      <td>11.171371</td>\n",
              "      <td>2023</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>6</td>\n",
              "      <td>36</td>\n",
              "      <td>139.866566</td>\n",
              "      <td>1.220000e-16</td>\n",
              "      <td>-1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>64219</th>\n",
              "      <td>13.062665</td>\n",
              "      <td>11.171371</td>\n",
              "      <td>2023</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>6</td>\n",
              "      <td>39</td>\n",
              "      <td>15.105740</td>\n",
              "      <td>1.220000e-16</td>\n",
              "      <td>-1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>64220</th>\n",
              "      <td>13.062665</td>\n",
              "      <td>11.171371</td>\n",
              "      <td>2023</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>6</td>\n",
              "      <td>37</td>\n",
              "      <td>9.431097</td>\n",
              "      <td>1.220000e-16</td>\n",
              "      <td>-1.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "        latitude  longitude  year  season_categorical  pricetype_binary  \\\n",
              "64216  13.062665  11.171371  2023                   2                 1   \n",
              "64217  13.062665  11.171371  2023                   2                 1   \n",
              "64218  13.062665  11.171371  2023                   2                 1   \n",
              "64219  13.062665  11.171371  2023                   2                 1   \n",
              "64220  13.062665  11.171371  2023                   2                 1   \n",
              "\n",
              "       month_categorical  commodities_categorical  adjusted_price  \\\n",
              "64216                  6                       31      224.488083   \n",
              "64217                  6                       35      203.507889   \n",
              "64218                  6                       36      139.866566   \n",
              "64219                  6                       39       15.105740   \n",
              "64220                  6                       37        9.431097   \n",
              "\n",
              "          month_sin  month_cos  \n",
              "64216  1.220000e-16       -1.0  \n",
              "64217  1.220000e-16       -1.0  \n",
              "64218  1.220000e-16       -1.0  \n",
              "64219  1.220000e-16       -1.0  \n",
              "64220  1.220000e-16       -1.0  "
            ]
          },
          "execution_count": 4,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df = pd.read_csv('train.csv')\n",
        "df.tail()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "id": "tubE7trC9LFd"
      },
      "outputs": [],
      "source": [
        "# Split data into features and target\n",
        "X = df.drop(columns=['adjusted_price'])\n",
        "y = df['adjusted_price']\n",
        "\n",
        "# Split the data into a training set and a test set (e.g., 80% training, 30% testing)\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42, shuffle=True)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Modeling- **RandomForestRegressor**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1OunYi23BtIV",
        "outputId": "8ff7cf63-cb2c-4b40-e2b2-341050878470"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Fitting 5 folds for each of 9 candidates, totalling 45 fits\n",
            "Best Parameters: {'regressor__max_depth': None, 'regressor__n_estimators': 100}\n"
          ]
        }
      ],
      "source": [
        "#Getting all the columns\n",
        "num_features = list(X.columns)\n",
        "numeric_features = num_features\n",
        "\n",
        "# Create a column transformer to apply standardization to numeric features\n",
        "numeric_transformer = StandardScaler()\n",
        "\n",
        "# Combine transformers using the column transformer\n",
        "preprocessor = ColumnTransformer(\n",
        "    transformers=[\n",
        "        ('num', numeric_transformer, numeric_features)\n",
        "    ])\n",
        "\n",
        "# Define the hyperparameters and their possible values\n",
        "param_grid = {\n",
        "    'regressor__n_estimators': [50, 75, 100],  # Number of trees in the forest\n",
        "    'regressor__max_depth': [None, 6, 13],  # Maximum depth of the trees\n",
        "}\n",
        "# Pipeline to automate the preprocessing\n",
        "pipeline = Pipeline(steps=[\n",
        "    ('preprocessor', preprocessor),\n",
        "    ('regressor', RandomForestRegressor(random_state=42))\n",
        "])\n",
        "\n",
        "# Initialize the GridSearchCV\n",
        "grid_search = GridSearchCV(pipeline, param_grid, cv=5, scoring='neg_mean_squared_error', verbose=1)\n",
        "\n",
        "# Fit the grid search to the data\n",
        "grid_search.fit(X_train, y_train)\n",
        "\n",
        "# Get the best parameters and best estimator from the grid search\n",
        "best_params = grid_search.best_params_\n",
        "best_estimator = grid_search.best_estimator_\n",
        "\n",
        "# View the best parameters\n",
        "print(f'Best Parameters: {best_params}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Evaluation Metrics"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2X6DdxvWFNtw",
        "outputId": "d078a250-ff30-4a93-d6c0-a4c651391aed"
      },
      "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>Metric</th>\n",
              "      <th>Train</th>\n",
              "      <th>Test</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>MAE</td>\n",
              "      <td>34.628450</td>\n",
              "      <td>48.793197</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>MSE</td>\n",
              "      <td>199874.204113</td>\n",
              "      <td>297699.529986</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>RMSE</td>\n",
              "      <td>447.072929</td>\n",
              "      <td>545.618484</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>R2 Score</td>\n",
              "      <td>0.987746</td>\n",
              "      <td>0.985586</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "     Metric          Train           Test\n",
              "0       MAE      34.628450      48.793197\n",
              "1       MSE  199874.204113  297699.529986\n",
              "2      RMSE     447.072929     545.618484\n",
              "3  R2 Score       0.987746       0.985586"
            ]
          },
          "execution_count": 6,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "y_pred = loaded_model.predict(X_test)\n",
        "y_pred_train = loaded_model.predict(X_train)\n",
        "\n",
        "# Calculate (MAE),(R2),(MSE) score for training data\n",
        "mae = mean_absolute_error(y_train, y_pred_train)\n",
        "mse = mean_squared_error(y_train, y_pred_train)\n",
        "rmse = np.sqrt(mean_squared_error(y_train, y_pred_train))\n",
        "r2 = r2_score(y_train, y_pred_train)\n",
        "\n",
        "# Calculate (MAE),(R2),(MSE) score for test data\n",
        "mae1 = mean_absolute_error(y_test, y_pred)\n",
        "mse1 = mean_squared_error(y_test, y_pred)\n",
        "rmse1 = np.sqrt(mean_squared_error(y_test, y_pred))\n",
        "r21 = r2_score(y_test, y_pred)\n",
        "\n",
        "# Create a dataframe for evaluation metrics\n",
        "metrics_data = {\n",
        "    'Metric': ['MAE', 'MSE', 'RMSE', 'R2 Score'],\n",
        "    'Train': [mae, mse, rmse, r2],\n",
        "    'Test': [mae1, mse1, rmse1, r21]\n",
        "}\n",
        "metrics_df = pd.DataFrame(metrics_data)\n",
        "# Print the dataframe\n",
        "metrics_df"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Visualizing & Testing the model with **KNOWN** & **UNKNOWN** data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {},
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1500x500 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Visualizing the predictions with known data\n",
        "plt.figure(figsize=(15, 5))\n",
        "plt.plot(y_test[0:10000].values, color='blue', label='Actual')\n",
        "plt.plot(y_pred[0:10000], color='red', label='Predicted')\n",
        "plt.title('RandomForestRegressor')\n",
        "plt.legend()\n",
        "plt.show();"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Saving the model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 23,
      "metadata": {},
      "outputs": [],
      "source": [
        "pickle.dump(best_estimator,open('model.pkl','wb'))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Testing with **UNKNOWN** dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Load the model\n",
        "with open('abhinash_model.pkl', 'rb') as file:\n",
        "    loaded_model = pickle.load(file)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 132
        },
        "id": "Trtz1f3fG77U",
        "outputId": "44b71f29-3948-4f8f-d7a7-f53a57f22103"
      },
      "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>latitude</th>\n",
              "      <th>longitude</th>\n",
              "      <th>year</th>\n",
              "      <th>season_categorical</th>\n",
              "      <th>pricetype_binary</th>\n",
              "      <th>month_categorical</th>\n",
              "      <th>commodities_categorical</th>\n",
              "      <th>month_sin</th>\n",
              "      <th>month_cos</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>12.362300</td>\n",
              "      <td>9.583600</td>\n",
              "      <td>2023</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>6</td>\n",
              "      <td>0.500000</td>\n",
              "      <td>8.660254e-01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>12.496693</td>\n",
              "      <td>11.499503</td>\n",
              "      <td>2023</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>23</td>\n",
              "      <td>0.866025</td>\n",
              "      <td>5.000000e-01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>11.285202</td>\n",
              "      <td>11.999501</td>\n",
              "      <td>2023</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>40</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>6.120000e-17</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>11.834551</td>\n",
              "      <td>13.152417</td>\n",
              "      <td>2023</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>4</td>\n",
              "      <td>32</td>\n",
              "      <td>0.866025</td>\n",
              "      <td>-5.000000e-01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>11.858182</td>\n",
              "      <td>13.154892</td>\n",
              "      <td>2023</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>5</td>\n",
              "      <td>31</td>\n",
              "      <td>0.500000</td>\n",
              "      <td>-8.660254e-01</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "    latitude  longitude  year  season_categorical  pricetype_binary  \\\n",
              "2  12.362300   9.583600  2023                   0                 0   \n",
              "3  12.496693  11.499503  2023                   0                 1   \n",
              "4  11.285202  11.999501  2023                   1                 1   \n",
              "5  11.834551  13.152417  2023                   1                 1   \n",
              "6  11.858182  13.154892  2023                   1                 1   \n",
              "\n",
              "   month_categorical  commodities_categorical  month_sin     month_cos  \n",
              "2                  1                        6   0.500000  8.660254e-01  \n",
              "3                  2                       23   0.866025  5.000000e-01  \n",
              "4                  3                       40   1.000000  6.120000e-17  \n",
              "5                  4                       32   0.866025 -5.000000e-01  \n",
              "6                  5                       31   0.500000 -8.660254e-01  "
            ]
          },
          "execution_count": 11,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Loading test.csv\n",
        "test_data = pd.read_csv(\"evaluate.csv\")\n",
        "data = test_data.drop(columns=['adjusted_price'])\n",
        "data.tail()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "metadata": {},
      "outputs": [
        {
          "data": {
            "text/plain": [
              "0      275.782714\n",
              "1    43753.664660\n",
              "2      188.821752\n",
              "3       15.944948\n",
              "4      275.260154\n",
              "5       22.378874\n",
              "6       16.784156\n",
              "Name: adjusted_price, dtype: float64"
            ]
          },
          "execution_count": 16,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "test_data['adjusted_price']"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 23,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7cEE3vDiRv61",
        "outputId": "d1183005-775a-4bb1-f37f-15962bd3443f"
      },
      "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>Actual Price</th>\n",
              "      <th>Predicted Price</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>275.782714</td>\n",
              "      <td>269.923459</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>43753.664660</td>\n",
              "      <td>37928.936156</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>188.821752</td>\n",
              "      <td>190.466626</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>15.944948</td>\n",
              "      <td>17.899251</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>275.260154</td>\n",
              "      <td>235.850957</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>22.378874</td>\n",
              "      <td>22.799474</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>16.784156</td>\n",
              "      <td>16.848555</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Actual Price  Predicted Price\n",
              "0    275.782714       269.923459\n",
              "1  43753.664660     37928.936156\n",
              "2    188.821752       190.466626\n",
              "3     15.944948        17.899251\n",
              "4    275.260154       235.850957\n",
              "5     22.378874        22.799474\n",
              "6     16.784156        16.848555"
            ]
          },
          "execution_count": 23,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "actual_data = test_data['adjusted_price']\n",
        "predicted_result = loaded_model.predict(data)\n",
        "\n",
        "outcome_data = {\n",
        "    'Actual Price': actual_data.values,  # Use .values to get the value from the pandas series\n",
        "    'Predicted Price': predicted_result.flatten()  # Use flatten to convert the result to a 1D array\n",
        "}\n",
        "\n",
        "outcome_df = pd.DataFrame(outcome_data)\n",
        "\n",
        "# Print the dataframe\n",
        "outcome_df"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "colab": {
      "gpuType": "T4",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.8.16"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}