1_2_RS_Decision_Tree+Random_Forest.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "collapsed_sections": [
        "2pzy3-Oips4B"
      ],
      "authorship_tag": "ABX9TyNNpe4l2hlRRHngW+fCk6/j",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/pvanand07/Retail-Sales-Prediction-Regression/blob/master/1_2_RS_Decision_Tree%2BRandom_Forest.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 1. Import Dataset"
      ],
      "metadata": {
        "id": "FpWjfLoRpBHw"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "3e6_Lk-MowYI"
      },
      "outputs": [],
      "source": [
        "# Import Libraries\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore')\n",
        "from sklearn.metrics import accuracy_score, auc\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from sklearn import tree"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8h7e1ScYpNUN",
        "outputId": "3a0ef303-d06a-4a4a-bc22-e01740150144"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def Load_Dataset():\n",
        "  df = pd.read_csv('/content/drive/MyDrive/Almabetter/Almabetter Projects/Data & Resources/Rossmann Stores Data.csv')\n",
        "  df2 = pd.read_csv('/content/drive/MyDrive/Almabetter/Almabetter Projects/Data & Resources/store.csv')\n",
        "  return df,df2\n",
        "def merge_data(df,df2):\n",
        "  df.set_index('Store', inplace=True)\n",
        "  df2.set_index('Store', inplace=True)\n",
        "  df_m = df.join(df2, on='Store')\n",
        "  return df_m\n",
        "df,df2 = Load_Dataset()\n",
        "df_m = merge_data(df,df2)"
      ],
      "metadata": {
        "id": "muvrRAKapSah"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 2. Data Cleaning"
      ],
      "metadata": {
        "id": "kJ0vC4WHqG43"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Selecting only the rows with Open = 1\n",
        "df_m2 = df_m[df_m['Open'] == 1].drop('Open', axis=1).copy()\n",
        "\n",
        "# Converting Date to Datetime for analysis and feature engineering\n",
        "df_m2['Date'] = pd.to_datetime(df_m2['Date'])\n",
        "\n",
        "# We can also convert object Dtype to category for reduced memory usage\n",
        "for col in df_m2.select_dtypes('object').columns:\n",
        "  df_m2[col] = df_m2[col].astype('category')\n",
        "\n",
        "# Replace all variations of \"0\" with a single representation\n",
        "df_m2['StateHoliday'] = df_m2['StateHoliday'].replace(['0', 0], '0')"
      ],
      "metadata": {
        "id": "Eb1uRYUqqItX"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 3. Data Preprocessing"
      ],
      "metadata": {
        "id": "2pzy3-Oips4B"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Data pre-processing\n",
        "def cap_outliers(df):\n",
        "    # Create a copy of the DataFrame to avoid modifying the original data\n",
        "    cleaned_df = df.copy()\n",
        "\n",
        "    # Iterate over numerical columns\n",
        "    for column in cleaned_df.select_dtypes(include=np.number):\n",
        "        # Calculate the 99th percentile value\n",
        "        cap_value = cleaned_df[column].quantile(0.95)\n",
        "\n",
        "        # Cap outliers to the 99th percentile value\n",
        "        cleaned_df[column] = np.where(cleaned_df[column] > cap_value, cap_value, cleaned_df[column])\n",
        "\n",
        "    return cleaned_df\n",
        "\n",
        "def pre_processing2(df_m):\n",
        "\n",
        "  target_col = 'Sales'\n",
        "  df_c = df_m.drop_duplicates().copy()\n",
        "  df_c = df_c.dropna()#.sample(n = 5000, random_state = 42)\n",
        "  #df_c = df_c.sample(n = 5000, random_state = 42)\n",
        "\n",
        "  # Generate  week_number, month and year columns from datetime\n",
        "  df_c['week_number'] = (df_c['Date']).dt.week\n",
        "  df_c['month'] = (df_c['Date']).dt.month\n",
        "  df_c['year'] = (df_c['Date']).dt.year\n",
        "  df_c.drop(['Date'], axis=1, inplace=True)#,'Customers'\n",
        "\n",
        "  df_c = cap_outliers(df_c)\n",
        "\n",
        "\n",
        "  # Separate features and target\n",
        "  X = df_c.drop(target_col, axis=1)\n",
        "  y = df_c[target_col]\n",
        "\n",
        "  # Perform one-hot encoding for categorical features\n",
        "  categorical_features = X.select_dtypes(include='category').columns.tolist()\n",
        "  X_encoded = pd.get_dummies(X, columns=categorical_features)\n",
        "\n",
        "\n",
        "  return X_encoded,y"
      ],
      "metadata": {
        "id": "qWBX30qTprUg"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X,y= pre_processing2(df_m2)\n",
        "X.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 394
        },
        "id": "GFUHF3esp-iE",
        "outputId": "bc92700e-de2c-45a1-f5b6-5383e6ef02fd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "           DayOfWeek      Customers          Promo  SchoolHoliday  \\\n",
              "count  267812.000000  267812.000000  267812.000000  267812.000000   \n",
              "mean        3.509156     658.462825       0.446799       0.190193   \n",
              "std         1.713761     246.013467       0.497162       0.392454   \n",
              "min         1.000000       0.000000       0.000000       0.000000   \n",
              "25%         2.000000     479.000000       0.000000       0.000000   \n",
              "50%         3.000000     614.000000       0.000000       0.000000   \n",
              "75%         5.000000     799.000000       1.000000       0.000000   \n",
              "max         6.000000    1211.000000       1.000000       1.000000   \n",
              "\n",
              "       CompetitionDistance  CompetitionOpenSinceMonth  \\\n",
              "count        267812.000000              267812.000000   \n",
              "mean           4155.145102                   7.188464   \n",
              "std            4840.393380                   3.249393   \n",
              "min              40.000000                   1.000000   \n",
              "25%             600.000000                   4.000000   \n",
              "50%            2230.000000                   7.000000   \n",
              "75%            5630.000000                  10.000000   \n",
              "max           17110.000000                  12.000000   \n",
              "\n",
              "       CompetitionOpenSinceYear    Promo2  Promo2SinceWeek  Promo2SinceYear  \\\n",
              "count             267812.000000  267812.0    267812.000000    267812.000000   \n",
              "mean                2008.169630       1.0        21.860779      2011.832244   \n",
              "std                    7.384723       0.0        13.129778         1.637826   \n",
              "min                 1900.000000       1.0         1.000000      2009.000000   \n",
              "25%                 2005.000000       1.0        13.000000      2011.000000   \n",
              "50%                 2009.000000       1.0        18.000000      2012.000000   \n",
              "75%                 2012.000000       1.0        37.000000      2013.000000   \n",
              "max                 2014.000000       1.0        40.000000      2014.000000   \n",
              "\n",
              "       ...    StoreType_a  StoreType_b    StoreType_c    StoreType_d  \\\n",
              "count  ...  267812.000000     267812.0  267812.000000  267812.000000   \n",
              "mean   ...       0.549173          0.0       0.130879       0.319948   \n",
              "std    ...       0.497577          0.0       0.337269       0.466457   \n",
              "min    ...       0.000000          0.0       0.000000       0.000000   \n",
              "25%    ...       0.000000          0.0       0.000000       0.000000   \n",
              "50%    ...       1.000000          0.0       0.000000       0.000000   \n",
              "75%    ...       1.000000          0.0       0.000000       1.000000   \n",
              "max    ...       1.000000          0.0       1.000000       1.000000   \n",
              "\n",
              "        Assortment_a  Assortment_b   Assortment_c  \\\n",
              "count  267812.000000      267812.0  267812.000000   \n",
              "mean        0.582431           0.0       0.417569   \n",
              "std         0.493159           0.0       0.493159   \n",
              "min         0.000000           0.0       0.000000   \n",
              "25%         0.000000           0.0       0.000000   \n",
              "50%         1.000000           0.0       0.000000   \n",
              "75%         1.000000           0.0       1.000000   \n",
              "max         1.000000           0.0       1.000000   \n",
              "\n",
              "       PromoInterval_Feb,May,Aug,Nov  PromoInterval_Jan,Apr,Jul,Oct  \\\n",
              "count                  267812.000000                  267812.000000   \n",
              "mean                        0.217414                       0.609256   \n",
              "std                         0.412487                       0.487918   \n",
              "min                         0.000000                       0.000000   \n",
              "25%                         0.000000                       0.000000   \n",
              "50%                         0.000000                       1.000000   \n",
              "75%                         0.000000                       1.000000   \n",
              "max                         1.000000                       1.000000   \n",
              "\n",
              "       PromoInterval_Mar,Jun,Sept,Dec  \n",
              "count                   267812.000000  \n",
              "mean                         0.173331  \n",
              "std                          0.378533  \n",
              "min                          0.000000  \n",
              "25%                          0.000000  \n",
              "50%                          0.000000  \n",
              "75%                          0.000000  \n",
              "max                          1.000000  \n",
              "\n",
              "[8 rows x 27 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-fc6e0c78-abfb-4b8f-be37-fae6b00a6807\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>DayOfWeek</th>\n",
              "      <th>Customers</th>\n",
              "      <th>Promo</th>\n",
              "      <th>SchoolHoliday</th>\n",
              "      <th>CompetitionDistance</th>\n",
              "      <th>CompetitionOpenSinceMonth</th>\n",
              "      <th>CompetitionOpenSinceYear</th>\n",
              "      <th>Promo2</th>\n",
              "      <th>Promo2SinceWeek</th>\n",
              "      <th>Promo2SinceYear</th>\n",
              "      <th>...</th>\n",
              "      <th>StoreType_a</th>\n",
              "      <th>StoreType_b</th>\n",
              "      <th>StoreType_c</th>\n",
              "      <th>StoreType_d</th>\n",
              "      <th>Assortment_a</th>\n",
              "      <th>Assortment_b</th>\n",
              "      <th>Assortment_c</th>\n",
              "      <th>PromoInterval_Feb,May,Aug,Nov</th>\n",
              "      <th>PromoInterval_Jan,Apr,Jul,Oct</th>\n",
              "      <th>PromoInterval_Mar,Jun,Sept,Dec</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.0</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.0</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.0</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "      <td>267812.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>3.509156</td>\n",
              "      <td>658.462825</td>\n",
              "      <td>0.446799</td>\n",
              "      <td>0.190193</td>\n",
              "      <td>4155.145102</td>\n",
              "      <td>7.188464</td>\n",
              "      <td>2008.169630</td>\n",
              "      <td>1.0</td>\n",
              "      <td>21.860779</td>\n",
              "      <td>2011.832244</td>\n",
              "      <td>...</td>\n",
              "      <td>0.549173</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.130879</td>\n",
              "      <td>0.319948</td>\n",
              "      <td>0.582431</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.417569</td>\n",
              "      <td>0.217414</td>\n",
              "      <td>0.609256</td>\n",
              "      <td>0.173331</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>1.713761</td>\n",
              "      <td>246.013467</td>\n",
              "      <td>0.497162</td>\n",
              "      <td>0.392454</td>\n",
              "      <td>4840.393380</td>\n",
              "      <td>3.249393</td>\n",
              "      <td>7.384723</td>\n",
              "      <td>0.0</td>\n",
              "      <td>13.129778</td>\n",
              "      <td>1.637826</td>\n",
              "      <td>...</td>\n",
              "      <td>0.497577</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.337269</td>\n",
              "      <td>0.466457</td>\n",
              "      <td>0.493159</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.493159</td>\n",
              "      <td>0.412487</td>\n",
              "      <td>0.487918</td>\n",
              "      <td>0.378533</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>40.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1900.000000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>2009.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>2.000000</td>\n",
              "      <td>479.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>600.000000</td>\n",
              "      <td>4.000000</td>\n",
              "      <td>2005.000000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>13.000000</td>\n",
              "      <td>2011.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>3.000000</td>\n",
              "      <td>614.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>2230.000000</td>\n",
              "      <td>7.000000</td>\n",
              "      <td>2009.000000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>18.000000</td>\n",
              "      <td>2012.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>5.000000</td>\n",
              "      <td>799.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>5630.000000</td>\n",
              "      <td>10.000000</td>\n",
              "      <td>2012.000000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>37.000000</td>\n",
              "      <td>2013.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>6.000000</td>\n",
              "      <td>1211.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>17110.000000</td>\n",
              "      <td>12.000000</td>\n",
              "      <td>2014.000000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>40.000000</td>\n",
              "      <td>2014.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>8 rows × 27 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-fc6e0c78-abfb-4b8f-be37-fae6b00a6807')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-fc6e0c78-abfb-4b8f-be37-fae6b00a6807 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-fc6e0c78-abfb-4b8f-be37-fae6b00a6807');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Stats Model Results"
      ],
      "metadata": {
        "id": "1--1lmkbQqyH"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Model 2: Decision Tree(sklearn)"
      ],
      "metadata": {
        "id": "TTz0AJcVtlfe"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df_m2.columns"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8VHxcL_42Sga",
        "outputId": "aa78841f-3d2f-4389-9696-c4e4d0071818"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['DayOfWeek', 'Date', 'Sales', 'Customers', 'Promo', 'StateHoliday',\n",
              "       'SchoolHoliday', 'StoreType', 'Assortment', 'CompetitionDistance',\n",
              "       'CompetitionOpenSinceMonth', 'CompetitionOpenSinceYear', 'Promo2',\n",
              "       'Promo2SinceWeek', 'Promo2SinceYear', 'PromoInterval'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import statsmodels.api as sm\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from sklearn.linear_model import LinearRegression\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.tree import DecisionTreeRegressor\n",
        "from sklearn.ensemble import RandomForestRegressor\n",
        "\n",
        "# Assuming `pre_processing2` returns X_train, X_test, y_train, y_test\n",
        "X,y = pre_processing2((df_m2))#.drop(['Customers'], axis=1)))#.drop(['Promo2','Promo2SinceYear'], axis=1))\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
        "\n",
        "# Create the scaler and fit/transform X_train and X_test\n",
        "\n",
        "scaler = MinMaxScaler()\n",
        "X_train_s = pd.DataFrame(scaler.fit_transform(X_train), columns=X_train.columns, index=X_train.index)\n",
        "X_test_s = pd.DataFrame(scaler.transform(X_test), columns=X_test.columns, index=X_test.index)\n",
        "\n",
        "# Apply square root transformation to y_train and y_test\n",
        "y_train_s = np.sqrt(y_train)\n",
        "y_test_s = np.sqrt(y_test)\n",
        "\n",
        "stats = {}\n",
        "\n",
        "# Perform regression analysis\n",
        "X = X_train_s\n",
        "y = y_train_s\n",
        "#regressor = DecisionTreeRegressor(criterion='friedman_mse', max_leaf_nodes=15, random_state=0)\n",
        "regressor = RandomForestRegressor(n_estimators=100, random_state=0)\n",
        "regressor.fit(X, y)\n",
        "y_pred = regressor.predict(X_test_s)"
      ],
      "metadata": {
        "id": "TiQ2Ld-ptrEO"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(regressor.score(X, y))\n",
        "print(regressor.score(X_test_s, y_test_s))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PeQD7z4BYCag",
        "outputId": "2b0c7fa7-b618-4f17-85d8-8b0b72ee4e89"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.9960095559974053\n",
            "0.9720660671115722\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "regressor.feature_importances_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cBAZFJCAWOEG",
        "outputId": "46455319-d303-4d9d-afa1-68e96a4d0291"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([9.98888255e-03, 7.28273992e-01, 4.88970036e-02, 1.22920439e-03,\n",
              "       5.45501868e-02, 1.56811845e-02, 1.97402908e-02, 0.00000000e+00,\n",
              "       1.94134862e-02, 1.15755409e-02, 7.13597041e-03, 4.00508396e-03,\n",
              "       4.37091361e-03, 2.03884285e-05, 1.41005698e-05, 1.76176336e-07,\n",
              "       9.89075686e-08, 1.07900716e-03, 0.00000000e+00, 1.50719025e-03,\n",
              "       5.73026706e-02, 4.48121154e-03, 0.00000000e+00, 4.56122044e-03,\n",
              "       2.39116717e-03, 2.62123167e-03, 1.15979773e-03])"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pd.DataFrame(regressor.feature_importances_, X_train.columns, columns=['Coefficient']).sort_values('Coefficient', ascending=False)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 896
        },
        "id": "mxsUOcz_YLTj",
        "outputId": "57499eef-eb21-4824-d5ac-4403d7bab8a8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                 Coefficient\n",
              "Customers                       7.282740e-01\n",
              "StoreType_d                     5.730267e-02\n",
              "CompetitionDistance             5.455019e-02\n",
              "Promo                           4.889700e-02\n",
              "CompetitionOpenSinceYear        1.974029e-02\n",
              "Promo2SinceWeek                 1.941349e-02\n",
              "CompetitionOpenSinceMonth       1.568118e-02\n",
              "Promo2SinceYear                 1.157554e-02\n",
              "DayOfWeek                       9.988883e-03\n",
              "week_number                     7.135970e-03\n",
              "Assortment_c                    4.561220e-03\n",
              "Assortment_a                    4.481212e-03\n",
              "year                            4.370914e-03\n",
              "month                           4.005084e-03\n",
              "PromoInterval_Jan,Apr,Jul,Oct   2.621232e-03\n",
              "PromoInterval_Feb,May,Aug,Nov   2.391167e-03\n",
              "StoreType_c                     1.507190e-03\n",
              "SchoolHoliday                   1.229204e-03\n",
              "PromoInterval_Mar,Jun,Sept,Dec  1.159798e-03\n",
              "StoreType_a                     1.079007e-03\n",
              "StateHoliday_0                  2.038843e-05\n",
              "StateHoliday_a                  1.410057e-05\n",
              "StateHoliday_b                  1.761763e-07\n",
              "StateHoliday_c                  9.890757e-08\n",
              "StoreType_b                     0.000000e+00\n",
              "Assortment_b                    0.000000e+00\n",
              "Promo2                          0.000000e+00"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-62ca7ce4-c573-43b0-bda6-6907820e3daf\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Coefficient</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Customers</th>\n",
              "      <td>7.282740e-01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StoreType_d</th>\n",
              "      <td>5.730267e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>CompetitionDistance</th>\n",
              "      <td>5.455019e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Promo</th>\n",
              "      <td>4.889700e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>CompetitionOpenSinceYear</th>\n",
              "      <td>1.974029e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Promo2SinceWeek</th>\n",
              "      <td>1.941349e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>CompetitionOpenSinceMonth</th>\n",
              "      <td>1.568118e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Promo2SinceYear</th>\n",
              "      <td>1.157554e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>DayOfWeek</th>\n",
              "      <td>9.988883e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>week_number</th>\n",
              "      <td>7.135970e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Assortment_c</th>\n",
              "      <td>4.561220e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Assortment_a</th>\n",
              "      <td>4.481212e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>year</th>\n",
              "      <td>4.370914e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>month</th>\n",
              "      <td>4.005084e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PromoInterval_Jan,Apr,Jul,Oct</th>\n",
              "      <td>2.621232e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PromoInterval_Feb,May,Aug,Nov</th>\n",
              "      <td>2.391167e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StoreType_c</th>\n",
              "      <td>1.507190e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>SchoolHoliday</th>\n",
              "      <td>1.229204e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PromoInterval_Mar,Jun,Sept,Dec</th>\n",
              "      <td>1.159798e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StoreType_a</th>\n",
              "      <td>1.079007e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StateHoliday_0</th>\n",
              "      <td>2.038843e-05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StateHoliday_a</th>\n",
              "      <td>1.410057e-05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StateHoliday_b</th>\n",
              "      <td>1.761763e-07</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StateHoliday_c</th>\n",
              "      <td>9.890757e-08</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StoreType_b</th>\n",
              "      <td>0.000000e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Assortment_b</th>\n",
              "      <td>0.000000e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Promo2</th>\n",
              "      <td>0.000000e+00</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-62ca7ce4-c573-43b0-bda6-6907820e3daf')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-62ca7ce4-c573-43b0-bda6-6907820e3daf button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-62ca7ce4-c573-43b0-bda6-6907820e3daf');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pd.DataFrame(y_pred).describe()\n",
        "pd.DataFrame(y_test_s).describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        },
        "id": "GZXfZl3EWvJU",
        "outputId": "c6818518-b0cd-4dda-acb6-98f0dfd78e26"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "              Sales\n",
              "count  53563.000000\n",
              "mean      78.709717\n",
              "std       14.957155\n",
              "min        0.000000\n",
              "25%       68.102863\n",
              "50%       77.942286\n",
              "75%       88.932559\n",
              "max      107.459062"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-ed45abe2-bb03-48b3-b5d1-af64279b8c35\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Sales</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>53563.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>78.709717</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>14.957155</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>68.102863</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>77.942286</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>88.932559</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>107.459062</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ed45abe2-bb03-48b3-b5d1-af64279b8c35')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-ed45abe2-bb03-48b3-b5d1-af64279b8c35 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-ed45abe2-bb03-48b3-b5d1-af64279b8c35');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.scatter(y_pred,y_test_s)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 448
        },
        "id": "EPgxCC2iP6Zw",
        "outputId": "67601d51-f9d2-48b8-e857-2fb5d86a3aa4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.collections.PathCollection at 0x7f3fee4679a0>"
            ]
          },
          "metadata": {},
          "execution_count": 20
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "### Heteroscadacity\n",
        "plt.scatter(y_pred,y_test_s-y_pred)\n",
        "plt.xlabel('Predicted sales')\n",
        "plt.ylabel('residuals')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 467
        },
        "id": "w4h0tae7QAEu",
        "outputId": "434f2273-a007-40d5-dcc6-ded8f6903c47"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0, 0.5, 'residuals')"
            ]
          },
          "metadata": {},
          "execution_count": 21
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "nstMNBx7SYRL"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 3. Feature Selection and Engineering"
      ],
      "metadata": {
        "id": "lO-5WADiSQvz"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from statsmodels.stats.outliers_influence import variance_inflation_factor as vif\n",
        "\n",
        "def calculate_vif(df):\n",
        "    # Select numerical columns\n",
        "    numerical_columns = df.select_dtypes(include=['float64', 'int64'])\n",
        "\n",
        "    # Replace infinite values with NaN\n",
        "    numerical_columns.replace([np.inf, -np.inf], np.nan, inplace=True)\n",
        "\n",
        "    # Drop rows with NaN values\n",
        "    numerical_columns.dropna(inplace=True)\n",
        "\n",
        "    # Remove duplicates\n",
        "    numerical_columns = numerical_columns.loc[:,~numerical_columns.columns.duplicated()]\n",
        "\n",
        "    # Create a DataFrame to store VIF results\n",
        "    vif_data = pd.DataFrame()\n",
        "    vif_data['Variable'] = numerical_columns.columns\n",
        "    vif_data['VIF'] = [vif(numerical_columns.values, i) for i in range(numerical_columns.shape[1])]\n",
        "\n",
        "    return vif_data.sort_values(by='VIF', ascending=False)\n",
        "\n",
        "calculate_vif(df_m2.drop(['Sales'], axis=1))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 363
        },
        "id": "MGrI_tdJSPj7",
        "outputId": "ff452269-4cac-4bdb-b71e-ce34fdb6dcb6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                    Variable           VIF\n",
              "7                     Promo2  1.573677e+06\n",
              "2                      Promo  1.153423e+00\n",
              "1                  Customers  1.119583e+00\n",
              "0                  DayOfWeek  1.117165e+00\n",
              "4        CompetitionDistance  1.059632e+00\n",
              "9            Promo2SinceYear  1.037353e+00\n",
              "3              SchoolHoliday  1.020993e+00\n",
              "8            Promo2SinceWeek  1.019017e+00\n",
              "6   CompetitionOpenSinceYear  1.010080e+00\n",
              "5  CompetitionOpenSinceMonth  1.009137e+00"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d47cca1b-c218-4f2a-87eb-b21208d28e9a\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Variable</th>\n",
              "      <th>VIF</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>Promo2</td>\n",
              "      <td>1.573677e+06</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Promo</td>\n",
              "      <td>1.153423e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Customers</td>\n",
              "      <td>1.119583e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>DayOfWeek</td>\n",
              "      <td>1.117165e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CompetitionDistance</td>\n",
              "      <td>1.059632e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>Promo2SinceYear</td>\n",
              "      <td>1.037353e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>SchoolHoliday</td>\n",
              "      <td>1.020993e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>Promo2SinceWeek</td>\n",
              "      <td>1.019017e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>CompetitionOpenSinceYear</td>\n",
              "      <td>1.010080e+00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>CompetitionOpenSinceMonth</td>\n",
              "      <td>1.009137e+00</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d47cca1b-c218-4f2a-87eb-b21208d28e9a')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-d47cca1b-c218-4f2a-87eb-b21208d28e9a button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-d47cca1b-c218-4f2a-87eb-b21208d28e9a');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 144
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "calculate_vif((df_m2).drop(['Promo2','Promo2SinceYear','Sales','CompetitionOpenSinceYear'], axis=1))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 269
        },
        "id": "Q5U9pd_RT1mS",
        "outputId": "cbdfe74c-6bf4-46dc-8835-13dedafcc949"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                    Variable       VIF\n",
              "1                  Customers  5.140540\n",
              "5  CompetitionOpenSinceMonth  4.461682\n",
              "0                  DayOfWeek  4.066374\n",
              "6            Promo2SinceWeek  3.218630\n",
              "2                      Promo  2.017833\n",
              "4        CompetitionDistance  1.600253\n",
              "3              SchoolHoliday  1.230049"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-25b342df-2e4b-4c71-b8c5-5c789f44a74f\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Variable</th>\n",
              "      <th>VIF</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Customers</td>\n",
              "      <td>5.140540</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>CompetitionOpenSinceMonth</td>\n",
              "      <td>4.461682</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>DayOfWeek</td>\n",
              "      <td>4.066374</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>Promo2SinceWeek</td>\n",
              "      <td>3.218630</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Promo</td>\n",
              "      <td>2.017833</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CompetitionDistance</td>\n",
              "      <td>1.600253</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>SchoolHoliday</td>\n",
              "      <td>1.230049</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-25b342df-2e4b-4c71-b8c5-5c789f44a74f')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-25b342df-2e4b-4c71-b8c5-5c789f44a74f button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-25b342df-2e4b-4c71-b8c5-5c789f44a74f');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 146
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!unzip /content/test.csv.zip"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dkKI0rdhf3kK",
        "outputId": "54a3379a-609a-4638-d560-31c83a3f3fc5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Archive:  /content/test.csv.zip\n",
            "  inflating: test.csv                \n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "Ia9RcneggM_b"
      }
    }
  ]
}