Predicting_Food_Delivery_Time.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "name": "Predicting_Food_Delivery_Time.ipynb",
      "provenance": [],
      "collapsed_sections": [
        "dBV2JLd1ALQH",
        "UceqrG8LAFr_",
        "_YYJ_HI9A1qg",
        "pwjvNSkCBLC6",
        "Hjn_pdlpBD8w",
        "u1kumctM5Jf5",
        "SCbszxL0-NPg",
        "wRVErMt0HBFp",
        "tQXtDXaONwjx",
        "1R2AgdQg5OKR"
      ]
    },
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "YFpFT7cpAS4i"
      },
      "source": [
        "# Solving MachineHack's 'Predicting Food Delivery Time - Hackathon by IMS Proschool'\n",
        "\n",
        "---\n",
        "The entire world is transforming digitally and our relationship with technology has grown exponentially over the last few years. We have grown closer to technology, and it has made our life a lot easier by saving time and effort. Today everything is accessible with smartphones — from groceries to cooked food and from medicines to doctors. In this hackathon, we provide you with data that is a by-product as well as a thriving proof of this growing relationship. \n",
        "\n",
        "When was the last time you ordered food online? And how long did it take to reach you?\n",
        "\n",
        "In this hackathon, we are providing you with data from thousands of restaurants in India regarding the time they take to deliver food for online order. As data scientists, your goal is to predict the online order delivery time based on the given factors.\n",
        "\n",
        "Analytics India Magazine and IMS Proschool bring to you [‘Predicting Predicting Food Delivery Time Hackathon’](https://www.machinehack.com/course/predicting-food-delivery-time-hackathon-by-ims-proschool/).\n",
        "\n",
        "Size of training set: 11,094 records\n",
        "\n",
        "Size of test set: 2,774 records\n",
        "\n",
        "**FEATURES:**\n",
        "\n",
        "* Restaurant: A unique ID that represents a restaurant.\n",
        "* Location: The location of the restaurant.\n",
        "* Cuisines: The cuisines offered by the restaurant.\n",
        "* Average_Cost: The average cost for one person/order.\n",
        "* Minimum_Order: The minimum order amount.\n",
        "* Rating: Customer rating for the restaurant.\n",
        "* Votes: The total number of customer votes for the restaurant.\n",
        "* Reviews: The number of customer reviews for the restaurant.\n",
        "* Delivery_Time: The order delivery time of the restaurant. (Target Classes) \n",
        "\n",
        "About IMS Proschool\n",
        "\n",
        "IMS, since 1977, has worked towards building a long term successful career for its students. It emerged as the fourth most trusted education brands in an AC Nielsen and Brand Equity Survey. IMS Proschool is the extension of the same mission. Proschool helps individuals realize their potential by mentoring and imparting skills.\n",
        "\n",
        "**Link to the Hackathon [here](https://www.machinehack.com/course/predicting-food-delivery-time-hackathon-by-ims-proschool/).**\n",
        " "
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "S_jBYc1XPmJ3"
      },
      "source": [
        "##Mounting Google Drive "
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "pe6bXU0rQUqC"
      },
      "source": [
        "Mount your google drive to access files in the drive, here I have uploaded all the requires datasets in to my google drive, mounted it to colab by authorising access."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "dfsrnSdXiyjg",
        "outputId": "cc52eb64-a348-4df9-95f0-ec2e63ac4e88",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 125
        }
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount(\"/GD\")"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&response_type=code&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly\n",
            "\n",
            "Enter your authorization code:\n",
            "··········\n",
            "Mounted at /GD\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "dBV2JLd1ALQH"
      },
      "source": [
        "##Loading The Data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "lDkaeJm_j1R0",
        "colab": {}
      },
      "source": [
        "#Importing necessary libraries\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import re\n",
        "from tqdm import tqdm"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "iPqcGP9PQqnC"
      },
      "source": [
        "We will now load the datasets using pandas by mentioning the path to the files residing in the drive as given below."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "dqndqEBzjReJ",
        "colab": {}
      },
      "source": [
        "train = pd.read_excel(\"/GD/My Drive/Colab Notebooks/Food Delivery/Participants Data/Data_Train.xlsx\")\n",
        "test = pd.read_excel(\"/GD/My Drive/Colab Notebooks/Food Delivery/Participants Data/Data_Test.xlsx\")"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "UceqrG8LAFr_"
      },
      "source": [
        "##Dataset Features"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "5L36MM2DRJNz"
      },
      "source": [
        "Before proceeding any further,lets have a look at the dataset and its basic features.\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "kRIwn_yRAJVE"
      },
      "source": [
        "####Trainig Data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "PkH-VCvOj0Ai",
        "outputId": "759ff486-bc6c-43f3-94b2-c738db6da673",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "train.shape"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(11094, 9)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "Fi1vTZOjRT_2",
        "outputId": "23b8b728-444c-4a09-982d-2c4ce137cee6",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        }
      },
      "source": [
        "train.columns"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['Restaurant', 'Location', 'Cuisines', 'Average_Cost', 'Minimum_Order',\n",
              "       'Rating', 'Votes', 'Reviews', 'Delivery_Time'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "S-u0Y6aHlRmn",
        "outputId": "cd0756ed-35d5-4779-f98d-8019906e71d8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 212
        }
      },
      "source": [
        "train.head()"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "      <th>Delivery_Time</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>ID_6321</td>\n",
              "      <td>FTI College, Law College Road, Pune</td>\n",
              "      <td>Fast Food, Rolls, Burger, Salad, Wraps</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>12</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>ID_2882</td>\n",
              "      <td>Sector 3, Marathalli</td>\n",
              "      <td>Ice Cream, Desserts</td>\n",
              "      <td>₹100</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>11</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>ID_1595</td>\n",
              "      <td>Mumbai Central</td>\n",
              "      <td>Italian, Street Food, Fast Food</td>\n",
              "      <td>₹150</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.6</td>\n",
              "      <td>99</td>\n",
              "      <td>30</td>\n",
              "      <td>65 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ID_5929</td>\n",
              "      <td>Sector 1, Noida</td>\n",
              "      <td>Mughlai, North Indian, Chinese</td>\n",
              "      <td>₹250</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.7</td>\n",
              "      <td>176</td>\n",
              "      <td>95</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>ID_6123</td>\n",
              "      <td>Rmz Centennial, I Gate, Whitefield</td>\n",
              "      <td>Cafe, Beverages</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.2</td>\n",
              "      <td>521</td>\n",
              "      <td>235</td>\n",
              "      <td>65 minutes</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "  Restaurant                             Location  ... Reviews Delivery_Time\n",
              "0    ID_6321  FTI College, Law College Road, Pune  ...       4    30 minutes\n",
              "1    ID_2882                 Sector 3, Marathalli  ...       4    30 minutes\n",
              "2    ID_1595                       Mumbai Central  ...      30    65 minutes\n",
              "3    ID_5929                      Sector 1, Noida  ...      95    30 minutes\n",
              "4    ID_6123   Rmz Centennial, I Gate, Whitefield  ...     235    65 minutes\n",
              "\n",
              "[5 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "zg-AtOlZ_nRZ",
        "outputId": "ce38df63-b396-42dd-8326-3e76ef944e7a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 193
        }
      },
      "source": [
        "train.isnull().sum()"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Restaurant       0\n",
              "Location         0\n",
              "Cuisines         0\n",
              "Average_Cost     0\n",
              "Minimum_Order    0\n",
              "Rating           0\n",
              "Votes            0\n",
              "Reviews          0\n",
              "Delivery_Time    0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "MDc0ws0igEqr",
        "outputId": "5aa3fe3f-fcc0-47a6-f70d-f14a6fcf59d1",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 166
        }
      },
      "source": [
        "train.describe(include = 'all')"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "      <th>Delivery_Time</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>unique</th>\n",
              "      <td>7480</td>\n",
              "      <td>35</td>\n",
              "      <td>2179</td>\n",
              "      <td>26</td>\n",
              "      <td>18</td>\n",
              "      <td>33</td>\n",
              "      <td>1103</td>\n",
              "      <td>761</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>top</th>\n",
              "      <td>ID_7184</td>\n",
              "      <td>Mico Layout, Stage 2, BTM Layout,Bangalore</td>\n",
              "      <td>North Indian</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹50</td>\n",
              "      <td>-</td>\n",
              "      <td>-</td>\n",
              "      <td>-</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>freq</th>\n",
              "      <td>22</td>\n",
              "      <td>947</td>\n",
              "      <td>850</td>\n",
              "      <td>3241</td>\n",
              "      <td>10118</td>\n",
              "      <td>1191</td>\n",
              "      <td>2074</td>\n",
              "      <td>2312</td>\n",
              "      <td>7406</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "       Restaurant  ... Delivery_Time\n",
              "count       11094  ...         11094\n",
              "unique       7480  ...             7\n",
              "top       ID_7184  ...    30 minutes\n",
              "freq           22  ...          7406\n",
              "\n",
              "[4 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "nnlbbxSa_75y",
        "outputId": "0aec9ce2-29aa-4830-a824-9ff6be9d7fe1",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 263
        }
      },
      "source": [
        "train.info()"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 11094 entries, 0 to 11093\n",
            "Data columns (total 9 columns):\n",
            "Restaurant       11094 non-null object\n",
            "Location         11094 non-null object\n",
            "Cuisines         11094 non-null object\n",
            "Average_Cost     11094 non-null object\n",
            "Minimum_Order    11094 non-null object\n",
            "Rating           11094 non-null object\n",
            "Votes            11094 non-null object\n",
            "Reviews          11094 non-null object\n",
            "Delivery_Time    11094 non-null object\n",
            "dtypes: object(9)\n",
            "memory usage: 780.2+ KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "ucWulRUiAaO-"
      },
      "source": [
        "####Test Data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "R2hWiEHllP7D",
        "outputId": "2cc14f44-2891-45db-d628-731b7a2c3735",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "test.shape"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(2774, 8)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "ECOLxRPMRaZa",
        "outputId": "cb7f2c23-87f2-403f-dcdc-f7f3a0eed6f8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        }
      },
      "source": [
        "test.columns"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['Restaurant', 'Location', 'Cuisines', 'Average_Cost', 'Minimum_Order',\n",
              "       'Rating', 'Votes', 'Reviews'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "kA709EfflT1M",
        "outputId": "01b2d687-4f67-4bf8-8625-e51a6e6df5fa",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 246
        }
      },
      "source": [
        "test.head()"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>ID_2842</td>\n",
              "      <td>Mico Layout, Stage 2, BTM Layout,Bangalore</td>\n",
              "      <td>North Indian, Chinese, Assamese</td>\n",
              "      <td>₹350</td>\n",
              "      <td>₹50</td>\n",
              "      <td>4.2</td>\n",
              "      <td>361</td>\n",
              "      <td>225</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>ID_730</td>\n",
              "      <td>Mico Layout, Stage 2, BTM Layout,Bangalore</td>\n",
              "      <td>Biryani, Kebab</td>\n",
              "      <td>₹100</td>\n",
              "      <td>₹50</td>\n",
              "      <td>NEW</td>\n",
              "      <td>-</td>\n",
              "      <td>-</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>ID_4620</td>\n",
              "      <td>Sector 1, Noida</td>\n",
              "      <td>Fast Food</td>\n",
              "      <td>₹100</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.6</td>\n",
              "      <td>36</td>\n",
              "      <td>16</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ID_5470</td>\n",
              "      <td>Babarpur, New Delhi, Delhi</td>\n",
              "      <td>Mithai, North Indian, Chinese, Fast Food, Sout...</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.6</td>\n",
              "      <td>66</td>\n",
              "      <td>33</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>ID_3249</td>\n",
              "      <td>Sector 1, Noida</td>\n",
              "      <td>Chinese, Fast Food</td>\n",
              "      <td>₹150</td>\n",
              "      <td>₹50</td>\n",
              "      <td>2.9</td>\n",
              "      <td>38</td>\n",
              "      <td>14</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "  Restaurant                                    Location  ... Votes Reviews\n",
              "0    ID_2842  Mico Layout, Stage 2, BTM Layout,Bangalore  ...   361     225\n",
              "1     ID_730  Mico Layout, Stage 2, BTM Layout,Bangalore  ...     -       -\n",
              "2    ID_4620                             Sector 1, Noida  ...    36      16\n",
              "3    ID_5470                  Babarpur, New Delhi, Delhi  ...    66      33\n",
              "4    ID_3249                             Sector 1, Noida  ...    38      14\n",
              "\n",
              "[5 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "cV8c6gTx_y1_",
        "outputId": "e94f2fab-3dac-409d-e606-43c821b6a856",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 175
        }
      },
      "source": [
        "test.isnull().sum()"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Restaurant       0\n",
              "Location         0\n",
              "Cuisines         0\n",
              "Average_Cost     0\n",
              "Minimum_Order    0\n",
              "Rating           0\n",
              "Votes            0\n",
              "Reviews          0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "vMQHK61o___h",
        "outputId": "4d193f79-5c5a-4cd7-a6f7-24c27243470b",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 246
        }
      },
      "source": [
        "test.info()"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 2774 entries, 0 to 2773\n",
            "Data columns (total 8 columns):\n",
            "Restaurant       2774 non-null object\n",
            "Location         2774 non-null object\n",
            "Cuisines         2774 non-null object\n",
            "Average_Cost     2774 non-null object\n",
            "Minimum_Order    2774 non-null object\n",
            "Rating           2774 non-null object\n",
            "Votes            2774 non-null object\n",
            "Reviews          2774 non-null object\n",
            "dtypes: object(8)\n",
            "memory usage: 173.5+ KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "mIMWYFUDAgAv",
        "outputId": "e3622044-761f-4c5d-9cd0-13a944efea55",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 166
        }
      },
      "source": [
        "test.describe(include = 'all')"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>2774</td>\n",
              "      <td>2774</td>\n",
              "      <td>2774</td>\n",
              "      <td>2774</td>\n",
              "      <td>2774</td>\n",
              "      <td>2774</td>\n",
              "      <td>2774</td>\n",
              "      <td>2774</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>unique</th>\n",
              "      <td>2401</td>\n",
              "      <td>35</td>\n",
              "      <td>881</td>\n",
              "      <td>19</td>\n",
              "      <td>9</td>\n",
              "      <td>30</td>\n",
              "      <td>580</td>\n",
              "      <td>392</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>top</th>\n",
              "      <td>ID_1209</td>\n",
              "      <td>D-Block, Sector 63, Noida</td>\n",
              "      <td>North Indian</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹50</td>\n",
              "      <td>-</td>\n",
              "      <td>-</td>\n",
              "      <td>-</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>freq</th>\n",
              "      <td>8</td>\n",
              "      <td>221</td>\n",
              "      <td>226</td>\n",
              "      <td>820</td>\n",
              "      <td>2556</td>\n",
              "      <td>305</td>\n",
              "      <td>542</td>\n",
              "      <td>593</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "       Restaurant                   Location      Cuisines  ... Rating Votes Reviews\n",
              "count        2774                       2774          2774  ...   2774  2774    2774\n",
              "unique       2401                         35           881  ...     30   580     392\n",
              "top       ID_1209  D-Block, Sector 63, Noida  North Indian  ...      -     -       -\n",
              "freq            8                        221           226  ...    305   542     593\n",
              "\n",
              "[4 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "_YYJ_HI9A1qg"
      },
      "source": [
        "##Data Cleaning"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "yyJYTvr8RjwO"
      },
      "source": [
        "We will consider the following features of training and test datasets. Here I have grouped the columns based on similarity of values which will make it easy for cleaning.\n",
        "\n",
        "* Cleaning Average_Cost & Minimum_order columns to remove special characters and make them float variables.\n",
        "* Location & Cuisines are categoriacal variables that needs to be cleaned before encoding.\n",
        "* Rating, Votes & Reviews needs to be cleaned and converted to respective types.\n",
        "\n",
        "We will delve deeper in the coming sections.\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "pwjvNSkCBLC6"
      },
      "source": [
        "####Average_Cost\t& Minimum_order"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "sRsfJuPbkW3C",
        "outputId": "5d4d76d9-13fc-4698-b5da-7fb1cc145eaa",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 212
        }
      },
      "source": [
        "train.head()"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "      <th>Delivery_Time</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>ID_6321</td>\n",
              "      <td>FTI College, Law College Road, Pune</td>\n",
              "      <td>Fast Food, Rolls, Burger, Salad, Wraps</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>12</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>ID_2882</td>\n",
              "      <td>Sector 3, Marathalli</td>\n",
              "      <td>Ice Cream, Desserts</td>\n",
              "      <td>₹100</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>11</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>ID_1595</td>\n",
              "      <td>Mumbai Central</td>\n",
              "      <td>Italian, Street Food, Fast Food</td>\n",
              "      <td>₹150</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.6</td>\n",
              "      <td>99</td>\n",
              "      <td>30</td>\n",
              "      <td>65 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ID_5929</td>\n",
              "      <td>Sector 1, Noida</td>\n",
              "      <td>Mughlai, North Indian, Chinese</td>\n",
              "      <td>₹250</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.7</td>\n",
              "      <td>176</td>\n",
              "      <td>95</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>ID_6123</td>\n",
              "      <td>Rmz Centennial, I Gate, Whitefield</td>\n",
              "      <td>Cafe, Beverages</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.2</td>\n",
              "      <td>521</td>\n",
              "      <td>235</td>\n",
              "      <td>65 minutes</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "  Restaurant                             Location  ... Reviews Delivery_Time\n",
              "0    ID_6321  FTI College, Law College Road, Pune  ...       4    30 minutes\n",
              "1    ID_2882                 Sector 3, Marathalli  ...       4    30 minutes\n",
              "2    ID_1595                       Mumbai Central  ...      30    65 minutes\n",
              "3    ID_5929                      Sector 1, Noida  ...      95    30 minutes\n",
              "4    ID_6123   Rmz Centennial, I Gate, Whitefield  ...     235    65 minutes\n",
              "\n",
              "[5 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "tqNZCFbcm15K",
        "outputId": "b5e11455-3f89-45eb-d1c3-8cb72f9da28d",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 87
        }
      },
      "source": [
        "#Finding the unique values in Average_Cost\n",
        "train['Average_Cost'].unique()"
      ],
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['₹200', '₹100', '₹150', '₹250', '₹650', '₹350', '₹800', '₹50',\n",
              "       '₹400', '₹600', '₹300', '₹750', '₹450', '₹550', '₹1,000', '₹500',\n",
              "       '₹900', '₹1,200', '₹950', '₹850', '₹700', '₹1,150', 'for',\n",
              "       '₹1,100', '₹1,400', '₹2,050'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "XCtKvvfUTRqn"
      },
      "source": [
        "The Average_Cost has an invalid value in one of its rows. We will replace it with 200 which is the most frequent value in the column.(Check the train.describe() method). We will add 200 as a string and not as an integer as the column is of type object and all its values are strings."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "9eFmcCodty24",
        "outputId": "9f9ce5b8-b4c3-450a-f084-1eca31c7bfdf",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 77
        }
      },
      "source": [
        "train[train['Average_Cost'] == 'for']"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "      <th>Delivery_Time</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>6297</th>\n",
              "      <td>ID_6472</td>\n",
              "      <td>Pune University</td>\n",
              "      <td>Fast Food</td>\n",
              "      <td>for</td>\n",
              "      <td>₹50</td>\n",
              "      <td>NEW</td>\n",
              "      <td>-</td>\n",
              "      <td>-</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "     Restaurant         Location   Cuisines  ... Votes Reviews Delivery_Time\n",
              "6297    ID_6472  Pune University  Fast Food  ...     -       -    30 minutes\n",
              "\n",
              "[1 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "YxAdTpeojHJF",
        "colab": {}
      },
      "source": [
        "#replacing 'for' with 200\n",
        "train['Average_Cost'].replace('for', '200', inplace = True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "Mo-S0e7HT2T2"
      },
      "source": [
        "Now we will clean all the values and will convert it in to integer. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "eoJghDs-OB-K",
        "colab": {}
      },
      "source": [
        "train['Average_Cost_Cleaned'] = train['Average_Cost'].apply(lambda x: int(re.sub(\"[^0-9]\", \"\", x)))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "H_POcn32wdck",
        "outputId": "16470ab0-286c-4f69-ac75-3f2db78c4c3b",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        }
      },
      "source": [
        "train['Average_Cost_Cleaned'].unique()"
      ],
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([ 200,  100,  150,  250,  650,  350,  800,   50,  400,  600,  300,\n",
              "        750,  450,  550, 1000,  500,  900, 1200,  950,  850,  700, 1150,\n",
              "       1100, 1400, 2050])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "iNlGUAMuUTye"
      },
      "source": [
        "We can see that all the special characters ahave been removed and strings have been converted to integers.\n",
        "\n",
        "---\n",
        "\n",
        "Let's perform the same operations on the test set\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "wCZxzEqSOB8D",
        "outputId": "f5b32377-e7cb-4560-8bdd-dae7244f379f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        }
      },
      "source": [
        "test['Average_Cost'].unique()"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['₹350', '₹100', '₹200', '₹150', '₹300', '₹50', '₹250', '₹500',\n",
              "       '₹650', '₹400', '₹550', '₹450', '₹600', '₹750', '₹850', '₹1,000',\n",
              "       '₹700', '₹800', '₹1,200'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "Q4gYXWVhOB6S",
        "colab": {}
      },
      "source": [
        "test['Average_Cost_Cleaned'] = test['Average_Cost'].apply(lambda x: int(re.sub(\"[^0-9]\", \"\", x)))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "hmDLCsnVwoLi",
        "outputId": "9c554fdb-79a8-4f36-cd6e-564a17714a08",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 52
        }
      },
      "source": [
        "test['Average_Cost_Cleaned'].unique()"
      ],
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([ 350,  100,  200,  150,  300,   50,  250,  500,  650,  400,  550,\n",
              "        450,  600,  750,  850, 1000,  700,  800, 1200])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "0TtRyWCAUwfC"
      },
      "source": [
        "Now lets do the same for Minimum_Order column"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "XgKZKZYEJHdu",
        "outputId": "b70f6afd-8ba6-46d2-b010-be6d54ddcc1a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        }
      },
      "source": [
        "train['Minimum_Order'].unique()"
      ],
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['₹50', '₹99', '₹0', '₹200', '₹450', '₹350', '₹79', '₹400', '₹199',\n",
              "       '₹500', '₹250', '₹150', '₹90', '₹299', '₹300', '₹240', '₹89',\n",
              "       '₹59'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "P3a-jxJDUNXu",
        "colab": {}
      },
      "source": [
        "train['Minimum_Order_Cleaned'] = train['Minimum_Order'].apply(lambda x: int(re.sub(\"[^0-9]\", \"\", x)))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "2KZl-XPAUNV3",
        "outputId": "85e6ace4-1596-4c86-8430-efe4b06df3c4",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 52
        }
      },
      "source": [
        "test['Minimum_Order'].unique()"
      ],
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['₹50', '₹99', '₹500', '₹0', '₹200', '₹149', '₹199', '₹399', '₹89'],\n",
              "      dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "uZMbJwFnUNTh",
        "colab": {}
      },
      "source": [
        "test['Minimum_Order_Cleaned'] = test['Minimum_Order'].apply(lambda x: int(re.sub(\"[^0-9]\", \"\", x)))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "NRddLSAzUNRu",
        "outputId": "d8e74757-f929-461a-b83c-64523a38c723",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 467
        }
      },
      "source": [
        "train.head()"
      ],
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "      <th>Delivery_Time</th>\n",
              "      <th>Average_Cost_Cleaned</th>\n",
              "      <th>Minimum_Order_Cleaned</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>ID_6321</td>\n",
              "      <td>FTI College, Law College Road, Pune</td>\n",
              "      <td>Fast Food, Rolls, Burger, Salad, Wraps</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>12</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>200</td>\n",
              "      <td>50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>ID_2882</td>\n",
              "      <td>Sector 3, Marathalli</td>\n",
              "      <td>Ice Cream, Desserts</td>\n",
              "      <td>₹100</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>11</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>100</td>\n",
              "      <td>50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>ID_1595</td>\n",
              "      <td>Mumbai Central</td>\n",
              "      <td>Italian, Street Food, Fast Food</td>\n",
              "      <td>₹150</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.6</td>\n",
              "      <td>99</td>\n",
              "      <td>30</td>\n",
              "      <td>65 minutes</td>\n",
              "      <td>150</td>\n",
              "      <td>50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ID_5929</td>\n",
              "      <td>Sector 1, Noida</td>\n",
              "      <td>Mughlai, North Indian, Chinese</td>\n",
              "      <td>₹250</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.7</td>\n",
              "      <td>176</td>\n",
              "      <td>95</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>250</td>\n",
              "      <td>99</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>ID_6123</td>\n",
              "      <td>Rmz Centennial, I Gate, Whitefield</td>\n",
              "      <td>Cafe, Beverages</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.2</td>\n",
              "      <td>521</td>\n",
              "      <td>235</td>\n",
              "      <td>65 minutes</td>\n",
              "      <td>200</td>\n",
              "      <td>99</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "  Restaurant  ... Minimum_Order_Cleaned\n",
              "0    ID_6321  ...                    50\n",
              "1    ID_2882  ...                    50\n",
              "2    ID_1595  ...                    50\n",
              "3    ID_5929  ...                    99\n",
              "4    ID_6123  ...                    99\n",
              "\n",
              "[5 rows x 11 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "Hjn_pdlpBD8w"
      },
      "source": [
        "####Location & CUISINES"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "1S2LHft5U9YN"
      },
      "source": [
        "Location and Cuisines are categorical variables that need to be encoded later. By looking at the dataset, we can see that each of these columns have multiple values in them. We can use each of them as a feature by splitting each column into n number of features.\n",
        "To do that we will first find the maximum number(n) of features a column has in the entire dataset including both test and train data. Once the maximum number of features within a cell is found, we will split all the rows in the dataset for that specific column into n features. \n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "TlVQYHp0Sldz",
        "colab": {}
      },
      "source": [
        "#A function to find the maximun number of features in a single cell\n",
        "def max_features_in_single_row(train, test, delimiter):\n",
        "  max_info = 0 \n",
        "  item_lis = list(train.append(test))\n",
        "  for i in item_lis:\n",
        "    if len(i.split(\"{}\".format(delimiter))) > max_info:\n",
        "      max_info = len(i.split(\"{}\".format(delimiter)))\n",
        "  print(\"\\n\",\"-\"*35)    \n",
        "  print(\"Max_Features in One Observation = \", max_info)\n",
        "  return max_info"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "3eNvsPsPlVjZ",
        "colab": {}
      },
      "source": [
        "#This function splits a column in to n features where n is the maximum number of features in a single cell\n",
        "def feature_splitter(feat, name, delimiter, max_info):\n",
        "  item_lis = list(feat)\n",
        "  extracted_features = {}\n",
        "\n",
        "  for i in range(max_info):\n",
        "    extracted_features['{}_Feature_{}'.format(name, i+1)] = []\n",
        "  \n",
        "  print(\"-\"*35)\n",
        "  print(\"Features Dictionary : \", extracted_features)\n",
        "\n",
        "  for i in tqdm(range(len(item_lis))):\n",
        "    for j in range(max_info):  \n",
        "      try:\n",
        "        extracted_features['{}_Feature_{}'.format(name,j+1)].append(item_lis[i].split(\"{}\".format(delimiter))[j].lower().strip())\n",
        "      except: \n",
        "        extracted_features['{}_Feature_{}'.format(name, j+1)].append(np.nan)\n",
        "\n",
        "\n",
        "  return extracted_features\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "hIgyWIdKNiXi",
        "outputId": "61dc17a9-26c7-4279-98ad-aa8ece747851",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 175
        }
      },
      "source": [
        "#Splitting Location\n",
        "loc_max = max_features_in_single_row(test['Location'],train['Location'], ',')\n",
        "train_Location_splits = feature_splitter(train['Location'], 'Location', ',', loc_max)\n",
        "test_Location_splits = feature_splitter(test['Location'], 'Location', ',', loc_max)\n"
      ],
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "100%|██████████| 11094/11094 [00:00<00:00, 200329.82it/s]\n",
            "100%|██████████| 2774/2774 [00:00<00:00, 146446.14it/s]"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            " -----------------------------------\n",
            "Max_Features in One Observation =  4\n",
            "-----------------------------------\n",
            "Features Dictionary :  {'Location_Feature_1': [], 'Location_Feature_2': [], 'Location_Feature_3': [], 'Location_Feature_4': []}\n",
            "-----------------------------------\n",
            "Features Dictionary :  {'Location_Feature_1': [], 'Location_Feature_2': [], 'Location_Feature_3': [], 'Location_Feature_4': []}\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "KqcwdG_gkCPa",
        "outputId": "177a9d0a-39ec-44a8-ef3b-a21db97fe66f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 195
        }
      },
      "source": [
        "#Splitting Cuisines\n",
        "cus_max = max_features_in_single_row(test['Cuisines'],train['Cuisines'], ',')\n",
        "train_Cuisines_splits = feature_splitter(train['Cuisines'], 'Cuisines', ',', cus_max)\n",
        "test_Cuisines_splits = feature_splitter(test['Cuisines'], 'Cuisines', ',', cus_max)"
      ],
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\r  0%|          | 0/11094 [00:00<?, ?it/s]"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            " -----------------------------------\n",
            "Max_Features in One Observation =  8\n",
            "-----------------------------------\n",
            "Features Dictionary :  {'Cuisines_Feature_1': [], 'Cuisines_Feature_2': [], 'Cuisines_Feature_3': [], 'Cuisines_Feature_4': [], 'Cuisines_Feature_5': [], 'Cuisines_Feature_6': [], 'Cuisines_Feature_7': [], 'Cuisines_Feature_8': []}\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "100%|██████████| 11094/11094 [00:00<00:00, 97491.47it/s]\n",
            "100%|██████████| 2774/2774 [00:00<00:00, 92581.54it/s]"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "-----------------------------------\n",
            "Features Dictionary :  {'Cuisines_Feature_1': [], 'Cuisines_Feature_2': [], 'Cuisines_Feature_3': [], 'Cuisines_Feature_4': [], 'Cuisines_Feature_5': [], 'Cuisines_Feature_6': [], 'Cuisines_Feature_7': [], 'Cuisines_Feature_8': []}\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "telTCWSRUvZp"
      },
      "source": [
        "####Rating, Votes & Reviews"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "br9VvuoNW0nB"
      },
      "source": [
        "We will now clean Rating, Votes & Reviews columns to remove invalid values and to convert them to the right type."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "pdSxC7iJVJVA",
        "outputId": "c94f2f88-70ef-4366-f92a-1ab74f96ebdc",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 426
        }
      },
      "source": [
        "train.describe(include = 'all')"
      ],
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "      <th>Delivery_Time</th>\n",
              "      <th>Average_Cost_Cleaned</th>\n",
              "      <th>Minimum_Order_Cleaned</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094</td>\n",
              "      <td>11094.000000</td>\n",
              "      <td>11094.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>unique</th>\n",
              "      <td>7480</td>\n",
              "      <td>35</td>\n",
              "      <td>2179</td>\n",
              "      <td>26</td>\n",
              "      <td>18</td>\n",
              "      <td>33</td>\n",
              "      <td>1103</td>\n",
              "      <td>761</td>\n",
              "      <td>7</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>top</th>\n",
              "      <td>ID_7184</td>\n",
              "      <td>Mico Layout, Stage 2, BTM Layout,Bangalore</td>\n",
              "      <td>North Indian</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹50</td>\n",
              "      <td>-</td>\n",
              "      <td>-</td>\n",
              "      <td>-</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>freq</th>\n",
              "      <td>22</td>\n",
              "      <td>947</td>\n",
              "      <td>850</td>\n",
              "      <td>3241</td>\n",
              "      <td>10118</td>\n",
              "      <td>1191</td>\n",
              "      <td>2074</td>\n",
              "      <td>2312</td>\n",
              "      <td>7406</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>202.708671</td>\n",
              "      <td>53.344511</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>129.833261</td>\n",
              "      <td>18.551245</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>50.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>100.000000</td>\n",
              "      <td>50.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>200.000000</td>\n",
              "      <td>50.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>200.000000</td>\n",
              "      <td>50.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>2050.000000</td>\n",
              "      <td>500.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "       Restaurant  ... Minimum_Order_Cleaned\n",
              "count       11094  ...          11094.000000\n",
              "unique       7480  ...                   NaN\n",
              "top       ID_7184  ...                   NaN\n",
              "freq           22  ...                   NaN\n",
              "mean          NaN  ...             53.344511\n",
              "std           NaN  ...             18.551245\n",
              "min           NaN  ...              0.000000\n",
              "25%           NaN  ...             50.000000\n",
              "50%           NaN  ...             50.000000\n",
              "75%           NaN  ...             50.000000\n",
              "max           NaN  ...            500.000000\n",
              "\n",
              "[11 rows x 11 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 35
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "98JSZquOUuhA",
        "colab": {}
      },
      "source": [
        "#A function to find all the non numeric values\n",
        "def non_numerals(series):\n",
        "  non_numerals = []\n",
        "  for i in series.unique():\n",
        "    try :\n",
        "      i = float(i)\n",
        "    except:\n",
        "      non_numerals.append(i)\n",
        "  return non_numerals"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "Xd-2qqH7dPcD",
        "colab": {}
      },
      "source": [
        "# A function to replace the non-numeric values\n",
        "def replace_nn_with(series, type_, fill_with = None, method = 'mean'):\n",
        "\n",
        "  nn = non_numerals(series)\n",
        "  print('-'*30)\n",
        "  print('-'*30)\n",
        "  print(\"Non Numerals in column \",series.name,\" : \",nn)\n",
        "\n",
        "  series = series.replace(nn, np.nan, inplace = False)\n",
        "  nulls = series.isnull().sum()\n",
        "  if fill_with:\n",
        "    series.fillna(fill_with, inplace = True)\n",
        "    print(\"Filling Non Numerals with {}\".format(fill_with))\n",
        "  \n",
        "  else:\n",
        "    series = series.replace(nn, np.nan, inplace = False)\n",
        "\n",
        "    if method == 'mean' :\n",
        "      rep = series.astype(float).mean()\n",
        "      print(\"Filling Non Numerals with MEAN = \", rep)\n",
        "\n",
        "    elif method == 'median' :\n",
        "      rep = series.astype(float).median()\n",
        "      print(\"Filling Non Numerals with MEDIAN = \", rep)\n",
        "\n",
        "    elif method == 'min' :\n",
        "      rep = series.astype(float).min()\n",
        "      print(\"Filling Non Numerals with MINIMUM = \", rep)\n",
        "\n",
        "    else:\n",
        "      print('Please pass a valid method as a string -- (\"mean\" or \"median\" or \"min\")')\n",
        "      return 0\n",
        "\n",
        "    series.fillna(rep, inplace = True)\n",
        "    \n",
        "  try:\n",
        "    series = series.astype(type_)\n",
        "    print(nulls, \": observations replaced\")\n",
        "    return series\n",
        "  except:\n",
        "    # Since type conversion of a string containting decimals to int is not possible, it is first converted to float\n",
        "    series =  series.astype(float)\n",
        "    print(nulls, \": observations replaced\")\n",
        "    series =  series.astype(type_)\n",
        "    return series\n",
        "    \n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "UgP5SZBbvH-n",
        "outputId": "4297aa2c-77ff-4661-ab66-b084b113486e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 467
        }
      },
      "source": [
        "train.head()"
      ],
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "      <th>Delivery_Time</th>\n",
              "      <th>Average_Cost_Cleaned</th>\n",
              "      <th>Minimum_Order_Cleaned</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>ID_6321</td>\n",
              "      <td>FTI College, Law College Road, Pune</td>\n",
              "      <td>Fast Food, Rolls, Burger, Salad, Wraps</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>12</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>200</td>\n",
              "      <td>50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>ID_2882</td>\n",
              "      <td>Sector 3, Marathalli</td>\n",
              "      <td>Ice Cream, Desserts</td>\n",
              "      <td>₹100</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>11</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>100</td>\n",
              "      <td>50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>ID_1595</td>\n",
              "      <td>Mumbai Central</td>\n",
              "      <td>Italian, Street Food, Fast Food</td>\n",
              "      <td>₹150</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.6</td>\n",
              "      <td>99</td>\n",
              "      <td>30</td>\n",
              "      <td>65 minutes</td>\n",
              "      <td>150</td>\n",
              "      <td>50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ID_5929</td>\n",
              "      <td>Sector 1, Noida</td>\n",
              "      <td>Mughlai, North Indian, Chinese</td>\n",
              "      <td>₹250</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.7</td>\n",
              "      <td>176</td>\n",
              "      <td>95</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>250</td>\n",
              "      <td>99</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>ID_6123</td>\n",
              "      <td>Rmz Centennial, I Gate, Whitefield</td>\n",
              "      <td>Cafe, Beverages</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.2</td>\n",
              "      <td>521</td>\n",
              "      <td>235</td>\n",
              "      <td>65 minutes</td>\n",
              "      <td>200</td>\n",
              "      <td>99</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "  Restaurant  ... Minimum_Order_Cleaned\n",
              "0    ID_6321  ...                    50\n",
              "1    ID_2882  ...                    50\n",
              "2    ID_1595  ...                    50\n",
              "3    ID_5929  ...                    99\n",
              "4    ID_6123  ...                    99\n",
              "\n",
              "[5 rows x 11 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 38
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "D2UGyd1YXR_w"
      },
      "source": [
        "Lets Clean the columns"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "N0hBJrrPcnAN",
        "outputId": "59adac76-6541-4264-a518-151dd22350ee",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        }
      },
      "source": [
        "train['Rating_Cleaned'] = replace_nn_with(train['Rating'],float, method = 'mean')"
      ],
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "------------------------------\n",
            "------------------------------\n",
            "Non Numerals in column  Rating  :  ['-', 'NEW', 'Opening Soon', 'Temporarily Closed']\n",
            "Filling Non Numerals with MEAN =  3.6134596429744668\n",
            "1963 : observations replaced\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "mDNBE-N3yZFq",
        "outputId": "4ad058e4-30de-44f3-992a-7ffee7284ae9",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        }
      },
      "source": [
        "test['Rating_Cleaned'] = replace_nn_with(test['Rating'],float, fill_with = 3.6134596429744668)"
      ],
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "------------------------------\n",
            "------------------------------\n",
            "Non Numerals in column  Rating  :  ['NEW', '-', 'Opening Soon']\n",
            "Filling Non Numerals with 3.6134596429744668\n",
            "507 : observations replaced\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "SrSqjkJ9cm46",
        "outputId": "04aa23c4-3fc3-4745-dcb4-b3fc18465b1f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        }
      },
      "source": [
        "train['Votes_Cleaned'] = replace_nn_with(train['Votes'],int,method =  'mean')\n"
      ],
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "------------------------------\n",
            "------------------------------\n",
            "Non Numerals in column  Votes  :  ['-']\n",
            "Filling Non Numerals with MEAN =  244.54445676274943\n",
            "2074 : observations replaced\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "NK45gKPj4m9L",
        "outputId": "464ee934-3436-4cff-fd38-08acc28daabc",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        }
      },
      "source": [
        "test['Votes_Cleaned'] = replace_nn_with(test['Votes'],int,fill_with = 244.54445676274943)"
      ],
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "------------------------------\n",
            "------------------------------\n",
            "Non Numerals in column  Votes  :  ['-']\n",
            "Filling Non Numerals with 244.54445676274943\n",
            "542 : observations replaced\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "D3ZTqnwIzmHa",
        "outputId": "b1a7f628-f11b-4693-a40f-68e9e6ce4a00",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        }
      },
      "source": [
        "train['Reviews_Cleaned'] = replace_nn_with(train['Reviews'],int, method =  'mean')"
      ],
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "------------------------------\n",
            "------------------------------\n",
            "Non Numerals in column  Reviews  :  ['-']\n",
            "Filling Non Numerals with MEAN =  123.24789341835573\n",
            "2312 : observations replaced\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "iEMVlV2R4vcW",
        "outputId": "79278b85-6058-4ad3-9658-8312322b3795",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        }
      },
      "source": [
        "test['Reviews_Cleaned'] = replace_nn_with(test['Reviews'],int, method =  'mean',fill_with = 123.247893 )"
      ],
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "------------------------------\n",
            "------------------------------\n",
            "Non Numerals in column  Reviews  :  ['-']\n",
            "Filling Non Numerals with 123.247893\n",
            "593 : observations replaced\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "kXVltCBZwXly",
        "outputId": "307b43b7-7a72-414c-a147-43a390a883a6",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 467
        }
      },
      "source": [
        "train.head(5)"
      ],
      "execution_count": 45,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Restaurant</th>\n",
              "      <th>Location</th>\n",
              "      <th>Cuisines</th>\n",
              "      <th>Average_Cost</th>\n",
              "      <th>Minimum_Order</th>\n",
              "      <th>Rating</th>\n",
              "      <th>Votes</th>\n",
              "      <th>Reviews</th>\n",
              "      <th>Delivery_Time</th>\n",
              "      <th>Average_Cost_Cleaned</th>\n",
              "      <th>Minimum_Order_Cleaned</th>\n",
              "      <th>Rating_Cleaned</th>\n",
              "      <th>Votes_Cleaned</th>\n",
              "      <th>Reviews_Cleaned</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>ID_6321</td>\n",
              "      <td>FTI College, Law College Road, Pune</td>\n",
              "      <td>Fast Food, Rolls, Burger, Salad, Wraps</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>12</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>200</td>\n",
              "      <td>50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>12</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>ID_2882</td>\n",
              "      <td>Sector 3, Marathalli</td>\n",
              "      <td>Ice Cream, Desserts</td>\n",
              "      <td>₹100</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>11</td>\n",
              "      <td>4</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>100</td>\n",
              "      <td>50</td>\n",
              "      <td>3.5</td>\n",
              "      <td>11</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>ID_1595</td>\n",
              "      <td>Mumbai Central</td>\n",
              "      <td>Italian, Street Food, Fast Food</td>\n",
              "      <td>₹150</td>\n",
              "      <td>₹50</td>\n",
              "      <td>3.6</td>\n",
              "      <td>99</td>\n",
              "      <td>30</td>\n",
              "      <td>65 minutes</td>\n",
              "      <td>150</td>\n",
              "      <td>50</td>\n",
              "      <td>3.6</td>\n",
              "      <td>99</td>\n",
              "      <td>30</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ID_5929</td>\n",
              "      <td>Sector 1, Noida</td>\n",
              "      <td>Mughlai, North Indian, Chinese</td>\n",
              "      <td>₹250</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.7</td>\n",
              "      <td>176</td>\n",
              "      <td>95</td>\n",
              "      <td>30 minutes</td>\n",
              "      <td>250</td>\n",
              "      <td>99</td>\n",
              "      <td>3.7</td>\n",
              "      <td>176</td>\n",
              "      <td>95</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>ID_6123</td>\n",
              "      <td>Rmz Centennial, I Gate, Whitefield</td>\n",
              "      <td>Cafe, Beverages</td>\n",
              "      <td>₹200</td>\n",
              "      <td>₹99</td>\n",
              "      <td>3.2</td>\n",
              "      <td>521</td>\n",
              "      <td>235</td>\n",
              "      <td>65 minutes</td>\n",
              "      <td>200</td>\n",
              "      <td>99</td>\n",
              "      <td>3.2</td>\n",
              "      <td>521</td>\n",
              "      <td>235</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "  Restaurant  ... Reviews_Cleaned\n",
              "0    ID_6321  ...               4\n",
              "1    ID_2882  ...               4\n",
              "2    ID_1595  ...              30\n",
              "3    ID_5929  ...              95\n",
              "4    ID_6123  ...             235\n",
              "\n",
              "[5 rows x 14 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 45
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "fbQIqpjpAZxP",
        "outputId": "41fa50ce-8faa-431f-9b3c-c56a37bea558",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        }
      },
      "source": [
        "train.columns"
      ],
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['Restaurant', 'Location', 'Cuisines', 'Average_Cost', 'Minimum_Order',\n",
              "       'Rating', 'Votes', 'Reviews', 'Delivery_Time', 'Average_Cost_Cleaned',\n",
              "       'Minimum_Order_Cleaned', 'Rating_Cleaned', 'Votes_Cleaned',\n",
              "       'Reviews_Cleaned'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 46
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "WZvTDcx3Xgtc"
      },
      "source": [
        "We are done with the cleaning part and now we will select only the columns we need for further stages. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "3r-RUSjAAIgL",
        "colab": {}
      },
      "source": [
        "cols = ['Restaurant',  'Average_Cost_Cleaned',\n",
        "       'Minimum_Order_Cleaned', 'Rating_Cleaned', 'Votes_Cleaned',\n",
        "       'Reviews_Cleaned','Delivery_Time' ]"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "zdLJ2jsUAoCb",
        "colab": {}
      },
      "source": [
        "train_sample = train[cols]\n",
        "test_sample = test[cols[:-1]]"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "rRbkFzexX00x"
      },
      "source": [
        "We will now merge all the cleaned features to form a perfect dataframe"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "2bYpHnkkBEOt",
        "colab": {}
      },
      "source": [
        "train_sample = pd.concat([pd.DataFrame(train_Location_splits), pd.DataFrame(train_Cuisines_splits),train_sample],sort=False,axis = 1)\n",
        "test_sample = pd.concat([pd.DataFrame(test_Location_splits), pd.DataFrame(test_Cuisines_splits), test_sample],sort=False,axis = 1)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "eBQh4JoFCEY-",
        "outputId": "0d0acebb-f037-4145-a075-256b446e962a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 945
        }
      },
      "source": [
        "#lets take a look at the relation between the numeric features in the dataset\n",
        "import seaborn\n",
        "seaborn.pairplot(train_sample)"
      ],
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<seaborn.axisgrid.PairGrid at 0x7fc4cf1610b8>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 50
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA5AAAAOOCAYAAAB2kP3PAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nGAwGg8FgMBjaxP8HisaGcaUr8A8AAAAASUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 900x900 with 30 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "RmXx7yZTGUs9",
        "outputId": "3f4a96c3-4330-4fba-af9d-a22fb482534e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 945
        }
      },
      "source": [
        "seaborn.pairplot(test_sample)"
      ],
      "execution_count": 51,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<seaborn.axisgrid.PairGrid at 0x7fc4c1f19240>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 51
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA5cAAAOOCAYAAACUTOa2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n29ZF//iWAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 900x900 with 30 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "u1kumctM5Jf5"
      },
      "source": [
        "##Data Preprocessing"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "1bxiaN83YEcA"
      },
      "source": [
        "After cleaning, there are still some Data-Preparation tasks left. We still have some missing values that we allotted during the feature generation.\n",
        "\n",
        "In the Preprocessing stage we will perform the following :\n",
        "\n",
        "* Dealing with Nulls/empty cells\n",
        "* Encoding Categorical variables\n",
        "* Scaling the features"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "SCbszxL0-NPg"
      },
      "source": [
        "### Removing Nulls"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "MkXVhYBP2EL4",
        "outputId": "8502bb52-cee0-48c7-cfe6-3c5bbc342f46",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 369
        }
      },
      "source": [
        "train_sample.isnull().sum()"
      ],
      "execution_count": 52,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Location_Feature_1           0\n",
              "Location_Feature_2        1942\n",
              "Location_Feature_3        6364\n",
              "Location_Feature_4       10068\n",
              "Cuisines_Feature_1           0\n",
              "Cuisines_Feature_2        3012\n",
              "Cuisines_Feature_3        6931\n",
              "Cuisines_Feature_4        9393\n",
              "Cuisines_Feature_5       10449\n",
              "Cuisines_Feature_6       10854\n",
              "Cuisines_Feature_7       10978\n",
              "Cuisines_Feature_8       11046\n",
              "Restaurant                   0\n",
              "Average_Cost_Cleaned         0\n",
              "Minimum_Order_Cleaned        0\n",
              "Rating_Cleaned               0\n",
              "Votes_Cleaned                0\n",
              "Reviews_Cleaned              0\n",
              "Delivery_Time                0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 52
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "xVejY3poZKSx"
      },
      "source": [
        "Since the nulls are present only in the categorical features, in this approach, to make it simple I will just replace all the NaNs with a string 'NAN' and will use it as a added category or class."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "iQUda-wk2VvR",
        "colab": {}
      },
      "source": [
        "train_sample.fillna('NAN', inplace = True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "i11idxAi2gI0",
        "outputId": "8b621127-4f8d-404e-d98f-efbaeca2669a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 369
        }
      },
      "source": [
        "train_sample.isnull().sum()"
      ],
      "execution_count": 54,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Location_Feature_1       0\n",
              "Location_Feature_2       0\n",
              "Location_Feature_3       0\n",
              "Location_Feature_4       0\n",
              "Cuisines_Feature_1       0\n",
              "Cuisines_Feature_2       0\n",
              "Cuisines_Feature_3       0\n",
              "Cuisines_Feature_4       0\n",
              "Cuisines_Feature_5       0\n",
              "Cuisines_Feature_6       0\n",
              "Cuisines_Feature_7       0\n",
              "Cuisines_Feature_8       0\n",
              "Restaurant               0\n",
              "Average_Cost_Cleaned     0\n",
              "Minimum_Order_Cleaned    0\n",
              "Rating_Cleaned           0\n",
              "Votes_Cleaned            0\n",
              "Reviews_Cleaned          0\n",
              "Delivery_Time            0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 54
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "b3UkAuNO2ntr",
        "outputId": "b6e08b1b-54b2-4be1-9066-cf0a2867ced9",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 369
        }
      },
      "source": [
        "train_sample.isnull().sum()"
      ],
      "execution_count": 55,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Location_Feature_1       0\n",
              "Location_Feature_2       0\n",
              "Location_Feature_3       0\n",
              "Location_Feature_4       0\n",
              "Cuisines_Feature_1       0\n",
              "Cuisines_Feature_2       0\n",
              "Cuisines_Feature_3       0\n",
              "Cuisines_Feature_4       0\n",
              "Cuisines_Feature_5       0\n",
              "Cuisines_Feature_6       0\n",
              "Cuisines_Feature_7       0\n",
              "Cuisines_Feature_8       0\n",
              "Restaurant               0\n",
              "Average_Cost_Cleaned     0\n",
              "Minimum_Order_Cleaned    0\n",
              "Rating_Cleaned           0\n",
              "Votes_Cleaned            0\n",
              "Reviews_Cleaned          0\n",
              "Delivery_Time            0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 55
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "7ePhAXn12iBg",
        "colab": {}
      },
      "source": [
        "test_sample.fillna('NAN', inplace = True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "ddDN2nVH2h_S",
        "outputId": "58f41966-1f73-4e2f-9f26-821aabbe30cf",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 369
        }
      },
      "source": [
        "train_sample.isnull().sum()"
      ],
      "execution_count": 57,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Location_Feature_1       0\n",
              "Location_Feature_2       0\n",
              "Location_Feature_3       0\n",
              "Location_Feature_4       0\n",
              "Cuisines_Feature_1       0\n",
              "Cuisines_Feature_2       0\n",
              "Cuisines_Feature_3       0\n",
              "Cuisines_Feature_4       0\n",
              "Cuisines_Feature_5       0\n",
              "Cuisines_Feature_6       0\n",
              "Cuisines_Feature_7       0\n",
              "Cuisines_Feature_8       0\n",
              "Restaurant               0\n",
              "Average_Cost_Cleaned     0\n",
              "Minimum_Order_Cleaned    0\n",
              "Rating_Cleaned           0\n",
              "Votes_Cleaned            0\n",
              "Reviews_Cleaned          0\n",
              "Delivery_Time            0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 57
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "wRVErMt0HBFp"
      },
      "source": [
        "### Encoding Categories"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "qkuN0nZ8ZcMo"
      },
      "source": [
        "\n",
        "\n",
        "---\n",
        "\n",
        "Here we will use a simple Label Encoder to transform all the strings or categories."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "tQXtDXaONwjx"
      },
      "source": [
        "####Locations & Cuisines"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "PWKUUgjRZ3oO"
      },
      "source": [
        "We will first find the unique values or categories in each of the categorical features and fit the label encoder with the unique values. The encoder eill assign an integer code to each of the categories which can be used to tranform the entire categorical feature column."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "3C5FxHrpJyy1",
        "colab": {}
      },
      "source": [
        "temp1 = []\n",
        "for i in train_Cuisines_splits.keys():\n",
        "  for j in train_Cuisines_splits.get(i):\n",
        "    temp1.append(j)\n",
        "\n",
        "temp2 = []\n",
        "for i in test_Cuisines_splits.keys():\n",
        "  for j in test_Cuisines_splits.get(i):\n",
        "    temp2.append(j)\n",
        "\n",
        "temp1.extend(temp2)\n",
        "\n",
        "unique_cuisines = list(pd.Series(temp1).unique())\n",
        "unique_cuisines.append('NAN')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "-TwuUkxbafu2"
      },
      "source": [
        "**Note:**\n",
        "We are also adding an extra category called NAN that we used to replace the NaN values."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "zVFV3HlYcnB8",
        "outputId": "ae6dd596-333f-4d81-bcdc-1276ab53a1df",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "len(unique_cuisines)"
      ],
      "execution_count": 59,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "103"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 59
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "sXmPQgxIayR2"
      },
      "source": [
        "The location is a tricky feature. You can use external data to fill the missing data. For example, if the city is missing you can use the street name and try to find the City for the missing fields.\n",
        "\n",
        "For simplicity, here I have followed the same approach as I did for Cuisines which is not a perfect solution."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "PFdxEMFYapOg",
        "colab": {}
      },
      "source": [
        "temp1 = []\n",
        "for i in train_Location_splits.keys():\n",
        "  for j in train_Location_splits.get(i):\n",
        "    temp1.append(j)\n",
        "\n",
        "temp2 = []\n",
        "for i in test_Location_splits.keys():\n",
        "  for j in test_Location_splits.get(i):\n",
        "    temp2.append(j)\n",
        "\n",
        "temp1.extend(temp2)\n",
        "\n",
        "unique_locations = list(pd.Series(temp1).unique())\n",
        "unique_locations.append('NAN')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "NgYB9IGpao_8",
        "outputId": "7e110ca1-f9ce-418f-aa70-129f1fc43a73",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "len(unique_locations)"
      ],
      "execution_count": 61,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "67"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 61
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "y4VLRR_SXPeM",
        "colab": {}
      },
      "source": [
        "#encoding the categorical Features\n",
        "from sklearn.preprocessing import LabelEncoder\n",
        "le_c = LabelEncoder().fit(unique_cuisines)\n",
        "le_l = LabelEncoder().fit(unique_locations)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "LRZw0YSE3dYe",
        "colab": {}
      },
      "source": [
        "for i in train_Location_splits.keys():\n",
        "  train_sample[i] = le_l.transform(train_sample[i])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "4U5u_YD63dVs",
        "colab": {}
      },
      "source": [
        "\n",
        "for i in train_Cuisines_splits.keys():\n",
        "  train_sample[i] = le_c.transform(train_sample[i])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "Fj2Jj6BW3fuL",
        "colab": {}
      },
      "source": [
        "for i in train_Location_splits.keys():\n",
        "  test_sample[i] = le_l.transform(test_sample[i])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "o1syc4_-3fsG",
        "colab": {}
      },
      "source": [
        "for i in test_Cuisines_splits.keys():\n",
        "  test_sample[i] = le_c.transform(test_sample[i])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "1R2AgdQg5OKR"
      },
      "source": [
        "####Restaurant IDs"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "DAY-qFUkbvOn"
      },
      "source": [
        "We will follow a similar approach for encoding the Restaurant IDs"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "Gjy67q7m4yyI",
        "colab": {}
      },
      "source": [
        "t1 = list(train_sample['Restaurant'])\n",
        "t2 = list(test_sample['Restaurant'])\n",
        "\n",
        "t1.extend(t2)\n",
        "unique_ids = list(set(t1))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "rMEP1sK351oP",
        "outputId": "28392015-2ec5-475f-f0af-0f40262ca4d9",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "len(unique_ids)"
      ],
      "execution_count": 68,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "8661"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 68
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "MPZ8Vu2q3foQ",
        "colab": {}
      },
      "source": [
        "le_id = LabelEncoder().fit(unique_ids)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "OkIo4_xX3fmb",
        "colab": {}
      },
      "source": [
        "train_sample['Restaurant'] = le_id.transform(train_sample['Restaurant'])\n",
        "test_sample['Restaurant'] = le_id.transform(test_sample['Restaurant'])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "FIGYqSTs6siA"
      },
      "source": [
        "### Scaling"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "RLNrIonDb77p"
      },
      "source": [
        "We will now normalize the data using the StandardScaler"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "BapushLu67t_",
        "colab": {}
      },
      "source": [
        "cols = list(train_sample.columns)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "iN9VLzktXPZV",
        "colab": {}
      },
      "source": [
        "from sklearn.preprocessing import StandardScaler\n",
        "ss = StandardScaler()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "FnZPES32XPQX",
        "colab": {}
      },
      "source": [
        "train_sample[cols[:-1]] = ss.fit_transform(train_sample[cols[:-1]])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "usUErPxy7arJ",
        "colab": {}
      },
      "source": [
        "test_sample[cols[:-1]] = ss.fit_transform(test_sample[cols[:-1]])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "SeC25GVmgItl",
        "outputId": "6cf87202-6da3-44f5-9a11-ccde6c736b44",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 215
        }
      },
      "source": [
        "train_sample.head()"
      ],
      "execution_count": 75,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Location_Feature_1</th>\n",
              "      <th>Location_Feature_2</th>\n",
              "      <th>Location_Feature_3</th>\n",
              "      <th>Location_Feature_4</th>\n",
              "      <th>Cuisines_Feature_1</th>\n",
              "      <th>Cuisines_Feature_2</th>\n",
              "      <th>Cuisines_Feature_3</th>\n",
              "      <th>Cuisines_Feature_4</th>\n",
              "      <th>Cuisines_Feature_5</th>\n",
              "      <th>Cuisines_Feature_6</th>\n",
              "      <th>Cuisines_Feature_7</th>\n",
              "      <th>Cuisines_Feature_8</th>\n",
              "      <th>Restaurant</th>\n",
              "      <th>Average_Cost_Cleaned</th>\n",
              "      <th>Minimum_Order_Cleaned</th>\n",
              "      <th>Rating_Cleaned</th>\n",
              "      <th>Votes_Cleaned</th>\n",
              "      <th>Reviews_Cleaned</th>\n",
              "      <th>Delivery_Time</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>-0.867166</td>\n",
              "      <td>-0.408678</td>\n",
              "      <td>1.683093</td>\n",
              "      <td>-0.161374</td>\n",
              "      <td>-0.714599</td>\n",
              "      <td>1.656380</td>\n",
              "      <td>0.137213</td>\n",
              "      <td>3.865914</td>\n",
              "      <td>7.460013</td>\n",
              "      <td>-0.125106</td>\n",
              "      <td>-0.08579</td>\n",
              "      <td>-0.057042</td>\n",
              "      <td>0.625956</td>\n",
              "      <td>-0.020864</td>\n",
              "      <td>-0.180293</td>\n",
              "      <td>-0.301852</td>\n",
              "      <td>-0.464423</td>\n",
              "      <td>-0.417345</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1.246323</td>\n",
              "      <td>-0.117669</td>\n",
              "      <td>-0.660441</td>\n",
              "      <td>-0.161374</td>\n",
              "      <td>-0.312564</td>\n",
              "      <td>-0.125757</td>\n",
              "      <td>-0.621557</td>\n",
              "      <td>-0.359765</td>\n",
              "      <td>-0.205249</td>\n",
              "      <td>-0.125106</td>\n",
              "      <td>-0.08579</td>\n",
              "      <td>-0.057042</td>\n",
              "      <td>-0.897145</td>\n",
              "      <td>-0.791117</td>\n",
              "      <td>-0.180293</td>\n",
              "      <td>-0.301852</td>\n",
              "      <td>-0.466421</td>\n",
              "      <td>-0.417345</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.242416</td>\n",
              "      <td>-1.669717</td>\n",
              "      <td>-0.660441</td>\n",
              "      <td>-0.161374</td>\n",
              "      <td>-0.129821</td>\n",
              "      <td>1.953402</td>\n",
              "      <td>0.534663</td>\n",
              "      <td>-0.359765</td>\n",
              "      <td>-0.205249</td>\n",
              "      <td>-0.125106</td>\n",
              "      <td>-0.08579</td>\n",
              "      <td>-0.057042</td>\n",
              "      <td>-1.467013</td>\n",
              "      <td>-0.405990</td>\n",
              "      <td>-0.180293</td>\n",
              "      <td>-0.035808</td>\n",
              "      <td>-0.290596</td>\n",
              "      <td>-0.326311</td>\n",
              "      <td>65 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1.140649</td>\n",
              "      <td>0.415848</td>\n",
              "      <td>-0.660441</td>\n",
              "      <td>-0.161374</td>\n",
              "      <td>0.637700</td>\n",
              "      <td>1.326354</td>\n",
              "      <td>0.354004</td>\n",
              "      <td>-0.359765</td>\n",
              "      <td>-0.205249</td>\n",
              "      <td>-0.125106</td>\n",
              "      <td>-0.08579</td>\n",
              "      <td>-0.057042</td>\n",
              "      <td>0.451808</td>\n",
              "      <td>0.364263</td>\n",
              "      <td>2.461158</td>\n",
              "      <td>0.230235</td>\n",
              "      <td>-0.136749</td>\n",
              "      <td>-0.098724</td>\n",
              "      <td>30 minutes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.982137</td>\n",
              "      <td>-0.602684</td>\n",
              "      <td>2.580618</td>\n",
              "      <td>-0.161374</td>\n",
              "      <td>-1.043537</td>\n",
              "      <td>-0.620795</td>\n",
              "      <td>-0.621557</td>\n",
              "      <td>-0.359765</td>\n",
              "      <td>-0.205249</td>\n",
              "      <td>-0.125106</td>\n",
              "      <td>-0.08579</td>\n",
              "      <td>-0.057042</td>\n",
              "      <td>0.538284</td>\n",
              "      <td>-0.020864</td>\n",
              "      <td>2.461158</td>\n",
              "      <td>-1.099981</td>\n",
              "      <td>0.552564</td>\n",
              "      <td>0.391462</td>\n",
              "      <td>65 minutes</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Location_Feature_1  Location_Feature_2  ...  Reviews_Cleaned  Delivery_Time\n",
              "0           -0.867166           -0.408678  ...        -0.417345     30 minutes\n",
              "1            1.246323           -0.117669  ...        -0.417345     30 minutes\n",
              "2            0.242416           -1.669717  ...        -0.326311     65 minutes\n",
              "3            1.140649            0.415848  ...        -0.098724     30 minutes\n",
              "4            0.982137           -0.602684  ...         0.391462     65 minutes\n",
              "\n",
              "[5 rows x 19 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 75
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "mF9OMgtMgKRt",
        "outputId": "e3487516-6633-45f8-f205-c41635fe51c8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 215
        }
      },
      "source": [
        "test_sample.head()"
      ],
      "execution_count": 76,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Location_Feature_1</th>\n",
              "      <th>Location_Feature_2</th>\n",
              "      <th>Location_Feature_3</th>\n",
              "      <th>Location_Feature_4</th>\n",
              "      <th>Cuisines_Feature_1</th>\n",
              "      <th>Cuisines_Feature_2</th>\n",
              "      <th>Cuisines_Feature_3</th>\n",
              "      <th>Cuisines_Feature_4</th>\n",
              "      <th>Cuisines_Feature_5</th>\n",
              "      <th>Cuisines_Feature_6</th>\n",
              "      <th>Cuisines_Feature_7</th>\n",
              "      <th>Cuisines_Feature_8</th>\n",
              "      <th>Restaurant</th>\n",
              "      <th>Average_Cost_Cleaned</th>\n",
              "      <th>Minimum_Order_Cleaned</th>\n",
              "      <th>Rating_Cleaned</th>\n",
              "      <th>Votes_Cleaned</th>\n",
              "      <th>Reviews_Cleaned</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.083713</td>\n",
              "      <td>1.243494</td>\n",
              "      <td>-0.479103</td>\n",
              "      <td>0.871523</td>\n",
              "      <td>0.809765</td>\n",
              "      <td>-0.204497</td>\n",
              "      <td>-0.346423</td>\n",
              "      <td>-0.351099</td>\n",
              "      <td>-0.196822</td>\n",
              "      <td>-0.12173</td>\n",
              "      <td>-0.082445</td>\n",
              "      <td>-0.042516</td>\n",
              "      <td>-0.897086</td>\n",
              "      <td>1.350471</td>\n",
              "      <td>-0.177278</td>\n",
              "      <td>1.612406</td>\n",
              "      <td>0.276837</td>\n",
              "      <td>0.428327</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.083713</td>\n",
              "      <td>1.243494</td>\n",
              "      <td>-0.479103</td>\n",
              "      <td>0.871523</td>\n",
              "      <td>-1.302905</td>\n",
              "      <td>0.628995</td>\n",
              "      <td>-0.605296</td>\n",
              "      <td>-0.351099</td>\n",
              "      <td>-0.196822</td>\n",
              "      <td>-0.12173</td>\n",
              "      <td>-0.082445</td>\n",
              "      <td>-0.042516</td>\n",
              "      <td>1.096904</td>\n",
              "      <td>-0.833142</td>\n",
              "      <td>-0.177278</td>\n",
              "      <td>0.029586</td>\n",
              "      <td>0.029087</td>\n",
              "      <td>0.035125</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1.143599</td>\n",
              "      <td>0.416451</td>\n",
              "      <td>-0.673221</td>\n",
              "      <td>-0.151585</td>\n",
              "      <td>-0.746940</td>\n",
              "      <td>-1.104668</td>\n",
              "      <td>-0.605296</td>\n",
              "      <td>-0.351099</td>\n",
              "      <td>-0.196822</td>\n",
              "      <td>-0.12173</td>\n",
              "      <td>-0.082445</td>\n",
              "      <td>-0.042516</td>\n",
              "      <td>-0.101583</td>\n",
              "      <td>-0.833142</td>\n",
              "      <td>-0.177278</td>\n",
              "      <td>-0.006736</td>\n",
              "      <td>-0.411358</td>\n",
              "      <td>-0.377352</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>-1.665097</td>\n",
              "      <td>0.367801</td>\n",
              "      <td>-0.236455</td>\n",
              "      <td>-0.151585</td>\n",
              "      <td>0.513250</td>\n",
              "      <td>1.362467</td>\n",
              "      <td>0.393217</td>\n",
              "      <td>1.259565</td>\n",
              "      <td>7.241203</td>\n",
              "      <td>-0.12173</td>\n",
              "      <td>-0.082445</td>\n",
              "      <td>-0.042516</td>\n",
              "      <td>0.278454</td>\n",
              "      <td>0.040303</td>\n",
              "      <td>-0.177278</td>\n",
              "      <td>-0.006736</td>\n",
              "      <td>-0.347833</td>\n",
              "      <td>-0.311818</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1.143599</td>\n",
              "      <td>0.416451</td>\n",
              "      <td>-0.673221</td>\n",
              "      <td>-0.151585</td>\n",
              "      <td>-0.932262</td>\n",
              "      <td>-0.037799</td>\n",
              "      <td>-0.605296</td>\n",
              "      <td>-0.351099</td>\n",
              "      <td>-0.196822</td>\n",
              "      <td>-0.12173</td>\n",
              "      <td>-0.082445</td>\n",
              "      <td>-0.042516</td>\n",
              "      <td>-0.715119</td>\n",
              "      <td>-0.396419</td>\n",
              "      <td>-0.177278</td>\n",
              "      <td>-1.895735</td>\n",
              "      <td>-0.407123</td>\n",
              "      <td>-0.385062</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Location_Feature_1  Location_Feature_2  ...  Votes_Cleaned  Reviews_Cleaned\n",
              "0            0.083713            1.243494  ...       0.276837         0.428327\n",
              "1            0.083713            1.243494  ...       0.029087         0.035125\n",
              "2            1.143599            0.416451  ...      -0.411358        -0.377352\n",
              "3           -1.665097            0.367801  ...      -0.347833        -0.311818\n",
              "4            1.143599            0.416451  ...      -0.407123        -0.385062\n",
              "\n",
              "[5 rows x 18 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 76
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "cVLi3tWF77GQ"
      },
      "source": [
        "##Modeling"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "r7mSn15PcLBy"
      },
      "source": [
        "Finally, we are ready for modeling. We will split the training set into training and validation sets.\n",
        "\n",
        "We will then use the training set to train and validation set to test the performance of the model.\n",
        "\n",
        "Finally we will use the given test set for predicting.\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "GyvnZnyAcmTF",
        "colab": {}
      },
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "train, val = train_test_split(train_sample, test_size = 0.1, random_state = 123)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "moR5oT7H8Gj2",
        "colab": {}
      },
      "source": [
        "X_train = train[cols[:-1]]\n",
        "Y_train = train[cols[-1]]\n",
        "\n",
        "X_Val = val[cols[:-1]]\n",
        "Y_Val = val[cols[-1]]\n",
        "\n",
        "X_test = test_sample[cols[:-1]]"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "nsciW_cU7ak5",
        "outputId": "8e442d4e-cb7d-4aed-b7ae-7acbf11d8694",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 140
        }
      },
      "source": [
        "from xgboost import XGBClassifier\n",
        "\n",
        "xgb = XGBClassifier()\n",
        "\n",
        "xgb.fit(X_train,Y_train)"
      ],
      "execution_count": 79,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n",
              "              colsample_bynode=1, colsample_bytree=1, gamma=0,\n",
              "              learning_rate=0.1, max_delta_step=0, max_depth=3,\n",
              "              min_child_weight=1, missing=None, n_estimators=100, n_jobs=1,\n",
              "              nthread=None, objective='multi:softprob', random_state=0,\n",
              "              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n",
              "              silent=None, subsample=1, verbosity=1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 79
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab_type": "code",
        "id": "0hBSBM_y76WT",
        "outputId": "ccd83863-a0f8-4ebb-d19f-48265af64416",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "xgb.score(X_Val,Y_Val)"
      ],
      "execution_count": 80,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.7216216216216216"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 80
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "colab_type": "text",
        "id": "fJ6fmF5FiDGi"
      },
      "source": [
        "\n",
        "---\n",
        "\n",
        "This is a baseline model. Fine tuning the model can give better results. Also, tryout different algorithms to find the best."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZNacLwWr6Lpo",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn.tree import DecisionTreeClassifier\n",
        "clf = DecisionTreeClassifier(random_state=0)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rpCQpSlh6Lpr",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "c3e596fa-f1e7-462e-9f84-70111b16ecbf"
      },
      "source": [
        "clf.fit(X_train,Y_train)\n",
        "clf.score(X_Val,Y_Val)"
      ],
      "execution_count": 82,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.6954954954954955"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 82
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "oWy-MjbV6Lpy",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn.ensemble import RandomForestClassifier\n",
        "Rforest = RandomForestClassifier()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8BFDn5Nt6Lp0",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "f8e13d6a-bfe4-4d50-dcfd-d506d7a87187"
      },
      "source": [
        "Rforest.fit(X_train,Y_train)\n",
        "Rforest.score(X_Val,Y_Val)"
      ],
      "execution_count": 84,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.7774774774774775"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 84
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cjYfsDP36Lp3",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import warnings\n",
        "warnings.filterwarnings('ignore')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JaVPuOYV8yRC",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "Predictions = Rforest.predict(X_test)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3DSsS73R9C5k",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "pd.DataFrame(Predictions, columns = ['Delivery_Time']).to_excel(\"/GD/My Drive/Colab Notebooks/Food Delivery/Participants Data/Submission.xlsx\", index = False)"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}