Project_EDA.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FZCAObV12d4h"
      },
      "source": [
        "#Restaurants Recommendation System  "
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "background_save": true
        },
        "collapsed": true,
        "id": "9MugTzyw2d4n"
      },
      "outputs": [],
      "source": [
        "#importing packages\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import scipy as stats\n",
        "%matplotlib inline"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "t6vP6iaw2pvG",
        "outputId": "8c7334b6-f9b5-4ce0-b855-59d032ae96cd"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "FK5jdafN2d4x"
      },
      "outputs": [],
      "source": [
        "#Reading the csv files from all three category\n",
        "#Restaurants\n",
        "chefmozaccepts_df=pd.read_csv('/content/drive/MyDrive/Colab Notebooks/FDS data/project/chefmozaccepts.csv')\n",
        "chefmozcuisine_df=pd.read_csv('/content/drive/MyDrive/Colab Notebooks/FDS data/project/chefmozcuisine.csv')\n",
        "chefmozhours4_df=pd.read_csv('/content/drive/MyDrive/Colab Notebooks/FDS data/project/chefmozhours4.csv')\n",
        "chefmozparking_df=pd.read_csv('/content/drive/MyDrive/Colab Notebooks/FDS data/project/chefmozparking.csv')\n",
        "geoplaces2_df=pd.read_csv('/content/drive/MyDrive/Colab Notebooks/FDS data/project/geoplaces2.csv',encoding='latin-1')\n",
        "#User-Item-Rating\n",
        "rating_final_df=pd.read_csv('/content/drive/MyDrive/Colab Notebooks/FDS data/project/rating_final.csv')\n",
        "#Consumers \n",
        "usercuisine_df=pd.read_csv('/content/drive/MyDrive/Colab Notebooks/FDS data/project/usercuisine.csv')\n",
        "userpayment_df=pd.read_csv('/content/drive/MyDrive/Colab Notebooks/FDS data/project/userpayment.csv')\n",
        "userprofile_df=pd.read_csv('/content/drive/MyDrive/Colab Notebooks/FDS data/project/userprofile.csv')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ayvILW-K2d4y"
      },
      "source": [
        "### Explore the Restaurent files\n",
        "#### chefmozaccepts.csv dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "uRe6GRlp2d42",
        "outputId": "ae469cfe-178a-42c1-ec9a-6518d6ad8a9f"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-ed768a5a-fe67-4ae2-9a8c-bffa6c824a53\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>Rpayment</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>135110</td>\n",
              "      <td>cash</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>135110</td>\n",
              "      <td>VISA</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>135110</td>\n",
              "      <td>MasterCard-Eurocard</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>135110</td>\n",
              "      <td>American_Express</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>135110</td>\n",
              "      <td>bank_debit_cards</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ed768a5a-fe67-4ae2-9a8c-bffa6c824a53')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-ed768a5a-fe67-4ae2-9a8c-bffa6c824a53 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-ed768a5a-fe67-4ae2-9a8c-bffa6c824a53');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID             Rpayment\n",
              "0   135110                 cash\n",
              "1   135110                 VISA\n",
              "2   135110  MasterCard-Eurocard\n",
              "3   135110     American_Express\n",
              "4   135110     bank_debit_cards"
            ]
          },
          "execution_count": 4,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting first five rows\n",
        "chefmozaccepts_df.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Q1Slz8WPPsm8"
      },
      "source": [
        "There are 2 columns in the dataset, Restaurant ID and "
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fZbn1R3d2d40",
        "outputId": "82c8b3e1-d176-4ed4-9428-94cda05d0c41"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(1314, 2)"
            ]
          },
          "execution_count": 5,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting information of shape \n",
        "chefmozaccepts_df.shape"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "r22ainxXWQgx"
      },
      "source": [
        "Total 1314 rows"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "S-QdbkxW2d41",
        "outputId": "2a6e1b17-5d09-432d-a49c-ce6011abdc52"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "placeID     0\n",
              "Rpayment    0\n",
              "dtype: int64"
            ]
          },
          "execution_count": 6,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#checking for null value\n",
        "chefmozaccepts_df.isnull().sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "W5S-g6En2d41",
        "outputId": "51288361-8a36-4755-abc8-7ab3015d85e8"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "placeID      int64\n",
              "Rpayment    object\n",
              "dtype: object"
            ]
          },
          "execution_count": 7,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting dtypes of this columns\n",
        "chefmozaccepts_df.dtypes"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XHu0hJtY2d42",
        "outputId": "f9c7a697-a1af-44c7-fcfb-9542396eac74"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "count     1314\n",
              "unique      12\n",
              "top       cash\n",
              "freq       500\n",
              "Name: Rpayment, dtype: object"
            ]
          },
          "execution_count": 8,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Describe the dataset\n",
        "chefmozaccepts_df['Rpayment'].describe()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "TSNuVFvjWfIg"
      },
      "source": [
        "Most of the restaurants(500) accepts ony cash payments"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vO86h1iO2d42"
      },
      "source": [
        "#### chefmozcuisine.csv dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "EjHjproQ2d45",
        "outputId": "dac5d07e-52b3-4093-bd41-839477fe1dcb"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-15858d71-00dd-4c3d-ac38-597311cce9dc\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>Rcuisine</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>135110</td>\n",
              "      <td>Spanish</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>135109</td>\n",
              "      <td>Italian</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>135107</td>\n",
              "      <td>Latin_American</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>135106</td>\n",
              "      <td>Mexican</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>135105</td>\n",
              "      <td>Fast_Food</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-15858d71-00dd-4c3d-ac38-597311cce9dc')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-15858d71-00dd-4c3d-ac38-597311cce9dc button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-15858d71-00dd-4c3d-ac38-597311cce9dc');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID        Rcuisine\n",
              "0   135110         Spanish\n",
              "1   135109         Italian\n",
              "2   135107  Latin_American\n",
              "3   135106         Mexican\n",
              "4   135105       Fast_Food"
            ]
          },
          "execution_count": 9,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting top five rows of dataset\n",
        "chefmozcuisine_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ck4NFzlJ2d43",
        "outputId": "18677fe7-eda4-4b86-abfc-92d839e731f0"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(916, 2)"
            ]
          },
          "execution_count": 10,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting information of shape and size\n",
        "chefmozcuisine_df.shape"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "gakJF1W8XLg9"
      },
      "source": [
        "total 916 rows of data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MWtK45re2d44",
        "outputId": "512cfd25-a41f-4d98-b4f8-d6a1a8b90812"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "count         916\n",
              "unique         59\n",
              "top       Mexican\n",
              "freq          239\n",
              "Name: Rcuisine, dtype: object"
            ]
          },
          "execution_count": 11,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Describe the dataset\n",
        "chefmozcuisine_df['Rcuisine'].describe()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ACx8MgCXXW1s"
      },
      "source": [
        "Most of the restaurants(239) serve mexican dishes"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "e32KfPCv2d45",
        "outputId": "f00fe6e2-1638-4649-9c33-0fbf0e84ecf5"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "placeID     0\n",
              "Rcuisine    0\n",
              "dtype: int64"
            ]
          },
          "execution_count": 12,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Checking for null value\n",
        "chefmozcuisine_df.isnull().sum()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "KlmLyR9-XhDF"
      },
      "source": [
        "No null values in data"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2Qxy9A3z2d46"
      },
      "source": [
        "#### chefmozhours4.csv dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DMiyf8Hw2d47",
        "outputId": "daf5bd8e-70e1-43b3-dff8-0a9442ed8f8f"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(2339, 3)"
            ]
          },
          "execution_count": 13,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting shape \n",
        "chefmozhours4_df.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "sXkBaTWPY1d2",
        "outputId": "9439369c-31ac-4da7-cb15-24f756498fe8"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-fcc84b7e-7740-473e-89cb-b09b1962807e\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>hours</th>\n",
              "      <th>days</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>135111</td>\n",
              "      <td>00:00-23:30;</td>\n",
              "      <td>Mon;Tue;Wed;Thu;Fri;</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>135111</td>\n",
              "      <td>00:00-23:30;</td>\n",
              "      <td>Sat;</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>135111</td>\n",
              "      <td>00:00-23:30;</td>\n",
              "      <td>Sun;</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>135110</td>\n",
              "      <td>08:00-19:00;</td>\n",
              "      <td>Mon;Tue;Wed;Thu;Fri;</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>135110</td>\n",
              "      <td>00:00-00:00;</td>\n",
              "      <td>Sat;</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-fcc84b7e-7740-473e-89cb-b09b1962807e')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-fcc84b7e-7740-473e-89cb-b09b1962807e button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-fcc84b7e-7740-473e-89cb-b09b1962807e');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID         hours                  days\n",
              "0   135111  00:00-23:30;  Mon;Tue;Wed;Thu;Fri;\n",
              "1   135111  00:00-23:30;                  Sat;\n",
              "2   135111  00:00-23:30;                  Sun;\n",
              "3   135110  08:00-19:00;  Mon;Tue;Wed;Thu;Fri;\n",
              "4   135110  00:00-00:00;                  Sat;"
            ]
          },
          "execution_count": 14,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "chefmozhours4_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FzXdbWe02d47",
        "outputId": "10ebe1df-9c30-44c3-c833-435f590e5958"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "count                     2339\n",
              "unique                       3\n",
              "top       Mon;Tue;Wed;Thu;Fri;\n",
              "freq                       793\n",
              "Name: days, dtype: object"
            ]
          },
          "execution_count": 15,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Describe the dataset\n",
        "chefmozhours4_df['days'].describe()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yDl2juAU2d48",
        "outputId": "f7ae9120-ff46-4180-ab10-f1f966755b0f"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "placeID    0\n",
              "hours      0\n",
              "days       0\n",
              "dtype: int64"
            ]
          },
          "execution_count": 16,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#checking for null value\n",
        "chefmozhours4_df.isnull().sum()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "N0NB420U2d49"
      },
      "source": [
        "#### chefmozparking.csv dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "4baAx_at2d5F",
        "outputId": "1e794d7a-4fcc-4c54-aa35-9a3d326f516b"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-b9d1407e-4883-467d-9f51-d7ad6f3c805a\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>parking_lot</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>135111</td>\n",
              "      <td>public</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>135110</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>135109</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>135108</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>135107</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b9d1407e-4883-467d-9f51-d7ad6f3c805a')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-b9d1407e-4883-467d-9f51-d7ad6f3c805a button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-b9d1407e-4883-467d-9f51-d7ad6f3c805a');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID parking_lot\n",
              "0   135111      public\n",
              "1   135110        none\n",
              "2   135109        none\n",
              "3   135108        none\n",
              "4   135107        none"
            ]
          },
          "execution_count": 17,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting first five rows\n",
        "chefmozparking_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZVxm6KVi2d4-",
        "outputId": "660f0437-c3cf-4e70-dcbb-8d5d61d1b08b"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(702, 2)"
            ]
          },
          "execution_count": 18,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting information of shape \n",
        "chefmozparking_df.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1Kqje2wy2d5E",
        "outputId": "cdf557ee-f23f-49a1-c096-d4773faf4af9"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "count      702\n",
              "unique       7\n",
              "top       none\n",
              "freq       348\n",
              "Name: parking_lot, dtype: object"
            ]
          },
          "execution_count": 19,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Describe the dataset\n",
        "chefmozparking_df['parking_lot'].describe()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "x4wHV1KmIAz-"
      },
      "source": [
        "most of the restaurants(348) does not have a dedicated parking space for the customers."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2MoZXshA2d5F"
      },
      "source": [
        "#### geoplaces2.csv dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 467
        },
        "id": "cyH3Q3b62d5G",
        "outputId": "bb47b6e7-8e64-410d-dba1-3e151b2da58c"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-448fd362-9675-40f2-a60d-b4a7a8c3c9e1\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>latitude</th>\n",
              "      <th>longitude</th>\n",
              "      <th>the_geom_meter</th>\n",
              "      <th>name</th>\n",
              "      <th>address</th>\n",
              "      <th>city</th>\n",
              "      <th>state</th>\n",
              "      <th>country</th>\n",
              "      <th>fax</th>\n",
              "      <th>...</th>\n",
              "      <th>alcohol</th>\n",
              "      <th>smoking_area</th>\n",
              "      <th>dress_code</th>\n",
              "      <th>accessibility</th>\n",
              "      <th>price</th>\n",
              "      <th>url</th>\n",
              "      <th>Rambience</th>\n",
              "      <th>franchise</th>\n",
              "      <th>area</th>\n",
              "      <th>other_services</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>134999</td>\n",
              "      <td>18.915421</td>\n",
              "      <td>-99.184871</td>\n",
              "      <td>0101000020957F000088568DE356715AC138C0A525FC46...</td>\n",
              "      <td>Kiku Cuernavaca</td>\n",
              "      <td>Revolucion</td>\n",
              "      <td>Cuernavaca</td>\n",
              "      <td>Morelos</td>\n",
              "      <td>Mexico</td>\n",
              "      <td>?</td>\n",
              "      <td>...</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>informal</td>\n",
              "      <td>no_accessibility</td>\n",
              "      <td>medium</td>\n",
              "      <td>kikucuernavaca.com.mx</td>\n",
              "      <td>familiar</td>\n",
              "      <td>f</td>\n",
              "      <td>closed</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>132825</td>\n",
              "      <td>22.147392</td>\n",
              "      <td>-100.983092</td>\n",
              "      <td>0101000020957F00001AD016568C4858C1243261274BA5...</td>\n",
              "      <td>puesto de tacos</td>\n",
              "      <td>esquina santos degollado y leon guzman</td>\n",
              "      <td>s.l.p.</td>\n",
              "      <td>s.l.p.</td>\n",
              "      <td>mexico</td>\n",
              "      <td>?</td>\n",
              "      <td>...</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>low</td>\n",
              "      <td>?</td>\n",
              "      <td>familiar</td>\n",
              "      <td>f</td>\n",
              "      <td>open</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>135106</td>\n",
              "      <td>22.149709</td>\n",
              "      <td>-100.976093</td>\n",
              "      <td>0101000020957F0000649D6F21634858C119AE9BF528A3...</td>\n",
              "      <td>El Rincón de San Francisco</td>\n",
              "      <td>Universidad 169</td>\n",
              "      <td>San Luis Potosi</td>\n",
              "      <td>San Luis Potosi</td>\n",
              "      <td>Mexico</td>\n",
              "      <td>?</td>\n",
              "      <td>...</td>\n",
              "      <td>Wine-Beer</td>\n",
              "      <td>only at bar</td>\n",
              "      <td>informal</td>\n",
              "      <td>partially</td>\n",
              "      <td>medium</td>\n",
              "      <td>?</td>\n",
              "      <td>familiar</td>\n",
              "      <td>f</td>\n",
              "      <td>open</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>132667</td>\n",
              "      <td>23.752697</td>\n",
              "      <td>-99.163359</td>\n",
              "      <td>0101000020957F00005D67BCDDED8157C1222A2DC8D84D...</td>\n",
              "      <td>little pizza Emilio Portes Gil</td>\n",
              "      <td>calle emilio portes gil</td>\n",
              "      <td>victoria</td>\n",
              "      <td>tamaulipas</td>\n",
              "      <td>?</td>\n",
              "      <td>?</td>\n",
              "      <td>...</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>low</td>\n",
              "      <td>?</td>\n",
              "      <td>familiar</td>\n",
              "      <td>t</td>\n",
              "      <td>closed</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>132613</td>\n",
              "      <td>23.752903</td>\n",
              "      <td>-99.165076</td>\n",
              "      <td>0101000020957F00008EBA2D06DC8157C194E03B7B504E...</td>\n",
              "      <td>carnitas_mata</td>\n",
              "      <td>lic. Emilio portes gil</td>\n",
              "      <td>victoria</td>\n",
              "      <td>Tamaulipas</td>\n",
              "      <td>Mexico</td>\n",
              "      <td>?</td>\n",
              "      <td>...</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>permitted</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>medium</td>\n",
              "      <td>?</td>\n",
              "      <td>familiar</td>\n",
              "      <td>t</td>\n",
              "      <td>closed</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 21 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-448fd362-9675-40f2-a60d-b4a7a8c3c9e1')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-448fd362-9675-40f2-a60d-b4a7a8c3c9e1 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-448fd362-9675-40f2-a60d-b4a7a8c3c9e1');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID   latitude   longitude  \\\n",
              "0   134999  18.915421  -99.184871   \n",
              "1   132825  22.147392 -100.983092   \n",
              "2   135106  22.149709 -100.976093   \n",
              "3   132667  23.752697  -99.163359   \n",
              "4   132613  23.752903  -99.165076   \n",
              "\n",
              "                                      the_geom_meter  \\\n",
              "0  0101000020957F000088568DE356715AC138C0A525FC46...   \n",
              "1  0101000020957F00001AD016568C4858C1243261274BA5...   \n",
              "2  0101000020957F0000649D6F21634858C119AE9BF528A3...   \n",
              "3  0101000020957F00005D67BCDDED8157C1222A2DC8D84D...   \n",
              "4  0101000020957F00008EBA2D06DC8157C194E03B7B504E...   \n",
              "\n",
              "                             name                                 address  \\\n",
              "0                 Kiku Cuernavaca                              Revolucion   \n",
              "1                 puesto de tacos  esquina santos degollado y leon guzman   \n",
              "2      El Rincón de San Francisco                         Universidad 169   \n",
              "3  little pizza Emilio Portes Gil                 calle emilio portes gil   \n",
              "4                   carnitas_mata                  lic. Emilio portes gil   \n",
              "\n",
              "              city            state country fax  ...            alcohol  \\\n",
              "0       Cuernavaca          Morelos  Mexico   ?  ...  No_Alcohol_Served   \n",
              "1           s.l.p.           s.l.p.  mexico   ?  ...  No_Alcohol_Served   \n",
              "2  San Luis Potosi  San Luis Potosi  Mexico   ?  ...          Wine-Beer   \n",
              "3        victoria        tamaulipas       ?   ?  ...  No_Alcohol_Served   \n",
              "4         victoria       Tamaulipas  Mexico   ?  ...  No_Alcohol_Served   \n",
              "\n",
              "  smoking_area dress_code     accessibility   price                    url  \\\n",
              "0         none   informal  no_accessibility  medium  kikucuernavaca.com.mx   \n",
              "1         none   informal        completely     low                      ?   \n",
              "2  only at bar   informal         partially  medium                      ?   \n",
              "3         none   informal        completely     low                      ?   \n",
              "4    permitted   informal        completely  medium                      ?   \n",
              "\n",
              "  Rambience franchise    area other_services  \n",
              "0  familiar         f  closed           none  \n",
              "1  familiar         f    open           none  \n",
              "2  familiar         f    open           none  \n",
              "3  familiar         t  closed           none  \n",
              "4  familiar         t  closed           none  \n",
              "\n",
              "[5 rows x 21 columns]"
            ]
          },
          "execution_count": 20,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting Top five rows\n",
        "geoplaces2_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lg_pjko32d5G",
        "outputId": "5e2ac5b1-14aa-481a-b383-dc7593ef44b4"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "placeID           0\n",
              "latitude          0\n",
              "longitude         0\n",
              "the_geom_meter    0\n",
              "name              0\n",
              "address           0\n",
              "city              0\n",
              "state             0\n",
              "country           0\n",
              "fax               0\n",
              "zip               0\n",
              "alcohol           0\n",
              "smoking_area      0\n",
              "dress_code        0\n",
              "accessibility     0\n",
              "price             0\n",
              "url               0\n",
              "Rambience         0\n",
              "franchise         0\n",
              "area              0\n",
              "other_services    0\n",
              "dtype: int64"
            ]
          },
          "execution_count": 21,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Check for null value\n",
        "geoplaces2_df.isnull().sum()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OK95tb9_N5HJ"
      },
      "source": [
        "No null values in the data, but on observing we found that there were ? instead of null values."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aO4tpCpF2d5G",
        "outputId": "07be68c6-eed4-4bba-a9f2-d6914dfa5c3f"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(130, 21)"
            ]
          },
          "execution_count": 22,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting information of shape\n",
        "geoplaces2_df.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4vvHyKZq2d5H",
        "outputId": "881e9afe-63d9-49c6-deab-7cebc312e8a1"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "the_geom_meter 0\n",
            "name 0\n",
            "address 27\n",
            "city 18\n",
            "state 18\n",
            "country 28\n",
            "fax 130\n",
            "zip 74\n",
            "alcohol 0\n",
            "smoking_area 0\n",
            "dress_code 0\n",
            "accessibility 0\n",
            "price 0\n",
            "url 116\n",
            "Rambience 0\n",
            "franchise 0\n",
            "area 0\n",
            "other_services 0\n"
          ]
        }
      ],
      "source": [
        "#Print the column name with total number of unknown value ('\\?')\n",
        "#str.contains(' \\?') -String into it contains unknown values\n",
        "for col in geoplaces2_df.columns:\n",
        "    if geoplaces2_df[col].dtype == object:         \n",
        "            print(col, (geoplaces2_df[col].str.contains('\\?') == True).sum()) "
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "so7Mgkl22d5H"
      },
      "outputs": [],
      "source": [
        "#Taking unknown value ' ?' column as another parameter\n",
        "columns_with_na_vals= ['address','city','state','country','fax','zip','url']"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "IrXlRojY2d5H"
      },
      "outputs": [],
      "source": [
        "#Replace the '\\?' value with nan to all columns\n",
        "for col in columns_with_na_vals:\n",
        "    geoplaces2_df[col] = (geoplaces2_df[col].replace({'?': np.NaN})) "
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 467
        },
        "id": "wwLDHDhY2d5I",
        "outputId": "8b62c07d-6523-4b2a-e213-b68e0b1c8fc5"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-5b84094e-585d-4728-952e-26accab62212\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>latitude</th>\n",
              "      <th>longitude</th>\n",
              "      <th>the_geom_meter</th>\n",
              "      <th>name</th>\n",
              "      <th>address</th>\n",
              "      <th>city</th>\n",
              "      <th>state</th>\n",
              "      <th>country</th>\n",
              "      <th>fax</th>\n",
              "      <th>...</th>\n",
              "      <th>alcohol</th>\n",
              "      <th>smoking_area</th>\n",
              "      <th>dress_code</th>\n",
              "      <th>accessibility</th>\n",
              "      <th>price</th>\n",
              "      <th>url</th>\n",
              "      <th>Rambience</th>\n",
              "      <th>franchise</th>\n",
              "      <th>area</th>\n",
              "      <th>other_services</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>134999</td>\n",
              "      <td>18.915421</td>\n",
              "      <td>-99.184871</td>\n",
              "      <td>0101000020957F000088568DE356715AC138C0A525FC46...</td>\n",
              "      <td>Kiku Cuernavaca</td>\n",
              "      <td>Revolucion</td>\n",
              "      <td>Cuernavaca</td>\n",
              "      <td>Morelos</td>\n",
              "      <td>Mexico</td>\n",
              "      <td>NaN</td>\n",
              "      <td>...</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>informal</td>\n",
              "      <td>no_accessibility</td>\n",
              "      <td>medium</td>\n",
              "      <td>kikucuernavaca.com.mx</td>\n",
              "      <td>familiar</td>\n",
              "      <td>f</td>\n",
              "      <td>closed</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>132825</td>\n",
              "      <td>22.147392</td>\n",
              "      <td>-100.983092</td>\n",
              "      <td>0101000020957F00001AD016568C4858C1243261274BA5...</td>\n",
              "      <td>puesto de tacos</td>\n",
              "      <td>esquina santos degollado y leon guzman</td>\n",
              "      <td>s.l.p.</td>\n",
              "      <td>s.l.p.</td>\n",
              "      <td>mexico</td>\n",
              "      <td>NaN</td>\n",
              "      <td>...</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>low</td>\n",
              "      <td>NaN</td>\n",
              "      <td>familiar</td>\n",
              "      <td>f</td>\n",
              "      <td>open</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>135106</td>\n",
              "      <td>22.149709</td>\n",
              "      <td>-100.976093</td>\n",
              "      <td>0101000020957F0000649D6F21634858C119AE9BF528A3...</td>\n",
              "      <td>El Rincón de San Francisco</td>\n",
              "      <td>Universidad 169</td>\n",
              "      <td>San Luis Potosi</td>\n",
              "      <td>San Luis Potosi</td>\n",
              "      <td>Mexico</td>\n",
              "      <td>NaN</td>\n",
              "      <td>...</td>\n",
              "      <td>Wine-Beer</td>\n",
              "      <td>only at bar</td>\n",
              "      <td>informal</td>\n",
              "      <td>partially</td>\n",
              "      <td>medium</td>\n",
              "      <td>NaN</td>\n",
              "      <td>familiar</td>\n",
              "      <td>f</td>\n",
              "      <td>open</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>132667</td>\n",
              "      <td>23.752697</td>\n",
              "      <td>-99.163359</td>\n",
              "      <td>0101000020957F00005D67BCDDED8157C1222A2DC8D84D...</td>\n",
              "      <td>little pizza Emilio Portes Gil</td>\n",
              "      <td>calle emilio portes gil</td>\n",
              "      <td>victoria</td>\n",
              "      <td>tamaulipas</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>...</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>low</td>\n",
              "      <td>NaN</td>\n",
              "      <td>familiar</td>\n",
              "      <td>t</td>\n",
              "      <td>closed</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>132613</td>\n",
              "      <td>23.752903</td>\n",
              "      <td>-99.165076</td>\n",
              "      <td>0101000020957F00008EBA2D06DC8157C194E03B7B504E...</td>\n",
              "      <td>carnitas_mata</td>\n",
              "      <td>lic. Emilio portes gil</td>\n",
              "      <td>victoria</td>\n",
              "      <td>Tamaulipas</td>\n",
              "      <td>Mexico</td>\n",
              "      <td>NaN</td>\n",
              "      <td>...</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>permitted</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>medium</td>\n",
              "      <td>NaN</td>\n",
              "      <td>familiar</td>\n",
              "      <td>t</td>\n",
              "      <td>closed</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 21 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-5b84094e-585d-4728-952e-26accab62212')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-5b84094e-585d-4728-952e-26accab62212 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-5b84094e-585d-4728-952e-26accab62212');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID   latitude   longitude  \\\n",
              "0   134999  18.915421  -99.184871   \n",
              "1   132825  22.147392 -100.983092   \n",
              "2   135106  22.149709 -100.976093   \n",
              "3   132667  23.752697  -99.163359   \n",
              "4   132613  23.752903  -99.165076   \n",
              "\n",
              "                                      the_geom_meter  \\\n",
              "0  0101000020957F000088568DE356715AC138C0A525FC46...   \n",
              "1  0101000020957F00001AD016568C4858C1243261274BA5...   \n",
              "2  0101000020957F0000649D6F21634858C119AE9BF528A3...   \n",
              "3  0101000020957F00005D67BCDDED8157C1222A2DC8D84D...   \n",
              "4  0101000020957F00008EBA2D06DC8157C194E03B7B504E...   \n",
              "\n",
              "                             name                                 address  \\\n",
              "0                 Kiku Cuernavaca                              Revolucion   \n",
              "1                 puesto de tacos  esquina santos degollado y leon guzman   \n",
              "2      El Rincón de San Francisco                         Universidad 169   \n",
              "3  little pizza Emilio Portes Gil                 calle emilio portes gil   \n",
              "4                   carnitas_mata                  lic. Emilio portes gil   \n",
              "\n",
              "              city            state country  fax  ...            alcohol  \\\n",
              "0       Cuernavaca          Morelos  Mexico  NaN  ...  No_Alcohol_Served   \n",
              "1           s.l.p.           s.l.p.  mexico  NaN  ...  No_Alcohol_Served   \n",
              "2  San Luis Potosi  San Luis Potosi  Mexico  NaN  ...          Wine-Beer   \n",
              "3        victoria        tamaulipas     NaN  NaN  ...  No_Alcohol_Served   \n",
              "4         victoria       Tamaulipas  Mexico  NaN  ...  No_Alcohol_Served   \n",
              "\n",
              "  smoking_area dress_code     accessibility   price                    url  \\\n",
              "0         none   informal  no_accessibility  medium  kikucuernavaca.com.mx   \n",
              "1         none   informal        completely     low                    NaN   \n",
              "2  only at bar   informal         partially  medium                    NaN   \n",
              "3         none   informal        completely     low                    NaN   \n",
              "4    permitted   informal        completely  medium                    NaN   \n",
              "\n",
              "  Rambience franchise    area other_services  \n",
              "0  familiar         f  closed           none  \n",
              "1  familiar         f    open           none  \n",
              "2  familiar         f    open           none  \n",
              "3  familiar         t  closed           none  \n",
              "4  familiar         t  closed           none  \n",
              "\n",
              "[5 rows x 21 columns]"
            ]
          },
          "execution_count": 26,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting Top five rows\n",
        "geoplaces2_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "G-l9F3Cb2d5I",
        "outputId": "24a82cf8-ea9c-479b-f7ce-cf248d8aad37"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "placeID             0\n",
              "latitude            0\n",
              "longitude           0\n",
              "the_geom_meter      0\n",
              "name                0\n",
              "address            27\n",
              "city               18\n",
              "state              18\n",
              "country            28\n",
              "fax               130\n",
              "zip                74\n",
              "alcohol             0\n",
              "smoking_area        0\n",
              "dress_code          0\n",
              "accessibility       0\n",
              "price               0\n",
              "url               116\n",
              "Rambience           0\n",
              "franchise           0\n",
              "area                0\n",
              "other_services      0\n",
              "dtype: int64"
            ]
          },
          "execution_count": 27,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Check for null value\n",
        "geoplaces2_df.isnull().sum()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "J0ZQf0QXw44E"
      },
      "source": [
        "Although there are a few null values in the dataset, we dont require those feilds for recommending the restaurant."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "b9IPkD4e2d5I"
      },
      "source": [
        "#### Concatenate All restaurent file together of common column placeID"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "a0Zb1Ate2d5I",
        "outputId": "c565b391-cc81-458b-be95-1cca939fd887"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "938\n"
          ]
        }
      ],
      "source": [
        "#Concatenate All restaurent file together of common column placeID\n",
        "restaurant_all = np.concatenate((chefmozaccepts_df.placeID, chefmozcuisine_df.placeID, chefmozhours4_df.placeID, chefmozparking_df.placeID, geoplaces2_df.placeID))\n",
        "restaurant_all = np.sort(np.unique(restaurant_all) ) # All the unique placeID's\n",
        "print(len(restaurant_all))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7BV3DH4JNa2Q"
      },
      "source": [
        "Inner Join - We have data having 938 unique restaurants\n",
        "We concatenated all restaurant files according to their placeID, it will give all common placeID which is present in all five .csv file. Finally, we get total 938 placeID which is unique."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EwiuSrkrFpJZ"
      },
      "source": [
        "Aditi part begins"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fm440YNx2d5J"
      },
      "source": [
        "### Explore the user item rating files\n",
        "#### rating_final.csv "
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "Q6-E-8ZU2d5L",
        "outputId": "e35da167-0e7e-4c25-a612-0bfdee476524"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-99d381c4-5e7f-443f-ac8e-71762cbc1b91\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>userID</th>\n",
              "      <th>placeID</th>\n",
              "      <th>rating</th>\n",
              "      <th>food_rating</th>\n",
              "      <th>service_rating</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>U1077</td>\n",
              "      <td>135085</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>U1077</td>\n",
              "      <td>135038</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>U1077</td>\n",
              "      <td>132825</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>U1077</td>\n",
              "      <td>135060</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>U1068</td>\n",
              "      <td>135104</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-99d381c4-5e7f-443f-ac8e-71762cbc1b91')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-99d381c4-5e7f-443f-ac8e-71762cbc1b91 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-99d381c4-5e7f-443f-ac8e-71762cbc1b91');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "  userID  placeID  rating  food_rating  service_rating\n",
              "0  U1077   135085       2            2               2\n",
              "1  U1077   135038       2            2               1\n",
              "2  U1077   132825       2            2               2\n",
              "3  U1077   135060       1            2               2\n",
              "4  U1068   135104       1            1               2"
            ]
          },
          "execution_count": 29,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Top five rows information\n",
        "rating_final_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qUNPAvoo2d5K",
        "outputId": "10420462-9646-488e-f1bd-4df7e8cf03e4"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(1161, 5)"
            ]
          },
          "execution_count": 30,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting information of shape \n",
        "rating_final_df.shape"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6n5GZlV2yj0h"
      },
      "source": [
        "There are 1161 number of rows in the dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2NmD-PTG2d5K",
        "outputId": "12aa73e8-fbc4-42b5-8bec-007cebc5a72c"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "userID            0\n",
              "placeID           0\n",
              "rating            0\n",
              "food_rating       0\n",
              "service_rating    0\n",
              "dtype: int64"
            ]
          },
          "execution_count": 31,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Checking for null values\n",
        "rating_final_df.isnull().sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 297
        },
        "id": "J1x8OwRY2d5K",
        "outputId": "e771894c-4211-4e5c-b174-9deea48a5f64"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-04af7e6d-1913-4fa9-8e3d-e105384d9a24\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>rating</th>\n",
              "      <th>food_rating</th>\n",
              "      <th>service_rating</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>1161.000000</td>\n",
              "      <td>1161.000000</td>\n",
              "      <td>1161.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>1.199828</td>\n",
              "      <td>1.215332</td>\n",
              "      <td>1.090439</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>0.773282</td>\n",
              "      <td>0.792294</td>\n",
              "      <td>0.790844</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>2.000000</td>\n",
              "      <td>2.000000</td>\n",
              "      <td>2.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>2.000000</td>\n",
              "      <td>2.000000</td>\n",
              "      <td>2.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-04af7e6d-1913-4fa9-8e3d-e105384d9a24')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-04af7e6d-1913-4fa9-8e3d-e105384d9a24 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-04af7e6d-1913-4fa9-8e3d-e105384d9a24');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "            rating  food_rating  service_rating\n",
              "count  1161.000000  1161.000000     1161.000000\n",
              "mean      1.199828     1.215332        1.090439\n",
              "std       0.773282     0.792294        0.790844\n",
              "min       0.000000     0.000000        0.000000\n",
              "25%       1.000000     1.000000        0.000000\n",
              "50%       1.000000     1.000000        1.000000\n",
              "75%       2.000000     2.000000        2.000000\n",
              "max       2.000000     2.000000        2.000000"
            ]
          },
          "execution_count": 32,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Describe the dataset\n",
        "rating_final_df[['rating','food_rating','service_rating']].describe()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SO2hhATd2d5L",
        "outputId": "011608de-b8fa-4eae-aefb-25445d93c6b9"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "130"
            ]
          },
          "execution_count": 33,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#The total number of restaurent having rating value\n",
        "len(rating_final_df.placeID.unique())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EpuGZDrH2d5L",
        "outputId": "40c37125-325d-4829-8d50-ec1befd5337d"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "138"
            ]
          },
          "execution_count": 34,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#The total number of users who gave rating\n",
        "len(rating_final_df.userID.unique())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 384
        },
        "id": "FCFr2dha5WIG",
        "outputId": "88a5e566-07fd-40b1-e928-ae9c37b1724b"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 2 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "import matplotlib.pyplot as mp\n",
        "import seaborn as sns\n",
        "mp.rcParams[\"figure.figsize\"] = (5,5)\n",
        "dataplot = sns.heatmap(rating_final_df.corr(), cmap=\"PiYG\", annot=True)\n",
        "mp.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 337
        },
        "id": "_id_MmaU2d5M",
        "outputId": "d657800c-05dd-4d30-d7d5-546a9281f1f0"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f0fdf261690>"
            ]
          },
          "execution_count": 36,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Another way to plot a histogram of rating is shown below\n",
        "rating_final_df['rating'].hist(bins=50)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 337
        },
        "id": "7mn6ZWQT2d5M",
        "outputId": "123e2f74-a2aa-42c5-e4fa-e45598f9f980"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f0fdf1093d0>"
            ]
          },
          "execution_count": 37,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Another way to plot a histogram of food_rating is shown below\n",
        "rating_final_df['food_rating'].hist(bins=50)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 337
        },
        "id": "LzuXHRML2d5M",
        "outputId": "e6415b85-141c-475c-8d99-23a135824dc9"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f0fdf015e90>"
            ]
          },
          "execution_count": 38,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Another way to plot a histogram of service_rating is shown below\n",
        "rating_final_df['service_rating'].hist(bins=50)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NnBAwgLj2d5N"
      },
      "source": [
        "### Explore the Consumers files\n",
        "#### usercuisine.csv file"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 285
        },
        "id": "celsnBzp2d5O",
        "outputId": "37eb2d37-6793-4547-85fb-92c24d006f75"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-4bb71de7-7bf0-428e-9425-3b867b5e3078\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>userID</th>\n",
              "      <th>Rcuisine</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>U1001</td>\n",
              "      <td>American</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>U1002</td>\n",
              "      <td>Mexican</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>U1003</td>\n",
              "      <td>Mexican</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>U1004</td>\n",
              "      <td>Bakery</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>U1004</td>\n",
              "      <td>Breakfast-Brunch</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4bb71de7-7bf0-428e-9425-3b867b5e3078')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-4bb71de7-7bf0-428e-9425-3b867b5e3078 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-4bb71de7-7bf0-428e-9425-3b867b5e3078');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "  userID          Rcuisine\n",
              "0  U1001          American\n",
              "1  U1002           Mexican\n",
              "2  U1003           Mexican\n",
              "3  U1004            Bakery\n",
              "4  U1004  Breakfast-Brunch"
            ]
          },
          "execution_count": 39,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting top five rows\n",
        "usercuisine_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dF504FsA2d5N",
        "outputId": "0fd07260-ba43-4d52-e7d0-e996cda39c6b"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(330, 2)"
            ]
          },
          "execution_count": 40,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting information of shape and size\n",
        "usercuisine_df.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kOMSc49M2d5O",
        "outputId": "88f0c107-3edb-4123-9ced-979a5229b2e1"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "userID      0\n",
              "Rcuisine    0\n",
              "dtype: int64"
            ]
          },
          "execution_count": 41,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Checking for null values\n",
        "usercuisine_df.isnull().sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rlewV55V2d5O",
        "outputId": "a7766dca-876c-4aff-9fda-0bdadae63f68"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "count         330\n",
              "unique        103\n",
              "top       Mexican\n",
              "freq           97\n",
              "Name: Rcuisine, dtype: object"
            ]
          },
          "execution_count": 42,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Describe the dataset\n",
        "usercuisine_df['Rcuisine'].describe()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "k-di8MlD2d5P"
      },
      "source": [
        "#### userpayment.csv"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 268
        },
        "id": "Ojtcfy5d2d5Q",
        "outputId": "33d706db-073e-402d-e6dd-ef1fb7b100a8"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-1c26f79f-7524-4552-9a9e-b450f27daa41\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>userID</th>\n",
              "      <th>Upayment</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>U1001</td>\n",
              "      <td>cash</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>U1002</td>\n",
              "      <td>cash</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>U1003</td>\n",
              "      <td>cash</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>U1004</td>\n",
              "      <td>cash</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>U1004</td>\n",
              "      <td>bank_debit_cards</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1c26f79f-7524-4552-9a9e-b450f27daa41')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-1c26f79f-7524-4552-9a9e-b450f27daa41 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-1c26f79f-7524-4552-9a9e-b450f27daa41');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "  userID          Upayment\n",
              "0  U1001              cash\n",
              "1  U1002              cash\n",
              "2  U1003              cash\n",
              "3  U1004              cash\n",
              "4  U1004  bank_debit_cards"
            ]
          },
          "execution_count": 43,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting Top five rows\n",
        "userpayment_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "j4y149KG2d5Q",
        "outputId": "de5a7b91-cff4-4d2d-a4ba-852365b1046e"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(177, 2)"
            ]
          },
          "execution_count": 44,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting information of shape \n",
        "userpayment_df.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nWxX2Akb2d5Q",
        "outputId": "e6289e51-08d7-4b49-a3eb-9709f8baf85e"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "userID      0\n",
              "Upayment    0\n",
              "dtype: int64"
            ]
          },
          "execution_count": 45,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Checking for null values\n",
        "userpayment_df.isnull().sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "P3SXSZ3I2d5Q",
        "outputId": "1815144a-b2b8-42d3-971f-b81dbabf738b"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "count      177\n",
              "unique       5\n",
              "top       cash\n",
              "freq       131\n",
              "Name: Upayment, dtype: object"
            ]
          },
          "execution_count": 46,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Describe the dataset\n",
        "userpayment_df['Upayment'].describe()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "e_kqbT9k2d5R"
      },
      "source": [
        "#### userprofile.csv"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 319
        },
        "id": "mknXYGm82d5S",
        "outputId": "30d0c24c-f861-4f9b-ab31-074cfdade703"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-617e1e84-a411-44a7-b8c0-085f104c70b3\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>userID</th>\n",
              "      <th>latitude</th>\n",
              "      <th>longitude</th>\n",
              "      <th>smoker</th>\n",
              "      <th>drink_level</th>\n",
              "      <th>dress_preference</th>\n",
              "      <th>ambience</th>\n",
              "      <th>transport</th>\n",
              "      <th>marital_status</th>\n",
              "      <th>hijos</th>\n",
              "      <th>birth_year</th>\n",
              "      <th>interest</th>\n",
              "      <th>personality</th>\n",
              "      <th>religion</th>\n",
              "      <th>activity</th>\n",
              "      <th>color</th>\n",
              "      <th>weight</th>\n",
              "      <th>budget</th>\n",
              "      <th>height</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>U1001</td>\n",
              "      <td>22.139997</td>\n",
              "      <td>-100.978803</td>\n",
              "      <td>false</td>\n",
              "      <td>abstemious</td>\n",
              "      <td>informal</td>\n",
              "      <td>family</td>\n",
              "      <td>on foot</td>\n",
              "      <td>single</td>\n",
              "      <td>independent</td>\n",
              "      <td>1989</td>\n",
              "      <td>variety</td>\n",
              "      <td>thrifty-protector</td>\n",
              "      <td>none</td>\n",
              "      <td>student</td>\n",
              "      <td>black</td>\n",
              "      <td>69</td>\n",
              "      <td>medium</td>\n",
              "      <td>1.77</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>U1002</td>\n",
              "      <td>22.150087</td>\n",
              "      <td>-100.983325</td>\n",
              "      <td>false</td>\n",
              "      <td>abstemious</td>\n",
              "      <td>informal</td>\n",
              "      <td>family</td>\n",
              "      <td>public</td>\n",
              "      <td>single</td>\n",
              "      <td>independent</td>\n",
              "      <td>1990</td>\n",
              "      <td>technology</td>\n",
              "      <td>hunter-ostentatious</td>\n",
              "      <td>Catholic</td>\n",
              "      <td>student</td>\n",
              "      <td>red</td>\n",
              "      <td>40</td>\n",
              "      <td>low</td>\n",
              "      <td>1.87</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>U1003</td>\n",
              "      <td>22.119847</td>\n",
              "      <td>-100.946527</td>\n",
              "      <td>false</td>\n",
              "      <td>social drinker</td>\n",
              "      <td>formal</td>\n",
              "      <td>family</td>\n",
              "      <td>public</td>\n",
              "      <td>single</td>\n",
              "      <td>independent</td>\n",
              "      <td>1989</td>\n",
              "      <td>none</td>\n",
              "      <td>hard-worker</td>\n",
              "      <td>Catholic</td>\n",
              "      <td>student</td>\n",
              "      <td>blue</td>\n",
              "      <td>60</td>\n",
              "      <td>low</td>\n",
              "      <td>1.69</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>U1004</td>\n",
              "      <td>18.867000</td>\n",
              "      <td>-99.183000</td>\n",
              "      <td>false</td>\n",
              "      <td>abstemious</td>\n",
              "      <td>informal</td>\n",
              "      <td>family</td>\n",
              "      <td>public</td>\n",
              "      <td>single</td>\n",
              "      <td>independent</td>\n",
              "      <td>1940</td>\n",
              "      <td>variety</td>\n",
              "      <td>hard-worker</td>\n",
              "      <td>none</td>\n",
              "      <td>professional</td>\n",
              "      <td>green</td>\n",
              "      <td>44</td>\n",
              "      <td>medium</td>\n",
              "      <td>1.53</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>U1005</td>\n",
              "      <td>22.183477</td>\n",
              "      <td>-100.959891</td>\n",
              "      <td>false</td>\n",
              "      <td>abstemious</td>\n",
              "      <td>no preference</td>\n",
              "      <td>family</td>\n",
              "      <td>public</td>\n",
              "      <td>single</td>\n",
              "      <td>independent</td>\n",
              "      <td>1992</td>\n",
              "      <td>none</td>\n",
              "      <td>thrifty-protector</td>\n",
              "      <td>Catholic</td>\n",
              "      <td>student</td>\n",
              "      <td>black</td>\n",
              "      <td>65</td>\n",
              "      <td>medium</td>\n",
              "      <td>1.69</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-617e1e84-a411-44a7-b8c0-085f104c70b3')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-617e1e84-a411-44a7-b8c0-085f104c70b3 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-617e1e84-a411-44a7-b8c0-085f104c70b3');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "  userID   latitude   longitude smoker     drink_level dress_preference  \\\n",
              "0  U1001  22.139997 -100.978803  false      abstemious         informal   \n",
              "1  U1002  22.150087 -100.983325  false      abstemious         informal   \n",
              "2  U1003  22.119847 -100.946527  false  social drinker           formal   \n",
              "3  U1004  18.867000  -99.183000  false      abstemious         informal   \n",
              "4  U1005  22.183477 -100.959891  false      abstemious    no preference   \n",
              "\n",
              "  ambience transport marital_status        hijos  birth_year    interest  \\\n",
              "0   family   on foot         single  independent        1989     variety   \n",
              "1   family    public         single  independent        1990  technology   \n",
              "2   family    public         single  independent        1989        none   \n",
              "3   family    public         single  independent        1940     variety   \n",
              "4   family    public         single  independent        1992        none   \n",
              "\n",
              "           personality  religion      activity  color  weight  budget  height  \n",
              "0    thrifty-protector      none       student  black      69  medium    1.77  \n",
              "1  hunter-ostentatious  Catholic       student    red      40     low    1.87  \n",
              "2          hard-worker  Catholic       student   blue      60     low    1.69  \n",
              "3          hard-worker      none  professional  green      44  medium    1.53  \n",
              "4    thrifty-protector  Catholic       student  black      65  medium    1.69  "
            ]
          },
          "execution_count": 47,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting top five rows\n",
        "userprofile_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 237
        },
        "id": "P_YaCBLD2d5S",
        "outputId": "aed1fabe-2ad2-48a8-9b9a-9b341ab0e3cf"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-261aa6b1-d218-4ada-9394-8b63c7e1c219\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>smoker</th>\n",
              "      <th>drink_level</th>\n",
              "      <th>dress_preference</th>\n",
              "      <th>ambience</th>\n",
              "      <th>transport</th>\n",
              "      <th>marital_status</th>\n",
              "      <th>hijos</th>\n",
              "      <th>interest</th>\n",
              "      <th>personality</th>\n",
              "      <th>religion</th>\n",
              "      <th>activity</th>\n",
              "      <th>color</th>\n",
              "      <th>budget</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "      <td>138</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>unique</th>\n",
              "      <td>3</td>\n",
              "      <td>3</td>\n",
              "      <td>5</td>\n",
              "      <td>4</td>\n",
              "      <td>4</td>\n",
              "      <td>4</td>\n",
              "      <td>4</td>\n",
              "      <td>5</td>\n",
              "      <td>4</td>\n",
              "      <td>5</td>\n",
              "      <td>5</td>\n",
              "      <td>8</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>top</th>\n",
              "      <td>false</td>\n",
              "      <td>abstemious</td>\n",
              "      <td>no preference</td>\n",
              "      <td>family</td>\n",
              "      <td>public</td>\n",
              "      <td>single</td>\n",
              "      <td>independent</td>\n",
              "      <td>variety</td>\n",
              "      <td>hard-worker</td>\n",
              "      <td>Catholic</td>\n",
              "      <td>student</td>\n",
              "      <td>blue</td>\n",
              "      <td>medium</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>freq</th>\n",
              "      <td>109</td>\n",
              "      <td>51</td>\n",
              "      <td>53</td>\n",
              "      <td>70</td>\n",
              "      <td>82</td>\n",
              "      <td>122</td>\n",
              "      <td>113</td>\n",
              "      <td>50</td>\n",
              "      <td>61</td>\n",
              "      <td>99</td>\n",
              "      <td>113</td>\n",
              "      <td>45</td>\n",
              "      <td>91</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-261aa6b1-d218-4ada-9394-8b63c7e1c219')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-261aa6b1-d218-4ada-9394-8b63c7e1c219 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-261aa6b1-d218-4ada-9394-8b63c7e1c219');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "       smoker drink_level dress_preference ambience transport marital_status  \\\n",
              "count     138         138              138      138       138            138   \n",
              "unique      3           3                5        4         4              4   \n",
              "top     false  abstemious    no preference   family    public         single   \n",
              "freq      109          51               53       70        82            122   \n",
              "\n",
              "              hijos interest  personality  religion activity color  budget  \n",
              "count           138      138          138       138      138   138     138  \n",
              "unique            4        5            4         5        5     8       4  \n",
              "top     independent  variety  hard-worker  Catholic  student  blue  medium  \n",
              "freq            113       50           61        99      113    45      91  "
            ]
          },
          "execution_count": 48,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Describe the dataset\n",
        "userprofile_df[['smoker', 'drink_level',\n",
        "       'dress_preference', 'ambience', 'transport', 'marital_status', 'hijos',\n",
        "       'interest', 'personality', 'religion', 'activity',\n",
        "       'color','budget']].describe()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "G0jGt3em2d5S",
        "outputId": "40903c3e-9715-4f5d-defc-1e751c57606d"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(138, 19)"
            ]
          },
          "execution_count": 49,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting information of shape \n",
        "userprofile_df.shape"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "oaK513F32d5T"
      },
      "source": [
        "#### combined all user according to their userID"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bkv0EGqjUNqG"
      },
      "source": [
        "Now combine all user of all three .csv file according to their userID and get their unique value, so that it is easy to compare."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sq6tKkek2d5T",
        "outputId": "56feef1d-4232-4527-9c8b-45dba9bc5a71"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "138"
            ]
          },
          "execution_count": 50,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "user_all = np.concatenate((usercuisine_df.userID, userpayment_df.userID, userprofile_df.userID))\n",
        "user_all = np.sort( np.unique(user_all) ) #UserID's of all theree users\n",
        "len(user_all)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "1DqTQ7JUUQeO"
      },
      "source": [
        "There are total 138 users in the database"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "js1uuMq92d5T",
        "outputId": "10b05a3d-63a2-4dbf-9f4a-d9f444b1f0ee"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "array(['userID', 'latitude', 'longitude', 'smoker', 'drink_level',\n",
              "       'dress_preference', 'ambience', 'transport', 'marital_status',\n",
              "       'hijos', 'birth_year', 'interest', 'personality', 'religion',\n",
              "       'activity', 'color', 'weight', 'budget', 'height'], dtype=object)"
            ]
          },
          "execution_count": 51,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Check the column present in user profile\n",
        "userprofile_df.columns.values"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IGauRaRDUadk"
      },
      "source": [
        "On analysis, we found that only\n",
        "\n",
        " 'smoker','drink_level','transport','budget','dress_preference','ambience','activity','interest' are more effective features which mostly effect the results. I will take only these features for further analysis."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1DFO1AM82d5U",
        "outputId": "eb0d2863-1c07-4772-cf20-00f85392f26f"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "false    109\n",
            "true      26\n",
            "?          3\n",
            "Name: smoker, dtype: int64 \n",
            "--------------------------------------\n",
            "\n",
            "abstemious        51\n",
            "casual drinker    47\n",
            "social drinker    40\n",
            "Name: drink_level, dtype: int64 \n",
            "--------------------------------------\n",
            "\n",
            "public       82\n",
            "car owner    35\n",
            "on foot      14\n",
            "?             7\n",
            "Name: transport, dtype: int64 \n",
            "--------------------------------------\n",
            "\n",
            "medium    91\n",
            "low       35\n",
            "?          7\n",
            "high       5\n",
            "Name: budget, dtype: int64 \n",
            "--------------------------------------\n",
            "\n",
            "no preference    53\n",
            "formal           41\n",
            "informal         35\n",
            "?                 5\n",
            "elegant           4\n",
            "Name: dress_preference, dtype: int64 \n",
            "--------------------------------------\n",
            "\n",
            "family      70\n",
            "friends     46\n",
            "solitary    16\n",
            "?            6\n",
            "Name: ambience, dtype: int64 \n",
            "--------------------------------------\n",
            "\n",
            "student          113\n",
            "professional      15\n",
            "?                  7\n",
            "unemployed         2\n",
            "working-class      1\n",
            "Name: activity, dtype: int64 \n",
            "--------------------------------------\n",
            "\n",
            "variety         50\n",
            "technology      36\n",
            "none            30\n",
            "eco-friendly    16\n",
            "retro            6\n",
            "Name: interest, dtype: int64 \n",
            "--------------------------------------\n",
            "\n"
          ]
        }
      ],
      "source": [
        "#Taking some important features from userprofile_df and print their value counts\n",
        "features_user =userprofile_df[['smoker','drink_level','transport','budget','dress_preference','ambience','activity','interest']]\n",
        "#Getting all information about features users\n",
        "for col in features_user.columns.values:\n",
        "        print(features_user[col].value_counts() , \"\\n--------------------------------------\\n\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uFgG1KLbUyFt"
      },
      "source": [
        "Here we see that some values from transport and dress_preference have same category, so we replace those value with common value for analysis purpose."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bI_vb93t2d5U",
        "outputId": "26cacf24-4a50-47cb-f57c-55b7707a9026"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:2: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  \n",
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:3: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  This is separate from the ipykernel package so we can avoid doing imports until\n"
          ]
        }
      ],
      "source": [
        "#Replace some values of column which is similar type\n",
        "features_user['transport'] = features_user['transport'].replace({'public':'no car','on foot':'no car'}) \n",
        "features_user['dress_preference'] = features_user['dress_preference'].replace({'elegant':'formal'})  "
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VmYD3dhQ2d5V",
        "outputId": "82d223a8-db4c-44b8-8509-6af7cdf571e0"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:3: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  This is separate from the ipykernel package so we can avoid doing imports until\n"
          ]
        }
      ],
      "source": [
        "#Replace the '\\?' value with nan to all 'workclass', 'occupation', 'native_country' columns\n",
        "for col in features_user.columns:\n",
        "    features_user[col] = (features_user[col].replace({'?': np.NaN}))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 268
        },
        "id": "Y5IFKrPY2d5V",
        "outputId": "767c4746-d638-4b28-d3ab-a1a38494dabe"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-822411c4-b471-44b0-b968-efba4d10cd3e\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>smoker</th>\n",
              "      <th>drink_level</th>\n",
              "      <th>transport</th>\n",
              "      <th>budget</th>\n",
              "      <th>dress_preference</th>\n",
              "      <th>ambience</th>\n",
              "      <th>activity</th>\n",
              "      <th>interest</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>false</td>\n",
              "      <td>abstemious</td>\n",
              "      <td>no car</td>\n",
              "      <td>medium</td>\n",
              "      <td>informal</td>\n",
              "      <td>family</td>\n",
              "      <td>student</td>\n",
              "      <td>variety</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>false</td>\n",
              "      <td>abstemious</td>\n",
              "      <td>no car</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>family</td>\n",
              "      <td>student</td>\n",
              "      <td>technology</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>false</td>\n",
              "      <td>social drinker</td>\n",
              "      <td>no car</td>\n",
              "      <td>low</td>\n",
              "      <td>formal</td>\n",
              "      <td>family</td>\n",
              "      <td>student</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>false</td>\n",
              "      <td>abstemious</td>\n",
              "      <td>no car</td>\n",
              "      <td>medium</td>\n",
              "      <td>informal</td>\n",
              "      <td>family</td>\n",
              "      <td>professional</td>\n",
              "      <td>variety</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>false</td>\n",
              "      <td>abstemious</td>\n",
              "      <td>no car</td>\n",
              "      <td>medium</td>\n",
              "      <td>no preference</td>\n",
              "      <td>family</td>\n",
              "      <td>student</td>\n",
              "      <td>none</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-822411c4-b471-44b0-b968-efba4d10cd3e')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-822411c4-b471-44b0-b968-efba4d10cd3e button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-822411c4-b471-44b0-b968-efba4d10cd3e');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "  smoker     drink_level transport  budget dress_preference ambience  \\\n",
              "0  false      abstemious    no car  medium         informal   family   \n",
              "1  false      abstemious    no car     low         informal   family   \n",
              "2  false  social drinker    no car     low           formal   family   \n",
              "3  false      abstemious    no car  medium         informal   family   \n",
              "4  false      abstemious    no car  medium    no preference   family   \n",
              "\n",
              "       activity    interest  \n",
              "0       student     variety  \n",
              "1       student  technology  \n",
              "2       student        none  \n",
              "3  professional     variety  \n",
              "4       student        none  "
            ]
          },
          "execution_count": 55,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Drop the row having all value is Nan\n",
        "(features_user.dropna(axis=0, how='all')).head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "9LnHtcG_Y-Ud"
      },
      "outputs": [],
      "source": [
        "features_user.to_csv(r'/content/sample_data/a', index=False)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-EvjBvuE2d5W"
      },
      "source": [
        "#### Plotting graph of some categorical data from user profile using plotly\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vXfNt4qB4c6y",
        "outputId": "2c30b40f-3aa2-4657-e5f1-3397f3768948"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Collecting chart-studio\n",
            "  Downloading chart_studio-1.1.0-py3-none-any.whl (64 kB)\n",
            "\u001b[?25l\r\u001b[K     |█████                           | 10 kB 16.5 MB/s eta 0:00:01\r\u001b[K     |██████████▏                     | 20 kB 8.6 MB/s eta 0:00:01\r\u001b[K     |███████████████▎                | 30 kB 7.5 MB/s eta 0:00:01\r\u001b[K     |████████████████████▍           | 40 kB 6.9 MB/s eta 0:00:01\r\u001b[K     |█████████████████████████▍      | 51 kB 5.0 MB/s eta 0:00:01\r\u001b[K     |██████████████████████████████▌ | 61 kB 5.2 MB/s eta 0:00:01\r\u001b[K     |████████████████████████████████| 64 kB 1.9 MB/s \n",
            "\u001b[?25hCollecting retrying>=1.3.3\n",
            "  Downloading retrying-1.3.3.tar.gz (10 kB)\n",
            "Requirement already satisfied: plotly in /usr/local/lib/python3.7/dist-packages (from chart-studio) (5.5.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.7/dist-packages (from chart-studio) (2.23.0)\n",
            "Requirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from chart-studio) (1.15.0)\n",
            "Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.7/dist-packages (from plotly->chart-studio) (8.0.1)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests->chart-studio) (2.10)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests->chart-studio) (3.0.4)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests->chart-studio) (1.24.3)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests->chart-studio) (2021.10.8)\n",
            "Building wheels for collected packages: retrying\n",
            "  Building wheel for retrying (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for retrying: filename=retrying-1.3.3-py3-none-any.whl size=11447 sha256=14f3126a574dd27dc2b13ea2a0874b8b8fce3c75ad2c6f303de9f79d3a486d32\n",
            "  Stored in directory: /root/.cache/pip/wheels/f9/8d/8d/f6af3f7f9eea3553bc2fe6d53e4b287dad18b06a861ac56ddf\n",
            "Successfully built retrying\n",
            "Installing collected packages: retrying, chart-studio\n",
            "Successfully installed chart-studio-1.1.0 retrying-1.3.3\n"
          ]
        }
      ],
      "source": [
        "!pip install chart-studio"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 37
        },
        "id": "gaYeRmo_2d5W",
        "outputId": "2005ae9d-1258-45e1-ff2a-29bd5fba9345"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "        <script type=\"text/javascript\">\n",
              "        window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
              "        if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
              "        if (typeof require !== 'undefined') {\n",
              "        require.undef(\"plotly\");\n",
              "        requirejs.config({\n",
              "            paths: {\n",
              "                'plotly': ['https://cdn.plot.ly/plotly-2.8.3.min']\n",
              "            }\n",
              "        });\n",
              "        require(['plotly'], function(Plotly) {\n",
              "            window._Plotly = Plotly;\n",
              "        });\n",
              "        }\n",
              "        </script>\n",
              "        "
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "#importing the packeges\n",
        "from IPython.core.interactiveshell import InteractiveShell     #An enhanced, interactive shell for Python\n",
        "#‘all’, ‘last’, ‘last_expr’ or ‘none’, ‘last_expr_or_assign’\n",
        "#specifying which nodes should be run interactively \n",
        "\n",
        "from chart_studio import plotly\n",
        "\n",
        "InteractiveShell.ast_node_interactivity = \"all\"   #Options:\t'all','last','last_expr','none','last_expr_or_assign'\n",
        "\n",
        "import numpy as np # linear algebra\n",
        "import pandas as pd # data processing\n",
        "\n",
        "#Plotly Offline brings interactive Plotly graphs to the offline (local) environment\n",
        "import plotly.offline as py\n",
        "import plotly.figure_factory as ff\n",
        "import plotly.graph_objs as gobj\n",
        "import chart_studio.plotly as plty\n",
        "from plotly.graph_objs import *\n",
        "py.init_notebook_mode(connected=True)  # initiate notebook for offline plot"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "SSgz7gUI2d5W"
      },
      "outputs": [],
      "source": [
        "#Getting some features of categorical data which is important\n",
        "features_user_col=features_user.columns"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "bQmXJRWS2d5X"
      },
      "outputs": [],
      "source": [
        "#Method for plotting \n",
        "\n",
        "def plot_value_counts(col_name,table=False,bar=False):\n",
        "    \n",
        "    values_count = pd.DataFrame(features_user[col_name].value_counts())\n",
        "    values_count.columns = ['count']\n",
        "   \n",
        "    # Converting the index column into value count\n",
        "    values_count[col_name] = [ str(i) for i in values_count.index ]\n",
        "    \n",
        "    # add a column with the percentage of each data point to the sum of all data points\n",
        "    values_count['percent'] = values_count['count'].div(values_count['count'].sum()).multiply(100).round(2)\n",
        "    \n",
        "    # change the order of the columns.\n",
        "    values_count = values_count.reindex([col_name,'count','percent'],axis=1)\n",
        "    values_count.reset_index(drop=True,inplace=True)    \n",
        "    \n",
        "    if bar :\n",
        "        # add a font size for annotations0 which is relevant to the length of the data points.\n",
        "        font_size = 20 - (.25 * len(values_count[col_name]))\n",
        "        \n",
        "        trace0 = gobj.Bar( x = values_count[col_name], y = values_count['count'] )\n",
        "        data_ = gobj.Data( [trace0] )\n",
        "        \n",
        "        annotations0 = [ dict(x = xi,\n",
        "                             y = yi, \n",
        "                             showarrow=False,\n",
        "                             font={'size':font_size},\n",
        "                             text = \"{:,}\".format(yi),\n",
        "                             xanchor='center',\n",
        "                             yanchor='bottom' )\n",
        "                       for xi,yi,_ in values_count.values ]\n",
        "        \n",
        "        annotations1 = [ dict( x = xi,\n",
        "                              y = yi/2,\n",
        "                              showarrow = False,\n",
        "                              text = \"{}%\".format(pi),\n",
        "                              xanchor = 'center',\n",
        "                              yanchor = 'center',\n",
        "                              font = {'color':'yellow'})\n",
        "                         for xi,yi,pi in values_count.values if pi > 10 ]\n",
        "        \n",
        "        annotations = annotations0 + annotations1                       \n",
        "        \n",
        "        layout = gobj.Layout( title = col_name.replace('_',' ').capitalize(),\n",
        "                             titlefont = {'size': 50},\n",
        "                             yaxis = {'title':'count'},\n",
        "                             xaxis = {'type':'category'},\n",
        "                            annotations = annotations  )\n",
        "        figure = gobj.Figure( data = data_, layout = layout )\n",
        "        py.iplot(figure)\n",
        "    \n",
        "    if table : \n",
        "        values_count['count'] = values_count['count'].apply(lambda d : \"{:,}\".format(d))\n",
        "        table = ff.create_table(values_count,index_title=\"race\")      #Creating the table for race\n",
        "        py.iplot(table)\n",
        "    \n",
        "    return values_count"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "piNCanFc2d5X"
      },
      "source": [
        "### Combined Analysis"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "twTjL9PMVYAY"
      },
      "source": [
        "Now we will make a data frame of all 938 restaurant and 138 users for rating purpose. Here initially i'll put all the value of rating of all category (rating,food_rating,service_rating) restaurant-user combination to -1"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "R_WoYPOb2d5Y"
      },
      "outputs": [],
      "source": [
        "#Combined the rating\n",
        "combined_rating = pd.DataFrame(np.zeros((len(restaurant_all),len(user_all)))-1.0,columns=user_all,index=restaurant_all)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "eBb7KE852d5Y"
      },
      "outputs": [],
      "source": [
        "#Assign a food rating\n",
        "food_rating =combined_rating.copy()  "
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "hBSQ84b42d5Y"
      },
      "outputs": [],
      "source": [
        "#Assign a service rating\n",
        "service_rating = combined_rating.copy()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9_U-FlXvVD-U"
      },
      "source": [
        "Now we assign some rating value to those pair of restaurant-user which have some rating in rating_final.csv file and rest rating remain -1."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "46s0i0wQ2d5Z"
      },
      "outputs": [],
      "source": [
        "#Assign a particular value of rating for those user who has given rating\n",
        "for i,j,p,q,r in zip(rating_final_df.placeID, rating_final_df.userID, rating_final_df.rating, rating_final_df.food_rating, \n",
        "                            rating_final_df.service_rating):\n",
        "    combined_rating.loc[i,j] = p\n",
        "    food_rating.loc[i,j] = q\n",
        "    service_rating.loc[i,j] = r"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tgHY_pJSVORi"
      },
      "source": [
        "Now i'll review all rating of user-restaurant combination which having some rating in rating_final.csv file.Now assign 0 for no rating and 1 for rating."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "oL4kJrcH2d5Z"
      },
      "outputs": [],
      "source": [
        "#Rastaurant-user pair rating, 0 means no rating and 1 means yes rating\n",
        "review_rate = pd.DataFrame( np.zeros(combined_rating.shape),columns=user_all,index=restaurant_all)\n",
        "review_rate[combined_rating >= 0] = 1"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "ZKU4BHRO2d5a"
      },
      "outputs": [],
      "source": [
        "# For the different cuisine categories of the restaurants use dummy variable\n",
        "cuisine_res = pd.get_dummies(chefmozcuisine_df,columns=['Rcuisine'])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "8Zs3e_sb2d5a"
      },
      "outputs": [],
      "source": [
        "#Applying groupby on placeID for removing duplicate restaurant ID's\n",
        "cuisine_res = cuisine_res.groupby('placeID',as_index=False).sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 297
        },
        "id": "PxzPy4wN2d5a",
        "outputId": "e9c5a48f-303d-401f-d0b2-db6a7805b538"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-c9e5b0de-e4e6-4c71-a55f-4b896bd298e6\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>Rcuisine_Afghan</th>\n",
              "      <th>Rcuisine_African</th>\n",
              "      <th>Rcuisine_American</th>\n",
              "      <th>Rcuisine_Armenian</th>\n",
              "      <th>Rcuisine_Asian</th>\n",
              "      <th>Rcuisine_Bagels</th>\n",
              "      <th>Rcuisine_Bakery</th>\n",
              "      <th>Rcuisine_Bar</th>\n",
              "      <th>Rcuisine_Bar_Pub_Brewery</th>\n",
              "      <th>...</th>\n",
              "      <th>Rcuisine_Soup</th>\n",
              "      <th>Rcuisine_Southern</th>\n",
              "      <th>Rcuisine_Southwestern</th>\n",
              "      <th>Rcuisine_Spanish</th>\n",
              "      <th>Rcuisine_Steaks</th>\n",
              "      <th>Rcuisine_Sushi</th>\n",
              "      <th>Rcuisine_Thai</th>\n",
              "      <th>Rcuisine_Turkish</th>\n",
              "      <th>Rcuisine_Vegetarian</th>\n",
              "      <th>Rcuisine_Vietnamese</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>132001</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>132002</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>132003</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>132004</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>132005</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 60 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c9e5b0de-e4e6-4c71-a55f-4b896bd298e6')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-c9e5b0de-e4e6-4c71-a55f-4b896bd298e6 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-c9e5b0de-e4e6-4c71-a55f-4b896bd298e6');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID  Rcuisine_Afghan  Rcuisine_African  Rcuisine_American  \\\n",
              "0   132001                0                 0                  0   \n",
              "1   132002                0                 0                  0   \n",
              "2   132003                0                 0                  0   \n",
              "3   132004                0                 0                  0   \n",
              "4   132005                0                 0                  0   \n",
              "\n",
              "   Rcuisine_Armenian  Rcuisine_Asian  Rcuisine_Bagels  Rcuisine_Bakery  \\\n",
              "0                  0               0                0                0   \n",
              "1                  0               0                0                0   \n",
              "2                  0               0                0                0   \n",
              "3                  0               0                0                0   \n",
              "4                  0               0                0                0   \n",
              "\n",
              "   Rcuisine_Bar  Rcuisine_Bar_Pub_Brewery  ...  Rcuisine_Soup  \\\n",
              "0             0                         0  ...              0   \n",
              "1             0                         0  ...              0   \n",
              "2             0                         0  ...              0   \n",
              "3             0                         0  ...              0   \n",
              "4             0                         0  ...              0   \n",
              "\n",
              "   Rcuisine_Southern  Rcuisine_Southwestern  Rcuisine_Spanish  \\\n",
              "0                  0                      0                 0   \n",
              "1                  0                      0                 0   \n",
              "2                  0                      0                 0   \n",
              "3                  0                      0                 0   \n",
              "4                  0                      0                 0   \n",
              "\n",
              "   Rcuisine_Steaks  Rcuisine_Sushi  Rcuisine_Thai  Rcuisine_Turkish  \\\n",
              "0                0               0              0                 0   \n",
              "1                0               0              0                 0   \n",
              "2                0               0              0                 0   \n",
              "3                0               0              0                 0   \n",
              "4                0               0              0                 0   \n",
              "\n",
              "   Rcuisine_Vegetarian  Rcuisine_Vietnamese  \n",
              "0                    0                    0  \n",
              "1                    0                    0  \n",
              "2                    0                    0  \n",
              "3                    0                    0  \n",
              "4                    0                    0  \n",
              "\n",
              "[5 rows x 60 columns]"
            ]
          },
          "execution_count": 68,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "cuisine_res.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "DF2DYzIA2d5a"
      },
      "outputs": [],
      "source": [
        "#For different cuisine categories of the restaurants use dummy variable\n",
        "parking_res = pd.get_dummies(chefmozparking_df,columns=['parking_lot'])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "j1TeTT7B2d5b"
      },
      "outputs": [],
      "source": [
        "#Applying groupby on placeID for removing duplicate restaurant ID's\n",
        "parking_res= parking_res.groupby('placeID',as_index=False).sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 285
        },
        "id": "OxSA_qu22d5b",
        "outputId": "85ea6e5c-d0be-4994-f894-047af0479d02"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-9de3c35e-6441-4fb5-b577-7663c9cc94c7\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>parking_lot_fee</th>\n",
              "      <th>parking_lot_none</th>\n",
              "      <th>parking_lot_public</th>\n",
              "      <th>parking_lot_street</th>\n",
              "      <th>parking_lot_valet parking</th>\n",
              "      <th>parking_lot_validated parking</th>\n",
              "      <th>parking_lot_yes</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>132012</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>132023</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>132024</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>132026</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>132030</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9de3c35e-6441-4fb5-b577-7663c9cc94c7')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-9de3c35e-6441-4fb5-b577-7663c9cc94c7 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-9de3c35e-6441-4fb5-b577-7663c9cc94c7');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID  parking_lot_fee  parking_lot_none  parking_lot_public  \\\n",
              "0   132012                0                 0                   1   \n",
              "1   132023                1                 0                   1   \n",
              "2   132024                0                 0                   0   \n",
              "3   132026                1                 0                   0   \n",
              "4   132030                0                 0                   0   \n",
              "\n",
              "   parking_lot_street  parking_lot_valet parking  \\\n",
              "0                   1                          0   \n",
              "1                   0                          0   \n",
              "2                   1                          0   \n",
              "3                   0                          0   \n",
              "4                   1                          0   \n",
              "\n",
              "   parking_lot_validated parking  parking_lot_yes  \n",
              "0                              0                0  \n",
              "1                              0                0  \n",
              "2                              0                0  \n",
              "3                              0                0  \n",
              "4                              0                0  "
            ]
          },
          "execution_count": 71,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "parking_res.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "15rTnJPm2d5b"
      },
      "outputs": [],
      "source": [
        "# Taking some features which are more relevant\n",
        "features_res = geoplaces2_df[['placeID','alcohol','smoking_area','Rambience','other_services','price','dress_code',\n",
        "                    'accessibility','area']]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 268
        },
        "id": "CANP-BA02d5b",
        "outputId": "ce51adf2-3a2d-4b51-e201-7265c408b59c"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-a73b1495-c6b0-4662-91de-5c182f712eac\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>132001</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>132002</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>132003</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>132004</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>132005</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a73b1495-c6b0-4662-91de-5c182f712eac')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-a73b1495-c6b0-4662-91de-5c182f712eac button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-a73b1495-c6b0-4662-91de-5c182f712eac');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID\n",
              "0   132001\n",
              "1   132002\n",
              "2   132003\n",
              "3   132004\n",
              "4   132005"
            ]
          },
          "execution_count": 73,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Applying groupby on placeID for removing duplicate restaurant ID's\n",
        "restaurant_df = pd.DataFrame({'placeID': restaurant_all})\n",
        "restaurant_df.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9iweD2QSVjer"
      },
      "source": [
        "Left join on restaurant_df, using common place ID\n",
        "\n",
        "Here we will merge restaurant file with cuisine,parking and features columns on placeID to get all important features which will effect the result."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 314
        },
        "id": "nsEhCaBt2d5c",
        "outputId": "69135167-8fad-4d73-c892-6c85e023644e"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-b2989539-a633-4d12-af7c-8a8f56f5a673\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>Rcuisine_Afghan</th>\n",
              "      <th>Rcuisine_African</th>\n",
              "      <th>Rcuisine_American</th>\n",
              "      <th>Rcuisine_Armenian</th>\n",
              "      <th>Rcuisine_Asian</th>\n",
              "      <th>Rcuisine_Bagels</th>\n",
              "      <th>Rcuisine_Bakery</th>\n",
              "      <th>Rcuisine_Bar</th>\n",
              "      <th>Rcuisine_Bar_Pub_Brewery</th>\n",
              "      <th>...</th>\n",
              "      <th>parking_lot_validated parking</th>\n",
              "      <th>parking_lot_yes</th>\n",
              "      <th>alcohol</th>\n",
              "      <th>smoking_area</th>\n",
              "      <th>Rambience</th>\n",
              "      <th>other_services</th>\n",
              "      <th>price</th>\n",
              "      <th>dress_code</th>\n",
              "      <th>accessibility</th>\n",
              "      <th>area</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>132001</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</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>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>132002</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</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>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>132003</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</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>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>132004</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</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>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>132005</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</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>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 75 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b2989539-a633-4d12-af7c-8a8f56f5a673')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-b2989539-a633-4d12-af7c-8a8f56f5a673 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-b2989539-a633-4d12-af7c-8a8f56f5a673');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID  Rcuisine_Afghan  Rcuisine_African  Rcuisine_American  \\\n",
              "0   132001              0.0               0.0                0.0   \n",
              "1   132002              0.0               0.0                0.0   \n",
              "2   132003              0.0               0.0                0.0   \n",
              "3   132004              0.0               0.0                0.0   \n",
              "4   132005              0.0               0.0                0.0   \n",
              "\n",
              "   Rcuisine_Armenian  Rcuisine_Asian  Rcuisine_Bagels  Rcuisine_Bakery  \\\n",
              "0                0.0             0.0              0.0              0.0   \n",
              "1                0.0             0.0              0.0              0.0   \n",
              "2                0.0             0.0              0.0              0.0   \n",
              "3                0.0             0.0              0.0              0.0   \n",
              "4                0.0             0.0              0.0              0.0   \n",
              "\n",
              "   Rcuisine_Bar  Rcuisine_Bar_Pub_Brewery  ...  parking_lot_validated parking  \\\n",
              "0           0.0                       0.0  ...                            NaN   \n",
              "1           0.0                       0.0  ...                            NaN   \n",
              "2           0.0                       0.0  ...                            NaN   \n",
              "3           0.0                       0.0  ...                            NaN   \n",
              "4           0.0                       0.0  ...                            NaN   \n",
              "\n",
              "   parking_lot_yes  alcohol  smoking_area  Rambience  other_services  price  \\\n",
              "0              NaN      NaN           NaN        NaN             NaN    NaN   \n",
              "1              NaN      NaN           NaN        NaN             NaN    NaN   \n",
              "2              NaN      NaN           NaN        NaN             NaN    NaN   \n",
              "3              NaN      NaN           NaN        NaN             NaN    NaN   \n",
              "4              NaN      NaN           NaN        NaN             NaN    NaN   \n",
              "\n",
              "   dress_code  accessibility  area  \n",
              "0         NaN            NaN   NaN  \n",
              "1         NaN            NaN   NaN  \n",
              "2         NaN            NaN   NaN  \n",
              "3         NaN            NaN   NaN  \n",
              "4         NaN            NaN   NaN  \n",
              "\n",
              "[5 rows x 75 columns]"
            ]
          },
          "execution_count": 74,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Merge the restaurant_df according to cuisine,parking and features\n",
        "restaurant_df = pd.merge(left=restaurant_df, right=cuisine_res, how=\"left\", on=\"placeID\")\n",
        "restaurant_df = pd.merge(left=restaurant_df, right=parking_res, how=\"left\", on=\"placeID\")\n",
        "restaurant_df = pd.merge(left=restaurant_df, right=features_res, how=\"left\", on=\"placeID\")\n",
        "restaurant_df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "yZL_d3Wr2d5c"
      },
      "outputs": [],
      "source": [
        "# Getting the placeID's for all 938 restaurant having rating\n",
        "rated_res = restaurant_all[np.sum(review_rate,axis=1) > 0]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RSoqowyi2d5c",
        "outputId": "53bbfcba-7ce1-49fb-f58e-1f17ee104d61"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "array([[0., 0., 0., ..., 0., 0., 0.],\n",
              "       [0., 0., 0., ..., 0., 0., 0.],\n",
              "       [0., 0., 0., ..., 0., 0., 0.],\n",
              "       ...,\n",
              "       [0., 1., 0., ..., 0., 0., 0.],\n",
              "       [0., 0., 0., ..., 0., 0., 0.],\n",
              "       [0., 0., 0., ..., 0., 0., 0.]])"
            ]
          },
          "execution_count": 76,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Check for restaurant has rating, 0 means No and 1 means Yes.\n",
        "Rate = review_rate.loc[rated_res].values\n",
        "Rate"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "6VHZ2Jzm2d5d"
      },
      "outputs": [],
      "source": [
        "# Assigning combined,food and service rating of combined restaurant file\n",
        "combined_Y = combined_rating.loc[rated_res].values\n",
        "food_Y  = food_rating.loc[rated_res].values\n",
        "service_Y = service_rating.loc[rated_res].values"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "WjJ2MVkT2d5d"
      },
      "outputs": [],
      "source": [
        "#Getting index value of restaurant_df having rating value\n",
        "index = [x in rated_res for x in restaurant_df['placeID'].values]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "nLGYyDWj2d5e"
      },
      "outputs": [],
      "source": [
        "# Features for all 938 restaurant having rating\n",
        "X_val = restaurant_df.loc[index, :].reset_index(drop=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vE0l4Q7V2d5e",
        "outputId": "d33e884c-7a5a-4f5d-da78-9368120ed429"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "placeID               0\n",
              "Rcuisine_Afghan      35\n",
              "Rcuisine_African     35\n",
              "Rcuisine_American    35\n",
              "Rcuisine_Armenian    35\n",
              "                     ..\n",
              "other_services        0\n",
              "price                 0\n",
              "dress_code            0\n",
              "accessibility         0\n",
              "area                  0\n",
              "Length: 75, dtype: int64"
            ]
          },
          "execution_count": 80,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.isnull().sum() # all the NANs are from cuisine"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 314
        },
        "id": "1D2CbbyI2d5f",
        "outputId": "c809aadd-bb95-4a94-f361-f0e4df96da23"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-50a6fb57-dfaf-4038-b335-d1b577df8f20\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>Rcuisine_Afghan</th>\n",
              "      <th>Rcuisine_African</th>\n",
              "      <th>Rcuisine_American</th>\n",
              "      <th>Rcuisine_Armenian</th>\n",
              "      <th>Rcuisine_Asian</th>\n",
              "      <th>Rcuisine_Bagels</th>\n",
              "      <th>Rcuisine_Bakery</th>\n",
              "      <th>Rcuisine_Bar</th>\n",
              "      <th>Rcuisine_Bar_Pub_Brewery</th>\n",
              "      <th>...</th>\n",
              "      <th>parking_lot_validated parking</th>\n",
              "      <th>parking_lot_yes</th>\n",
              "      <th>alcohol</th>\n",
              "      <th>smoking_area</th>\n",
              "      <th>Rambience</th>\n",
              "      <th>other_services</th>\n",
              "      <th>price</th>\n",
              "      <th>dress_code</th>\n",
              "      <th>accessibility</th>\n",
              "      <th>area</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>132560</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>permitted</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>no_accessibility</td>\n",
              "      <td>open</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>132561</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>closed</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>132564</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>closed</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>132572</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>not permitted</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>closed</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>132583</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>not permitted</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>partially</td>\n",
              "      <td>closed</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 75 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-50a6fb57-dfaf-4038-b335-d1b577df8f20')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-50a6fb57-dfaf-4038-b335-d1b577df8f20 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-50a6fb57-dfaf-4038-b335-d1b577df8f20');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID  Rcuisine_Afghan  Rcuisine_African  Rcuisine_American  \\\n",
              "0   132560              0.0               0.0                0.0   \n",
              "1   132561              0.0               0.0                0.0   \n",
              "2   132564              0.0               0.0                0.0   \n",
              "3   132572              0.0               0.0                0.0   \n",
              "4   132583              0.0               0.0                1.0   \n",
              "\n",
              "   Rcuisine_Armenian  Rcuisine_Asian  Rcuisine_Bagels  Rcuisine_Bakery  \\\n",
              "0                0.0             0.0              0.0              0.0   \n",
              "1                0.0             0.0              0.0              0.0   \n",
              "2                0.0             0.0              0.0              0.0   \n",
              "3                0.0             0.0              0.0              0.0   \n",
              "4                0.0             0.0              0.0              0.0   \n",
              "\n",
              "   Rcuisine_Bar  Rcuisine_Bar_Pub_Brewery  ...  parking_lot_validated parking  \\\n",
              "0           0.0                       0.0  ...                            0.0   \n",
              "1           0.0                       0.0  ...                            0.0   \n",
              "2           0.0                       0.0  ...                            0.0   \n",
              "3           0.0                       0.0  ...                            0.0   \n",
              "4           0.0                       0.0  ...                            0.0   \n",
              "\n",
              "   parking_lot_yes            alcohol   smoking_area  Rambience  \\\n",
              "0              0.0  No_Alcohol_Served      permitted   familiar   \n",
              "1              0.0  No_Alcohol_Served           none   familiar   \n",
              "2              0.0  No_Alcohol_Served           none   familiar   \n",
              "3              1.0  No_Alcohol_Served  not permitted   familiar   \n",
              "4              0.0  No_Alcohol_Served  not permitted   familiar   \n",
              "\n",
              "   other_services  price  dress_code     accessibility    area  \n",
              "0            none    low    informal  no_accessibility    open  \n",
              "1            none    low    informal        completely  closed  \n",
              "2            none    low    informal        completely  closed  \n",
              "3            none    low    informal        completely  closed  \n",
              "4            none    low    informal         partially  closed  \n",
              "\n",
              "[5 rows x 75 columns]"
            ]
          },
          "execution_count": 81,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Fill the na value with zero\n",
        "X_val.fillna(0).head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 314
        },
        "id": "7N6VDXhr2d5f",
        "outputId": "bc30fcbf-6776-4922-9c9a-499b395229f1"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-57570d5d-0b4b-4f19-b7b4-ffe9f06c2ff2\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>placeID</th>\n",
              "      <th>Rcuisine_American</th>\n",
              "      <th>Rcuisine_Armenian</th>\n",
              "      <th>Rcuisine_Bakery</th>\n",
              "      <th>Rcuisine_Bar</th>\n",
              "      <th>Rcuisine_Bar_Pub_Brewery</th>\n",
              "      <th>Rcuisine_Breakfast-Brunch</th>\n",
              "      <th>Rcuisine_Burgers</th>\n",
              "      <th>Rcuisine_Cafe-Coffee_Shop</th>\n",
              "      <th>Rcuisine_Cafeteria</th>\n",
              "      <th>...</th>\n",
              "      <th>parking_lot_valet parking</th>\n",
              "      <th>parking_lot_yes</th>\n",
              "      <th>alcohol</th>\n",
              "      <th>smoking_area</th>\n",
              "      <th>Rambience</th>\n",
              "      <th>other_services</th>\n",
              "      <th>price</th>\n",
              "      <th>dress_code</th>\n",
              "      <th>accessibility</th>\n",
              "      <th>area</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>132560</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>permitted</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>no_accessibility</td>\n",
              "      <td>open</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>132561</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>NaN</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>closed</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>132564</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>NaN</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>none</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>closed</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>132572</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>not permitted</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>completely</td>\n",
              "      <td>closed</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>132583</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No_Alcohol_Served</td>\n",
              "      <td>not permitted</td>\n",
              "      <td>familiar</td>\n",
              "      <td>none</td>\n",
              "      <td>low</td>\n",
              "      <td>informal</td>\n",
              "      <td>partially</td>\n",
              "      <td>closed</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 36 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-57570d5d-0b4b-4f19-b7b4-ffe9f06c2ff2')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-57570d5d-0b4b-4f19-b7b4-ffe9f06c2ff2 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-57570d5d-0b4b-4f19-b7b4-ffe9f06c2ff2');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "   placeID  Rcuisine_American  Rcuisine_Armenian  Rcuisine_Bakery  \\\n",
              "0   132560                0.0                0.0              0.0   \n",
              "1   132561                NaN                NaN              NaN   \n",
              "2   132564                NaN                NaN              NaN   \n",
              "3   132572                0.0                0.0              0.0   \n",
              "4   132583                1.0                0.0              0.0   \n",
              "\n",
              "   Rcuisine_Bar  Rcuisine_Bar_Pub_Brewery  Rcuisine_Breakfast-Brunch  \\\n",
              "0           0.0                       0.0                        0.0   \n",
              "1           NaN                       NaN                        NaN   \n",
              "2           NaN                       NaN                        NaN   \n",
              "3           0.0                       0.0                        0.0   \n",
              "4           0.0                       0.0                        0.0   \n",
              "\n",
              "   Rcuisine_Burgers  Rcuisine_Cafe-Coffee_Shop  Rcuisine_Cafeteria  ...  \\\n",
              "0               0.0                        0.0                 0.0  ...   \n",
              "1               NaN                        NaN                 NaN  ...   \n",
              "2               NaN                        NaN                 NaN  ...   \n",
              "3               0.0                        0.0                 1.0  ...   \n",
              "4               0.0                        0.0                 0.0  ...   \n",
              "\n",
              "   parking_lot_valet parking  parking_lot_yes            alcohol  \\\n",
              "0                        0.0              0.0  No_Alcohol_Served   \n",
              "1                        0.0              0.0  No_Alcohol_Served   \n",
              "2                        0.0              0.0  No_Alcohol_Served   \n",
              "3                        0.0              1.0  No_Alcohol_Served   \n",
              "4                        0.0              0.0  No_Alcohol_Served   \n",
              "\n",
              "    smoking_area  Rambience  other_services  price  dress_code  \\\n",
              "0      permitted   familiar            none    low    informal   \n",
              "1           none   familiar            none    low    informal   \n",
              "2           none   familiar            none    low    informal   \n",
              "3  not permitted   familiar            none    low    informal   \n",
              "4  not permitted   familiar            none    low    informal   \n",
              "\n",
              "      accessibility    area  \n",
              "0  no_accessibility    open  \n",
              "1        completely  closed  \n",
              "2        completely  closed  \n",
              "3        completely  closed  \n",
              "4         partially  closed  \n",
              "\n",
              "[5 rows x 36 columns]"
            ]
          },
          "execution_count": 82,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# drop a feature if the entire column are 0\n",
        "features_to_drop = X_val.columns.values[np.sum(X_val,axis=0) == 0] \n",
        "X_val = X_val.drop(features_to_drop, axis=1)\n",
        "X_val.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AFI3WdCO2d5g",
        "outputId": "19db2518-aae5-4f7b-da27-7b4fe662d832"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "Index(['placeID', 'Rcuisine_American', 'Rcuisine_Armenian', 'Rcuisine_Bakery',\n",
              "       'Rcuisine_Bar', 'Rcuisine_Bar_Pub_Brewery', 'Rcuisine_Breakfast-Brunch',\n",
              "       'Rcuisine_Burgers', 'Rcuisine_Cafe-Coffee_Shop', 'Rcuisine_Cafeteria',\n",
              "       'Rcuisine_Chinese', 'Rcuisine_Contemporary', 'Rcuisine_Family',\n",
              "       'Rcuisine_Fast_Food', 'Rcuisine_Game', 'Rcuisine_International',\n",
              "       'Rcuisine_Italian', 'Rcuisine_Japanese', 'Rcuisine_Mediterranean',\n",
              "       'Rcuisine_Mexican', 'Rcuisine_Pizzeria', 'Rcuisine_Regional',\n",
              "       'Rcuisine_Seafood', 'Rcuisine_Vietnamese', 'parking_lot_none',\n",
              "       'parking_lot_public', 'parking_lot_valet parking', 'parking_lot_yes',\n",
              "       'alcohol', 'smoking_area', 'Rambience', 'other_services', 'price',\n",
              "       'dress_code', 'accessibility', 'area'],\n",
              "      dtype='object')"
            ]
          },
          "execution_count": 83,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Columns in X_val which contain placeID,cuisine,parking and some features from geo file.\n",
        "X_val.columns"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "Ie5XHPQR2d5h"
      },
      "outputs": [],
      "source": [
        "# drop placeID for getting only important features which will effect the result\n",
        "X_val = X_val.drop(['placeID'], axis=1)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1YMISGFl2d5h",
        "outputId": "875ea34d-948a-48d9-e81d-817fe40de702"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "Rcuisine_American            float64\n",
              "Rcuisine_Armenian            float64\n",
              "Rcuisine_Bakery              float64\n",
              "Rcuisine_Bar                 float64\n",
              "Rcuisine_Bar_Pub_Brewery     float64\n",
              "Rcuisine_Breakfast-Brunch    float64\n",
              "Rcuisine_Burgers             float64\n",
              "Rcuisine_Cafe-Coffee_Shop    float64\n",
              "Rcuisine_Cafeteria           float64\n",
              "Rcuisine_Chinese             float64\n",
              "Rcuisine_Contemporary        float64\n",
              "Rcuisine_Family              float64\n",
              "Rcuisine_Fast_Food           float64\n",
              "Rcuisine_Game                float64\n",
              "Rcuisine_International       float64\n",
              "Rcuisine_Italian             float64\n",
              "Rcuisine_Japanese            float64\n",
              "Rcuisine_Mediterranean       float64\n",
              "Rcuisine_Mexican             float64\n",
              "Rcuisine_Pizzeria            float64\n",
              "Rcuisine_Regional            float64\n",
              "Rcuisine_Seafood             float64\n",
              "Rcuisine_Vietnamese          float64\n",
              "parking_lot_none             float64\n",
              "parking_lot_public           float64\n",
              "parking_lot_valet parking    float64\n",
              "parking_lot_yes              float64\n",
              "alcohol                       object\n",
              "smoking_area                  object\n",
              "Rambience                     object\n",
              "other_services                object\n",
              "price                         object\n",
              "dress_code                    object\n",
              "accessibility                 object\n",
              "area                          object\n",
              "dtype: object"
            ]
          },
          "execution_count": 85,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.dtypes"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "PGpjVQ952d5h"
      },
      "outputs": [],
      "source": [
        "#Categorize the column of dataset which is object type \n",
        "for col in X_val.columns:\n",
        "    if X_val[col].dtype == object:\n",
        "        X_val[col] = X_val[col].astype('category')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-cfBd27X2d5i",
        "outputId": "fc3a32c1-5db0-4379-b4a8-849a14dac4a1"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 130 entries, 0 to 129\n",
            "Data columns (total 35 columns):\n",
            " #   Column                     Non-Null Count  Dtype   \n",
            "---  ------                     --------------  -----   \n",
            " 0   Rcuisine_American          95 non-null     float64 \n",
            " 1   Rcuisine_Armenian          95 non-null     float64 \n",
            " 2   Rcuisine_Bakery            95 non-null     float64 \n",
            " 3   Rcuisine_Bar               95 non-null     float64 \n",
            " 4   Rcuisine_Bar_Pub_Brewery   95 non-null     float64 \n",
            " 5   Rcuisine_Breakfast-Brunch  95 non-null     float64 \n",
            " 6   Rcuisine_Burgers           95 non-null     float64 \n",
            " 7   Rcuisine_Cafe-Coffee_Shop  95 non-null     float64 \n",
            " 8   Rcuisine_Cafeteria         95 non-null     float64 \n",
            " 9   Rcuisine_Chinese           95 non-null     float64 \n",
            " 10  Rcuisine_Contemporary      95 non-null     float64 \n",
            " 11  Rcuisine_Family            95 non-null     float64 \n",
            " 12  Rcuisine_Fast_Food         95 non-null     float64 \n",
            " 13  Rcuisine_Game              95 non-null     float64 \n",
            " 14  Rcuisine_International     95 non-null     float64 \n",
            " 15  Rcuisine_Italian           95 non-null     float64 \n",
            " 16  Rcuisine_Japanese          95 non-null     float64 \n",
            " 17  Rcuisine_Mediterranean     95 non-null     float64 \n",
            " 18  Rcuisine_Mexican           95 non-null     float64 \n",
            " 19  Rcuisine_Pizzeria          95 non-null     float64 \n",
            " 20  Rcuisine_Regional          95 non-null     float64 \n",
            " 21  Rcuisine_Seafood           95 non-null     float64 \n",
            " 22  Rcuisine_Vietnamese        95 non-null     float64 \n",
            " 23  parking_lot_none           130 non-null    float64 \n",
            " 24  parking_lot_public         130 non-null    float64 \n",
            " 25  parking_lot_valet parking  130 non-null    float64 \n",
            " 26  parking_lot_yes            130 non-null    float64 \n",
            " 27  alcohol                    130 non-null    category\n",
            " 28  smoking_area               130 non-null    category\n",
            " 29  Rambience                  130 non-null    category\n",
            " 30  other_services             130 non-null    category\n",
            " 31  price                      130 non-null    category\n",
            " 32  dress_code                 130 non-null    category\n",
            " 33  accessibility              130 non-null    category\n",
            " 34  area                       130 non-null    category\n",
            "dtypes: category(8), float64(27)\n",
            "memory usage: 29.7 KB\n"
          ]
        }
      ],
      "source": [
        "X_val.info()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "W3eDAos-2d5i"
      },
      "source": [
        "### Plotting the above features using plotly"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 37
        },
        "id": "Vbk-jq-O2d5j",
        "outputId": "674d5804-c52a-4f1b-e99f-1941c9185628"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "        <script type=\"text/javascript\">\n",
              "        window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
              "        if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
              "        if (typeof require !== 'undefined') {\n",
              "        require.undef(\"plotly\");\n",
              "        requirejs.config({\n",
              "            paths: {\n",
              "                'plotly': ['https://cdn.plot.ly/plotly-2.8.3.min']\n",
              "            }\n",
              "        });\n",
              "        require(['plotly'], function(Plotly) {\n",
              "            window._Plotly = Plotly;\n",
              "        });\n",
              "        }\n",
              "        </script>\n",
              "        "
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "#importing the packeges\n",
        "from IPython.core.interactiveshell import InteractiveShell     #An enhanced, interactive shell for Python\n",
        "#‘all’, ‘last’, ‘last_expr’ or ‘none’, ‘last_expr_or_assign’\n",
        "#specifying which nodes should be run interactively \n",
        "InteractiveShell.ast_node_interactivity = \"all\"   #Options:\t'all','last','last_expr','none','last_expr_or_assign'\n",
        "\n",
        "import numpy as np # linear algebra\n",
        "import pandas as pd # data processing\n",
        "\n",
        "#Plotly Offline brings interactive Plotly graphs to the offline (local) environment\n",
        "import plotly.offline as py\n",
        "import plotly.figure_factory as ff\n",
        "import plotly.graph_objs as gobj\n",
        "from plotly.graph_objs import *\n",
        "py.init_notebook_mode(connected=True)  # initiate notebook for offline plot"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "_SKlPxb12d5j"
      },
      "outputs": [],
      "source": [
        "#Method for plotting \n",
        "\n",
        "def plot_value_counts(col_name,table=False,bar=False):\n",
        "    \n",
        "    values_count = pd.DataFrame(X_val[col_name].value_counts())\n",
        "    values_count.columns = ['count']\n",
        "   \n",
        "    # Converting the index column into value count\n",
        "    values_count[col_name] = [ str(i) for i in values_count.index ]\n",
        "    \n",
        "    # add a column with the percentage of each data point to the sum of all data points\n",
        "    values_count['percent'] = values_count['count'].div(values_count['count'].sum()).multiply(100).round(2)\n",
        "    \n",
        "    # change the order of the columns.\n",
        "    values_count = values_count.reindex([col_name,'count','percent'],axis=1)\n",
        "    values_count.reset_index(drop=True,inplace=True)    \n",
        "    \n",
        "    if bar :\n",
        "        # add a font size for annotations0 which is relevant to the length of the data points.\n",
        "        font_size = 20 - (.25 * len(values_count[col_name]))\n",
        "        \n",
        "        trace0 = gobj.Bar( x = values_count[col_name], y = values_count['count'] )\n",
        "        data_ = gobj.Data( [trace0] )\n",
        "        \n",
        "        annotations0 = [ dict(x = xi,\n",
        "                             y = yi, \n",
        "                             showarrow=False,\n",
        "                             font={'size':font_size},\n",
        "                             text = \"{:,}\".format(yi),\n",
        "                             xanchor='center',\n",
        "                             yanchor='bottom' )\n",
        "                       for xi,yi,_ in values_count.values ]\n",
        "        \n",
        "        annotations1 = [ dict( x = xi,\n",
        "                              y = yi/2,\n",
        "                              showarrow = False,\n",
        "                              text = \"{}%\".format(pi),\n",
        "                              xanchor = 'center',\n",
        "                              yanchor = 'center',\n",
        "                              font = {'color':'yellow'})\n",
        "                         for xi,yi,pi in values_count.values if pi > 10 ]\n",
        "        \n",
        "        annotations = annotations0 + annotations1                       \n",
        "        \n",
        "        layout = gobj.Layout( title = col_name.replace('_',' ').capitalize(),\n",
        "                             titlefont = {'size': 50},\n",
        "                             yaxis = {'title':'count'},\n",
        "                             xaxis = {'type':'category'},\n",
        "                            annotations = annotations  )\n",
        "        figure = gobj.Figure( data = data_, layout = layout )\n",
        "        py.iplot(figure)\n",
        "    \n",
        "    if table : \n",
        "        values_count['count'] = values_count['count'].apply(lambda d : \"{:,}\".format(d))\n",
        "        table = ff.create_table(values_count,index_title=\"race\")      #Creating the table for race\n",
        "        py.iplot(table)\n",
        "    \n",
        "    return values_count"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "PX7jzG072d5k"
      },
      "source": [
        "### Calculate the mean rating of restaurant"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "Qw-RJmjz2d5k"
      },
      "outputs": [],
      "source": [
        "#Method to get mean value\n",
        "def calculate_Mean(col1,col2):\n",
        "    col1 = col1*col2\n",
        "    mean =  (np.sum(col1,axis=1)/np.sum((col2 == 1.0), axis=1)).reshape(col1.shape[0],1)\n",
        "    return mean"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "vKe5diMF2d5k"
      },
      "outputs": [],
      "source": [
        "#Taking mean value of all kind of rating like combined rating, food rating, service rating\n",
        "combined_mean_Y = calculate_Mean(combined_Y,Rate)\n",
        "food_mean_Y = calculate_Mean(food_Y,Rate)\n",
        "service_mean_Y = calculate_Mean(service_Y,Rate)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "G4za9EHO2d5k"
      },
      "source": [
        "#### Plotting mean value of all rating by using matplotlib"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "6peEvQ6R2d5l"
      },
      "outputs": [],
      "source": [
        "#Method to to print the ratings of different groups of restaurants based on different value\n",
        "\n",
        "def mean_rating_plotting(df,rotate=False):\n",
        "    \n",
        "    n = df.shape[1]\n",
        "    columns = df.columns.values\n",
        "    \n",
        "    if n > 1:\n",
        "        combined_y = [ combined_mean_Y[df[i] == 1].mean() for i in columns ]\n",
        "        food_y = [food_mean_Y[df[i] == 1].mean() for i in columns ]\n",
        "        service_y = [service_mean_Y[df[i] == 1].mean() for i in columns ] \n",
        "        y = pd.DataFrame({'combined':combined_y, 'food':food_y, 'service':service_y},\n",
        "                         columns=['combined','food','service'],index=columns) \n",
        "        ticks = columns\n",
        "        \n",
        "    else:\n",
        "        values = df[columns[0]].unique()\n",
        "        values = values[values != '?']\n",
        "        combined_y = [combined_mean_Y[df[columns[0]] == i].mean() for i in values ]\n",
        "        food_y = [food_mean_Y[df[columns[0]] == i].mean() for i in values ]\n",
        "        service_y = [service_mean_Y[df[columns[0]] == i].mean() for i in values ] \n",
        "        y = pd.DataFrame({'combined':combined_y, 'food':food_y, 'service':service_y},\n",
        "                         columns=['combined','food','service'],index=values) \n",
        "        ticks = values\n",
        "   \n",
        "    fig = plt.figure()\n",
        "    plt.plot(range(y.shape[0]),y['combined'],'-o',c='g',label='overall')\n",
        "    plt.plot(range(y.shape[0]),y['food'],'-o',c='r',label='food')   \n",
        "    plt.plot(range(y.shape[0]),y['service'],'-o',c='b',label='service')\n",
        "    plt.xticks(range(y.shape[0]),ticks,fontsize=13)\n",
        "    if rotate: plt.xticks(rotation=40)\n",
        "    plt.yticks(fontsize=13) \n",
        "    if n == 1: plt.xlabel(columns[0],fontsize=15)\n",
        "    plt.ylabel('mean rating',fontsize=15)\n",
        "    plt.legend(fontsize=15,frameon=False)\n",
        "    plt.show()\n",
        "    \n",
        "    print(y)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2pqHXc0d2d5l",
        "outputId": "f82a7b73-5087-4592-c4c2-317f94feed54"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "Index(['Rcuisine_American', 'Rcuisine_Armenian', 'Rcuisine_Bakery',\n",
              "       'Rcuisine_Bar', 'Rcuisine_Bar_Pub_Brewery', 'Rcuisine_Breakfast-Brunch',\n",
              "       'Rcuisine_Burgers', 'Rcuisine_Cafe-Coffee_Shop', 'Rcuisine_Cafeteria',\n",
              "       'Rcuisine_Chinese', 'Rcuisine_Contemporary', 'Rcuisine_Family',\n",
              "       'Rcuisine_Fast_Food', 'Rcuisine_Game', 'Rcuisine_International',\n",
              "       'Rcuisine_Italian', 'Rcuisine_Japanese', 'Rcuisine_Mediterranean',\n",
              "       'Rcuisine_Mexican', 'Rcuisine_Pizzeria', 'Rcuisine_Regional',\n",
              "       'Rcuisine_Seafood', 'Rcuisine_Vietnamese', 'parking_lot_none',\n",
              "       'parking_lot_public', 'parking_lot_valet parking', 'parking_lot_yes',\n",
              "       'alcohol', 'smoking_area', 'Rambience', 'other_services', 'price',\n",
              "       'dress_code', 'accessibility', 'area'],\n",
              "      dtype='object')"
            ]
          },
          "execution_count": 93,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.columns"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "5n31AyJw2d5l"
      },
      "outputs": [],
      "source": [
        "features_col=['parking_lot_none',\n",
        "       'parking_lot_public', 'parking_lot_valet parking', 'parking_lot_yes',\n",
        "       'alcohol', 'smoking_area', 'Rambience', 'other_services', 'price',\n",
        "       'dress_code', 'accessibility', 'area']"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zG9XlAGK2d5m"
      },
      "source": [
        "#### Analysing some features_col by using matplotlib"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DvQc-SYr2d5m",
        "outputId": "b9d1f200-0c7a-46f9-9836-a3ea8ef4c4e8"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    60\n",
              "low       45\n",
              "high      25\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 95,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Getting price detail\n",
        "X_val.price.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "P6m1PBA72d5m",
        "outputId": "74597578-cc8b-4c73-f57d-832393c18a2c"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    91\n",
              "low       35\n",
              "?          7\n",
              "high       5\n",
              "Name: budget, dtype: int64"
            ]
          },
          "execution_count": 96,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Finding budget detail\n",
        "userprofile_df.budget.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 122
        },
        "id": "MhZYXEei2d5m",
        "outputId": "a27219d3-fb60-4304-e4e0-5deb2d027673"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "        combined      food   service\n",
            "low     1.063059  1.135805  0.935632\n",
            "medium  1.234342  1.255871  1.161361\n",
            "high    1.258106  1.253816  1.174754\n"
          ]
        }
      ],
      "source": [
        "# plotting the mean rating as a function of price\n",
        "mean_rating_plotting(X_val[['price']])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "65eQJVyO2d5m",
        "outputId": "2d67f64c-a3b0-4abe-bfa9-064dc4df9c06"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "parking_lot_none             65.0\n",
              "parking_lot_public           16.0\n",
              "parking_lot_valet parking     3.0\n",
              "parking_lot_yes              46.0\n",
              "dtype: float64"
            ]
          },
          "execution_count": 98,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Taking subset of features which is imoortant for parking \n",
        "columns = ['parking_lot_none','parking_lot_public', 'parking_lot_valet parking','parking_lot_yes']\n",
        "X_val[columns].sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tKieF-Bc2d5n",
        "outputId": "37654083-1966-4050-ca68-8ca88ea0932e"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "130.0"
            ]
          },
          "execution_count": 99,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "#Finding the tital sum of parking features\n",
        "X_val[columns].sum().sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 139
        },
        "id": "9dDaFGG62d5n",
        "outputId": "d9120293-3aeb-4ff6-8960-ac449c1121cd"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "                           combined      food   service\n",
            "parking_lot_none           1.170202  1.194014  1.097035\n",
            "parking_lot_public         1.101438  1.233839  0.977173\n",
            "parking_lot_valet parking  1.393519  1.324074  1.300926\n",
            "parking_lot_yes            1.206176  1.227920  1.093676\n"
          ]
        }
      ],
      "source": [
        "# finding mean rating of parking features\n",
        "mean_rating_plotting(X_val[columns], rotate=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eH4IiOZz2d5n",
        "outputId": "d5610997-a88f-43da-ea6d-8c4ea585affd"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "high      3\n",
              "low       0\n",
              "medium    0\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 101,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val['parking_lot_valet parking']==1].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "08CrZ5sY2d5o",
        "outputId": "ad152575-ff93-4d61-f7b5-d0e9510a7848"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    8\n",
              "low       7\n",
              "high      1\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 102,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val['parking_lot_public']==1].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MaTsdbhq2d5o",
        "outputId": "322bca21-0679-4f45-a639-88f571c8f0ae"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "low       31\n",
              "medium    29\n",
              "high       5\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 103,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val['parking_lot_none']==1].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tuAbYIlO2d5o",
        "outputId": "bf0da220-61c5-402f-a1da-028f027aebd0"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "none             70\n",
              "not permitted    25\n",
              "section          24\n",
              "permitted         9\n",
              "only at bar       2\n",
              "Name: smoking_area, dtype: int64"
            ]
          },
          "execution_count": 104,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.smoking_area.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7sFLYE_n2d5p",
        "outputId": "82c9de48-6aaa-4a5a-dd0c-079b10c7e56a"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "false    109\n",
              "true      26\n",
              "Name: smoker, dtype: int64"
            ]
          },
          "execution_count": 105,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "features_user.smoker.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 156
        },
        "id": "ufLGv_b_2d5p",
        "outputId": "16dc90ee-d66a-4dab-cbfc-58d672f73f6d"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "               combined      food   service\n",
            "permitted      1.201852  1.331481  1.128704\n",
            "none           1.171497  1.208648  1.086371\n",
            "not permitted  1.071238  1.175244  0.986184\n",
            "section        1.291368  1.221073  1.147479\n",
            "only at bar    1.377778  1.266667  1.377778\n"
          ]
        }
      ],
      "source": [
        "# Mean rating of smoking area \n",
        "mean_rating_plotting(X_val[['smoking_area']])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tXcvjnGO2d5p",
        "outputId": "5eabdd33-c70d-4f39-ada5-ab655d64b408"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "No_Alcohol_Served    87\n",
              "Wine-Beer            34\n",
              "Full_Bar              9\n",
              "Name: alcohol, dtype: int64"
            ]
          },
          "execution_count": 107,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.alcohol.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 122
        },
        "id": "P7_LOEgD2d5p",
        "outputId": "a6584d12-0ff2-48fd-95d7-7afec899b9bd"
      },
      "outputs": [
        {
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXEAAAFFCAYAAAAabN0fAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdd3hUVf7H8fdJISGUIDXUBJUugjQBUSlSY2gSifSiWQsIuC67LCCgC/uzIKigKwrCmggJINKJVAtFQEQQVxCkG+nSQkLK+f1xJqQnE8jMnUm+r+eZJ5M7d+79hiQfbs49RWmtEUII4Z48rC5ACCHE7ZMQF0IINyYhLoQQbkxCXAgh3JiEuBBCuDEJcSGEcGNeVhdglfLly+ugoCCryxBCFDLff//9ea11BWedr8iGeFBQELt377a6DCFEIaOUOu7M80lzihBCuDEJcSGEcGMS4kII4cYkxIUQwo1JiAshhBuTEBdCCDcmIS6EEG5MQlyIXETujyRoZhAeUzwImhlE5P5Iq0sSIoMiO9hHiLxE7o8kfGU4cYlxABy/fJzwleEA9G/Y38rShLhFrsSFyMH4jeNvBXiquMQ4xm8cb1FFQmQlIS5EDk5cPpGv7UJYQUJciBxUKJH9HEaeHp58sOsDrt+87uSKhMhKQlyIbOz9Yy9X4q+gUBm2F/MsRvXS1Xl+zfNUn1Gdf2z4B6eunLKoSiEkxIXI4uilo3SN7EqFEhV4p8s7BPoHolAE+gcyr8c8jrx4hK3DttLh7g68ue1NgmYG8dTSp9h5eqfVpYsiSGmtra7BEs2aNdMyFa3I7Nz1czw07yHOx51n67Ct1KtQL9f9j/15jFk7Z/HRno+4knCF1tVbM/rB0fSq1wsvD+n8VRQppb7XWjdz1vnkSlwIm2s3rxH8WTCnrpxiVb9VeQY4QFCZIN7q9Banxpzi3S7vcubaGZ5c8iT3vHsPb217iz/j/3RC5aIokxAXAriZfJM+0X3YE7uHqD5RtK7eOl/vL+VTipEPjuTgiIN80fcL7r7rbv62/m9Ue7saL659kcMXDzuoclHUSYiLIi9FpzB8xXBijsTw4eMfElIn5LaP5enhSY+6Pdg8eDN7wvfQp34f/rP7P9R+rzY9FvVg89HNFNUmTOEYEuKiyBu7fiwR+yKY2n4qw5sML7DjPlD5Aeb3nM+JMSeY8MgEtp3cRvv/tqfJnCYs2LuAhKSEAjuXKLokxEWRNn3bdKZvn86I5iMY12acQ84RUDKAV9u9yskxJ/k45GOSUpIYsnwIgTMDefWrVzl7/axDziuKBumdIoqsiH0RDFw2kND6oSx8YiGeHp5OOa/Wmo1HNzJjxwzW/LoGH08f+jfsz+iWo2lYqaFTahCO4+zeKRLiokiKORzD4wsf5+EaD7O2/1p8vHwsqePg+YO88907LPhxAXGJcXSo2YHRLUfTrVY3PJT8oeyOJMSdREK86Np1ehftFrSjVrlabBm8BX9ff6tL4uKNi3z0/Ue8t/M9Tl89Te1ytRn14CgGNxpMiWIlrC5P5IOEuJNIiBdNhy4c4qF5D1GqWCm2Dd9GQMkAq0vKIDE5kaX/W8qMHTPYeXonZXzLEN4knBEtRlDdv7rV5Qk7yGAfIRwk9mosnSM6o1DEDIhxuQAH8Pb0Juy+MHYM38G2YdvoeHdH3tr+FjXfqUnYkjC+O/Wd1SUKFyMhLoqEy/GX6RrZlXPXz7Gm/xpqlatldUm5UkrRqnorokOj+e3F3xjTcgzrDq+j5dyWtJrbiugD0SSlJFldpnABEuKi0ItPiqdnVE8OnDvA530/p1kVp/2lWyACywTyZqc3OTnmJO91fY/zcefpu6Qvd79zN29ufVOG9hdxEuKiUEtOSWbgsoFsObaF+T3m0+meTlaXdNtK+ZRiRIsRHBxxkBVhK7i37L2M3TCWam9XY8SaEfx64VerSxQWkBAXhZbWmlHrRrHk5yVM7zSd/vcXjnUxPZQHIXVC2DR4E3v/spfQBqF8tOcj6syqQ8jCEDYd3SRD+4sQCXFRaE37Zhqzd83m5VYv81Krl6wuxyEaBTTikx6fcHz0cV559BW+O/UdHf7bgcYfNuaTHz4hPine6hKFg0kXQ1EofbznY55Z+QwD7h/Agp4LiszAmfikeBbuX8iMHTPYf3Y/FUtU5Plmz/Nss2epVLKS1eUVCdJP3EkkxAuvFQdX0CuqF53u6cSKsBV4e3pbXZLTaa3ZdHQTM7+byapDqyjmWYz+Dfsz6sFRNApoZHV5hZqEuJNIiBdOW09s5bFPH6NhxYZsGryJksVKWl2S5Q5dOMS7373LJ3s/IS4xjnZB7RjTcgzBtYOLzF8oziSDfYS4TQfOHiBkYQjVS1dndb/VEuA2tcvVZla3WZwac4rXH3udXy/+SvdF3akzqw6zds7i2s1rVpfomiIjISgIPDzMx8hIqyvKllyJi0Lh5OWTtJ7XmqSUJLYN20bNu2paXZLLSkxO5PP/fc6MHTP47vR3lPEtwzNNnmFEixHU8K9hdXmuITISwsMhLi5tm58fzJkD/XPv5STNKU4iIV54XLxxkTbz2nD66mm+HvK1tPnmw45TO5ixYwZLf14KwBP1n2D0g6NpVb2VxZVZrEoViI3Nuj0wEI4dy/Wt0pwiRD7EJcYRsjCEI5eOsDxsuQR4PrWs1pKoPlH8Nuo3Xmr1EjGHY2g9rzUtP25J1E9RJCYnWl2i8/z2G0ybBg0bZh/gACdOOLcmO0iIC7eVlJJE2JIwtp/cTmTvSNoGtbW6JLdVw78Gb3R8g1MvnWJW11lcvHGRsKVh3P3u3byx9Q0u3bhkdYmO8fvvMHMmPPgg3HMPjB8P/v5w113Z71/D9ZqbJMSFW9Ja8+yqZ1l5aCWzus2iT/0+VpdUKJQsVpIXWrzALyN+YeVTK6ldrjZ/3/B3qs2oxgurX+DQhUNWl3jnLlwwbdvt2kG1ajBmDCQmwuuvm6aSb7+F994zbeDp+fnB1KmWlJwrrXWRfDRt2lQL9zVh4wTNZPSEjROsLqXQ2xu7Vw/9Yqgu9loxzWR0cGSw3nBkg05JSbG6NPtduaL1p59q3a2b1l5eWoPWtWtrPWmS1v/7X/bviYjQOjBQa6XMx4gIu04F7NZOzDK5sSnczqydsxi5diRPP/A0c0LmoJSyuqQi4cy1M/xn9394f/f7nL1+loYVGzK65Wj6NeyHr5ev1eVlFR8Pa9bAwoWwapX5vHp1CAuDp56Cxo3BAT870jvFSSTE3dPiA4vpu6QvIXVCWPrkUrw8vKwuqciJT4pn0U+LmLFjBvvO7KOCXwWea/Yczzd/3vqh/YmJsHEjLFoEy5bBlStQoQI8+aQJ7latTL9vB5IQdxIJcfez+ehmukR2oXmV5qwfuJ7i3sWtLqlI01qz5dgWZuyYwapDq/D29Oap+55iTMsxzu0llJICW7eaK+7Fi+H8eXNzsndvE9zt2oGX8/6zlxB3Eglx97L3j708Ov9RqpWuxjdDv6Fs8bJWlyTS+fXCr7eG9l9PvE67oHaMbjma4FrBeHp4FvwJtYY9e0xwR0XBqVNQvDh0726aS7p2BR+fgj+vHQp9iCulwoAXgEaAn9Y6x/8ilVItgYlAM8AXOAy8prX+It0+x4AAIP1aVa201vtzq0NC3H0cvXSU1vNa4+3hzbbh26hWuprVJYkcXLpxibk/zOW9ne9x4vIJ7rnrHkY9OIqhDwwtmGkQ/vc/E9yLFsGvv4K3N3TubK64u3eHktZPtVAUQrwzUBYoDszJI8S7AeWBNcBFoDuwEHhEa73Lts8xYILWOiI/dUiIu4dz18/x0LyHOB93nq3DtlKvQj2rSxJ2SEpJ4vP/fc7MHTPZfmo7/j7+PN3kaUa2GElgmcD8HezYMRPaCxfCvn3mZmS7dia4e/eGsq71V1mhD/FbJ1aqLbAhtxDP4X07gGit9du2z48hIV4oXbt5jfYL2vPT2Z/YMGgDrau3trokcRu+O/UdM7+byeIDi9FoetfrzZiWY2hVrVXOPYv++AOio014b99utrVsaYI7NBQqV3beF5BPEuK5vycA+BXoqbXeaNt2DPADvIATwAda6w/zOpaEuGu7mXyT7gu7s+G3DSzru4yQOiFWlyTu0MnLJ5m1cxZz9szhz/g/aVG1BaMfHE2f+n3MnO+XLsHSpSa4N282Nyzvv98Ed9++UNM9JjWTEM95/xLAl8BJrXVYuu2PAt8DCUBbYBHwz+yCXCkVDoQD1KhRo+nx48fv8KsQjpCiUxj8xWAi9kUwt/tchj0wzOqSRAG6fvM6C35cwDvfvcPp3w8x+MRdjD4WwL07D6MSE+Hee01wh4VB/fpWl5tvzg5xt+hkq5QqBawGzgKD0r+mtf4q3afrlVJvAwOALCGutZ4DzAFzJe6wgsUdGbt+LBH7IpjafqoEeCFUQnvx/O9Vee7bxiSvOI7XjUucKnWJ91p4EdfnCXr1/xd1KtS1uky34fJzpyilygEbgd+BUK31zTzekgLIED43NX3bdKZvn86I5iMY12ac1eWIgpKUBOvXw7BhUKkS9OyJ2rARr8FD4auvuHRwLz/+bRCTr62i7vv1CP4smPVH1lNUu0DnizPH+Nu+IZ6Y7oKdMN0CfW0Plc2+AcBPwALAM5vXA4F2tvd7Ao9irtZH5lWHzJ3iej798VPNZHRodKhOSk6yuhxxp5KTtf72W61feEHrihXNfCWlSmk9aJDWa9dqffNmlrecuXZGT9kyRVd6s5JmMvq+9+/TH3//sY67GWfBF3B7cPLcKVaE+BBAZ/MIAh4GrgE1bPtOsr123bY99fFP2+v1gR+Aq8AVW+CPsKcOCXHXsu7XddrrVS/dbn47HZ8Yb3U54nalpGi9Z4/WY8dqXaOGiRhfX6379NF66VKt4+wL4/jEeD3/h/m60QeNNJPR5d8orydumqhjr8Y6+Au4c84OcRmxKSy36/Qu2i1oR61ytdgyeAv+vv5WlyTy6+DBtL7cBw+aYe6dOpmbkz16QOnSt3VYrTVfHf+KGTtmsPLgSrw8vHiqoRna3zigcQF/EQWjyPROsZqEuGs4dOEQD817iFLFSrFt+DYCSgZYXZKw14kTZsj7woXwww9mEM6jj5rgfuIJKF++QE/364VfeW/ne8z7YR7XE6/zaOCjjGk5hsdrP+6Yof23SULcSSTErRd7NZbW81pz/eZ1tg7bSq1ytawuSeTl7FkzydTChWbSKYAWLUxwP/kkVK3q8BL+jP+TuXvm8u7Od28N7X/xwRcZ2ngopXxKOfz8eZEQdxIJcWtdjr/Mo/Mf5fDFw2wZsoVmVZz2My/y688/zbSuixaZaV6Tk6FBg7S+3PfcY0lZSSlJfPHLF8zYMYNtJ7dR2qc0Tz/wNCMfHElQmSBLagIJcaeRELdOfFI8XSO78u2Jb1ndbzWd7ulkdUkis7g4WLnSBPeaNXDzphkxmRrcDRtaXWEGO0/vZOaOmSz+eTEpOoVedXsxpuUYWldv7fRFQyTEnURC3BrJKcmELQ1jyc9LiOgVQf/7+1tdkkh18ybExJjgXr4crl83c5T07WuCu0ULh6yEU5BOXTnF7J2z+fD7D7kUf4lmVZoxpuUYQuuHmqH9TiAh7iQS4s6ntWbk2pHM3jWb6Z2m81Krl6wuSSQnw1dfmTbupUvN/CV33QV9+pir7kceAU/XuWlor+s3r/Ppvk+ZuWMmBy8cpEqpKoxoPoLwpuGU8yvn0HNLiDuJhLjzTf16KhM2T+DlVi/zZqc3rS6n6NIavvvOBHd0tJkxsEQJ6NnTBHfHjlCsmNVVFogUncK6w+uYuWMm639bT3Gv4gxqNIjRLUdTt7xjhvZLiDuJhLhzfbznY55Z+QwD7h/Agp4L8FAuP+ND4aI17N+ftqDCsWNm5Ztu3UxwBweDn5/VVTrUT2d/YuaOmUTsiyAhOYGu93ZldMvRdLy7Y4G2m0uIO4mEuPOsOLiCXlG96HRPJ1aErXBa26QADh82wb1woVkVx9MTHnvMBHfPnmYtyiLm3PVz/Gf3f5i9azZnrp+hfoX6jH5wNAPuH1Ag67ZKiDuJhLhzbD2xlcc+fYyGFRuyafCmglmiS+Tu1CnTTLJwIaT+jD/8sAnuPn3M6u+ChKQEog5EMWPHDPb+sZfyfuV5tumzPN/8eSqXqkzk/kjGbxzPicsnqOFfg6kdptK/Yd434iXEnURC3PEOnD3Aw588THm/8mwdtpUKJSQ8HObcOXNjcuFC+OYb03zStKnpVdK3L1SvbnWFLktrzdfHv2bGjhmsOLgCLw8vWlRtwfex3xOfFH9rPz9vP+aEzMkzyCXEnURC3LFOXj5J63mtSUpJYtuwbdS8yz1WZXErV67AF1+Y4F6/3vQ0qVs3rS937dpWV+h2jlw8wrvfvct7O99DkzUbA/0DOTb6WK7HkBB3Eglxx7l44yJt5rXh9NXTfD3kaxoFNLK6pMLjxg1YvdoE9+rVkJAAgYEmtJ96yixn5uJ9ud2BxxSPbENcoUiZlJLre2VlH+HW4hLjCFkYwpFLR4gZECMBXhASE82V9sKF5sr72jWzsEJ4uAnuli0luAtYDf8aHL+cdfnGGv41LKgmdxLiosAkpSQRtiSM7Se3Ex0aTdugtlaX5L6Sk03b9sKFsGQJXLwIZcqY9u2nnjKzBXrJr6+jTO0wlfCV4cQlxt3a5uftx9QOUy2sKnvyUyAKhNaaZ1c9y8pDK5ndbTZ96vexuiT3ozXs2mX6cUdFwe+/m77bPXqY5pLOnU3fbuFwqTcvb6d3irNJiIsC8crmV5j7w1wmPjKR55s/b3U57uXAgbRBOEeOgLc3dO1qrrhDQsxoSuF0/Rv2d8nQzkxCXNyxWTtn8a9v/sUzTZ5hStspVpfjHn77LW0lnJ9+Ag8PaN8e/vlP6NXLzF8ihB0kxMUdWXxgMS+ufZHudbrzfvD7Tp/20638/nvaIJydO8221q3hvfcgNNTcrBQinyTExW3bfHQzA5YNoHX11ix6YhFeHvLjlMWFC2YQzqJFsGWLafdu3Bhef93cpAwMtLpC4ebkt07clr1/7KVnVE/uLXsvK55aUSBzThQaV6+a+bgXLTLzcyclmYE3r7xiblDWdczseaJokhAX+Xb00lG6RnbF38efmAExlC1e1uqSrBcfD2vXmqaSVavMoJzq1WHMGBPcDzwgfbmFQ0iIi3w5d/0cnSM6k5CUwKZhm6hWuprVJVknKcmsOblwoVmD8soVM7nU0KGmZ0nr1uaGpRAOJCEu7Hbt5jWCPwvm1JVTbBi0gXoV6lldkuNFRsL48XDiBNSoAf/6l2nHXrjQrPp+/jyULg29e5vgbt9eBuEIp5KfNmGXm8k36RPdhz2xe1jWdxmtq7e2uiTHi4w0Q9vjbKP2jh+HQYPMzcnixU0f7qeegi5dwNfX2lpFkSUhLvKUolMYvmI4MUdimNt9LiF1QqwuyXG0Nlfde/fCCy+kBXj618uXh6NHoaTMjS6sJyEu8jR2/Vgi9kUwtf1Uhj0wzOpyCs7Nm2a1m717Mz7+/DP39124IAEuXIaEuMjV9G3Tmb59OiOaj2Bcm3FWl3P7Ll+GH3/MGNYHDpggB9M8cv/9pu9248bm8eSTcPJk1mPVcL2Z7ETRJSEuchSxL4KX179MaP1QZnaZ6R6jMbU2wZv56vro0bR9KlQwXf7GjEkL7Fq1zPqT6f373xnbxMFMSDXV9WayE0WXhLjIVszhGIYuH0q7oHZ82utTPD08836TsyUmwi+/ZA3sixfN60qZcG7eHJ55Ji2wAwLs67Pd3zb5UfreKVOnpm0XwgXIyj4ii12nd9FuQTtqlavFlsFb8Pd1gRXRr1zJ2hzy009pzSG+vqY5JDWoGzeGhg2l7Vo4nazsIyx16MIhun3WjYolKrK2/1rnB7jWcPq0CekffkgL7N9+S9unfHnTHDJqVFpg164t/bNFkSQ/9eKW2KuxdI7ojEIRMyCGgJIBjj1hYiIcPJi1OeTChbR9atUyq7YPH54W2JUryxB2IWwkxAUAl+Mv0zWyK+eun2PLkC3UKlerYE9w5Qrs25e1OSQhwbzu42OaP3r3ztgcUqpUwdYhRCEjIS6IT4qnZ1RPDpw7wOp+q2lW5Q6a87Q282anD+sffjAr1qQqV840h4wcmRbYdepIc4gQt0F+a4q45JRkBi4byJZjW4joFUGnezrZ/+akpOybQ86fT9vn3ntNYA8dmhbYVapIc4gQBcSuEFdKpQA5dWPRwBXgR+BdrfWyAqpNOJjWmlHrRrHk5yVM7zSd/vfn0nXu2rW05pDUG44//WSmYAXTHHLffWZR38aNTXA3bGgmhxJCOIy9V+Iv2R5XgJXAOaAiEAKUAuYCDwNLlFKDtdYRDqhVFLBp30xj9q7ZvNzqZV5q9ZLZqDXExma9uj582LwGULasCekXXsjYHOLtbd0XI0QRZW+IVwG2aq2fyrT9H0qpRcBdWuvHlFL/BcYCEuIu7uM9H/PKxgn8vXx3pp1rBGPHpgX2uXNpO95zjwnpQYPSArtqVWkOEcJF2BviQ4Gc/tb+BPgMGA1EAaEFUJcoaNeuwf79sHcvx7Ysp+HWGK6f88D35gpgBRQrZppDQkLSwvr++8HfBQb6CCFyZG+IewF1gS+zea0ekLp8yU0gvgDqEnciu+aQX3+91RxSujicCyyFR5/B0LSFCey6daU5RAg3ZG+ILwL+rZTyIq1NvALQA3gVczUO0AT4JbcDKaXCgBeARoCf1jrHGpRSLYGJQDPAFzgMvKa1/iLdPhWB/wAdMf+BzAPGaa1T7Pza3FdysgnnzIF95kzaPjVrmpAeMIDjQWV5/OfxJFSuwNbh2yhWooJ1tQshCoS9IT4Kc5X9L+DNdNsTgI+Av9k+/w7YmMexLgHvA8WBOXnsWxbTRDMYuAh0BxYqpR7RWu+y7RMJXAWqAeWAdbZ9X8/zq3In16/fag659di3zyzIC+Yq+r77oFu3jM0hZcoAcPLySdrMa01S+eJsG/glFSTAhSgU8jUBllKqLNAQCAD+APZrrS/e1omVagtsyO1KPIf37QCitdZvK6VqAr8B92qtj9heHw5M0FrXzO04Lj0B1pkzGecN2bsXDh1K6x1SpozpHZJ+sqe6dU27djYu3rhIm3ltOH31NF8P+ZpGAY2c+MUIUbS49ARYtsD+ykG15EkpFQA0wPRJB9Mkczk1wG32AEFKqdJa6yuZ3h8OhAPUcIWJ/ZOTTde9zM0hf/yRtk9QkAnpp55KC+waNezuHRKXGEfIwhCOXDpCzIAYCXAhChm7Q1wp5Qs8gmm2yLwqrNZaf1CQhWVz/hLAUmC11jq1yaYUcDnTrqlra5XG9GtPX+QcbE04zZo1c+4cvHFx2TeHpC444O0NDRqYRXdTw7pRo1vNIbcjKSWJsCVhbD+5nejQaNoGtS2Yr0UI4TLsHbHZBhOgOTWkasBhIa6UKgWsBs4Cg9K9dBXI3AeuTLrXrHH2bNar64MHIcV2r7VMGRPS4eFpgV2vXo7NIbdDa82zq55l5aGVzO42mz71+xTYsYUQrsPeK/F3MW3PnYCftdaJjispI6VUOWCt7fwDtNZJ6V7+EfBXSt2ttU6dcPoB4JjWOvMV+u2LjMx+dZeUlOybQ2Jj094bGJi2XmNqYAcGOnywzCubX2HuD3OZ+MhEnm/+vEPPJYSwjl03NpVS14HeWuuYOz6hUp6AN6ZpZg2QuvRKgs5UjK0NfAPwPTBMa52czfHWY5pUhpHWO+UTrfX/5VaH3Tc2IyOzrrPo5WXaqmNjTa+R1G0NGmS82dioEdx1V97nKGCzds5i5NqRPNPkGT58/EP3WBtTiELCVW9s7sP0SCkIA0nrVw5g6yNHTaVUdcxVd32t9QngL5gbmTWBJ9KF0TSt9TTb8/6YfuKnMV0e5wFvFFCt5go8fYCDmb3v5En4y1/SeonUq2cmgbLY4gOLeXHti3Sv0533g9+XABeikLP3SrwxMB8YpbW2rHdKQbL7StzDI61rX3pKpbVxu4jNRzfTJbILzas0Z/3A9RT3Lm51SUIUOa56Jb4e8AM2KaVuks1NQ611xYIszGXUqAHHj2e/3YXs/WMvPaN6cm/Ze1nx1AoJcCGKCHtDfDY5zydeuE2dmrVN3M/PbHcRRy8dpWtkV/x9/IkZEEPZ4mWtLkkI4SR2hbjWerKD63Bd/W2TN2bXO8UFnLt+js4RnUlISmDTsE1UK13N6pKEEE4ky7PZo39/lwnt9K7dvEbwZ8GcunKKDYM2UK9CPatLEkI4WW4zCEZjZgM8YnueK631kwVamcjVzeSbPBH9BHti97Cs7zJaV29tdUlCCAvkdiVeAdOfG8xSbEWzTdwFpegUhi0fxpdHvmRu97mE1AmxuiQhhEVyDHGtdbt0z9s6pRphl7HrxxK5P5Kp7acy7IFhVpcjhLCQR967gFLqFaVUlRxeq6yUeqVgyxI5mb5tOtO3T2dE8xGMazPO6nKEEBazK8SBSZjZC7NTxfa6cLCIfRG8vP5lQuuHMrPLTBmNKYSwO8QVObeJV8Os1iMcKOZwDEOXD6V9zfZ82utTPD08rS5JCOECcuudMhizLBrYpppVSl3JtJsvZqWf7BZQFgVk1+ldPBH9BPdVvI9lfZfh42X9HC1CCNeQW++UOOCC7bnCzBSYeSm2m5gJq94v+NIEwKELh+j2WTcqlqjI2v5rKe1T2uqShBAuJLfeKYuBxQBKqU+AV7XWR51VmIDYq7F0juiMQhEzIIaAkgU1kaQQorCwd9j9UEcXIjK6HH+ZrpFdOXf9HFuGbKFWuVpWlySEcEH5WWMzCBgA1CbrGpsyYrMAxSfF0zOqJwfOHWB1v9U0q+K0WS2FEG7G3jU2mwJfAycwIb4Ps7ZlEHAKOOyg+oqc5JRkBi4byJZjW4joFUGnezpZXZIQwoXZ28XwTUz7+H2Ym5zDtdZ3A20wPVcKbiWdIkxrzah1o1jy8xKmd5pO//tdb9ItIYqKyEizCqOHh/kYGWl1RdmzN8QbAwuB1KVsfAG01tuAKUCu61kK+0z7Zhqzd83m5VYv81Krl6wuR4giK3Vp3ePHzcJex4+bz10xyO1tE9fATa21Vr6IV9kAACAASURBVEqdBQKBbbbXTgJy1+0OfbznYyZsnsDA+wfyesfXrS5HCLeltVkGNz4ebtzI+DG7bdm99s47WZfWjYszywq42qzU9ob4z8A9wGZgOzBGKbUb0098LHDEMeUVDSsOruAvq/5Cl3u7MLf7XDyUvX8gCeG6tM4ajvYG650E8I0bd7b8rVLZL6sLZl0YV2NviM/B3MQE+CdmhOYvts+vA30KtqyiY+uJrfRd0pemlZuyOHQx3p7eeb9JOE1kpMsu6mS3/FyV5ico89qWkHBndXt7g68vFC+e8WPq83Llsm7Lbf+8tqV+9PaGmjXdYmldwP5+4p+me/4/pVQ9oBVQHNihtT7roPoKtQNnDxCyMITqpauzut9qShYraXVJIp3UdtHUP6tT20Uh/0GutQk1Z4Rn5o/JyXf275Bb4BUvDmXL3llo5rTN08Lpgdxgad1b8gxxpZQvsAKYprXeAqC1vgasd2xphdvJyyfpEtkFHy8fYgbEUKFEBatLEpmMH599u+hzz8FXX+U/gO+El1fugXfXXQVzFZp5W7FipnmhqHHxpXUzyDPEtdbxSqnmgEybV0Au3rhI54jOXEm4wtdDvqbmXTWtLklkI6f2z6tXYeXK7EPQ379grkIzb/OS1XCdzkWX1s3C3h+NFUBPYKMDaykS4hLjCFkYwpFLR4gZEEOjgEZWlyRycNddcDHzlG9AYCAcO+b0coTIlr0hHgO8qZSqDKwBzpBpfnGt9ZoCrq3QSUpJImxJGNtPbic6NJq2QW2tLknk4OOPTYB7emZsU3bVdlFRdNkb4hG2j71tj8w00tySK601z656lpWHVjK722z61JcOPa5q/nxzU6trV+jbFyZNcv12UVF02Rvi0mh7hyZunsjcH+Yy8ZGJPN/8eavLETmIiIBhw+Cxx+Dzz0179ODBeb9PCKvY28Uwmx6Twl6zds5i6jdTeabJM0xpO8XqckQOFi40gd2uHXzxhQlwIVydDA10sMUHFvPi2hfpXqc77we/L4sbu6jFi2HgQGjTBlasMG3fQrgDCXEH2nx0MwOWDaB19dYsemIRXh7ST8wVLVsG/fpBy5awejWUKGF1RULYT0LcQfb+sZeeUT2pVbYWK55aQXHv4laXJLKxcqW5edmsGaxZAyVl0KxwMxLiDnD00lG6RnbF38efdQPWUbZ4WatLEtlYswb69IHGjWHdOigta1ALNyR/3xewc9fP0TmiMwlJCWwatolqpatZXZLIxpdfQu/ecN99EBNjRloK4Y7ys8amL/AIUI2sa2xqrfUHBVmYO7p28xrBnwVz6sopNgzaQL0K9awuSWRj40bo0QPq1oX1683ITCHclb1rbLYBlgI5zdKkgSId4jeTb/JE9BPsid3Dsr7LaF29tdUliWx89RWEhMC998KGDWYGPiHcmb1t4u8CvwEPAD5aa49MjyI9WjNFpzBs+TC+PPIlc0LmEFInxOqSRDa+/RaCg81c0Rs3QvnyVlckxJ2ztzmlDtBba/2jI4txV2PXjyVyfyRT209l2APDrC5HZGP7djOMvlo1E+AVK1pdkRAFw94r8X1AgCMLcVfTt01n+vbpjGg+gnFtxlldjsjGzp3QuTNUrgybNkGA/CSLQsTeEH8Os67mo44sxt1E7Ivg5fUvE1o/lJldZspoTBf0/ffQqRNUqGACvEoVqysSomDZG+LrMSvab1JK3VBKnc38sPeESqkwpdQ3SqkrSqmkPPYtrpRarJT6VSmVopSakM0+W5RSCUqpa+kej9tbz+2KORzD0OVDaV+zPZ/2+hRPjyJ9W8Al7d0LHTtCmTImwKtJb09RCNnbJj6bTPOH34FLwPuY9Tnn5LGvBrbZ9v93Lvu9prX+V8GUl7ddp3fxRPQT3FfxPpb1XYaPl4+zTi3stH+/mYmwZEnYvNks5CBEYWTvLIaTC+qEWusYAKVUWzv2jQdm2Pa/w1UKC8ahC4fo9lk3KpaoyNr+ayntI8P8XM2BA9Chg5mFcPNm0xtFiMKqsAy7H62UuqiUOqCUGqeU8i7Ig0fujyRoZhAeUzyoP7s+CYkJxAyIIaCk3CFzNb/8YgLcy8s0odxzj9UVCeFY+Rmx2QoYDtQm64hNtNYtCrCu/BgH/AJcAZoDkUBp2/YMlFLhQDhAjRo17Dp45P5IwleGE5dolj1P1skk6kR2/r6TWuVqFcgXIArGr79C+/bm+aZNULu2tfUI4Qx2XYkrpToCX2OG3LcBzgHXgEZAOeAnRxWYF631dq31Ja11stZ6B/AKMCCHfedorZtprZtVqJDT4NOMxm8cfyvAU8UnxTN+4/g7LV0UoCNHzGIOSUmmH3jdulZXJIRz2Nuc8irwDhBs+3yi1ro95qo8EdhS8KXdthSgwPr6nbh8Il/bhfMdPWoCPD7eDKVv0MDqioRwHntDvD6wFhOQGigBt5ZtmwzYfVmqlPK0TaZVzPa5r+2RbfAqpXxs+3sAXrZ9vW2vlVFKPa6UKqmMB2z1RNlbT15q+Gff7JLTduFcx4+bJpRr10yA33+/1RUJ4Vz2hng84KG11kAskP520RVMM4u9BgI3gBjA0/b8BhColHrY1s87fUIetL3+MDDJ9vwj22vewATgtK2OKOAzsmkPv11TO0zFzzvjWl1+3n5M7TC1oE4hbtOpUybAL10ysxE2bmx1RUI4n703Nn/EzJ+yHtgIjFNKnQZuYppa9tt7Qq31fGB+Di8fAzKsraK1DsrlWOeAlvae+3b0b9gfMG3jJy6foIZ/DaZ2mHpru7DG77+bJpTz502AN21qdUVCWEOZi+s8dlKqG1BTaz1bKVUVWAmkXvecAnpprb93XJkFr1mzZnr37t1WlyFuwx9/QNu2cPq0WdyhVSurKxIijVLqe611M2edz97BPmvSPT+tlGoK3IsZdfmL1vqmg+oTIoOzZ00TyqlTZkk1CXBR1OV7eTbbDcjKwFGtda5znwhRkM6fNwN5jh2DtWuhTRurKxLCenaP2FRKdVNKfYe5yXkSuN+2/SOlVLb9soUoKBcvmrlQDh82K9Q/KvNpCgHYP9hnELACMzIynIz9sA9hRnIK4RCXLpnZCH/5BZYvN1fjQgjD3ivx8cCbWuvBQESm1w5g+pELUeAuXzYLOvz0E3z+uZkbXAiRxt428UBM98LsxGPmKhGiQF25Al26mHnBly6Fbt2srkgI12PvlfhJzCLJ2WkGHC6YcoQwrl0zob1rF0RFmRXqhRBZ2Rvic4FJthuYxW3blFKqAzCWtBGUQtyx69fNqvQ7dsDChdCrl9UVCeG67G1OeR2oDiwAkm3btmGGzX+otX7XAbWJIiguDrp3h2+/hchICA21uiIhXJu9g3008IJS6m3gMcz0sxeBTVrrQw6sTxQh8fHQs6dZjee//4WwMKsrEsL15Wuwj9b6CHDEQbWIIiwhwTSbbNgA8+bBABl5IIRd8hXiSqk6QFWyX9lnTdZ3CJG3mzehTx8zjP6jj2DIEKsrEsJ92BXiSqmGwEKgHtkvuKAx7eNC5EtiIvTtC6tWwQcfwNNPW12REO7F3ivxeZgVfB7HdCeUCa/EHUtKgn794Isv4L334Nlnra5ICPdjb4jXA57QWsc4shhRdCQlwcCBsGQJvP02jBhhdUVCuCd7+4nvBGQ9MlEgkpNNu/eiRfDGGzBmjNUVCeG+7L0SDwcWKqXigM3An5l30FrHZXmXEJmkpMDw4aYP+NSp8Le/WV2REO7N3hA/j1k67b+57CM3NkWuUlIgPBwWLIApU+Cf/7S6IiHcn70hHgG0At5CbmyK26A1vPACzJ0LEybAK69YXZEQhYO9Id4OeEZr/ZkjixGFk9bw4ovwn//A3/8Or75qdUVCFB723tg8Bkibt8g3reGll2DWLPjrX+Hf/waV3UgDIcRtsTfE/waMV0oFOa4UUdhoDWPHwsyZMGoUvPmmBLgQBc3e5pQpmC6Gh5RSx8i+d0qLAqxLuDmtYfx4eOsteP55mDFDAlwIR7A3xH+yPYSwy+TJpukkPNyMxpQAF8Ix7J2KdqijCxGFx2uvmZuXw4aZ+VA87G20E0Lkm/x6iQL1f/9nug8OGgRz5kiAC+Fo8ismCsxbb8G4cWZSq3nzwFOGfwnhcBLiokDMnGmG0D/5pBmRKQEuhHNIiIs7Nnu2mcTqiScgIgK88rXUiBDiTkiIizvy4YdmGtnu3eGzz8Db2+qKhChaJMTFbZs71yzkEBwM0dFQrJjVFQlR9EiIi9uyYAE88wx07mwWdvDxsboiIYomCXGRb5GRMHQodOgAy5aBb5Zls4UQziIhLvIlKsr0AX/0UVi+HIoXt7oiIYo2CXFhtyVLoH9/eOghszq9n5/VFQkhJMSFXZYvh6eeggcfhNWroUQJqysSQoCEuLDDqlUQGgpNm8LatVCqlNUVCSFSSYiLXK1bZwbxNGpknpcubXVFQoj0JMRFjtavh549oUEDiImBMmWsrkgIkZmEuMjWpk1mFGadOibMy5a1uiIhRHacHuJKqTCl1DdKqStKqaQ89i2ulFqslPpVKZWilJqQzT5+Sql5Sqk/bY+5Sinp+HYHvv4aQkLgnntgwwYoV87qioQQObHiSvwS8D4w2o59NbANCAd25rDPO0BdoA5QG6gHvH3nZRZNW7dCt25QowZs3AgVKlhdkRAFr23btvTp0+fW55MnT6Z8+fIWVnT7nD7fnNY6BkAp1daOfeOBGbb94zO/brviHgA8rrU+Y9s2EViplBpje7+w044d0KULVK1qmlMqVbK6IiFEXty9TbwO4At8n27bHqA45qo8A6VUuFJqt1Jq97lz55xUonvYtcvMg1KpkgnwypWtrkiI/Llx44bVJVjC3UM8tcfy5XTbUp9n6QyntZ6jtW6mtW5WQdoJbtmzBzp1Mm3fmzebK3HhviL3RxI0MwiPKR4EzQwicn+kU88fHR1Nw4YN8fHxoXr16owfP56kpCSOHj2KUorVq1dn2D85OZmAgAAmTEi75fXTTz8RHBxMqVKlKFWqFKGhofzxxx+3Xt+yZQtKKWJiYujevTslS5ZkxIgRAEyfPp3mzZvj7+9PpUqVCAkJ4fDhw8754i3g7iF+1fbRP9221OdXnFyLW/rxR3jsMfD3NwFevbrVFYk7Ebk/kvCV4Ry/fByN5vjl44SvDHdakH/55Zf07duXJk2asHz5ckaOHMlbb73FiBEjqFmzJi1atCA6OjrDe7766ivOnDlDWFgYAIcPH+ahhx4iPj6eiIgI5s+fz4EDBwgJCUFrneG9w4cPp1GjRqxYsYLhw4cDcOrUKUaMGMHy5cv56KOPSE5OpnXr1ly+fJnCyN3XYDkIxANNgE22bQ8AN4BDVhXlLvbvNzMRlihhmlACA62uSKQ3et1o9v6xN1/v2XFqBwnJCRm2xSXGMXz5cD76/iO7j9M4oDEzu8zM17kBXnnlFdq2bcuCBQsA6NKlCwDjxo1jwoQJhIWFMWXKFBISEvCxzV8cFRVFgwYNuO+++wCYMmUKAQEBrF27lmK2Servv/9+6taty5o1awgODr51vtDQUF577bUMNcyYMePW8+TkZDp27EjFihVZvnw5gwYNyvfX5Oqs6GLoqZTyBYrZPve1PVQO+/vY9vcAvGz7egNorW8AEcCrSqmKSqmKwKvAf+WmZu5+/tkEuI+PuQK/+26rKxIFIXOA57W9ICUnJ7Nnzx5CQ0MzbO/bty8pKSls376dJ598kitXrrBu3ToAkpKS+Pzzz+nbt++t/Tds2ECvXr3w8PAgKSmJpKQkatasSVBQELt3785w7PSBnmrHjh107NiRcuXK4eXlhZ+fH9euXePQocJ5XWfFlfhA4JN0n6fejaiplKoOrAXqa61P2LYfBFKvER8GJgELgCG2baOB90i78l4KjHFI5YXEL79A+/ZmMeNNm+Dee62uSGTndq6Eg2YGcfzy8SzbA/0D2TJkSwFUlbPz58+TmJhIpUzdmlI/v3jxIlWrVqVNmzZERUXRo0cPNm7cyPnz5281paQe5/XXX+f111/Pco6TJ09me+xUJ06coFOnTrRo0YIPP/yQKlWqUKxYMYKDg4mPL5zXdVZ0MZwPzM/h5WNAyUz7B+VxvOvAMNtD5OHXX02Aa22uwOvUsboiUZCmdphK+Mpw4hLjbm3z8/ZjaoepDj93+fLl8fb25uzZsxm2nzlzBoCytmG/ffv25R//+Ac3btwgKiqKBx54gFq1at3av2zZsvTq1Yunn34623Okl/kP+HXr1hEXF8fy5cspYZtqMykpiYsXL975F+ii3P3GpsiH334zAZ6YaAby1KtndUWioPVv2J85IXMI9A9EoQj0D2ROyBz6N+zv8HN7enrStGlTFi9enGF7dHQ0Hh4etGrVCjDt2Ddu3GDZsmUsW7Ysw1U4QIcOHThw4ABNmzalWbNmGR5BQUG51nDjxg08PDzw8kq7Po2OjiYpKdfB4W7N3W9sCjsdOwbt2kFcnGlCsd1DEoVQ/4b9nRLa2ZkyZQqdO3dm6NChhIWFsX//fiZOnMgzzzxDtWrVAKhYsSJt27bl5Zdf5s8//+TJJ5/McIzJkyfTokULgoODGTZsGOXLl+f06dOsX7+eIUOG0LZt2xzP3759e5KTkxk6dCjDhw/nwIEDvPXWW5QpxLO3yZV4EXDihAnwK1fMZFaNGlldkSisOnXqxKJFi9i9ezchISHMnDmTv/71r8yaNSvDfmFhYcTGxtKyZcssV9e1a9dmx44d+Pn5ER4eTteuXZk0aRI+Pj7cm8cNnIYNGzJ//ny+++47Hn/8cT777DMWL16Mv79/ru9zZypzv8uiolmzZjrzne7C6NQpaNsWzp83k1k1a2Z1RUIUbkqp77XWTvtNk+aUQuz3300b+Nmz5gpcAlyIwkdCvJA6c8b0A4+NNQs6PPig1RUJIRxBQrwQOnvWXIGfOGGWVGvd2uqKhBCOIiFeyJw/b+ZCOXrUrEr/8MNWVySEcCQJ8ULk4kXo2NEM6Fm50vRIEUIUbhLihcSff5rpZH/+GVasMFfjQojCT0K8ELh82SzosG8fLFtmngshigYJcTd39Sp07WoWdli6FLKZ1E0IUYhJiLuxa9fMosY7d0JUFHTvbnVFQghnk2H3bur6dXj8cdi2DT77DJ54wuqKhIBXX32VqlWr4uHhwZAhQxx6rlWrVqGU4tixYw49j6uTK3E3dOOGuer+5hv49FPINH+QEJbYvXs3kyZNYtq0abRt25aKFStaXVKRICHuZuLjoWdPMxf4/PnQr5/VFQlh/PLLLwC88MILlC6dZZ1y4SDSnOJGEhJMs8mXX8LHH0MhXC5QuKkhQ4YwcOBAAPz9/VFKsWXLFo4ePUrPnj0pXbo0pUqVynbl+bi4OF588UUCAgLw9fWlefPmfPnllxn20VozefJkKlasSKlSpRg0aBBXrsha6ID5xymKj6ZNm2p3kpCgdUiI1qD1hx9aXY1waRERWgcGaq2U+RgR4fBTHj58WE+YMEEDetOmTXr79u36zz//1DVr1tS1a9fWixYt0kuWLNENGjTQVapU0RcuXLj13n79+umSJUvqd999V69Zs0b36tVLe3l56W+++ebWPjNnztRKKT1+/Hi9bt06HR4erqtWraoBffToUYd/ffkB7NZOzDLLw9SqhzuF+M2bWvfqZb5bs2dbXY1waRERWvv5mR+W1Iefn1OC/JNPPtGAvnr1qtZa6w8++EB7enrqI0eO3Nrn5MmT2tvbW0+bNk1rrfXPP/+slVJ6/vz5t/ZJTk7WDRo00J06ddJaa52UlKQrV66sn3322Qzne+yxxyTEtZY2cVeXlAT9+5tBPO+8A88/b3VFwmlGj4a9e/P3nh07TLtbenFxMHw4fPSR/cdp3Bhm5n+h5vR27txJkyZNuPvuu29tq1atGg899BDffvstALt27UJrTWho6K19PDw8CA0N5Y033gDM4sixsbH06NEjw/F79+7Nhg0b7qjGwkDaxF1YcrJp9168GKZPhxdftLoi4fIyB3he2x0oNjY2y2r0YFaoT124ODY2lpIlS+Ln55dln7i4OBISEvjjjz8AsvR2kd4vhlyJu6jkZBg6FBYuhP/7P3jpJasrEk53O1fCQUFw/HjW7YGBsGXLnVaUL5UrV+bAgQNZtp85c4ayZcve2ufatWvExcVlCPIzZ87g5+eHj48PAQEBAJw9ezbDcTJ/XlTJlbgLSkmBp582fcBfew3+/nerKxJuY+pUyHRVi5+f2e5kDz74IN9//z1Hjx69te306dNs27aNNm3aANC8eXOUUixZsuTWPlprlixZcmuf6tWrExAQwPLlyzMc//PPP3fCV+EGnNkA70oPV72xmZys9dNPm/tRkyZZXY1wSxb0TtE6643N+Ph4XbNmTV2nTh0dFRWllyxZohs2bJht75RSpUrpWbNm6bVr1+revXtn6Z3y9ttvaw8PDz1hwgQdExMjvVPSPSwPU6serhjiKSlaP/ec+a7885/mcyHcReYQ11rrI0eO6B49euiSJUvqEiVK6ODgYH3o0KEM77t+/boeMWKErlixoi5WrJhu2rSpXrduXYZ9UlJS9IQJE3T58uV1yZIldb9+/XRkZKSEuNay2r2r0BpGjYL33oOxY007uFJWVyWEyC9nr3YvbeIuQGv4619NgI8ZIwEuhLCfhLjFtIZ//ANmzICRI01XQglwIYS9JMQtpDVMmABvvAHPPWcG80iACyHyQ0LcQlOmwLRppjvhrFkS4EKI/JMQt8i//mVCfMgQ+PBD8JDvhBDiNkh0WOD112HiRBg40EwpKwEuhLhdEh9O9vbb5kZmWBh88gl4elpdkRDCnUmIO9G775quhKGhZki9BLgQ4k5JiDvJ+++bwTy9ekFkJHjJ1GNCiAIgIe4Ec+bACy9ASAgsWgTe3lZXJEThM3/+fJRSXLt2zepSnEpC3MHmzYO//AW6dTPzghcrZnVFQhROwcHBbN++Pcvc5IWd/FHvQP/9r+kD3qkTLF0KPj5WVySEe9Fak5CQgK+vb577VqhQgQoVKjihKtciV+IO8tlnZlGHdu3giy/Ajp9BIdzegQMH6NKlC2XLlqVEiRLUq1eP2bNn33p9+fLlNGvWDF9fXwICAhg7diyJiYm3Xp88eTLly5fn22+/pXnz5vj6+hIVFUWJEiUyHCdV8+bNGTBgAJB9c8qNGzcYO3YsgYGB+Pj4ULNmTcaNG5fhGB9//DENGjTAx8eHwMDAW8vCuQsJcQeIjjZ9wB9+GFauhOLFra5IFCWRkWaBHw8P8zEy0nnnDgkJwdPTk4iICFasWMHIkSO5evUqANHR0fTu3ZsWLVqwYsUKJk2axJw5c7KEalxcHIMHD+bpp59m3bp1tGzZkscff5zo6OgM+/3222/s3r2bsLCwbGvRWtOjRw8++OADXnjhBdasWcOUKVM4f/78rX3efPNNnnvuOXr27MmqVat47rnnmDhxIrNmzSrgfxkHcua8t7Zpb8OAb4ArQJId+zcDdgJxwBFgQKbXjwHxwLV0j4Z5HddR84kvWaK1p6fWbdponW5aZSGcwsLF7vW5c+c0oPft25fltZSUFF2jRg09ZMiQDNvnzp2rfX199fnz57XWWk+aNEkD+osvvsiw3+eff649PDz06dOnb22bNm2avuuuu/TNmze11lnnM1+3bp0G9PLly7Ot9/Lly7pEiRJ68uTJGbZPnDhRV6pUSSclJeXzX8CgCKx2fwl4HygOzMltR6WUP7AWeAt4GHgEWKaUOqK13p5u16e11hEOqtduy5ebQTwtWsCaNVCypNUVCXfmbovdly1blurVq/Pss8/y4osv0q5du1uLGR86dIgTJ07w5JNPkpSUdOs97du3Jz4+np9++olHH30UAKUUXbt2zXDsrl27UrJkSRYvXsyoUaMAiIqKolevXnjn0N1r06ZNlC1blu7du2f7+vbt27l+/TqhoaFZanrttdc4deoUgYGB+ftHsIDTm1O01jFa64XAb3bs3htzBf6G1jpBa70eWAaEO7LG27F6tRnE06QJrF0LpUpZXZEoiqxc7N7Dw4Mvv/ySgIAAhg0bRkBAAA8//DA//PDDrSaMbt264e3tfetRs2ZNAE6ePHnrOHfddRfFMnXj8vX1pUePHkRFRQFw8OBBfvzxxxybUgAuXLhA5cqVc3w9taYGDRpkqKldu3ZZanJlrt47pRHwg+1PlFR7gIGZ9ntbKfUucAL4QGv9obMKBIiJgd694f77zXN/f2eeXRRW7rjYfd26dVm6dCmJiYl88803/P3vfyc4OJj169cDMGfOHB544IEs70sNczBX4tnp27cvISEhnDhxgqioKCpUqED79u1zrKVcuXLExsbm+HrZsmUBWLVqFZUqVcryep06dXJ8rytx9RAvBVzOtO1PoHS6zwcD3wMJQFtgkVKK7IJcKRWO7Sq+Ro0aBVLghg3QowfUrw9ffgllyhTIYYW4LVOnQni4aUJJZcVi997e3rRv356XXnqJfv36UblyZapWrcqxY8d45plnbuuYnTp1okyZMkRHRxMVFUWfPn3wzGXuig4dOvDGG2+watUqHn/88Syvt2rViuLFi/P7778THBx8WzW5AlcP8atAUKZtZTA3RQHQWn+V7rX1Sqm3gQFAlhDXWs/B1g7frFmzO15cdPNm6N4dateG9evB9h+7EJbp3998HD8eTpyAGjVMgKdud6R9+/bx8ssv07dvX+6++24uXbrE66+/TqNGjShbtizTp09n4MCBXLlyha5du1KsWDF+++03vvjiC5YsWZLnIB1vb2969+7N22+/TWxsLO+//36u+3fs2JHOnTvTr18/XnnlFZo0aUJsbCxff/01H374IWXKlGHy5MmMGjWK48eP88gjj5CSksKhQ4fYvHkzy5YtK8h/Hsdx5l3U9A/MVXOuvVOAocCxTNv+C3ySy3vGAd/mdf47IWh7PgAADtdJREFU7Z3y1Vfmrn/9+lqfOXNHhxKiUDhz5oweMGCArlmzpvbx8dGVKlXSYWFh+vjx47f2WbNmjW7Tpo328/PTpUqV0o0aNdLjx4/XiYmJWmvTO6VcuXI5nmP9+vUa0FWqVNHJyckZXsvcO0VrrePi4vRf//pXXbVqVV2sWDEdFBSk//nPf2Z436effqqbNGmifX19dZkyZXSLFi309OnTb/vfgcK+2r1SyhPwxvQ0WQOk9uFI0JmKUUqVAX4F3gDewfRQWQ501FpvV0oFAncD24FEoA2wGHhNa/1ebnXcyWr327aZUZjVqpl2xoCA2zqMEKIQKgqr3Q8EbgAxgKft+Q0gUCn1sFLqmlKqBoDW+k+gGxCKaRv/CHhWp3UvLAG8DZzDdF2cDbyaV4DnV/rBE5UrQ/v2UKUKbNokAS6EsJbT28S11vOB+Tm8fIy0K/PU/XcBLXI41s9A1lvdBSgyMuONoj/+MGthjhxpglwIIawkw+7zMH58xjv9YMbBTZ9uTT1CCJGehHgeTpzI33YhhHAmCfE85NSdvIC6mQshxB2REM/D1KlmsER6VgyeEEKI7EiI56F/f7O8WmCguaEZGGg+d8bgCSGEyIurj9h0Cf37S2gLIVyTXIkLIYQbkxAXQgg3JiEuhBBuTEJcCCHcmIS4EEK4MQlxIYRwYxLiQgjhxiTEhRDCjTl9UQhXoZQ6B2SzpGyuygPnHVCOcH3yvS+68vu9D9RaV3BUMZkV2RC/HUqp3c5csUO4DvneF12u/r2X5hQhhHBjEuJCCOHGJMTzZ47VBQjLyPe+6HLp7720iQshhBuTK3EhhHBjEuJCiEJBKVVDKXVNKVXF6lqcyW1DXCm1RSk1oYCOpZVSbe7g/fOVUh8XRC2uQimVpJRqa3UdjqaUOqaUGmB7HmT7WahmdV0ClFIvKqWOZNo20vY96ppuW3GlVDzQWGtdUmv9uwNrOqaUirf9Z3FVKXVAKdXPUeezx22HuC1EtVLqkUzbDyulhtxxZeZY/W3nmFQQx7OaUspDKTVRKfWr7QfgglJqq1KqndW1uTvbz2OC7Zcr9eGw/1hd8Ze5ENoI3K2UCky3rQNwAGifbttDgCewxUl1Pa21LgmUBsYB/1VK1XXUyZRS3rm9fqdX4heAt5RS6g6Pk5O/ABeB4UopTwedw5n+DvQDumutSwGBwGvAjds5mDJkib00r9muxFIfTzv4fAX2y5zXL2pRpLU+AMRightbBjwKTErdZtMB2AWUTf+XlFJqslJqo1JqmlLqrO0xJf05lFL3KaVilFLnlFInlFL/tvd7oY0VwCWgfrpj1lBKLVFK/X975x7sVVXF8c8XLPHykIeKCihomJiZSRkoGuioaYwvxPIRkvnIcibHyjHGGMEM8zE+MwwUNIUMJ1/4GhHN1HyRQuYDFXlIoiBc5IKIV1Z/rP2DzfF3H9x7jX64PjNn7u/sffY6e5+zzzp7r33uWoskvSPpj5LaZ/ldJN0oaUE6718kdc3y50oaKelRSTXAkPrq0VwlPg7oDpxQLlPStyU9I2m5pFclndlYwZL6AAcApwA7AIc3cHxPSVPSRatOI9wuKW9nSXdLWpIu3FWStiqI2EvSc2lU9XT+MEqqknR1KrtE0l2SdmpsWzL2A+41s1cAzKzGzB40s6ezczXUAUzSzyQ9D6wCviVpjaRts2MkaY6kU7L6Xy7pLUlLJT0o6UvZ8e0l3Zzy5pXKVTqSBkqqLaRdKGlaS56nnod5QuozKyS9nI/US3WT9ANJc/DBSvBpprNeYfcFFgH3ALuWnu+UX9c9PRCYD+wIHAmMkLQ/gKTtgL8BfwW6Af2BQ/AXcoNIai3pGKAt8HxKa5Pq/DLQC+8P3YGrU76AuwAD9sQHciuASQXxpwPnAu2Bu+urR3OV+EpgJPBbSVvmGZJ6AQ8CfwC6AMOBMZKGNlL2GcAsM5sK3I+PyssiqQq/cO8Bu+O+Dn4OrEkj1fvwm78z0A+ffl1eEDMcf+NtAywArs3yrkzl+iUZS4B7mzA7eBw4TdKvJB0gqW2hHfV2gIwfAd8D2uGd50UgD+U8MLVjStofh1+XfsD2wDPA1GzEcRXQO51vL+AofHoaNIJyD3PiCWBvoCMwGpgoaY8svzVwBPB1oCtBOaax3nRyMDDdzD4GngIGSdoa2Ie6lfhsMxtrZrVpsPQiUPoX+mHATDO7wczWmNlCYExKr48bJFXj+u8O4BIzm5/yBuOfbo80sw/NbBnwa+CkpC/6pu2nZrbczFYB5wEHacO1mHFm9kIaINQ/UzezJm24/ekCvCO+BJyX0t/AFeII4MlCmTHAQ42Q3QY31ZyT9o8EaoHuxfOn38fj064tysjaD/gIaJulHYabMErfyRswNMv/LrAs/W4FrAYOyfLbAWuA/ml/IjC+Ee0ScDL+UlqW6nU30CPlHwe8WSjTNx3XOqvrsMIxZ+GdsbR/S+oE4MrcgJ2y/FbAcmBA1r6Ds/zeqczApvaP//WW+sOHQHW2nQ/UFo67EJiW7c8FTk6/e6Z2d2/E+ebiD3F1un6fACMbKPM88JP0e2DxvsRW9pr1SNdpD+BhYEhKPw+4Hh9w1ABfKN6/4r3O+klJb/w+PVt5n1kO1KT8sUl2DfBAsb+k/d2AV4FRaf+XwMcFmaU+0g0YmvpKMf9DYL/sHMMae42a/XWKmX2SKj4im96AX/y3Coe/mdIbYiiuKG9N+/cDi4G6bJw9gTlmVlsmrwew2MxWFurRBsg9jb2T/V6JT2NIx2xJ1hYzq8FH/Y1pyzrMudXMjjCzTvgLpidwWzqkF7BTMgdVp7f9I3jH3D4TNbcgejKwm6R9kullCHBTJhNgViZzKd7pe2Tty2UW71ulcLGZdSxtwNMNlmgeZ6ZztQH6ACcq2Vzli9ijJb2WzInVwNfYsM+txWd9QR2Y2QJgNj6w6g88mrJKZpaDgcfNR+cbyzxcyXfMtq3N1zkwsx/b+vWVsuZcM5sNTAWOzWTOLsjsaGZtzEf683D90rmQv5WZPZWJXtvYRrTIJ4Zm9gC+sDAyS16AK6icXWhcpz2DNMKXtAh4G+hE3Qucc4FedeQtALZNJpe8HqvxF0NDLMbf1j1LCZLaAdvRzAfQzGYA4/EpNzTcAUqsLcipxu1sw/FZyXwz+0cmE6B3QWaVmU3GTUNr2PBe5b8rmRVA64Kp7zP5hrjMw3wCPugYAnRKL5WZ+GwsK2bxL9MN8whuH37dzEprBy/gz+BQ6jalNMQtwDcknSqpTXrx7iLpO40VIGkX/AUzMyVNBb4oaURaa5KkbsncBj4bmwlck63ZbSvp+01sQ4t+J/4L3G5dGmlMBvpKGiZpC0n7pvwb6xOSbIYDgGNw5Vba9sVHo0eUKXYfroiulLR1Ol+/NCp9FjfxXJEW+HbEvwiZ0JgHyMzW4jf7Ikk7ppfBFfgU6tmGyhfadq6kw5MdD0m9cfvb39MhDXWA+piAf/lyRvpdqv97+KLJ9ZK6pfN2lHSMpHZpJjUJGCWpq6QOwCUb067/Y2bjU+HT0gM6ADdZtThlHuYOuAlwMdBK0qn4SDzYeKbhz/70UkLqt4+n9CYpcTNbBAwCjsYHgsuAO/FBXn2Ml39auhJ/dp8Ezk4yV+E2/D1wHbEcfwntnfLX4iYgATMkrcBnjAOb0oZSQ5pqq3qMZFvK0ibgU//haX8QruiWA6+R7IENyL0amFFH3iRgarnz4xf+TtzMUZ0ubueU1wu4Fx91vg1cA1RlZQ0YkO0PJLOl4gtW1wILk4x7gJ5Z/kQaZxM/DV+QeR9XLvNwu9s22TE9cDPSQuADMntbubpm6a3wVfhaYPtCXhXwG+B1fHS6IF3Ltim/A/AnvBPPw78IqqXybOIXlEk/DpiT2j0FX6RuKZv46nQfV6b7NR7omF3zKem87+IL6dOBC8v1sdhia+oWDrCCIAgqmIr9t/sgCIJgEynxZPOtqWM7YFPUqSVI337X1a4Rm7p+QeOR9EBd93JT1y0IcsKcEgRBUMGEOSUIgqCCCSUeBEFQwYQSDzZ7JA2XOw5r18JyJ8odkbWErMck3dESsoLPF6HEgyAIKphQ4kEQBBVMKPGg4pHUX9I9cv/rKyW9KOmkBspsJelSuf/0j+S+1sdk+a3lvsfnp/w6I/dIOkTSrHTuJyR9pZBfJekauY/41XK/9Ye2TOuDzzsRFSbYHNgZ918xFv9X+P2BCZLWmjv52gBJwl0A98f96MzA3YTm/6MwGnd3Ogp37jYEuE2SFWTuBFwGXIy7E70cuF3SV23997vjSAEJcD8+pwP3SRpkZk+0QPuDzzHxnXiwWZEUdGvcV3RvMztIHvN1AtDezGokHYYHLDnKPCJPUUZn3L/MpWY2Kku/H9jVzL6c9ifi/uH7mNnrKe1o3IdPHzN7VR6h6t/AD83s5nRMK2AWsNDMDktpjwFLzOwzcdAVbL6EOSWoeCR1SuaKebhD/o9xb4671VHkIGBpOQWe2JP1Dqxybsf9tuc+weeWFHji5fS3FKXlm7jHunWyzD3ZTcG9dQZBswglHmwOTMTD1V0GHIorzpvwwB/l6MKGQUCK7JD+vltIL+13ztKqC8esSX9L594BjxSzqoysKhXCGgbBxhI28aCikcclHYzHLBybpdc3QHmf9Yq6HCUFv106tkQpDubGBDV+B2gnqaqgyLsCq8zso42QFQSfIkbiQaWzJd6P1ynDFAzkyHrKPAJ0ljS4jvyXgFV41Jic4/HIS42JCFXiOdxH+Tpbd7LbH4cHUg6CZhEj8aCiMbPlkp4DRkr6AA9ddz4eiKRDHcUeBh4CJkkaDfwTH5kfaGZnmtlSSVcBF0iqxUNqHYtHlTphI+v3iqTJwHXp5fIm/nXK7niA6yBoFqHEg82BE4Eb8DB67wPX4QuTZ5c72Mwshby7CDgHDyn4HzzaUYmReHSjs3DTxxt4BKA/N6F+pwO/SzI7Av8CBsfnhUFLEJ8YBkEQVDBhEw+CIKhgQokHQRBUMKHEgyAIKphQ4kEQBBVMKPEgCIIKJpR4EARBBRNKPAiCoIIJJR4EQVDBhBIPgiCoYP4LeYio5Fl3Co4AAAAASUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "                   combined      food   service\n",
            "No_Alcohol_Served  1.148075  1.194730  1.042417\n",
            "Full_Bar           1.287124  1.218315  1.170311\n",
            "Wine-Beer          1.231887  1.261840  1.174437\n"
          ]
        }
      ],
      "source": [
        "# mean rating as a function of alcohol\n",
        "mean_rating_plotting(X_val[['alcohol']])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "19ZxnhoS2d5q",
        "outputId": "3194d7b8-791b-46f9-bbc2-3c125b1e3b2f"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    41\n",
              "low       39\n",
              "high       7\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 109,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.alcohol == 'No_Alcohol_Served'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JOSHEiRH2d5q",
        "outputId": "a6640ac4-23bf-4f26-cad7-3222bc9d6a3d"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    15\n",
              "high      14\n",
              "low        5\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 110,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.alcohol == 'Wine-Beer'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "O4ELqhrS2d5q",
        "outputId": "83397c24-4776-4059-f4c4-3d5aa7845547"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "high      4\n",
              "medium    4\n",
              "low       1\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 111,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.alcohol == 'Full_Bar'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "moAKPhxV2d5q",
        "outputId": "9e8ab067-d508-4dfd-a834-5a3d2f282354"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "none        119\n",
              "variety       7\n",
              "Internet      4\n",
              "Name: other_services, dtype: int64"
            ]
          },
          "execution_count": 112,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.other_services.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 122
        },
        "id": "6mD6oLwa2d5r",
        "outputId": "2fe0c1ac-2bfc-417f-ce74-c61110ffd4ea"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "          combined      food   service\n",
            "none      1.156273  1.193252  1.067643\n",
            "variety   1.498639  1.520748  1.322449\n",
            "Internet  1.315972  1.291667  1.211806\n"
          ]
        }
      ],
      "source": [
        "# mean rating as a function of other_services\n",
        "mean_rating_plotting(X_val[['other_services']])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CtnbdNw22d5r",
        "outputId": "876d0de6-a739-42fb-da8c-18eab907be61"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    4\n",
              "low       2\n",
              "high      1\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 114,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.other_services == 'variety'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UWxE9Z_N2d5r",
        "outputId": "fb003ad2-b8af-403b-b559-fa66e0ea21b6"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    53\n",
              "low       43\n",
              "high      23\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 115,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.other_services == 'none'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xlvYJQDG2d5r",
        "outputId": "e7b766fc-0349-4c90-bee3-f53eb12601cb"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "informal    118\n",
              "casual       10\n",
              "formal        2\n",
              "Name: dress_code, dtype: int64"
            ]
          },
          "execution_count": 116,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.dress_code.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 122
        },
        "id": "iYdkhXCB2d5r",
        "outputId": "bf70dc34-6a7c-410d-dcd5-c87cc77b9c1c"
      },
      "outputs": [
        {
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAVwAAAFGCAYAAAAmWyfRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdd3hUxdfA8e8kpJCE3kvoVUSUoiiICIIgIoIiCCIoyquConQIHem9WfCHIhKkS5ESmigKqKAUQUB6Cx1CSUid94/ZhJRN2CRbUs7nefZJ9t65957NsofZuVOU1hohhBCO5+bqAIQQIruQhCuEEE4iCVcIIZxEEq4QQjiJJFwhhHASSbhCCOEkOVwdgKMULFhQlylTxtVhCCGymD179lzVWhdKy7FZNuGWKVOG3bt3uzoMIUQWo5Q6ndZjpUlBCCGcRBKuEEI4iSRcIYRwEkm4QgjhJJJwhRDCSSThCiGEk0jCFUIIJ5GEK4TIdj4Y9ys58p9DqRhy5D/HB+N+dcp1s+zAByGEsOaDcb/y+dDHINIXgOgbJfl8aD7gVz4bUN+h15YarhAiW5kzoUxcso0T6Wu2O5gkXCFEthJ9o3iqttuTJFwhRLbinu9CqrbbkyRc4XANGzbk1VdfjXs+fPhwChYs6MKIRHb2xkdHgJiEGz3u0q3fKYdfW26aCSGylaMXgwE33HyvEnM3P+75LtCt3ymH3zADSbgijcLCwsiZM6erwxAiVbYe/pOdC5pQ8pHjnNlbHqUASloejidNCukUeCCQMtPK4DbCjTLTyhB4INCp11+yZAnVq1fHy8sLf39/AgICiIqK4uTJkyilWLt2bYLy0dHRFC1alMGDB8dt++eff2jRogW5cuUiV65ctG3blosXL8bt37ZtG0opgoKCeOmll/Dz86NHjx4ATJ48mTp16pAnTx6KFClCy5YtOXbsmHNevBCpEB0TzRt9/oa7RZg/u6gl2TqXJNx0CDwQSLc13TgdchqN5nTIabqt6ea0pLtx40batWtHzZo1WbVqFR9++CGTJk2iR48elC1blscff5wlS5YkOObnn3/m0qVLtG/fHoBjx45Rr1497t27x4IFC5g3bx4HDx6kZcuWaK0THNu1a1dq1KjB6tWr6dq1KwDnzp2jR48erFq1iq+++oro6GieeuopQkJCnPI3EMJWUzYtJHhjB554/jTP1vd98AEOIE0KFh9v+Ji9F/em6phd53YRHh2eYFtoZChdV3Xlqz1f2XyeR4s+yrRm01J1bYChQ4fSsGFDvv32WwCaNWsGwMCBAxk8eDDt27dnxIgRhIeH4+XlBcDixYupVq0aDz/8MAAjRoygaNGirF+/Hk9PTwAeeeQRqlSpwrp162jRokXc9dq2bcuoUaMSxDB16tS436Ojo2nSpAmFCxdm1apVvPnmm6l+TUI4wrXQawwZFoWK8ea7maVcFofUcNMhcbJ90HZ7io6O5q+//qJt27YJtrdr146YmBh27tzJa6+9xq1bt9iwYQMAUVFRrFixgnbt2sWV37x5M61bt8bNzY2oqCiioqIoW7as1SWK4iffWLt27aJJkyYUKFCAHDly4OPjw507dzh69KgDXrUQafPBtzMI/7MT7TvfpGJFF7QlWEgN1yItNcwy08pwOiTp8kal85RmW5dtdogqeVevXiUyMpIiRYok2B77/Pr165QoUYL69euzePFiWrVqxZYtW7h69Wpcc0LsecaPH8/48eOTXOPs2bNWzx3rzJkzNG3alMcff5wvv/yS4sWL4+npSYsWLbh37569XqoQ6bL7wm6WzHgUT68opo11bXdESbjpMLrxaLqt6UZoZGjcNh8PH0Y3Hu3waxcsWBAPDw8uX76cYPulS5cAyJ8/P2BqvAMGDCAsLIzFixfz2GOPUbFixbjy+fPnp3Xr1rzzzjtWrxGfSnSXYcOGDYSGhrJq1Sp8fU2bWFRUFNevX0//CxTCDmJ0DJ1nzIHDc+g77B6FC7s2HmlSSIeO1Tsyp+UcSucpjUJROk9p5rScQ8fqHR1+bXd3d2rVqsXSpUsTbF+yZAlubm48+eSTgGl3DQsL44cffuCHH35IULsFaNy4MQcPHqRWrVrUrl07weNBy8yHhYXh5uZGjhz3/99esmQJUVFR9nmRQqTTN3/P41BgF/IWCmVgX29XhyM13PTqWL2jUxKsNSNGjOD555/nrbfeon379hw4cIAhQ4bw7rvvUrKk6VdYuHBhGjZsSJ8+fbh58yavvfZagnMMHz6cxx9/nBYtWvD2229TsGBBzp8/z6ZNm+jSpQsNGzZM9vqNGjUiOjqat956i65du3Lw4EEmTZpE3rx5HfmyhbDJjbAbfDL9Zzj3NuO/1Pi6pmNCAlLDzcSaNm3KokWL2L17Ny1btmTatGn07t2bWbNmJSjXvn17goODqVu3bpJaa6VKldi1axc+Pj5069aN5s2bM2zYMLy8vKhQoUKK169evTrz5s3j999/58UXX2ThwoUsXbqUPHny2PulCpFqgzYN4/baQZSteI+333bdjbL4VOK+lllF7dq1deK77EKI7GHvxb3UfHcO+sfPWLUKXnrJfudWSu3RWtdOy7HSpCCEyFJidAzvregD2xbyZL1IWrb0cHVIcSThCiGylAX7F/D70npwpzBTJuGSIbzJkYQrhMgyQu6F0Hv5RNx2/k7rVzV162agbIvcNBNCZCHDtg3j6voPUNE5GTsmYyVbkIQrhMgiDlw6wMx1G1F/deO9/1PEG9+TYUiTghAi09Na031dd9x/Go+njxtDh7o6IuukhiuEyPS+/+d7tv8WSeQ/LenfT7l8CG9ypIYrhMjUboXfondQH/y2rcOvqKZXr4zXdhtLEq4QIlMb+fNILu6pA8cfZfKXZIghvMmRJoVMbuTIkZQoUQI3Nze6dOni0Gv9+OOPKKU4deqUQ68jhK0OXTnEtB2zyPPrF1SpAm+/7eqIUiY13Exs9+7dDBs2jDFjxtCwYUMKZ9SGKyEcQGvNh+s/xHP/e4ScK8a3KyFHBs9oGTw8kZLDhw8D0L17d3Lnzu3iaIRwrqWHlrL1yC5y/7KamvXsO1+Co0iTQibVpUsXOnXqBECePHlQSrFt2zZOnjzJyy+/TO7cucmVK5fVVXRDQ0P56KOPKFq0KN7e3tSpU4eNGzcmKKO1Zvjw4RQuXJhcuXLx5ptvcuvWLae9PiFScifiDr2CelHswERuXfNlwoSMNYQ3WVrrLPmoVauWdooFC7QuXVprpczPBQucctljx47pwYMHa0Bv3bpV79y5U9+8eVOXLVtWV6pUSS9atEgvW7ZMV6tWTRcvXlxfu3Yt7tgOHTpoPz8/PWPGDL1u3TrdunVrnSNHDr19+/a4MtOmTdNKKR0QEKA3bNigu3XrpkuUKKEBffLkSae8RiGS039Tf02fQjqnb5Ru08a51wZ26zTmJZcnRkc9nJJwFyzQ2sfH/BljHz4+Tku633zzjQb07du3tdZaf/7559rd3V0fP348rszZs2e1h4eHHjNmjNZa60OHDmmllJ43b15cmejoaF2tWjXdtGlTrbXWUVFRulixYvq9995LcL3nnntOEq5wucNXDmuPkR66cvNN2t1d68OHnXv99CRcacON9fHHsDd1y6SzaxeEJ1qhNzQUunaFr2xfJp1HH4VpqV/EMrE//viDmjVrUq5cubhtJUuWpF69evz6668A/Pnnn2itE6z26+bmRtu2bZkwYQJgFo8MDg6mVatWCc7fpk0bNm/enO44hUgrrc2NMq+Qhzm+qTHdukHlyq6OynZOb8NVSrVXSm1XSt1SSj1w8Sul1JtKqYNKqdtKqdNKqeEq8WqGrpI42T5ou4MFBwcnWVkXzGq7sQs7BgcH4+fnh4+PT5IyoaGhhIeHc/HiRYAkvR6kF4RwtR8O/8CmE5uo8PdivLwUw4a5OqLUcUUN9wbwGZATmJNSQaVUDeBroA2wBqgM/AScB1JRhbRBWmqYZcrA6aTLpFO6NGzblt6IUq1YsWIcPHgwyfZLly7FreJbrFgx7ty5Q2hoaIKke+nSJXx8fPDy8qJo0aIASVYETvxcCGcKjQzlk6BPKH+3I3u3VmT4cLBSv8jQnF7D1VoHaa2/B07YULw8cFlrvdrSfHIY2AbUcGSMNhs9GhLVFPHxMdtd4IknnmDPnj2cPHkybtv58+fZsWMH9evXB6BOnToopVi2bFlcGa01y5Ytiyvj7+9P0aJFWbVqVYLzr1ixwgmvQgjrxmwfw5mbZ/D9eTZFikDv3q6OKA3S2vib3gfQEIh6QBlfYDfQGvOfw8OY2m3TZMp3s5TfXapUqXQ2jdvIRb0UtE560+zevXu6bNmyunLlynrx4sV62bJlunr16lZ7KeTKlUvPmjVLr1+/Xrdp0yZJL4UpU6ZoNzc3PXjwYB0UFCS9FIRLHb16VHuO8tTPDJisQevPP3ddLGTGXgq2JFxLue7AbSAK0MA4W87vtG5hLpQ44Wqt9fHjx3WrVq20n5+f9vX11S1atNBHjx5NcNzdu3d1jx49dOHChbWnp6euVauW3rBhQ4IyMTExevDgwbpgwYLaz89Pd+jQQQcGBkrCFU4XExOjmy9orv1G5dUVK0foSpW0johwXTzpSbguW7VXKdUQ2Ky1TrYdWSn1FjABeBH4EygNfA9s0loPSen8smqvEFnD6iOrabWoFW3DNrJ0fBNWrIDWrV0XT3pW7c3oI81qAVu11r9rrWO01ieBQKCli+MSQjhBWGQYPTf0pGru2vw6/zmeegpeftnVUaWdK7qFuSulvAFPy3Nvy8NaV6/fgGeVUrUsZf2BN4A9TgtYCOEy438bz6mbp6h7bjHBwSrzDOFNhitquJ2AMCAIcLf8HgaUVko9rZS6o5QqBaBNb4aJwCKl1G3gD+AfoJcL4hZCONGJGycY9+s4WpV8l2VflePll6FePVdHlT5O74ertZ4HzEtm9ynAL1H5iZikK4TIRj4J+oQcbjnI98cUQkNh7FhXR5R+Gb0NVwiRDa37bx2rj6zmg/JTWPC1H++8A1WquDqq9JOEK4TIUO5F3eOj9R9RpWAVTi7vipcXDB/u6qjsQxKuECJDmbRjEsdvHOeDYvNYttSd3r3BMto805OEK4TIME7fPM2Y7WNoU+UVls94gsKFoU8fV0dlPzI9oxAiw+i1sRdKKV7kM97+GWbPhly5XB2V/UgNVwiRIWw8vpEV/65gwJODmTSyMBUrwrvvOuhigYFmtj83N/MzMNBBF0pIEq5Ik3nz5qGU4s6dO64ORWQB4VHhfLj+Qyrmr0ih//pw6JDpBubh4YCLBQZCt25malWtzc9u3ZySdCXhijRp0aIFO3fuTDKRuRBpMXXXVI5eO8qEhrMYNcKDunWhTRsHXSwgwKzMEl9oqNnuYNKGK+JorQkPD8fb2/uBZQsVKkShQoWcEJXI6s6GnGXUL6NoVbkVh9Y05cIFWLTIgUN4z5xJ3XY7khpuOrmoKQiAgwcP0qxZM/Lnz4+vry9Vq1Zl9uzZcftXrVpF7dq18fb2pmjRovTr14/IyMi4/cOHD6dgwYL8+uuv1KlTB29vbxYvXoyvr2+C88SqU6cOb7zxBmC9SSEsLIx+/fpRunRpvLy8KFu2LAMHDkxwjv/9739Uq1YNLy8vSpcuHbeOmsi++mzqQ4yOYUjtGYwbBy+9BE8/7cALFihgfXupUg68qCE13HSIbQqK/XYS2xQE0LGj46/fsmVLqlatyoIFC/Dy8uLIkSPcunULgCVLlvD666/zf//3f4wZM4bjx48zcOBAYmJimDRpUtw5QkND6dy5M/369aNSpUoUL16cF198kSVLltC9e/e4cidOnGD37t0MS2YRKa01rVq1YufOnQwZMoRatWpx/vx5tm/fHldm4sSJDBo0iH79+tGwYUP27NnDkCFD8PHxoUePHg76K4mMbMuJLSw5uIQRDUcwf2Yp7t6FceMceMGffoIbN0wNKSbm/nZnrdSS1ol0M/ojtROQ9+yp9TPPpO7h5aUTrJAe+/DySt15evZMVahaa62vXLmiAb1///4k+2JiYnSpUqV0ly5dEmyfO3eu9vb21levXtVaaz1s2DAN6JUrVyYot2LFCu3m5qbPnz8ft23MmDE6X758OsIy83Piyc83bNigAb1q1Sqr8YaEhGhfX189fPjwBNuHDBmiixQpoqOiolL5FxCZXXhUuK46q6ouN72cPnj4nvbw0Prddx14wX37tM6dW+uqVbX+8ss0r9RCOiYglyaFdHDlor358+fH39+f9957j8WLFydY4PHo0aOcOXOG1157jaioqLhHo0aNuHfvHv/8809cWaUUzZs3T3Du5s2b4+fnx9KlS+O2LV68mNatW+ORzG3jrVu3kj9/fl566SWr+3fu3Mndu3dp27ZtkpguXbrEuXPn0vPnEJnQjN9n8O/Vf5nebDojh3nh4eHAIbxnzkDz5qZT74YN5qvoqVOmlnvqlHO+kiJNCnEy26K9bm5ubNy4kYCAAN5++23CwsKoV68eM2bMINTSxvHCCy9YPfbs2bNxv+fLlw9PT88E+729vWnVqhWLFy+mZ8+eHDlyhH379jFxYvKTtl27do1ixYolu//q1asAVKtWLdmYSpcunezxImu5cPsCI34eQYuKLSgS8iKLF8PgwVC8uAMudu0aPP883L0L27c7pa02OZJw02H06IRtuODcRXurVKnC8uXLiYyMZPv27fTv358WLVqwadMmAObMmcNjjz2W5LiyZcvG/W593ndo164dLVu25MyZMyxevJhChQrRqFGjZGMpUKAAwcHBye6PXab9xx9/pIiVta0rV66c7LEi6+m7qS+R0ZFMe346774KhQpB374OuFBYmLkLd+IEbNwI1as74CKpkNa2iIz+cNYiki5ctDeJhQsXakBfu3ZNlyhRQg8aNCjF8sOGDdMFChSwui8iIkLny5dPT5w4UT/00EP6/fffT7A/cRtuUFCQBvSaNWusnu/GjRs6Z86ces6cOWl4ZSIr2XZym2Y4esjWIXrtWnPfY+ZMB1woMlLrVq3Mh3PpUrudlnS04UoNN506dnRa808C+/fvp0+fPrRr145y5cpx48YNxo8fT40aNcifPz+TJ0+mU6dO3Lp1i+bNm+Pp6cmJEydYuXIly5Yte+CABQ8PD9q0acOUKVMIDg7ms88+S7F8kyZNeP755+nQoQNDhw6lZs2aBAcH88svv/Dll1+SN29ehg8fTs+ePTl9+jQNGjQgJiaGo0eP8tNPP/HDDz/Y888jMqjI6Eh6rO9B6Tyl6fvkAJ6qAxUq3O/dYzdaQ/fusGoVzJgBr75q5wukUVozdUZ/ZPVl0i9duqTfeOMNXbZsWe3l5aWLFCmi27dvr0+fPh1XZt26dbp+/frax8dH58qVS9eoUUMHBAToyMhIrXXKNVyttd60aZMGdPHixXV0dHSCfdaWaA8NDdW9e/fWJUqU0J6enrpMmTJJatnfffedrlmzpvb29tZ58+bVjz/+uJ48ebI9/iQiE5i6c6pmOPqHf3/QX39tardLljjgQiNGmJMPGGD3U5MZl0l3NFkmXYiM5eKdi1SeVZknSz7J8tbrqVxZUaIE7Npl51Fl//ufmfXmzTdh3jy7D1lLzzLp0qQghHCK/pv7ExYZxozmM5g5U3H+PCxcaOd8uGYN/N//mV4J//tfhlviV/rhCiEc7rczvzF/33z6PNWH/LoSY8dCy5bQoIEdL7JrF7RrBzVrwrJlDppqLH2khiuEcKiomCi6r+uOf25/Ap4OYHB/uHPHzkN4jxyBF180HXnXrgU/vwcf4wKScIUQDvXF7i/Yd2kfS9su5fJ5X2bPhrffhocestMFgoNNE4KbGwQFQeHCdjqx/UnCFUI4zOW7lxm8dTCNyzbmlaqv0LEj5MgBI0bY6QIhIWbI7tWrZnhn+fJ2OrFjSBuuEMJhBm4eyN3Iu8xsPpO//lJ8/z306mWnIbzh4WaW8oMHYflyqJ2mjgNOJTVcIYRD7Dq3i6/3fk3fp/pSpWBVnmsPBQtCv352OHlMDHTpAlu3wrffmiaFTEASrhDC7qJjoum+rjvFcxVnSIMhBAWZ3Dh9OuTObYcL9O1rloUYN870t80kJOEKIezuq7++4q/gv/j+le/xyZGLfv2gXDl47z07nHzyZJgyBT780E7VZeeRhCuEsKuroVcZtGUQz5R+hnbV2jF/Phw4YCqkiWYCTb2FC6FPHzM3wtSpGW5gw4PITTMhhF0FbAngVvgtZr0wi3v3FIMHQ5060LZtOk+8ZYtpt33mGfjuO3B3t0e4TiU1XCGE3ey+sJuv/vqKj+t+zMOFH2bCBDh3zuRHt/RU7/7+G1q3hsqVYeVKsGFl6YxIJq8RQthFjI7hyblPcibkDEd6HCHyTm7Kl4f69eHHH9Nx4pMn4cknTXvEzp1QooTdYk4LmbxGCOFyX//9NX+c/4PvWn9Hbq/c9B4Et2+ncwjv1aumy1dEhOnm4OJkm16ScIUQ6XY97DoDNg+gfqn6dKzekVOnYNYs0+T68MNpPOndu2Z+hLNnYfNmO44Fdh1JuEKIdBuydQg37t1gVvNZKGVulLm5pWMIb1SUmfnrzz/NKLJ69ewar6tILwUhRLr8Hfw3X+z5gu51ulOjaA3++gsCA+GTT6BkyTScUGszp+3atTB7Nrz8st1jdhVJuEKINIvRMXRf152CPgUZ+exItDZjEQoUgP7903jSYcPg669hyBA7jZTIOKRJQQiRZvP3zWfnuZ180+ob8nrnJSjIdJedNg3y5EnDCb/4AkaNgq5d7TilWMYh3cKEEGly895NKs+qTLl85fjt7d/QMW7UqgW3bsG//4KXVypPuHIlvPKKmW5x5Uozj2MG5PBuYUqpGCC5zKyBW8A+YIbWWta7FiIbGPbTMK7cvcL6jutxU27MD4R9++D779OQbH/7DV5/3QxJW7w4wybb9LL1VfWyPG4Ba4ArQGGgJZALmAs8DSxTSnXWWi9wQKxCiAxi/6X9zPpzFu/Vfo+axWpy7x4MHgy1asFrr6XyZIcOmQXOSpUyIyR8fR0Sc0Zga8ItDvymtX490fYBSqlFQD6t9XNKqflAP0ASrhBZlNaa7uu6k887H582+hSAmTNNd9lvv03lEN5z56BZM1Ml3rDBTJibhdn6p3kL+CaZfd8AnSy/LwYqpjcoIUTGFXggkF/P/MrYxmPJnzM/16/DmDGm6fXZZ1Nxops3zUE3b8K6dVC2rMNizihsTbg5gCrJ7Ksa7zwRwL30BiWEyJhuhd+i76a+1Cleh641uwIwdqxZWmz8+FSc6N4907/2yBFYsQIee8wxAWcwtjYpLALGKqVycL8NtxDQChjJ/dpvTeCwvYMUQmQMI7aN4NKdS6xuvxo35cbp0zBjBnTuDNWr23iS6Gjo1Al+/tnMb/vccw6NOSOxNeH2xNRePwUmxtseDnwF9LU8/x3YYrfohBAZxsHLB5n++3TeqfkOdUrUAczYBDc3GDnSxpNobYagLVsGkyaZngnZiE0JV2sdAfRUSo0AqgNFgYvAAa319XjltjkiSCGEa2mt6bG+B7m9cjOm8RgA9u6FBQvMyDJ/fxtPNGGCucPWqxf07u24gDOoVHV2syTXnx0UixAig1p8cDHbTm3jsxc+o6CP6UnQvz/kywcDBth4kvnzTeHXX4eJEx9cPguyOeEqpbyBBkBJIPF061pr/bmN52kPdAdqAD5a6xRjUEr5AmOBtpg+v2eBDlrrv22NXQiRdnci7tB7Y29qFqtJt1rdANi0CTZuNGs55s1rw0k2bDDDdRs1gm++SefyD5mXrSPN6gPLMTfKrNGATQkXuAF8BuQE5jzgugpYCYQBj2utzyqlygF3bbyWECKdRv08igu3L7Cs7TLc3dyJiTHNCGXKwAcf2HCC3bvNoo/VqsEPP6RhGFrWYWsNdwZwAmgKHNJaR6b1glrrIAClVEMbijcF6gElY9uKtdYn0nptIUTqHL56mCm7pvDWo2/xpP+TgOlYsHevmYLxgbnz2DF44QUoVAjWr4fcuR0fdAZma72+MjBca70vPck2DZ4FTgIjlFKXlVLHlVJjlFIe1gorpboppXYrpXZfuXLFiWEKkfVorflw/Yf4evgy7jmzTk7sEN6aNaF9+wec4PJlM4osJsY0KRQr5vigMzhbE+5+TM8EZysIPITpflYKaIZpy+1nrbDWeo7WurbWunahQsm1fgghbLH83+VsPrGZUc+OorBvYcDMB376tOlskGIz7J070KIFXLhg5keoXNk5QWdwtibc94FPlFLPODIYK24D0UCA1vqe1vo/YDZmwIUQwkHuRtylV1AvHinyCO/XeR+AGzdg9GizpmPjxikcHBlp2mz//huWLIG6dZ0TdCZgaxvuJsAH2KqUisAkwgS01oXtGZjF3mS2Z81JfIXIIMZsH8PZW2dZ+MpCcriZNDF2rJn2IMUhvFrDO+9AUBB89ZVZBFLEsTXhzsZOSU4p5Q54AJ6W57FdzMJ10tnQVwDjMG24Q4ESmNr21/aIRQiR1H/X/mPSzkl0eqQT9UvVB+DMGTOEt1MnqFEjhYMHDTL9bUeMMIlXJGDrSLPhdrxmJxLOPBZm+VlWKeUPrAce0lqf0VrfVko9j0n4N4CrlmMn2TEeIYSF1pqPNnyEl7sXE5pMiNs+ZIj5OWpUCgfPmgXjxpkFIGMPEAk4fVp1rfU8YF4yu08BfonK78dMbi6EcLBVR1ax4dgGpjSdQlE/c5983z747jvo08fMEW7VsmXw0UfQqpW5s6aU84LORJJd00wptQQYqLU+bvk9RVrr1M7z7lCyppkQqRMWGUbV2VXx8/Tj7//7Gw930/uyWTP44w84ftwM5U3i55+haVOoXRs2b4acOZ0buJM5ak2zQpi2VjDL6ciNKiGysHG/juN0yGm2dd4Wl2w3bzb3vyZNSibZHjhgarXly8OaNVk+2aaXrNorhOD49eNU+6wabaq2YeErCwEzXqF2bbh+HQ4fBu/EM6icOQNPPWV6JuzcmUJ7Q9aSnhquTf1wlVJDlVLFk9lXzNKDQAiRSX0c9DEe7h5Manr/fvSiRaYr7aefWkm218WznCEAACAASURBVK+btobbt80osmySbNPL1oEPwzCzhFlT3LJfCJEJ/Xj0R348+iNDGwyleC5TrwoPh4AAePRR6NAh0QFhYfDSS6ZRd9WqVCz1IGztpaBIvg23JKbLlhAik7kXdY+eG3pSpWAVetbtGbf9s8/g1CkzBWOCIbzR0SYD79hhqsANGzo75Ewt2YSrlOoMdLY81cDnSqlbiYp5Y1aA2OiY8IQQjjTxt4mcuHGCzZ024+nuCZjRZJ9+ajoeNGkSr7DW0KMHrFwJ06fDaxmqY1KmkFINNxS4ZvldASHA9URlIjADFT6zf2hCCEc6dfMUY34dQ9uH2tK43P3JEcaNM/MmJBnCO3o0fPGFmQz3o4+cG2wWkWzC1VovBZYCKKW+AUZqrU86KzAhhGN9EvQJbsqNyU0nx207e9ZUXjt2NO23cb7+2owe69TJTKog0sTWob1vOToQIYTzbDi2gZWHVzKm0Rj889xfAXLoUNMd7NNP4xVeuxa6dTNtDHPnZtvlcewhNWualQHeACqRdE2zDDfSTAhhXXhUOB+t/4iK+SvS68lecdsPHIBvvzUL6pYubdn4++/Qtq2p7i5bBh5W5/4XNrJ1TbNawC/AGUzC3Q/kAcoA54BjDopPCGFnU3ZO4b/r/7Gh4wa8ctxfI6d/f8iTx0z4BcDRo2YS8WLFTC03Vy7XBJyF2PrdYCKmPfdhzA20rlrrckB9TA+GCSkcK4TIIM6EnOHT7Z/Sukprnq/wfNz2rVvNkmODBkH+/MDFi2amcTc3M7a3SBHXBZ2F2JpwHwW+B2Isz70BtNY7gBGYOWuFEBlc7429idExTH1+aty22FV4S5WCDz8Ebt0yCz9evmxqthUquC7gLMbWNlwNRGittVLqMlAa2GHZdxao6IjghBD2s/nEZpYdWsbIhiMpnbd03PYlS2DPHtN+6+0WAW3awP79ZjKaOnVcGHHWY2sN9xBQ3vL7Tsz6ZhWVUqUxCzoed0RwQgj7iIiO4MP1H1I+X3n61usbtz083DQj1KgBHV+Pgbfegi1bTG+E5s1dGHHWZGsNdw7mBhnAIMzIssOW53eBV+0blhDCnqbvms7hq4f58fUf8c5xv5PRF1/AyZNm/hn3Qf1h4UIYMwY6d07hbCKt0jQ9o1LKD3gSyAns0lpftndg6SXTMwphnL91nsqzKtOobCNWv746bntIiJnG9rHHYGPzqajevaB7d5g5U1ZsSIFDp2dUSnkrpTYqpRrGbtNa39Fab9Jar86IyVYIcV+fTX2IioliWrNpCbaPHw/XrsH4RkEm2b7yihlmJsnWYR6YcLXW94A6gLvjwxFC2NNPJ39i0T+L6F+vP+XylYvbfu4cTJ0KHRtfpOawltCgASxYAO7yMXckW2+arQZedmQgQgj7ioyO5MP1H1ImbxkG1B+QYN+wYRATHcOnu56DSpXMDGBJZhkX9mbrTbMgYKJSqhiwDrhEovlxtdbr7BybECIdZv0xi4NXDrKy3Upyetxfa+yff2DePM3H3nMoky8ENuxMZsEyYW823TRTSsU8oIjWWmeo7yJy00xkZ8G3g6k8qzL1S9VnbYe1qHjtsi82jeDXLfc47vcoBXasgWrVXBhp5uOoVXvjK5uWkwshXKPf5n6ER4czvdn0BMl224Z7rN3kzXj34RRYO1+SrZPZOj3jaUcHIoSwj+2nt7Ng/wIG1R9ExQL3B4HGRETRt/1ZSuLNh989DvXruzDK7EkmthQiC4mKiaLH+h745/Zn0NOD7u/QmqXN5rI7pCKfvvkfOV+Xe+CuYPN8uEKIjO/zPz9n/6X9LGu7DF9P37jtEUM/ZdBPHahe+CJvfN3IhRFmb5JwhcgiLt25xJCfhtCkXBPaVG1zf8eXX/Llp5c5QXnWfaOlq60LScIVIosYsGUAoZGhzGw+8/6NslWruPV+f0Z6nqZRvRiaNZdWRFeSv74QWcDOszuZt3cen9T9hMoFK5uNO3ZA+/ZMKDaFqxF5mDDRTUbtulhq1jTzBhoAJUm6ppnWWn9uz8CEELaJjomm+7rulMhVgiHPDDEb//0XWrbkfLHaTLn4Fq+/DrVquTZOYfuaZvWB5UChZIpoQBKuEC4wZ88c/r74N4teWYSfpx9cuADNmoGHB8PrrCXqB8Xo0a6OUoDtTQozgBPAY4CX1tot0UOa4YVwgauhVwnYGkCjso14rdprZs7F5s3h+nUOzf6Jr5flpnt3KCtDlzIEW5sUKgNttNb7HBmMECJ1Bm4eyO2I2+ZGWUQEvPwyHDoE69YxYGZV/PwgIMDVUYpYtibc/UBRRwYihEidP87/wdy/5/JJ3U94qEAVeP112LYNFizgF68mrFkDY8dCwYKujlTEsjXhvg/MU0qd0lr/7MiAhBAPFqNj6L6uO0X8ijDsmaHQq5dZDXLiRHSHjvStCyVKQM+ero5UxGdrwt0E+ABblVIRwO3EBbTWhe0ZmBAieXP/msvuC7tZ0HoBuWfOMSs1fPwx9O7NsmXwxx/w9deQM+eDzyWcx9aEO5tE898KIVzjeth1Bm4ZSIPSDeiwLwb69YN27WDyZCIiFYMGwcMPw5tvujpSkZits4UNd3AcQggbBWwJ4Oa9m3yT83XUG2/Ds8/Ct9+Cmxtz5sCxY7B2rayWkxHJSDMhMpG/gv/iyz1fMjZfW8q90xceegh++AG8vLh1C0aOhIYNTc8wkfGkZqTZk0BXoBJJR5qhtX7cjnEJIRKJvVFWOywfvT/dAgUKwPr1kCcPABMnwpUrMGGCLLybUdlUw1VKNQF+wQzrrQ9cAe4ANYACwD+OClAIYXy791uOH97F5oUeuEVFw4YNULw4YAaXTZlimnLr1HFxoCJZtjYpjASmAy0sz4dorRtharuRwDb7hyaEiHUj7AYj1/Zj23I/cl29BT/+CFWqxO0fPhwiI5EhvBmcrQn3IWA9EIPpreALcUvvDAdkLIsQDjR8UwCfzb9K1dOhqEWL4Mkn4/b9+y/MnQvvvw/ly7swSPFAtibce4CbNkv8BgPx39ZbmKYGIYQD7AveS81hn9P8P1BffAEvvZRg/4AB4OcHgwe7KEBhM1tvmu3DzKewCdgCDFRKnQciMM0NBxwTnhDZm9aafe+2pPNeCAvoT853302wf/t2WL3aNCUUSm4uP5Fh2FrDncb9gQ+DgLtAEPATUBjobv/QhBB/BHThzbXnONy6ATlHjU2wT2sz5qF4cTPITGR8tg58WBfv9/NKqVpABSAncFhrHeGg+ITItu4u+o464+bzS4281F+8KUlfrxUrYNcu+N//wMfHRUGKVEn1wAdlFksqBpzUWu9PbbJVSrVXSm1XSt1SSkWl4rjmSimtlPpfamMWItPZvh3PN99iVwnwW74GNw/PBLsjI2HgQDPuoXNnF8UoUs3mhKuUekEp9TvmBtpZ4BHL9q+UUm+k4po3gM8Am78EKaXyYLql/ZaK6wiROR08SHTLFhzLE82ycW9Ss3z9JEW++gr++w/Gj4ccshRspmHrwIc3gdXAYaAbEP+7zVHMCDSbaK2DtNbfY1aQsNUUYC5wLBXHCJH5nD2LbtaMGyqc9u/kIaD1lCRFbt+GESOgQQNo0cLKOUSGZWsNNwCYqLXuDCxItO8gpp+uQyilngceBSY56hpCZAg3bkCzZkTevEbj9hF88Mp4CvgUSFJs0iS4fNkM5ZUhvJmLrQm3NKZLmDX3gNz2CSchpVRuzOKU72ito20o300ptVsptfvKlSuOCEkIx7h3D1q1Qh87RsdOPng8Vot3ar6TpFhwMEyeDG3bwuMye0mmY2vCPYtZQNKa2jjuq/4kYLHW+m9bCmut52ita2utaxeSTokis4iOho4dYft2Ans3ZVmRa8x+YTbubknnVxwxAsLDYcwYF8Qp0s3W5va5wDCl1CVgpWWbUko1BvphBj84QlMgj1Iqtre3n+XCz2mtyzjomkI4j9ZmHZwVK7j46UDeipnI24+8zRMln0hS9PBh0wXs/fehQgUXxCrSzdaEOx7wB74FYr/a7wDcgS+11jNsvaBSyh3wADwtz2Onegy3DB2Or26iGKcAUUAfW68nRIY2dizMno3u04c3/P/AL9iPcc+Ns1p04EDT33bIECfHKOzG1oEPGuiulJoCPIeZkvE6sFVrfTSV1+wEfBPveZjlZ1mllD9mkpyHtNZntNYX4x+olAoForTWF1J5TSEynnnzzBrmHTuy7M3abFkxiVnNZ1HIN2lz2G+/wcqVMGoUFJbVAzMtlbRSmTXUrl1b796929VhCGHd+vXQsiU0asSdFYuo+lUNCvoUZPe7u5O03WoN9erBqVOm762vr2tCFoZSao/WunZajk1Vl2mlVGWgBNZXfFiX9AghRBJ//AGvvgo1asDy5YzeNYZzt86x6JVFVm+UrVwJO3fCnDmSbDM7mxKuUqo68D1QlYSDHmJpTHuuECIl//1nRisUKQJr13I0IpjJOyfzZo03qVeqXpLikZFm+sWqVeGtt1wQr7ArW2u4X2NWdngR0wVMJqsRIrUuXoTnnze/BwWhixTho8Au5PTIyYTnJlg9ZO5cOHoUVq2SIbxZga1vYVXgFa11kCODESLLun3b1GwvXYKffoKKFVn57w8EHQ9i2vPTKOJXJMkhd+6YpXOefto094rMz9aE+wdQypGBCJFlRUTAK6/Avn2wZg08/jihkaF8HPQx1QtXp/vj1qeTnjzZ5OeVK2UIb1Zha8LtBnxv6Zb1E3AzcQGtdag9AxMiS4iJga5dYdMm+OYbaN4cgLHbx3Im5Aw/d/mZHG5JP4YXL5q5El59FerWdXbQwlFsTbhXgVPA/BTKyE0zIRIbOBAWLDBr4HTpAsCx68eYsGMCHap3oEHpBlYPGzlShvBmRbYm3AXAk5i5DeSmmRC2mD4dJkyADz4widfi4w0f4+nuycQmE60eduSI6QL23ntQsaKzghXOYGvCfRZ4V2u90JHBCJFlLFkCn3wCbdrAjBlxjbBrjqxh7X9rmdRkEsVzFbd66KBBkDMnDB3qzICFM9g6W9gpQNpohbDFTz9Bp05meNiCBeBuWtvCIsPouaEnDxV6iI+e+MjqoTt2mLXK+vaVIbxZka013L7ACKXUXq31KQfGI0Tmtm8fvPyyaQtYvdpUVS0m/DaBkzdPsuXNLXi4eyQ5NHYV3qJFoVcvZwYtnMXWhDsC0y3sqFLqFNZ7Kch0yCJ7O33a9ELIlcvMlZAvX9yukzdOMu63cbxW7TUalW1k9fDVq80kNV98AX5+zgpaOJOtCfcfy0MIYc21a9CsGYSFwfbt4O+fYPcnQZ/grtyZ3HSy1cOjoswQ3sqVTS8ykTXZOj2jjOIWIjmhoWYo2MmTsHEjPPxwgt3r/1vPqiOrGNd4HCVzl7R6iq+/NhOM//CDDOHNymR6RiHSIyrKjCJbswaWLTO9EuIJjwrn4c8fxl25s//9/Xi6eyY5xd27ZgWH8uVN5VhGlWVsTpueUQgRj9bQvbtpfJ01K0myBZi0YxLHrh8j6I0gq8kWYMoUM7Js+XJJtlmdrd3ChBCJjRplRigMGmQSbyJnQs4wevto2lRtQ9PyTa2e4vJlMzaiTRt46ilHByxcTRKuEGnx1VcwbJgZrvvpp1aL9AoyfbumPj812dOMHGnus8kQ3uxBEq4QqbVmjRl327y5qeFaaQfYdHwTy/9dTsDTAZTKY32ivf/+gy+/hG7dTO8EkfVJwhUiNXbtgnbtoGZNM3zXI+kAhojoCD5c/yEV8legz1PJLzA9aBB4eZmKssge5KaZELY6fNhMIl6iBKxdm+zohKk7p3Lk2hHWdViHVw4vq2V27TKdGoYPN6vtiOxBarhC2OLCBTOwIUcOCApKdqKDc7fOMeqXUbxU+SWaV2xutUzsEN4iRaB3b0cGLTIaqeEK8SAhIfDCC2Y02bZtUK5cskX7bOxDtI5m2vPTki2zZo3pb/v55zKEN7uRGq4QKQkPN322Dh40HWVr1Uq26E8nf2LxwcUMqDeAsvnKWi0TO4S3UiUZwpsdSQ1XiOTExEDnzrB1K3z3HTS13pcWIDI6kh7re1A2b1n61euXbLlvvoF//zVTMFq53yayOEm4QiSnTx9YvBjGj4c33kix6IzfZ3DoyiFWt19NTo+cVsvcvWt6JDz1lJnBUWQ/knCFsGbyZJg6FXr2NLOBpyD4djDDfx7OCxVf4MVKLyZbbupUCA6GpUtlCG92JW24QiQWGGhqt6+9ZiY6eEB27LupLxHREUxvNh2VTNnYIbwvv2wWghDZkyRcIeLbvBneegsaNoT588Et5Y/IL6d/IfBAIP2e6keF/BWSLTdqlJnFcexYO8crMhVJuELE+vtvaN0aqlSBlSvNMLAURMVE0WNdD0rnKc3ApwcmW+7YMbOKwzvvmFOL7EsSrsi+AgOhTBlTiy1RwtRq8+c3y+PkyfPAw2f/MZsDlw8w9fmp+Hj4JFtu0CDw9JQhvEJumonsKjDQzBoTalmM+sIF83PwYJN8H+DSnUsM3TaUpuWb8nKV5Lsc/P67uUk2dCgUK2aPwEVmJjVckT0NGnQ/2cY3e7ZNh/ff3J+wyDBmNp+Z7I2y2CG8hQube3BCSA1XZF3R0XDmDBw9auZCjP/zzBnrxyS3PZ4dZ3fw7b5vGVBvAJUKVEq23Nq18MsvJofnypXWFyGyEkm4InPT2jQHJE6q//0Hx49DRMT9sn5+ZkxtnTpmXoSQkKTnK2V97tpY0THRdF/XnZK5SzK4weBky0VFQf/+ULEivPtuWl+cyGok4YqMT2u4ejVpLTU2scZvGvDyMisyVqliVtKtVMlkvUqVzPRcsV//E7fhAvj4wOjRKYby5Z4v2XtxL0teXYKvp2+y5b79Fg4dMlMwyhBeEUtW7RUZR0jI/SSaOLHevHm/XI4cULbs/UQa/6e//wP7zsYJDISAANOMUKqUSbYdOyZb/MrdK1SaVYmaxWqyudPmZNtuQ0NNKKVKwY4dMqosq5FVe0XmERpqOqZaS6yXL98vp5TJWBUrQocOCZNqmTL2qTZ27Jhigk1s4JaB3Im4w6zms5JNtgDTpplWjkWLJNmKhCThCvuLiICTJ63frDp3LmHZokVNIk389b98efD2dk38Vvx+7nfm/j2XPk/2oWqhqsmWu3IFxo2Dl16Cp592YoAiU5CEK9ImtgeAta//p06Z/bHy5TNJ9NlnE9ZUK1bMFLfvY2+UFc9VnKHPDE2x7KefmlnBxo1zUnAiU5GEK5KntZneylpN1VoPgIoVzQTdr7+eMLEWKOC612AHc/+ey57gPSxss5BcXsn/B3H8uFnFoWtXqJp8JVhkY5JwszutTRep+Hf94/9+9+79srE9ACpXNk0A8ZNq0aJZssHyWug1Bm4ZyDOln6H9w+1TLBsQYJqWhw93Tmwi85GEm13cumX96//Rowl7ALi7mx4AlSrBM88kbFctWdLsz0YCtgYQci+EWS+kfKPszz/NXOWDB0Px4k4MUGQqknCzkrCw+z0AEifWS5cSlo3tAZD463/ZstJx1GL3hd3M2TOHnk/05OHCDydbLnYIb6FCD5yrXGRzknAzm8jI5HsAnD2bsGzRoiaJtmiRtAdATuvLwAgjRsfQY10PCvsWZnjD4SmWXb/eLOY7cybkzu2U8EQmJQk3I4qONsnTWrvqyZPWewAk/vpfoYJ8+tNh3t55/H7+d+a/PJ883slP1RgdbYbwVqhgBq4JkRJJuK4S2wPA2tf/Y8cS9gDw9TWJtGZNaNcuYWLN5D0AMqIbYTfov7k/9fzr8cYjKS8eOX8+/PMPLFli5rwVIiWScB0tfg+AxD8T9wAoX/5+E0D8dtVixbJkD4CMashPQ7gedp3ZL8xO8UZZaCgMGQKPPw6vvurEAEWm5fSEq5RqD3QHagA+WutkY1BK1QWGALUBb+AYMEprvdIZsdrs9u3kewDcuHG/XGwPgIoVTRNA4jkAslkPgIxo78W9fL77cz6o/QE1itZIseyMGXD+PCxcKP8fCts4ffIapdTzQH4gJzDnAQn3BaAgsA64DrwEfA800Fr/mdJ1UjV5jS2TmISFmZ7t1marungxYVl//6STqlSqZOYAkO+dGVaMjuHpb57mv2v/cfTDo+T1zpts2atXzReSBg1gzRonBilcLlNNXqO1DgJQSjW0oey6RJtWKqX2AU8DKSZcmyWepu/0aTNUaP16c9MpNrGePWvaXWMVKWIS6QsvJEys5cubaf5EprNg/wJ2nN3B1y99nWKyBfN/8p07MoRXpE6masNVShUFqgH77HbSgICkS62Eh5tEnDevSaRPP520xio9ALKUkHsh9NvUjydKPEHnRzunWPbECbOKw1tvQbVqTgpQZAmZJuEqpXyB5cBarfWWZMp0A7oBlHrAzP1xkltSRSm4fl0a57KJYduGcfnuZdZ2WIubSnk+3cGDzZS8I0Y4KTiRZWSKhKuUygWsBS4DbyZXTms9B5gDpg3XppOXKmWaEaxtl2SbpQUeCCRgSwBnQs6g0TQu05haxWuleMzu3fD992YNShsW9xUigQy/aq9SqgCwBbgAtNVaRzzgkNQZPTppm6sNS62IzC1wfyDvrn6X0yGn0Zj/m3ec20HggcBkj9HaDHIoWNAM5RUitVzRLcwd8AA8Lc9jZ5kO14m6TFjabDcDe4C3tdbR2Ftsb4RULLUinC86Jpq7kXe5HX6bOxF3uB1h+ZnC85TKhIQnXUAyLCqMgC0BdKxu/b0PCoKtW2H6dMiT/OAzIZLlim5hXYBvrOwqC/gD64GHtNZnlFLDgOFAKBA/0DFa6zEpXUfWNHOt8KjwJEnOliSZ3DGhkaEPvqhFzhw5yeWVCz9PP3J5Wn4mej7zj5lWj1UoYobFJNkeHQ2PPWbGqvz7r/Tuy84yW7ewecC8ZHafAvzilR0ByK0JB4vRMYRGhtpUe7SWFK09j4yJtOnabsrNalL0z+1vnnskTZYPeu7u9uABJKuPrOZ0SNK2+1J5rN9sXbAADhww65RJshVplSlumomEIqMjba8tWqk9Jt52N+JuXDvmg3jn8E6S7PJ456Fk7pKpSoqxz3PmyJni8FlHGd14NN3WdEtQc/bx8GF046Rt92FhpmdCnTrQtq0zoxRZjSRcEt6tLpWnFKMbj062HS+1tNaERYWl3NaYwldqa8/Do8NturZCWU12JXKXSJj8bEySfp5+eLhnjblyY99fW973mTPN2pfffWf7CuxCWOP0NlxnsbUNN/BAYJKaTs4cORn/3HieK/dcum/Q3Im4Q4xO2iZojae7Z1yCs5r8Uvn1OqdHzgf2KRUpu3bNDB6sXx9+/NHV0YiMIFO14WY0AVsCktyQCYsK46MNHz3wWF8P3yQJr4hfESp4VkjT12tPd2kczGjGjDFzE8kQXmEP2T7hnglJZqQZ8P0r3yebJH09faX2mMWdOgWzZkGXLvBw8ivsCGGzbJ9wS+UpZfVudek8pR+4SqvI2gYPNm22MoRX2Eu2r6KNbjwaH4+EI82Su1stso+//jLzF33yiVmsWAh7yPYJt2P1jsxpOYfSeUqjUJTOU5o5LefYrZeCyHxiV+EtUMAM5RXCXrJ9kwKYpCsJVsTauBG2bIFp02QIr7CvbF/DFSK+2FV4y5aF995zdTQiq5EarhDxBAbCvn1mnTIvL1dHI7IaqeEKYXHvnumZUKuWWY1eCHuTGq4QFjNnmqXr5s2TIbzCMeSflRCY1ZTGjIHmzaFRI1dHI7IqSbhCYJJtSIgM4RWOJQlXZFuBgVCmjGk+mDzZTFDzyCOujkpkZZJwRbYUGAjdupn1Q2MnzNu922wXwlHkppnIFm7dMjfEzp41c9v26QOhiVbtCQszS9vJcnbCUSThikwvNNQk0diEau1x65Zt5zqT/ORxQqSbJFyRoYWHw/nzKSfT69eTHle4MPj7Q8WKpteBv//9R8mS0KCB9eRayvqSZkLYhSRc4TJRUXDhQvKJ9Nw5uHQp6XH5899Pnk89dT+Jxm4rUQK8vVO+9pgxpg03frOCjw+MlknihANJwhUOERMDFy8mTaDxnwcHm3Lx5c59P4E+9ljCmmnsdl/f9McX204bEGBquqVKmWQr7bfCkbL9mmYi9bSGK1esJ9HYx/nzpgYbX86cSRNo4kfu3K55TULYStY0E3ajNdy8mXKb6blzpm01Pk/P+1/rn37aejLNlw9csCK6EBmGJNxs5vbtByfTu3cTHuPubtpF/f2hTh1o0ybhV3x/fyhUSOYfEOJBJOFmIWFhySfR2N9DQhIeoxQUK2aSZvXq8MILCW9A+ftD0aIm6Qoh0kcSbiYREXE/cSbXbnrtWtLjChc2CbR8eWjYMOnX/OLFwcPD6S9HiGxJEm4GEBVl7tin9FXfWveofPnuJ866dZMmU1u6RwkhnEcSroPFxJhkmVIytdY9Kleu+4nz0Ucd1z1KCOE8knAxE5akpT+m1nD1aso3oM6fh8jIhMfF7x7VpEnSG1D+/rJ4oRBZUbZPuLGzRsWOODp92jwHcwMppY77586ZZVnii989qn79pDeg/P3NSCnpHiVE9pPtBz6UKWOSbGJK3Z+2L5a7u7nJlFLHfekeJUTWJgMf0iG52aG0NpNSS/coIYS9ZPuEW6qU9Rpu6dLQq5fz4xFCZF3Z/svv6NFmlqj4ZNYoIYQjZPuE27EjzJljarRKmZ9z5sisUUII+8v2TQpgkqskWCGEo2X7Gq4QQjiLJFwhhHASSbhCCOEkknCFEMJJJOEKIYSTSMIVQggnkYQrhBBOIglXCCGcJMvOFqaUugJYmSUhRQWBqw4IR2Rs8r5nX2l570trrQul5WJZNuGmhVJqd1qnXROZl7zv2Zez33tpUhBCCCeRhCuEEE4iCTehOa4OQLiEvO/Zl1Pfe2nDFUIIJ5EarhBCOEmmSLhKqfVKqX42ls2vlApSSoUopfY4OjZbKaW6KKWOS+o9CAAACUJJREFUuToO4ThKqVNKqTdcHUdWlhE/36n5bGeKCci11s1TUfw9wA8ooLWOclBIQgjXyNSf70xRw02lcsC/aX0zlFIedo5HCGE/af58Z4TPdqZIuEqpbUqpwUqpMkoprZTqpJQ6pJS6rZTaqJQqZim3BugMdFZK3VFKjbBsf0Yp9bvla8hhpdT/xTt3Q6VUlOWcJ4Dr8a7T2XKdu0qpdUqpfEqpcUqpy0qpi0qp7vHOU1IptUEpdcVyne1KqVpO/lNlG0opP6XUJKXUCcu/g0NKqaeVUu2VUvuUUreUUsFKqS+VUr7xjvtIKXXScsx5pdQYy/bY97xkvLIJvioqpXpa/v3cVkqdUUqNVUq5O/eVZ1/WPt+Z7rOttc7wD2AbMBgoA2jgR8yQvNzAb8BX8crOA/4X73lZIAzogmlCqQtcB9pa9je0nPN7IA/gE+86q4H8QAHgEHAUeNdynuZAJFDKcp5SwEuW43MC0zFDiz0s+7sAx1z9t8wqD2AxsN3y/iqgguXRHKiGqUxUsLxvYy3HVAJCgWqW53mBupbfY9/zkvGukeA9A16Jd73HgEvA/8Xbfwp4w9V/m6z8iP/5zoyf7UxRw7VihNb6qtb6FrAQSGlo3uvAX1rreVrrKK31LuBL4J1E5fprrUO01qHxto3SWl/XWl/DJPlIrfVXlvOsB25gPnhorc9orVdrrUO11mGY/yBKARXt8opFHKVUYeA14D2t9UltHLM81mutD2qtY7TWx4DPgMaWQ6MwybKaUspPa33T8u/BJlrr5fGu9zfwXbxzC+fLdJ/tzJpwg+P9fhfIlUJZf+Bkom3HLdtjxQBnH3Cd0ETPY7flAlBKFVRKzbd81bwV73xpmuRCpKiM5efRxDuUUk0sX/muWN6H8VjeA631CaAjpiZzQSn1q1Kqqa0XVUq9rpT6Uyl1TSkVAnRH3l9XynSf7cyacFPjLPc/oLHKkfBN0Nry3SAdxgLFgCe01rm5/6ardJ5XJHXK8jNBDUMp5QmsBBZhvg7mBvoT7z3QWq/QWjfBNEktAVYppXyA25YivvFOWTzeuf2BBcCnQDGtdR5gNvL+ulKm+2xnh4T7PVBLKfWmUiqHUupx4P+AuXa+Tm7M/4o3lFJ+mJqVcACt9WVgGfCZ5SaIUkpVwLTRegE3tNZhSqmHgB6xxymlKiulmlkSbCQQgmnPi7F8tTwNvK2UcldKVcfUhGP5YT4vV4BIpVRdoJPjX61IQab7bGf5hKu1Pgm8gPngXcO0uw3RWi+x86WGAoUt19gP7ACi7XwNcd/bwF7gZ0ztdBXmJtj7wASl1B1MDXRhvGM8Me9TMHAT+Ah4RWt9z7K/M/AiJhFPId4HV2v9LzDMcp2bwADMB164SGb8bMtcCkII4SRZvoYrhBAZhSRcIYRwEkm4QgjhJJJwhRDCSSThCiGEk0jCFUIIJ5GEK1xCKfWwZdamhq6OxVWUUsuUUttcHYdwHkm4QgjhJJJwRYaklMrp6hiEsDdJuMIplFIfKKXOWiZ8XoOZDCT+fq2U6qWUmqaUugIcsGz3VkpNsBwbbplc/IVEx76klNpjOfcNy4TUz8Tb39Uy2XSYUuqqUupnpVS1/2/v3ELrKqIw/P1a2oJgUWKTUq3iBUR9SLwkFCUpWKtYoVIUVEQQH4rgo2J9kYog7VMVEa8Eo5iXaAU1aWsaE4pSopFWi0iwooKXamOkaC8Gcfmw5rTbnZ2TU9Kck/SsDwYyM2vvWcMhi9kzw79Owfd2SYNJ9PqwXBC/JdPfLGlA0tE0/luSGnPvuCgJXR+T5z7LSwiW7K6R1CsXOf9TUo+kpkp9DeY28yKnWTC/kbQO1zV4CVfz6gA6C0wfA3bjojClxcDbQCuuY/AtroP7nqTrzWyfpMuSzXPp+cXAdbi4NJLa07hPAntwIZKVuCB1Jb6vAvqBQVxr4QhwI7Ac2CvpAlwg/2vgPlzkZjPQn3yckCRcg6EBeAg4DjyVfPwmM9bluKD+CHA//v/5NPC+pNbToHoV1JpaK7hHOfML8CmwPdf2Kq7UtSrVDReTztrcnNo7cu27gZ70913A72XGfhT4fAa+78EDoKbo34yL2ZybaWtLft+b6renelvG5mJcEH0o0/YmMAoszLRdgQulrK317xhl5iW2FIJZRdIC4Fp8hZdlW4F5X66+GjgIfJLk9xak9w1wMsvHfmCJpC5Ja5TJX5bYB7RI2pq2Bhaegu/n4MGzy1L0K6AV+NA8+wgAZjaMa/belLH5NbWXbH4A8mm+VwPvAv9m5vpdele5rCbBPCECbjDbNABnA7/l2vN18Bxh+WebcO3abNlEEoE2s1FgHS483QeMSepOn/qY2S7gQaAd//Qfk/RCQWAu4jxcZDqfDSDLsgK/S3M5P/3dRPF8820NuGB6fr6X8v8sBsE8JfZwg9lmDP8kXpprz9fBP7uzjAM/AXeWG8DMeoFeSUuAtcCzwPPAPam/C+hKQXg9sBXX0N04je9/4ClalpWx+WWKuTRycgV7cAqbpXgSxBLj+Ar3tQLbsWl8DeYBscINZhUz+wfYi69Cs6yv4PEBfHX4l5mN5EvBWIfNrBsPWlcV9B8ys5fxbL+T+gvsjwDDwAPp4KuIYeBWSSfy6km6AU/98nFq+gxolNSWsVmBb7Xk53s1vuecn+/30/kbzH1ihRtUg2eAbZJexINhB3BbBc/1AzvxE/8twFf4LYNmYLGZPSFpA37rYAfwM37IdDfwBoCk0m2AIXyV2JLGn251W2IjsAvYLukV/JbCSmDEzD7AM0M8DOxMPpZuKewH3knv6AO+AHokPQ78jd9SyG8pbMIPGHsldSZ/lwO3AK+b2VCFPgdzlVqf2kWpj4KnQfkRzw3VB6xh8i2FRwqeW4QHpwPABP55voN0ao8Hv1482B7HD5m2AItS/x34yvFQ6h/Fg2jhrYMpfO/Ab0YcxW8kDALNmf4W4KNMfzfQmHvHiuT3MTx32gb8OttQzu7K1D6ebA/gqb8vrPVvGGXmJVLsBEEQVInYww2CIKgSsYcb1C2SzqLMosP8wC8IThuxwg3qmU4m33k9USRdUjPPgjOS2MMN6pYUUBvKmHxpZhPV8SaoByLgBkEQVInYUgiCIKgSEXCDIAiqRATcIAiCKhEBNwiCoEpEwA2CIKgS/wGZ0ye6QARgZgAAAABJRU5ErkJggg==\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "          combined      food   service\n",
            "informal  1.166441  1.200562  1.068978\n",
            "casual    1.187739  1.264256  1.118116\n",
            "formal    1.916667  1.750000  1.916667\n"
          ]
        }
      ],
      "source": [
        "# Mean rating of dress code function\n",
        "mean_rating_plotting(X_val[['dress_code']])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eDs8B2iU2d5s",
        "outputId": "f8e70703-5f7e-4463-90f0-bb87aaab4c1d"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "high      1\n",
              "medium    1\n",
              "low       0\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 118,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.dress_code == 'formal'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yr7IaOyv2d5s",
        "outputId": "41869ac6-2441-441c-87f4-e738af76fa40"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    57\n",
              "low       40\n",
              "high      21\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 119,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.dress_code == 'informal'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KB8UDfRz2d5s",
        "outputId": "d11eb103-3dce-4eb2-a5f0-67678d50139c"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "low       5\n",
              "high      3\n",
              "medium    2\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 120,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.dress_code == 'casual'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eGA8GyvQ2d5t",
        "outputId": "add7ba35-121a-46f6-fc42-11c95bef628d"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "no_accessibility    76\n",
              "completely          45\n",
              "partially            9\n",
              "Name: accessibility, dtype: int64"
            ]
          },
          "execution_count": 121,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.accessibility.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 122
        },
        "id": "pFK0D2dj2d5u",
        "outputId": "a13d0fc8-a8e0-44f3-88ec-b505220e5cac"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "                  combined      food   service\n",
            "no_accessibility  1.196189  1.206242  1.091278\n",
            "completely        1.132494  1.203597  1.049709\n",
            "partially         1.275356  1.330294  1.219991\n"
          ]
        }
      ],
      "source": [
        "# mean rating as a function of dress accessibility\n",
        "mean_rating_plotting(X_val[['accessibility']])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "27PRUTq92d5u",
        "outputId": "0963af4b-7c46-459c-d449-1dc7781a2c3d"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    8\n",
              "low       1\n",
              "high      0\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 123,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.accessibility == 'partially'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "HRECHteY2d5v",
        "outputId": "877bf554-03cf-425a-c405-63343b7cb720"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "medium    39\n",
              "high      23\n",
              "low       14\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 124,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.accessibility == 'no_accessibility'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UN8Y8umh2d5v",
        "outputId": "761ee5dc-fc82-4373-8c3d-55dfc594f39e"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "low       30\n",
              "medium    13\n",
              "high       2\n",
              "Name: price, dtype: int64"
            ]
          },
          "execution_count": 125,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.price[X_val.accessibility == 'completely'].value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pBcbP22g2d5w",
        "outputId": "a022661d-127c-4fed-eb47-b1870b12a318"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "closed    115\n",
              "open       15\n",
              "Name: area, dtype: int64"
            ]
          },
          "execution_count": 126,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "X_val.area.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        },
        "id": "8CSwQmOD2d5w",
        "outputId": "13506f6e-6ae0-4e4f-bc9e-05ee62453db2"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "        combined      food   service\n",
            "open    1.069992  1.231315  0.949101\n",
            "closed  1.193921  1.211645  1.103630\n"
          ]
        }
      ],
      "source": [
        "# mean rating as a function of area\n",
        "mean_rating_plotting(X_val[['area']])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Rg7n0S3ZRQol"
      },
      "source": [
        "## K Nearest Neighbors"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6kJdu36mOIOl"
      },
      "source": [
        "![image.png](data:image/png;base64,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)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JaVVAFE5Uqyj"
      },
      "source": [
        "The two approaches are mathematically quite similar, but there is a conceptual difference between the two. Here’s how the two compare:\n",
        "\n",
        "1. **User-based:** For a user U, with a set of similar users determined based on rating vectors consisting of given item ratings, the rating for an item I, which hasn’t been rated, is found by picking out N users from the similarity list who have rated the item I and calculating the rating based on these N ratings.\n",
        "\n",
        "2. **Item-based:** For an item I, with a set of similar items determined based on rating vectors consisting of received user ratings, the rating by a user U, who hasn’t rated it, is found by picking out N items from the similarity list that have been rated by U and calculating the rating based on these N ratings."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tH8Ssx78VOwo"
      },
      "source": [
        "We will be using User based collaborative filtering technique for listing top recommendations for any user."
      ]
    }
  ],
  "metadata": {
    "colab": {
      "collapsed_sections": [
        "NnBAwgLj2d5N",
        "k-di8MlD2d5P",
        "e_kqbT9k2d5R",
        "oaK513F32d5T",
        "-EvjBvuE2d5W",
        "piNCanFc2d5X",
        "W3eDAos-2d5i",
        "PX7jzG072d5k",
        "G4za9EHO2d5k",
        "zG9XlAGK2d5m",
        "xTQ5SK_e2d5x",
        "H3R2yZVL2d5y"
      ],
      "name": "FDS Final Project EDA.ipynb",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.6.3"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}