predict_the_happiness_gcolab.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "predict the happiness.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "metadata": {
        "id": "MHPF_-ojngJW",
        "colab_type": "code",
        "outputId": "1026a888-fd80-4991-8f30-7ba49c2fda86",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "cell_type": "code",
      "source": [
        "from google.colab import drive \n",
        "drive.mount('/content/gdrive')"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount(\"/content/gdrive\", force_remount=True).\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "_2YSyYtpoAkP",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "import pandas as pd \n",
        "train=pd.read_csv('gdrive/My Drive/predict the happiness/train.csv')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "F7eLlqstpgYF",
        "colab_type": "code",
        "outputId": "d3537593-3ae1-4a34-9101-8f60642db82a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "cell_type": "code",
      "source": [
        "train.head()"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>User_ID</th>\n",
              "      <th>Description</th>\n",
              "      <th>Browser_Used</th>\n",
              "      <th>Device_Used</th>\n",
              "      <th>Is_Response</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>id10326</td>\n",
              "      <td>The room was kind of clean but had a VERY stro...</td>\n",
              "      <td>Edge</td>\n",
              "      <td>Mobile</td>\n",
              "      <td>not happy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>id10327</td>\n",
              "      <td>I stayed at the Crown Plaza April -- - April -...</td>\n",
              "      <td>Internet Explorer</td>\n",
              "      <td>Mobile</td>\n",
              "      <td>not happy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>id10328</td>\n",
              "      <td>I booked this hotel through Hotwire at the low...</td>\n",
              "      <td>Mozilla</td>\n",
              "      <td>Tablet</td>\n",
              "      <td>not happy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>id10329</td>\n",
              "      <td>Stayed here with husband and sons on the way t...</td>\n",
              "      <td>InternetExplorer</td>\n",
              "      <td>Desktop</td>\n",
              "      <td>happy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>id10330</td>\n",
              "      <td>My girlfriends and I stayed here to celebrate ...</td>\n",
              "      <td>Edge</td>\n",
              "      <td>Tablet</td>\n",
              "      <td>not happy</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   User_ID                                        Description  \\\n",
              "0  id10326  The room was kind of clean but had a VERY stro...   \n",
              "1  id10327  I stayed at the Crown Plaza April -- - April -...   \n",
              "2  id10328  I booked this hotel through Hotwire at the low...   \n",
              "3  id10329  Stayed here with husband and sons on the way t...   \n",
              "4  id10330  My girlfriends and I stayed here to celebrate ...   \n",
              "\n",
              "        Browser_Used Device_Used Is_Response  \n",
              "0               Edge      Mobile   not happy  \n",
              "1  Internet Explorer      Mobile   not happy  \n",
              "2            Mozilla      Tablet   not happy  \n",
              "3   InternetExplorer     Desktop       happy  \n",
              "4               Edge      Tablet   not happy  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 3
        }
      ]
    },
    {
      "metadata": {
        "id": "MZb1d7sWpriQ",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        " test=pd.read_csv('gdrive/My Drive/predict the happiness/test.csv')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "u8kIUWRxx4X5",
        "colab_type": "code",
        "outputId": "dc0cb508-7b6a-4e5e-9d87-3e08ed2a92ce",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "cell_type": "code",
      "source": [
        "test.head()"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>User_ID</th>\n",
              "      <th>Description</th>\n",
              "      <th>Browser_Used</th>\n",
              "      <th>Device_Used</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>id80132</td>\n",
              "      <td>Looking for a motel in close proximity to TV t...</td>\n",
              "      <td>Firefox</td>\n",
              "      <td>Mobile</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>id80133</td>\n",
              "      <td>Walking distance to Madison Square Garden and ...</td>\n",
              "      <td>InternetExplorer</td>\n",
              "      <td>Desktop</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>id80134</td>\n",
              "      <td>Visited Seattle on business. Spent - nights in...</td>\n",
              "      <td>IE</td>\n",
              "      <td>Tablet</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>id80135</td>\n",
              "      <td>This hotel location is excellent and the rooms...</td>\n",
              "      <td>Edge</td>\n",
              "      <td>Mobile</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>id80136</td>\n",
              "      <td>This hotel is awesome I love the service Antho...</td>\n",
              "      <td>Mozilla</td>\n",
              "      <td>Mobile</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   User_ID                                        Description  \\\n",
              "0  id80132  Looking for a motel in close proximity to TV t...   \n",
              "1  id80133  Walking distance to Madison Square Garden and ...   \n",
              "2  id80134  Visited Seattle on business. Spent - nights in...   \n",
              "3  id80135  This hotel location is excellent and the rooms...   \n",
              "4  id80136  This hotel is awesome I love the service Antho...   \n",
              "\n",
              "       Browser_Used Device_Used  \n",
              "0           Firefox      Mobile  \n",
              "1  InternetExplorer     Desktop  \n",
              "2                IE      Tablet  \n",
              "3              Edge      Mobile  \n",
              "4           Mozilla      Mobile  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "metadata": {
        "id": "XrDwl_VZ6_nn",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        ""
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "vCjZM-VVx75-",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "train[\"Type\"] = \"train\"\n",
        "test[\"Type\"] = \"test\""
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "N5oWcNTm7iSi",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "test1 = test.copy()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "N9v0QQgdyDL1",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "%matplotlib inline"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "gcJJ5K0kyH8E",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "\n",
        "data = pd.concat([train,test],ignore_index=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "PyWP08EAyMeY",
        "colab_type": "code",
        "outputId": "e970e8f4-7c95-4159-cb3f-80d4e5863447",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "cell_type": "code",
      "source": [
        "data.head()"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Browser_Used</th>\n",
              "      <th>Description</th>\n",
              "      <th>Device_Used</th>\n",
              "      <th>Is_Response</th>\n",
              "      <th>Type</th>\n",
              "      <th>User_ID</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Edge</td>\n",
              "      <td>The room was kind of clean but had a VERY stro...</td>\n",
              "      <td>Mobile</td>\n",
              "      <td>not happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10326</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Internet Explorer</td>\n",
              "      <td>I stayed at the Crown Plaza April -- - April -...</td>\n",
              "      <td>Mobile</td>\n",
              "      <td>not happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10327</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Mozilla</td>\n",
              "      <td>I booked this hotel through Hotwire at the low...</td>\n",
              "      <td>Tablet</td>\n",
              "      <td>not happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10328</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>InternetExplorer</td>\n",
              "      <td>Stayed here with husband and sons on the way t...</td>\n",
              "      <td>Desktop</td>\n",
              "      <td>happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10329</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Edge</td>\n",
              "      <td>My girlfriends and I stayed here to celebrate ...</td>\n",
              "      <td>Tablet</td>\n",
              "      <td>not happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10330</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "        Browser_Used                                        Description  \\\n",
              "0               Edge  The room was kind of clean but had a VERY stro...   \n",
              "1  Internet Explorer  I stayed at the Crown Plaza April -- - April -...   \n",
              "2            Mozilla  I booked this hotel through Hotwire at the low...   \n",
              "3   InternetExplorer  Stayed here with husband and sons on the way t...   \n",
              "4               Edge  My girlfriends and I stayed here to celebrate ...   \n",
              "\n",
              "  Device_Used Is_Response   Type  User_ID  \n",
              "0      Mobile   not happy  train  id10326  \n",
              "1      Mobile   not happy  train  id10327  \n",
              "2      Tablet   not happy  train  id10328  \n",
              "3     Desktop       happy  train  id10329  \n",
              "4      Tablet   not happy  train  id10330  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "metadata": {
        "id": "Jy0ZhhLTyOk4",
        "colab_type": "code",
        "outputId": "5fd95107-b0ad-465c-8712-9b185daa6e71",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 136
        }
      },
      "cell_type": "code",
      "source": [
        "data.isnull().sum()"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Browser_Used        0\n",
              "Description         0\n",
              "Device_Used         0\n",
              "Is_Response     29404\n",
              "Type                0\n",
              "User_ID             0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "metadata": {
        "id": "-F9gDJrRySzt",
        "colab_type": "code",
        "outputId": "6c892ed9-e1ef-42b6-e424-17467f750eb0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 68
        }
      },
      "cell_type": "code",
      "source": [
        "data.columns"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['Browser_Used', 'Description', 'Device_Used', 'Is_Response', 'Type',\n",
              "       'User_ID'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "metadata": {
        "id": "ENqw7Io6yWCV",
        "colab_type": "code",
        "outputId": "154aa7ab-6458-44d8-b0e5-a00f2454e746",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1343
        }
      },
      "cell_type": "code",
      "source": [
        "attributes = ['Browser_Used', 'Device_Used', 'User_ID']\n",
        "\n",
        "for attribute in attributes:\n",
        "    print(data[attribute].value_counts())"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Firefox              13043\n",
            "Edge                 12437\n",
            "InternetExplorer      8191\n",
            "Google Chrome         8050\n",
            "Mozilla Firefox       7526\n",
            "Mozilla               5425\n",
            "Chrome                4356\n",
            "IE                    4270\n",
            "Internet Explorer     3700\n",
            "Safari                 670\n",
            "Opera                  668\n",
            "Name: Browser_Used, dtype: int64\n",
            "Desktop    26375\n",
            "Mobile     26214\n",
            "Tablet     15747\n",
            "Name: Device_Used, dtype: int64\n",
            "id109217    1\n",
            "id10728     1\n",
            "id14237     1\n",
            "id24946     1\n",
            "id30433     1\n",
            "id12819     1\n",
            "id102064    1\n",
            "id104028    1\n",
            "id17841     1\n",
            "id44234     1\n",
            "id34237     1\n",
            "id18336     1\n",
            "id93815     1\n",
            "id32797     1\n",
            "id31315     1\n",
            "id97372     1\n",
            "id17326     1\n",
            "id99110     1\n",
            "id24350     1\n",
            "id87242     1\n",
            "id22379     1\n",
            "id13615     1\n",
            "id94854     1\n",
            "id35163     1\n",
            "id83162     1\n",
            "id88551     1\n",
            "id22040     1\n",
            "id16227     1\n",
            "id35649     1\n",
            "id39249     1\n",
            "           ..\n",
            "id95188     1\n",
            "id100043    1\n",
            "id19997     1\n",
            "id39860     1\n",
            "id47741     1\n",
            "id13292     1\n",
            "id96721     1\n",
            "id43482     1\n",
            "id33143     1\n",
            "id104061    1\n",
            "id81319     1\n",
            "id16009     1\n",
            "id40807     1\n",
            "id26932     1\n",
            "id105772    1\n",
            "id23925     1\n",
            "id17794     1\n",
            "id44302     1\n",
            "id98477     1\n",
            "id86421     1\n",
            "id18784     1\n",
            "id26459     1\n",
            "id34298     1\n",
            "id92593     1\n",
            "id108645    1\n",
            "id108111    1\n",
            "id20879     1\n",
            "id21959     1\n",
            "id32066     1\n",
            "id46537     1\n",
            "Name: User_ID, Length: 68336, dtype: int64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "9X4W_KZnyZH0",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "data[\"text length\"] = data[\"Description\"].apply(lambda x:len(x.split()))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "FHw4gtzqyekc",
        "colab_type": "code",
        "outputId": "daeb48f1-af09-4006-9725-42ca22daf841",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "cell_type": "code",
      "source": [
        "data.head()"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Browser_Used</th>\n",
              "      <th>Description</th>\n",
              "      <th>Device_Used</th>\n",
              "      <th>Is_Response</th>\n",
              "      <th>Type</th>\n",
              "      <th>User_ID</th>\n",
              "      <th>text length</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Edge</td>\n",
              "      <td>The room was kind of clean but had a VERY stro...</td>\n",
              "      <td>Mobile</td>\n",
              "      <td>not happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10326</td>\n",
              "      <td>46</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Internet Explorer</td>\n",
              "      <td>I stayed at the Crown Plaza April -- - April -...</td>\n",
              "      <td>Mobile</td>\n",
              "      <td>not happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10327</td>\n",
              "      <td>208</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Mozilla</td>\n",
              "      <td>I booked this hotel through Hotwire at the low...</td>\n",
              "      <td>Tablet</td>\n",
              "      <td>not happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10328</td>\n",
              "      <td>232</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>InternetExplorer</td>\n",
              "      <td>Stayed here with husband and sons on the way t...</td>\n",
              "      <td>Desktop</td>\n",
              "      <td>happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10329</td>\n",
              "      <td>93</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Edge</td>\n",
              "      <td>My girlfriends and I stayed here to celebrate ...</td>\n",
              "      <td>Tablet</td>\n",
              "      <td>not happy</td>\n",
              "      <td>train</td>\n",
              "      <td>id10330</td>\n",
              "      <td>297</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "        Browser_Used                                        Description  \\\n",
              "0               Edge  The room was kind of clean but had a VERY stro...   \n",
              "1  Internet Explorer  I stayed at the Crown Plaza April -- - April -...   \n",
              "2            Mozilla  I booked this hotel through Hotwire at the low...   \n",
              "3   InternetExplorer  Stayed here with husband and sons on the way t...   \n",
              "4               Edge  My girlfriends and I stayed here to celebrate ...   \n",
              "\n",
              "  Device_Used Is_Response   Type  User_ID  text length  \n",
              "0      Mobile   not happy  train  id10326           46  \n",
              "1      Mobile   not happy  train  id10327          208  \n",
              "2      Tablet   not happy  train  id10328          232  \n",
              "3     Desktop       happy  train  id10329           93  \n",
              "4      Tablet   not happy  train  id10330          297  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "metadata": {
        "id": "2AcDRcCQyhUz",
        "colab_type": "code",
        "outputId": "f0cafb2b-b055-462b-c060-b140e4b56bb8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 408
        }
      },
      "cell_type": "code",
      "source": [
        "print(train.info())\n",
        "print(test.info())"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 38932 entries, 0 to 38931\n",
            "Data columns (total 6 columns):\n",
            "User_ID         38932 non-null object\n",
            "Description     38932 non-null object\n",
            "Browser_Used    38932 non-null object\n",
            "Device_Used     38932 non-null object\n",
            "Is_Response     38932 non-null object\n",
            "Type            38932 non-null object\n",
            "dtypes: object(6)\n",
            "memory usage: 1.8+ MB\n",
            "None\n",
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 29404 entries, 0 to 29403\n",
            "Data columns (total 5 columns):\n",
            "User_ID         29404 non-null object\n",
            "Description     29404 non-null object\n",
            "Browser_Used    29404 non-null object\n",
            "Device_Used     29404 non-null object\n",
            "Type            29404 non-null object\n",
            "dtypes: object(5)\n",
            "memory usage: 1.1+ MB\n",
            "None\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "0y_p2q9Myke0",
        "colab_type": "code",
        "outputId": "ecbb3a45-dc43-4955-a1d7-64f9ff7c4968",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 330
        }
      },
      "cell_type": "code",
      "source": [
        "sns.boxplot(y=data[\"text length\"][:38932],x=data[\"Is_Response\"][:38932],palette=\"rainbow\")"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/seaborn/categorical.py:454: FutureWarning: remove_na is deprecated and is a private function. Do not use.\n",
            "  box_data = remove_na(group_data)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f2475167128>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 17
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEGCAYAAAB/+QKOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<matplotlib.figure.Figure at 0x7f2497e445c0>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "metadata": {
        "id": "fxZrSzkSynSN",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "train[\"text length\"] = train[\"Description\"].apply(lambda x:len(x.split()))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "jLP7-wVHyuTV",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "# sns.catplot(x=train[\"Device_Used\"],y=train[\"text length\"],hue=train[\"Is_Response\"],kind=\"swarm\")\n",
        "# sns.catplot(x=\"Device_Used\",y=\"text length\",hue=\"Is_Response\",data=train)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "weu7Aej7yv7I",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "data[\"Browser_Used\"] = data[\"Browser_Used\"].replace({\n",
        "    \"Mozilla\":\"Firefox\",\n",
        "    \"Mozilla Firefox\":\"Firefox\",\n",
        "    \"Google Chrome\":\"Chrome\",\n",
        "    \"InternetExplorer\":\"IE\",\n",
        "    \"Internet Explorer\":\"IE\"\n",
        "})"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "CjXjVmC-y4fV",
        "colab_type": "code",
        "outputId": "4794ff7c-989b-4b9b-f652-8e3bf7fe9d42",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "cell_type": "code",
      "source": [
        "data[\"Browser_Used\"].unique()"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Edge', 'IE', 'Firefox', 'Chrome', 'Opera', 'Safari'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "metadata": {
        "id": "E6ryUKtEy7fZ",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#Import library:\n",
        "from sklearn.preprocessing import LabelEncoder\n",
        "le = LabelEncoder()\n",
        "\n",
        "var_mod = ['Browser_Used', 'Device_Used']\n",
        "for i in var_mod:\n",
        "    data[i] = le.fit_transform(data[i])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "82IuyL3Xy-ST",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "data = pd.get_dummies(data,columns=['Browser_Used', 'Device_Used'])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "v_pUFk0vzBVA",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "data[\"Is_Response\"] = data[\"Is_Response\"].map({\"happy\":1 , \"not happy\":0})"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "nEsMu6PVzEN0",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "from sklearn.feature_extraction.text import CountVectorizer\n",
        "cv = CountVectorizer(analyzer=\"word\",ngram_range = (1,1), min_df=150)\n",
        "# , max_features=500"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "zJpqjT_OzGYb",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "X = cv.fit_transform(data[\"Description\"])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "yRQ1Be8CzKAt",
        "colab_type": "code",
        "outputId": "6a0efe5a-cb3e-44c9-abc3-5ab5d5d8fa00",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "cell_type": "code",
      "source": [
        "X.shape"
      ],
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(68336, 3226)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 27
        }
      ]
    },
    {
      "metadata": {
        "id": "2ovGxLyLzNRo",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "count_vect_df = pd.DataFrame(X.todense(),columns=cv.get_feature_names())"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "X9m9C0g6zQFu",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "data.drop([\"User_ID\",\"text length\",\"Description\"],axis=1,inplace=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "riya2x_ozSjf",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "# data[\"Description\"] = list(X.A)\n",
        "df = pd.concat([data, count_vect_df], axis=1)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "wUE-RxNKzV_t",
        "colab_type": "code",
        "outputId": "2c017d2f-d872-4709-a069-203379662fe7",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 253
        }
      },
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Is_Response</th>\n",
              "      <th>Type</th>\n",
              "      <th>Browser_Used_0</th>\n",
              "      <th>Browser_Used_1</th>\n",
              "      <th>Browser_Used_2</th>\n",
              "      <th>Browser_Used_3</th>\n",
              "      <th>Browser_Used_4</th>\n",
              "      <th>Browser_Used_5</th>\n",
              "      <th>Device_Used_0</th>\n",
              "      <th>Device_Used_1</th>\n",
              "      <th>...</th>\n",
              "      <th>yorker</th>\n",
              "      <th>you</th>\n",
              "      <th>young</th>\n",
              "      <th>younger</th>\n",
              "      <th>your</th>\n",
              "      <th>yourself</th>\n",
              "      <th>yr</th>\n",
              "      <th>yummy</th>\n",
              "      <th>zero</th>\n",
              "      <th>zoo</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.0</td>\n",
              "      <td>train</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",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</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",
              "      <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>0.0</td>\n",
              "      <td>train</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",
              "      <td>1</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>0.0</td>\n",
              "      <td>train</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",
              "      <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>1.0</td>\n",
              "      <td>train</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>1</td>\n",
              "      <td>0</td>\n",
              "      <td>...</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",
              "      <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>0.0</td>\n",
              "      <td>train</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",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</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",
              "      <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 × 3237 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "   Is_Response   Type  Browser_Used_0  Browser_Used_1  Browser_Used_2  \\\n",
              "0          0.0  train               0               1               0   \n",
              "1          0.0  train               0               0               0   \n",
              "2          0.0  train               0               0               1   \n",
              "3          1.0  train               0               0               0   \n",
              "4          0.0  train               0               1               0   \n",
              "\n",
              "   Browser_Used_3  Browser_Used_4  Browser_Used_5  Device_Used_0  \\\n",
              "0               0               0               0              0   \n",
              "1               1               0               0              0   \n",
              "2               0               0               0              0   \n",
              "3               1               0               0              1   \n",
              "4               0               0               0              0   \n",
              "\n",
              "   Device_Used_1 ...   yorker  you  young  younger  your  yourself  yr  yummy  \\\n",
              "0              1 ...        0    1      0        0     0         0   0      0   \n",
              "1              1 ...        0    0      0        0     0         0   0      0   \n",
              "2              0 ...        0    0      0        0     0         0   0      0   \n",
              "3              0 ...        0    1      0        0     0         0   0      0   \n",
              "4              0 ...        0    1      0        0     0         0   0      0   \n",
              "\n",
              "   zero  zoo  \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 3237 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 31
        }
      ]
    },
    {
      "metadata": {
        "id": "DWQ85zZ8zX8M",
        "colab_type": "code",
        "outputId": "1cdf7cdb-a803-4622-97cb-8476ffd617d0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 136
        }
      },
      "cell_type": "code",
      "source": [
        "df.columns"
      ],
      "execution_count": 32,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['Is_Response', 'Type', 'Browser_Used_0', 'Browser_Used_1',\n",
              "       'Browser_Used_2', 'Browser_Used_3', 'Browser_Used_4', 'Browser_Used_5',\n",
              "       'Device_Used_0', 'Device_Used_1',\n",
              "       ...\n",
              "       'yorker', 'you', 'young', 'younger', 'your', 'yourself', 'yr', 'yummy',\n",
              "       'zero', 'zoo'],\n",
              "      dtype='object', length=3237)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 32
        }
      ]
    },
    {
      "metadata": {
        "id": "JsqoOmyVzi6J",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "df1 = df.copy()\n",
        "df1.drop([\"Is_Response\"],axis=1,inplace=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "Bdb-_0Udzmp5",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "XCols = df1.columns\n",
        "\n",
        "YCols = ['Is_Response']"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "cPiAWaImzpMe",
        "colab_type": "code",
        "outputId": "61ccd1f4-29dd-461d-b403-4fc4544f3ab6",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 287
        }
      },
      "cell_type": "code",
      "source": [
        "XX = df.loc[df[\"Type\"]==\"train\",XCols]\n",
        "yy = df.loc[df[\"Type\"]==\"train\",YCols]\n",
        "\n",
        "print(XX.shape)\n",
        "print(yy.shape)\n",
        "XX.head()"
      ],
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "(38932, 3236)\n",
            "(38932, 1)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Type</th>\n",
              "      <th>Browser_Used_0</th>\n",
              "      <th>Browser_Used_1</th>\n",
              "      <th>Browser_Used_2</th>\n",
              "      <th>Browser_Used_3</th>\n",
              "      <th>Browser_Used_4</th>\n",
              "      <th>Browser_Used_5</th>\n",
              "      <th>Device_Used_0</th>\n",
              "      <th>Device_Used_1</th>\n",
              "      <th>Device_Used_2</th>\n",
              "      <th>...</th>\n",
              "      <th>yorker</th>\n",
              "      <th>you</th>\n",
              "      <th>young</th>\n",
              "      <th>younger</th>\n",
              "      <th>your</th>\n",
              "      <th>yourself</th>\n",
              "      <th>yr</th>\n",
              "      <th>yummy</th>\n",
              "      <th>zero</th>\n",
              "      <th>zoo</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>train</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",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>...</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",
              "      <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>train</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",
              "      <td>1</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>train</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",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</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>train</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>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</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",
              "      <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>train</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",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</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",
              "      <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 × 3236 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "    Type  Browser_Used_0  Browser_Used_1  Browser_Used_2  Browser_Used_3  \\\n",
              "0  train               0               1               0               0   \n",
              "1  train               0               0               0               1   \n",
              "2  train               0               0               1               0   \n",
              "3  train               0               0               0               1   \n",
              "4  train               0               1               0               0   \n",
              "\n",
              "   Browser_Used_4  Browser_Used_5  Device_Used_0  Device_Used_1  \\\n",
              "0               0               0              0              1   \n",
              "1               0               0              0              1   \n",
              "2               0               0              0              0   \n",
              "3               0               0              1              0   \n",
              "4               0               0              0              0   \n",
              "\n",
              "   Device_Used_2 ...   yorker  you  young  younger  your  yourself  yr  yummy  \\\n",
              "0              0 ...        0    1      0        0     0         0   0      0   \n",
              "1              0 ...        0    0      0        0     0         0   0      0   \n",
              "2              1 ...        0    0      0        0     0         0   0      0   \n",
              "3              0 ...        0    1      0        0     0         0   0      0   \n",
              "4              1 ...        0    1      0        0     0         0   0      0   \n",
              "\n",
              "   zero  zoo  \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 3236 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 35
        }
      ]
    },
    {
      "metadata": {
        "id": "QjYrV_kjzsNC",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "XX.drop([\"Type\"],axis=1,inplace=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "XZ6Mz8iEzxLn",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "XX_train, XX_test, yy_train, yy_test = train_test_split(XX, yy, test_size=0.3, random_state=101)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "JxGsShB6z0OZ",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "from sklearn.naive_bayes import MultinomialNB\n",
        "nb = MultinomialNB()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "ENE2-WWAz2fg",
        "colab_type": "code",
        "outputId": "bd4fa962-b35f-4e35-9048-bbef21733a56",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 88
        }
      },
      "cell_type": "code",
      "source": [
        "nb.fit(XX_train,yy_train)"
      ],
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:578: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 39
        }
      ]
    },
    {
      "metadata": {
        "id": "iBC8oN8Mz5SR",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "predict = nb.predict(XX_test)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "Wbtrz2yK0CV5",
        "colab_type": "code",
        "outputId": "51601080-20de-4b9a-eea6-be059cb42e38",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import accuracy_score\n",
        "print(accuracy_score(yy_test,predict))"
      ],
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.8620719178082191\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "z9f9gVPI0ODT",
        "colab_type": "code",
        "outputId": "43a7a1d3-b520-4410-8953-558ee3d71a45",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 253
        }
      },
      "cell_type": "code",
      "source": [
        "Predict_Happiness = df.loc[df[\"Type\"]==\"test\",XCols]\n",
        "Predict_Happiness.head()\n"
      ],
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Type</th>\n",
              "      <th>Browser_Used_0</th>\n",
              "      <th>Browser_Used_1</th>\n",
              "      <th>Browser_Used_2</th>\n",
              "      <th>Browser_Used_3</th>\n",
              "      <th>Browser_Used_4</th>\n",
              "      <th>Browser_Used_5</th>\n",
              "      <th>Device_Used_0</th>\n",
              "      <th>Device_Used_1</th>\n",
              "      <th>Device_Used_2</th>\n",
              "      <th>...</th>\n",
              "      <th>yorker</th>\n",
              "      <th>you</th>\n",
              "      <th>young</th>\n",
              "      <th>younger</th>\n",
              "      <th>your</th>\n",
              "      <th>yourself</th>\n",
              "      <th>yr</th>\n",
              "      <th>yummy</th>\n",
              "      <th>zero</th>\n",
              "      <th>zoo</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>38932</th>\n",
              "      <td>test</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",
              "      <td>0</td>\n",
              "      <td>1</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>38933</th>\n",
              "      <td>test</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>1</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>38934</th>\n",
              "      <td>test</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",
              "      <td>0</td>\n",
              "      <td>1</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>38935</th>\n",
              "      <td>test</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",
              "      <td>0</td>\n",
              "      <td>1</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>38936</th>\n",
              "      <td>test</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",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>...</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",
              "      <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 × 3236 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "       Type  Browser_Used_0  Browser_Used_1  Browser_Used_2  Browser_Used_3  \\\n",
              "38932  test               0               0               1               0   \n",
              "38933  test               0               0               0               1   \n",
              "38934  test               0               0               0               1   \n",
              "38935  test               0               1               0               0   \n",
              "38936  test               0               0               1               0   \n",
              "\n",
              "       Browser_Used_4  Browser_Used_5  Device_Used_0  Device_Used_1  \\\n",
              "38932               0               0              0              1   \n",
              "38933               0               0              1              0   \n",
              "38934               0               0              0              0   \n",
              "38935               0               0              0              1   \n",
              "38936               0               0              0              1   \n",
              "\n",
              "       Device_Used_2 ...   yorker  you  young  younger  your  yourself  yr  \\\n",
              "38932              0 ...        0    0      0        0     0         0   0   \n",
              "38933              0 ...        0    0      0        0     0         0   0   \n",
              "38934              1 ...        0    0      0        0     0         0   0   \n",
              "38935              0 ...        0    0      0        0     0         0   0   \n",
              "38936              0 ...        0    1      0        0     0         0   0   \n",
              "\n",
              "       yummy  zero  zoo  \n",
              "38932      0     0    0  \n",
              "38933      0     0    0  \n",
              "38934      0     0    0  \n",
              "38935      0     0    0  \n",
              "38936      0     0    0  \n",
              "\n",
              "[5 rows x 3236 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 42
        }
      ]
    },
    {
      "metadata": {
        "id": "xlHZp1ke6xs1",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "Predict_Happiness.drop([\"Type\"],axis=1,inplace=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "TPQo10yc87bh",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "Final_prediction = nb.predict(Predict_Happiness)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "yM1Vpo5B9ETY",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "Data_Predicted = test.copy()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "XoD3MfWu-May",
        "colab_type": "code",
        "outputId": "e9e3d3f0-5559-40b1-f9ce-a461bc0fd69f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "cell_type": "code",
      "source": [
        "Data_Predicted.head()"
      ],
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>User_ID</th>\n",
              "      <th>Description</th>\n",
              "      <th>Browser_Used</th>\n",
              "      <th>Device_Used</th>\n",
              "      <th>Type</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>id80132</td>\n",
              "      <td>Looking for a motel in close proximity to TV t...</td>\n",
              "      <td>Firefox</td>\n",
              "      <td>Mobile</td>\n",
              "      <td>test</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>id80133</td>\n",
              "      <td>Walking distance to Madison Square Garden and ...</td>\n",
              "      <td>InternetExplorer</td>\n",
              "      <td>Desktop</td>\n",
              "      <td>test</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>id80134</td>\n",
              "      <td>Visited Seattle on business. Spent - nights in...</td>\n",
              "      <td>IE</td>\n",
              "      <td>Tablet</td>\n",
              "      <td>test</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>id80135</td>\n",
              "      <td>This hotel location is excellent and the rooms...</td>\n",
              "      <td>Edge</td>\n",
              "      <td>Mobile</td>\n",
              "      <td>test</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>id80136</td>\n",
              "      <td>This hotel is awesome I love the service Antho...</td>\n",
              "      <td>Mozilla</td>\n",
              "      <td>Mobile</td>\n",
              "      <td>test</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   User_ID                                        Description  \\\n",
              "0  id80132  Looking for a motel in close proximity to TV t...   \n",
              "1  id80133  Walking distance to Madison Square Garden and ...   \n",
              "2  id80134  Visited Seattle on business. Spent - nights in...   \n",
              "3  id80135  This hotel location is excellent and the rooms...   \n",
              "4  id80136  This hotel is awesome I love the service Antho...   \n",
              "\n",
              "       Browser_Used Device_Used  Type  \n",
              "0           Firefox      Mobile  test  \n",
              "1  InternetExplorer     Desktop  test  \n",
              "2                IE      Tablet  test  \n",
              "3              Edge      Mobile  test  \n",
              "4           Mozilla      Mobile  test  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 46
        }
      ]
    },
    {
      "metadata": {
        "id": "lwV0gjcs-O5Q",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "Data_Predicted.drop([\"Description\",\"Browser_Used\",\"Device_Used\",\"Type\"],axis=1,inplace=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "z7Jc4SZ1-iwH",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "Data_Predicted[\"Is_Response\"] = pd.Series(Final_prediction)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "T2QefdaN-qGl",
        "colab_type": "code",
        "outputId": "fbd43b78-6667-4ecc-f5f0-7401d7b8bb6c",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "cell_type": "code",
      "source": [
        "Data_Predicted[\"Is_Response\"].unique()"
      ],
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0., 1.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 49
        }
      ]
    },
    {
      "metadata": {
        "id": "G7Aj9FuM-zxY",
        "colab_type": "code",
        "outputId": "ceb95cef-ad2f-478a-ed55-e1f1cbfb4121",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 68
        }
      },
      "cell_type": "code",
      "source": [
        "Data_Predicted[\"Is_Response\"].value_counts()"
      ],
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1.0    20437\n",
              "0.0     8967\n",
              "Name: Is_Response, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 50
        }
      ]
    },
    {
      "metadata": {
        "id": "n7oeSNd1-84F",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "Data_Predicted[\"Is_Response\"] = Data_Predicted[\"Is_Response\"].map({1.0:\"happy\",0.0:\"not_happy\"})"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "GOozep9W_T0S",
        "colab_type": "code",
        "outputId": "49f6b4a8-509c-43de-a87c-7fd35604bdbf",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "cell_type": "code",
      "source": [
        "Data_Predicted.head()"
      ],
      "execution_count": 52,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>User_ID</th>\n",
              "      <th>Is_Response</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>id80132</td>\n",
              "      <td>not_happy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>id80133</td>\n",
              "      <td>happy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>id80134</td>\n",
              "      <td>not_happy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>id80135</td>\n",
              "      <td>not_happy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>id80136</td>\n",
              "      <td>happy</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   User_ID Is_Response\n",
              "0  id80132   not_happy\n",
              "1  id80133       happy\n",
              "2  id80134   not_happy\n",
              "3  id80135   not_happy\n",
              "4  id80136       happy"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 52
        }
      ]
    },
    {
      "metadata": {
        "id": "DwNdLxmZ_X0G",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "Data_Predicted.to_csv(\"gdrive/My Drive/predict the happiness/Sample_Submission_NB.csv\", index=False)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "mHLymfBe_kC-",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "# XGBoost"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "cMOgaRjxK2m4",
        "colab_type": "text"
      },
      "cell_type": "markdown",
      "source": [
        "\n"
      ]
    },
    {
      "metadata": {
        "id": "7tUUPztwLI5x",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "# import xgboost\n",
        "from xgboost import XGBClassifier"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "-K0FCAWXLLAG",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "xgb = XGBClassifier()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "5FPflAreL8lm",
        "colab_type": "code",
        "outputId": "ecc650a0-a211-4135-ca61-d68657099e7c",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 207
        }
      },
      "cell_type": "code",
      "source": [
        "xgb.fit(XX_train,yy_train)"
      ],
      "execution_count": 57,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/sklearn/preprocessing/label.py:95: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/preprocessing/label.py:128: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n",
              "       colsample_bytree=1, gamma=0, learning_rate=0.1, max_delta_step=0,\n",
              "       max_depth=3, min_child_weight=1, missing=None, n_estimators=100,\n",
              "       n_jobs=1, nthread=None, objective='binary:logistic', random_state=0,\n",
              "       reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n",
              "       silent=True, subsample=1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 57
        }
      ]
    },
    {
      "metadata": {
        "id": "T6FkcAJZMQXb",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 71
        },
        "outputId": "2249a857-87d0-4d21-c243-1913fc9ab75f"
      },
      "cell_type": "code",
      "source": [
        "xgb_predict = xgb.predict(XX_test)"
      ],
      "execution_count": 59,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/sklearn/preprocessing/label.py:151: DeprecationWarning: The truth value of an empty array is ambiguous. Returning False, but in future this will result in an error. Use `array.size > 0` to check that an array is not empty.\n",
            "  if diff:\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "metadata": {
        "id": "y_QrFdUgQTcj",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "890caabf-3150-41e4-a1ba-40ce6fd060e2"
      },
      "cell_type": "code",
      "source": [
        "print(accuracy_score(yy_test,xgb_predict))"
      ],
      "execution_count": 60,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.8502568493150685\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "l6qGOv7WQcfo",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        ""
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}