{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "_cell_guid": "f1db3c56-d5cd-987c-3438-f2566fffcbca"
      },
      "source": ""
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "55a14f4e-8943-fd1e-0db8-1d3d95b7192a"
      },
      "outputs": [],
      "source": [
        "# This Python 3 environment comes with many helpful analytics libraries installed\n",
        "# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n",
        "# For example, here's several helpful packages to load in \n",
        "\n",
        "import numpy as np # linear algebra\n",
        "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
        "import gc\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore')\n",
        "%matplotlib inline\n",
        "\n",
        "from subprocess import check_output\n",
        "print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n",
        "\n",
        "# Any results you write to the current directory are saved as output."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "ef36a658-3ce1-441e-fd7e-87476ad6ee86"
      },
      "outputs": [],
      "source": [
        "df_train = pd.read_csv('../input/clicks_train.csv')\n",
        "df_test = pd.read_csv('../input/clicks_test.csv')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "066c71ef-8796-6776-1e9b-2ba3848657d2"
      },
      "outputs": [],
      "source": [
        "df_train.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "f13a0bbe-113b-45a7-4a3b-9afee7ffefad"
      },
      "outputs": [],
      "source": [
        "df_train.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "1fd6f289-0faf-3adb-be81-83329fcbc565"
      },
      "outputs": [],
      "source": [
        "print('the number of unique display_id: ' + str(len(df_train['display_id'].unique())))\n",
        "print('the number of unique ad_id: '+ str(len(df_train['ad_id'].unique())))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "5d21842e-ff02-54f0-14d9-f7f3256e8af5"
      },
      "outputs": [],
      "source": [
        "ad_in_display = df_train.groupby('display_id')['ad_id'].count().value_counts()\n",
        "sns.barplot(ad_in_display.index, ad_in_display.values)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_cell_guid": "b4d81a0d-2130-61ac-80c3-9201a342d856"
      },
      "source": [
        "groupby('ad_id')['ad_id'].count() \u6309ad_id\u8fdb\u884c\u6c47\u603b\uff0c\u5bf9ad_id\u8fdb\u884c\u53ef\u91cd\u590d\u7edf\u8ba1\u3002"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "8d9be560-b4b9-8e8e-2138-82f51a4c1558"
      },
      "outputs": [],
      "source": [
        "size_display.barplot()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "9d354e1b-0082-11c9-dec3-b0b384da3b5a"
      },
      "outputs": [],
      "source": [
        "ad_usage_train = df_train.groupby('ad_id')['ad_id'].count()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_cell_guid": "bf1de522-b7a9-ba07-7fee-a8a1a31c75bb"
      },
      "source": [
        "## page_view.csv"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "3e753e42-5606-20b3-5892-f0924534cb27"
      },
      "outputs": [],
      "source": [
        "page_view_user_country = pd.read.csv('../input/page_views_sample.csv', usecpls=['uuid', 'geo_location'])"
      ]
    }
  ],
  "metadata": {
    "_change_revision": 0,
    "_is_fork": false,
    "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": "3.5.2"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}