{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "3bd0f878-515b-ec4f-0dfe-80db63d61f8c"
      },
      "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 os\n",
        "\n",
        "# Input data files are available in the \"../input/\" directory.\n",
        "# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\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": "d881c07e-8e55-945c-039d-4f1d715c0f17"
      },
      "outputs": [],
      "source": [
        "print (\"file Sizes\")\n",
        "for filename in os.listdir('../input'):\n",
        "    print (filename.ljust(50)  + str( round(os.path.getsize('../input/' + filename)/1000000, 2))  + ' MB')\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "08c7cd8a-b586-a7da-04cd-026baa07bfda"
      },
      "outputs": [],
      "source": [
        "test  = pd.read_csv('../input/clicks_test.csv')\n",
        "train = pd.read_csv('../input/clicks_train.csv')\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "c1c44f14-3328-44e2-b085-e238feaeb060"
      },
      "outputs": [],
      "source": [
        "sizes_train = train.groupby('display_id')['ad_id'].count().value_counts()\n",
        "print(sizes_train)"
      ]
    }
  ],
  "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
}