{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "7e034776-0ca6-cd18-0886-a0ae50665dff"
      },
      "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",
        "\n",
        "pc=pd.read_csv('../input/promoted_content.csv')\n",
        "df_ct = pd.read_csv('../input/clicks_train.csv',nrows=1000000 )\n",
        "print(df_ct.size)\n",
        "print((pd.DataFrame(pc['document_id'].unique())).count())\n",
        "print(pc.size)\n",
        "M = df_ct.clicked.mean()\n",
        "pc.groupby('document_id',as_index=False).count()['advertiser_id'].unique()\n",
        "\n",
        "df_mrg=df_ct.merge(pc,on='ad_id' ,how='left')\n",
        "\n",
        "df_cmpg= df_mrg.groupby('campaign_id').clicked.agg(['count' ,'sum']).reset_index()\n",
        "df_cmpg['cmpg_Score']= (df_cmpg['sum'] + M) / (1 + df_cmpg['count'])\n",
        "pd.DataFrame(df_cmpg).sort('cmpg_Score')\n",
        "df_cmpg=df_cmpg.drop('count',1)\n",
        "df_cmpg=df_cmpg.drop('sum',1)\n",
        "df_cmpg.to_csv('df_cmpg.csv')\n",
        "\n",
        "df_adv= df_mrg.groupby('advertiser_id').clicked.agg(['count' ,'sum']).reset_index()\n",
        "df_adv['adv_Score']= (df_adv['sum'] + M) / (1 + df_adv['count'])\n",
        "df_adv.sort('adv_Score')\n",
        "\n",
        "\n",
        "#df_adv=df_adv.drop('count',1)\n",
        "#df_adv=df_adv.drop('sum',1)\n",
        "#df_adv.to_csv('df_adv.csv')\n",
        "#df_adv\n",
        "\n",
        "#pc=pc.merge(df_adv).merge(df_cmpg)\n",
        "#pc=pc.drop('campaign_id',1)\n",
        "#pc=pc.drop('advertiser_id',1)\n",
        "#pc=pc.drop('document_id',1)\n",
        "\n",
        "#pc\n",
        "\n"
      ]
    }
  ],
  "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
}