{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "bf7b008b-c726-3f11-e888-7fc2fe42950f"
      },
      "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",
        "import os"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "189e3cc6-61bc-8006-19c3-36fad5621bad"
      },
      "outputs": [],
      "source": [
        "os.listdir('../input')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "797b88e0-de81-74be-c01e-c55726e7e239"
      },
      "outputs": [],
      "source": [
        "documents_meta = pd.read_csv('../input/documents_meta.csv')\n",
        "documents_meta.head(3)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "17afc68f-fbf4-2242-cd78-a8054ae08793"
      },
      "outputs": [],
      "source": [
        "documents_meta.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "bc718b5f-3116-da22-2bcd-cf62f2a48123"
      },
      "outputs": [],
      "source": [
        "documents_meta.publisher_id.unique().size"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "221583c6-c633-b0c7-0ba7-248c06b87d7f"
      },
      "outputs": [],
      "source": [
        "documents_categories = pd.read_csv('../input/documents_categories.csv')\n",
        "documents_categories.head(3)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "aab3d2c4-ebea-4280-defc-650dc1fc567b"
      },
      "outputs": [],
      "source": [
        "documents_categories.category_id.unique().size"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "7711835f-5b25-26d1-1a26-011fe2d4a7b7"
      },
      "outputs": [],
      "source": [
        "documents_entities = pd.read_csv('../input/documents_entities.csv')\n",
        "documents_entities.head(3)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "80e15df2-76d0-af78-b967-01a5f9b25bbf"
      },
      "outputs": [],
      "source": [
        "documents_topics = pd.read_csv('../input/documents_topics.csv')\n",
        "documents_topics.head(3)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "7983c77b-6b96-4161-c2f5-8a0ce1e51387"
      },
      "outputs": [],
      "source": [
        "documents_topics.topic_id.unique().size"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "62d04016-991a-c29a-6932-e5e160a3de5a"
      },
      "outputs": [],
      "source": [
        "page_views_sample = pd.read_csv('../input/page_views_sample.csv')\n",
        "page_views_sample.head(3)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "9d65e7e0-49c3-9396-7444-84fd8133f27c"
      },
      "outputs": [],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "% matplotlib inline\n",
        "page_views_documment = page_views_sample.groupby(['document_id']).uuid.count().sort_values()\n",
        "\n",
        "page_views_documment.head(3)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "870395d5-38d5-d1d9-9c16-5c3a62afd0dd"
      },
      "outputs": [],
      "source": [
        "# transform data\n",
        "page_views_documment_log = [np.log(x) for x in page_views_documment.values]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "6739da3f-9487-968a-18d4-f58eea225daa"
      },
      "outputs": [],
      "source": [
        "plt.boxplot(page_views_documment_log )\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "c8f9b875-445d-c5af-6ce1-7907e1dc816d"
      },
      "outputs": [],
      "source": [
        "plt.hist(page_views_documment_log, bins=20)\n",
        "\n",
        "plt.xlabel('Log(counts)')\n",
        "\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "477052f8-d74a-b30b-0cbf-4639c7e212bf"
      },
      "outputs": [],
      "source": ""
    }
  ],
  "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
}