{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "89114ebf-e58e-52ee-c4fd-0e14d7fad968"
      },
      "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",
        "# 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": "696b7f45-4100-781d-2c59-85c2f8b09df2"
      },
      "outputs": [],
      "source": [
        "documents_categories = pd.read_csv(\"../input/documents_categories.csv\")\n",
        "unique_categories = pd.Series.unique(documents_categories['category_id'])\n",
        "groupbydocid = documents_categories.groupby(['document_id'])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "f63cb002-a388-c5ff-3aba-0355567118e2"
      },
      "outputs": [],
      "source": [
        "print(\"Length of Unique catgories {}\".format(len(unique_categories)))\n",
        "print(unique_categories)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "57792b08-cee0-c518-2e98-b0186ff6125b"
      },
      "outputs": [],
      "source": [
        "category_confidence = groupbydocid.agg(pd.Series.tolist)[['category_id', 'confidence_level']]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "42ef4e1f-a8c0-8a2d-0f51-07d494b7ccad"
      },
      "outputs": [],
      "source": [
        "category_confidence.to_csv(\"category_confidence.csv\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "bf607e3e-5810-a928-0104-74e7766544bb"
      },
      "outputs": [],
      "source": [
        "category_confidence.he"
      ]
    }
  ],
  "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
}