Pandas df.groupby() Example

pandas_groupby_example.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "pandas_groupby_example.ipynb",
      "private_outputs": true,
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyO64/h+qKt7uO/BsVmgroV1",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/Caellwyn/0866534f6d94ce6dd0137f90d9f690bf/untitled5.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-BPcWDDH_-c1"
      },
      "source": [
        "import pandas as pd\r\n",
        "import zipfile\r\n",
        "import wget\r\n",
        "\r\n",
        "url = 'https://analyse.kmi.open.ac.uk/open_dataset/download'\r\n",
        "# filename = wget.download(url)\r\n",
        "zpf = zipfile.ZipFile(filename)\r\n",
        "student_vle = pd.read_csv(zpf.open('studentVle.csv'))\r\n",
        "\r\n",
        "index_cols = ['code_module','code_presentation','id_student']\r\n",
        "student_groups = student_vle.groupby(index_cols)\r\n",
        "\r\n",
        "activity_counts = student_groups.count()\r\n",
        "average_clicks = student_groups.mean()\r\n",
        "\r\n",
        "activities_and_clicks = pd.merge(activity_counts['id_site'], \\\r\n",
        "                                average_clicks['sum_click'], \\\r\n",
        "                                how='inner', \\\r\n",
        "                                on=index_cols)\r\n",
        "                                \r\n",
        "activities_and_clicks.columns = ['Total Activities Engaged', 'Average Clicks per Activity']\r\n",
        "activities_and_clicks.reset_index(inplace=True)\r\n",
        "activities_and_clicks.head()"
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}