{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Example of Page-wise Aggregation" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "# import openLA as la\n", "import OpenLA as la" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "course_info, event_stream = la.start_analysis(files_dir=\"dataset_sample\", course_id=\"A\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Before conversion" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
useridcontentsidoperationnamepagenomarkermemo_lengthdevicecodeeventtime
0A_U1C1PREV10NaN0tablet2018-04-09 10:57:15
1A_U1C1PREV9NaN0tablet2018-04-09 11:00:59
2A_U1C1PREV8NaN0tablet2018-04-09 11:03:31
3A_U1C1PREV30NaN0tablet2018-04-10 10:14:12
4A_U1C1PREV29NaN0tablet2018-04-10 10:27:24
...........................
263279A_U99C8NEXT3NaN0pc2018-06-05 16:16:18
263280A_U99C8ADD MARKER4difficult0pc2018-06-05 16:18:34
263281A_U99C8NEXT4NaN0pc2018-06-05 16:19:24
263282A_U99C8NEXT5NaN0pc2018-06-05 16:20:45
263283A_U99C8PREV6NaN0pc2018-06-05 16:21:03
\n", "

263284 rows × 8 columns

\n", "
" ], "text/plain": [ " userid contentsid operationname pageno marker memo_length \\\n", "0 A_U1 C1 PREV 10 NaN 0 \n", "1 A_U1 C1 PREV 9 NaN 0 \n", "2 A_U1 C1 PREV 8 NaN 0 \n", "3 A_U1 C1 PREV 30 NaN 0 \n", "4 A_U1 C1 PREV 29 NaN 0 \n", "... ... ... ... ... ... ... \n", "263279 A_U99 C8 NEXT 3 NaN 0 \n", "263280 A_U99 C8 ADD MARKER 4 difficult 0 \n", "263281 A_U99 C8 NEXT 4 NaN 0 \n", "263282 A_U99 C8 NEXT 5 NaN 0 \n", "263283 A_U99 C8 PREV 6 NaN 0 \n", "\n", " devicecode eventtime \n", "0 tablet 2018-04-09 10:57:15 \n", "1 tablet 2018-04-09 11:00:59 \n", "2 tablet 2018-04-09 11:03:31 \n", "3 tablet 2018-04-10 10:14:12 \n", "4 tablet 2018-04-10 10:27:24 \n", "... ... ... \n", "263279 pc 2018-06-05 16:16:18 \n", "263280 pc 2018-06-05 16:18:34 \n", "263281 pc 2018-06-05 16:19:24 \n", "263282 pc 2018-06-05 16:20:45 \n", "263283 pc 2018-06-05 16:21:03 \n", "\n", "[263284 rows x 8 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "event_stream.df" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Behavior in each page (the total staying seconds and operation count in each page)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "behavior_each_page = la.convert_into_page_wise(event_stream=event_stream,\n", " user_id=course_info.user_id()[:5],\n", " contents_id=None, \n", " invalid_seconds=5,\n", " timeout_seconds=20*60,\n", " count_operation=True,\n", " operation_name=[\"OPEN\", \"CLOSE\", \"ADD MARKER\", \"ADD MEMO\", \"ADD BOOKMARK\"],\n", " separate_marker_type=False)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
useridcontentsidpagenonum_visitsaverage_reading_secondsreading_secondsOPENCLOSEADD MARKERADD MEMOADD BOOKMARK
0A_U1C1112148.416667178180000
1A_U1C128240.500000192401200
2A_U1C13593.40000046700000
3A_U1C14674.83333344900000
4A_U1C15687.83333352700000
....................................
1734A_U102C879646.16666727700000
1735A_U102C880644.16666726500000
1736A_U102C881428.25000011300000
1737A_U102C8826143.50000086100000
1738A_U102C8834100.00000040000000
\n", "

1739 rows × 11 columns

\n", "
" ], "text/plain": [ " userid contentsid pageno num_visits average_reading_seconds \\\n", "0 A_U1 C1 1 12 148.416667 \n", "1 A_U1 C1 2 8 240.500000 \n", "2 A_U1 C1 3 5 93.400000 \n", "3 A_U1 C1 4 6 74.833333 \n", "4 A_U1 C1 5 6 87.833333 \n", "... ... ... ... ... ... \n", "1734 A_U102 C8 79 6 46.166667 \n", "1735 A_U102 C8 80 6 44.166667 \n", "1736 A_U102 C8 81 4 28.250000 \n", "1737 A_U102 C8 82 6 143.500000 \n", "1738 A_U102 C8 83 4 100.000000 \n", "\n", " reading_seconds OPEN CLOSE ADD MARKER ADD MEMO ADD BOOKMARK \n", "0 1781 8 0 0 0 0 \n", "1 1924 0 1 2 0 0 \n", "2 467 0 0 0 0 0 \n", "3 449 0 0 0 0 0 \n", "4 527 0 0 0 0 0 \n", "... ... ... ... ... ... ... \n", "1734 277 0 0 0 0 0 \n", "1735 265 0 0 0 0 0 \n", "1736 113 0 0 0 0 0 \n", "1737 861 0 0 0 0 0 \n", "1738 400 0 0 0 0 0 \n", "\n", "[1739 rows x 11 columns]" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "behavior_each_page.df" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Save the data to CSV file" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "behavior_each_page.to_csv(save_file=\"data.csv\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Aggregate information" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "5" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Number of users in the data\n", "behavior_each_page.num_users()" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['A_U1', 'A_U10', 'A_U100', 'A_U101', 'A_U102']" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# User ids in the data\n", "behavior_each_page.user_id()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['C1', 'C2', 'C3', 'C4', 'C5', 'C7', 'C8', 'C6']" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Contents ids in the data\n", "behavior_each_page.contents_id()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['OPEN', 'CLOSE', 'ADD MARKER', 'ADD MEMO', 'ADD BOOKMARK']" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Operation names in the data\n", "behavior_each_page.operation_name()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "2" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Number of selected operation logs\n", "behavior_each_page.operation_count(operation_name=\"ADD MARKER\", \n", " user_id=\"A_U1\", \n", " contents_id=\"C1\")" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'ADD MARKER': 2, 'ADD BOOKMARK': 3}" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "behavior_each_page.operation_count(operation_name=[\"ADD MARKER\", \"ADD BOOKMARK\"], \n", " user_id=\"A_U1\", \n", " contents_id=\"C1\")" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "67" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Number of unique pages in the data\n", "behavior_each_page.num_unique_pages(user_id=\"A_U1\", contents_id=\"C1\")" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "42748" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Total reading seconds in the data\n", "behavior_each_page.reading_seconds(user_id=\"A_U1\", contents_id=\"C1\")" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "42748" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Total reading time in the data (seconds)\n", "behavior_each_page.reading_time(time_unit=\"seconds\", user_id=\"A_U1\", contents_id=\"C1\")" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "712.4666666666667" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Total reading time in the data (minutes)\n", "behavior_each_page.reading_time(time_unit=\"minutes\", user_id=\"A_U1\", contents_id=\"C1\")" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "11.874444444444444" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Total reading time in the data (hours)\n", "behavior_each_page.reading_time(time_unit=\"hours\", user_id=\"A_U1\", contents_id=\"C1\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Visualize information\n", "The average operation count of all users in each page." ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(,\n", " )" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "la.visualize_behavior_in_pages(behavior_each_page, \n", " user_id=None,\n", " contents_id=\"C6\",\n", " is_plot_operation=True,\n", " is_plot_reading_time=True,\n", " operation_name=None,\n", " reading_time_basis=\"minutes\",\n", " calculate_type=\"average\",\n", " operation_bar_colors=None,\n", " reading_time_color=\"brown\",\n", " figsize=(20, 10),\n", " fontsize=18,\n", " save_file=None)" ] } ], "metadata": { "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": "3.7.3" }, "pycharm": { "stem_cell": { "cell_type": "raw", "metadata": { "collapsed": false }, "source": [] } } }, "nbformat": 4, "nbformat_minor": 4 }