From 873d7eac163777e50e175a4be793e7f97d4e4d19 Mon Sep 17 00:00:00 2001 From: KenelmQLH <1097824882@qq.com> Date: Fri, 9 Apr 2021 11:52:36 +0800 Subject: [PATCH 1/8] Add OLI data analysis in doc --- docs/OLI_Fall2011/OLI_2011F_problem.ipynb | 51896 ++++++ docs/OLI_Fall2011/OLI_2011F_step.ipynb | 126148 +++++++++++++++ docs/OLI_Fall2011/OLI_2011F_transaction.ipynb | 12786 ++ 3 files changed, 190830 insertions(+) create mode 100644 docs/OLI_Fall2011/OLI_2011F_problem.ipynb create mode 100644 docs/OLI_Fall2011/OLI_2011F_step.ipynb create mode 100644 docs/OLI_Fall2011/OLI_2011F_transaction.ipynb diff --git a/docs/OLI_Fall2011/OLI_2011F_problem.ipynb b/docs/OLI_Fall2011/OLI_2011F_problem.ipynb new file mode 100644 index 0000000..232b080 --- /dev/null +++ b/docs/OLI_Fall2011/OLI_2011F_problem.ipynb @@ -0,0 +1,51896 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# OLI data in fall, 2011(problem)" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "#全局配置:显示所有行,列\n", + "pd.set_option('display.max_rows', None)\n", + "pd.set_option('max_colwidth',None)\n", + "pd.set_option('display.max_columns', None)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 1. 数据描述\n", + "## 1.1 列属性" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + " | Field | \n", + "Annotation | \n", + "
---|---|---|
0 | \n", + "Row | \n", + "A row counter. | \n", + "
1 | \n", + "Sample | \n", + "The sample that includes this problem. If you select more than one sample to export, problems that occur in more than one sample will be duplicated in the export. | \n", + "
2 | \n", + "Anon Student ID | \n", + "The student that worked on the problem. | \n", + "
3 | \n", + "Problem Hierarchy | \n", + "The location in the curriculum hierarchy where this problem occurs. | \n", + "
4 | \n", + "Problem Name | \n", + "The name of the problem. | \n", + "
5 | \n", + "Problem View | \n", + "The number of times the student encountered the problem so far. This counter increases with each instance of the same problem. See \"Problem View\" in the \"By Student-Step\" table above. | \n", + "
6 | \n", + "Problem Start Time | \n", + "If the problem start time is not given in the original log data, then it is set to the time of the last transaction of the prior problem. If there is no prior problem for the session, the time of the earliest transaction is used. Earliest transaction time is equivalent to the minimum transaction time for the earliest step of the problem. For more detail on how problem start time is determined, see Determining Problem Start Time. | \n", + "
7 | \n", + "Problem End Time | \n", + "Derived from the maximum transaction time of the latest step of the problem. | \n", + "
8 | \n", + "Latency (sec) | \n", + "The amount of time the student spent on this problem. Specifically, the difference between the problem start time and the last transaction on this problem. | \n", + "
9 | \n", + "Steps Missing Start Times | \n", + "The number of steps (from the student-step table) with \"Step Start Time\" values of \"null\". | \n", + "
10 | \n", + "Hints | \n", + "Total number of hints the student requested for this problem. | \n", + "
11 | \n", + "Incorrects | \n", + "Total number of incorrect attempts the student made on this problem. | \n", + "
12 | \n", + "Corrects | \n", + "Total number of correct attempts the student made for this problem. | \n", + "
13 | \n", + "Avg Corrects | \n", + "The total number of correct attempts / total number of steps in the problem. | \n", + "
14 | \n", + "Steps | \n", + "Total number of steps the student took while working on the problem. | \n", + "
15 | \n", + "Avg Assistance Score | \n", + "Calculated as (total hints requested + total incorrect attempts) / total steps. | \n", + "
16 | \n", + "Correct First Attempts | \n", + "Total number of correct first attempts made by the student for this problem. | \n", + "
17 | \n", + "Condition | \n", + "The name and type of the condition the student is assigned to. In the case of a student assigned to multiple conditions (factors in a factorial design), condition names are separated by a comma and space. This differs from the transaction format, which optionally has \"Condition Name\" and \"Condition Type\" columns. | \n", + "
18 | \n", + "KCs | \n", + "Total number of KCs practiced by the student for this problem. | \n", + "
19 | \n", + "Steps without KCs | \n", + "Total number of steps in this problem (performed by the student) without an assigned KC. | \n", + "
20 | \n", + "KC List | \n", + "Comma-delimited list of KCs practiced by the student for this problem. | \n", + "
\n", + " | Row | \n", + "Sample | \n", + "Anon Student Id | \n", + "Problem Hierarchy | \n", + "Problem Name | \n", + "Problem View | \n", + "Problem Start Time | \n", + "Problem End Time | \n", + "Latency (sec) | \n", + "Steps Missing Start Times | \n", + "Hints | \n", + "Incorrects | \n", + "Corrects | \n", + "Avg Corrects | \n", + "Steps | \n", + "Avg Assistance Score | \n", + "Correct First Attempts | \n", + "Condition | \n", + "KCs (F2011) | \n", + "Steps without KCs (F2011) | \n", + "KC List (F2011) | \n", + "KCs (Single-KC) | \n", + "Steps without KCs (Single-KC) | \n", + "KC List (Single-KC) | \n", + "KCs (Unique-step) | \n", + "Steps without KCs (Unique-step) | \n", + "KC List (Unique-step) | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "1 | \n", + "All Data | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "sequence Statics, unit Concentrated Forces and Their Effects, module Introduction to Free Body Diagrams | \n", + "_m2_assess | \n", + "1 | \n", + "2011/9/21 17:35 | \n", + "2011/9/21 17:35 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "9 | \n", + "12 | \n", + "0.571 | \n", + "21 | \n", + "0.429 | \n", + "12 | \n", + "NaN | \n", + "5 | \n", + "0 | \n", + "gravitational_forces, identify_interaction, represent_interaction_cord, represent_interaction_spring, simple_step | \n", + "1 | \n", + "0 | \n", + "Single-KC | \n", + "0 | \n", + "21 | \n", + ". | \n", + "
1 | \n", + "2 | \n", + "All Data | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "sequence Statics, unit Concentrated Forces and Their Effects, module Effects of Force | \n", + "tutor_03_01 | \n", + "1 | \n", + "2011/9/21 17:49 | \n", + "2011/9/21 17:49 | \n", + "9 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "3 | \n", + "1.000 | \n", + "3 | \n", + "0.000 | \n", + "3 | \n", + "NaN | \n", + "1 | \n", + "0 | \n", + "distinguish_rotation_translation | \n", + "1 | \n", + "0 | \n", + "Single-KC | \n", + "3 | \n", + "0 | \n", + "KC523, KC680, KC768 | \n", + "
\n", + " | Row | \n", + "Problem View | \n", + "Latency (sec) | \n", + "Steps Missing Start Times | \n", + "Hints | \n", + "Incorrects | \n", + "Corrects | \n", + "Avg Corrects | \n", + "Steps | \n", + "Avg Assistance Score | \n", + "Correct First Attempts | \n", + "Condition | \n", + "KCs (F2011) | \n", + "Steps without KCs (F2011) | \n", + "KCs (Single-KC) | \n", + "Steps without KCs (Single-KC) | \n", + "KCs (Unique-step) | \n", + "Steps without KCs (Unique-step) | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
count | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "0.0 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "45002.0 | \n", + "45002.0 | \n", + "45002.000000 | \n", + "45002.000000 | \n", + "
mean | \n", + "22501.500000 | \n", + "1.221146 | \n", + "85.639883 | \n", + "0.007000 | \n", + "0.620217 | \n", + "1.644460 | \n", + "4.176325 | \n", + "0.959571 | \n", + "4.331963 | \n", + "0.928014 | \n", + "3.219479 | \n", + "NaN | \n", + "1.223923 | \n", + "1.798920 | \n", + "1.0 | \n", + "0.0 | \n", + "4.289654 | \n", + "0.042309 | \n", + "
std | \n", + "12991.102744 | \n", + "1.140622 | \n", + "301.895374 | \n", + "0.106748 | \n", + "1.956302 | \n", + "3.378211 | \n", + "5.125742 | \n", + "0.358850 | \n", + "5.079484 | \n", + "2.221907 | \n", + "4.603916 | \n", + "NaN | \n", + "1.733856 | \n", + "3.830471 | \n", + "0.0 | \n", + "0.0 | \n", + "5.084490 | \n", + "0.557118 | \n", + "
min | \n", + "1.000000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "NaN | \n", + "0.000000 | \n", + "0.000000 | \n", + "1.0 | \n", + "0.0 | \n", + "0.000000 | \n", + "0.000000 | \n", + "
25% | \n", + "11251.250000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "1.000000 | \n", + "1.000000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "1.000000 | \n", + "NaN | \n", + "0.000000 | \n", + "0.000000 | \n", + "1.0 | \n", + "0.0 | \n", + "1.000000 | \n", + "0.000000 | \n", + "
50% | \n", + "22501.500000 | \n", + "1.000000 | \n", + "20.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "1.000000 | \n", + "3.000000 | \n", + "1.000000 | \n", + "3.000000 | \n", + "0.250000 | \n", + "2.000000 | \n", + "NaN | \n", + "1.000000 | \n", + "0.000000 | \n", + "1.0 | \n", + "0.0 | \n", + "3.000000 | \n", + "0.000000 | \n", + "
75% | \n", + "33751.750000 | \n", + "1.000000 | \n", + "73.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "2.000000 | \n", + "5.000000 | \n", + "1.000000 | \n", + "5.000000 | \n", + "1.000000 | \n", + "4.000000 | \n", + "NaN | \n", + "2.000000 | \n", + "2.000000 | \n", + "1.0 | \n", + "0.0 | \n", + "5.000000 | \n", + "0.000000 | \n", + "
max | \n", + "45002.000000 | \n", + "32.000000 | \n", + "20426.000000 | \n", + "8.000000 | \n", + "50.000000 | \n", + "413.000000 | \n", + "232.000000 | \n", + "19.333000 | \n", + "32.000000 | \n", + "210.500000 | \n", + "32.000000 | \n", + "NaN | \n", + "9.000000 | \n", + "32.000000 | \n", + "1.0 | \n", + "0.0 | \n", + "32.000000 | \n", + "29.000000 | \n", + "
\n", + " | col_name | \n", + "num_nonull | \n", + "num_null | \n", + "num_unique | \n", + "
---|---|---|---|---|
0 | \n", + "Row | \n", + "45002 | \n", + "0 | \n", + "45002 | \n", + "
1 | \n", + "Sample | \n", + "45002 | \n", + "0 | \n", + "1 | \n", + "
2 | \n", + "Anon Student Id | \n", + "45002 | \n", + "0 | \n", + "333 | \n", + "
3 | \n", + "Problem Hierarchy | \n", + "45002 | \n", + "0 | \n", + "27 | \n", + "
4 | \n", + "Problem Name | \n", + "45002 | \n", + "0 | \n", + "300 | \n", + "
5 | \n", + "Problem View | \n", + "45002 | \n", + "0 | \n", + "32 | \n", + "
6 | \n", + "Problem Start Time | \n", + "45002 | \n", + "0 | \n", + "25983 | \n", + "
7 | \n", + "Problem End Time | \n", + "45002 | \n", + "0 | \n", + "25884 | \n", + "
8 | \n", + "Latency (sec) | \n", + "45002 | \n", + "0 | \n", + "1290 | \n", + "
9 | \n", + "Steps Missing Start Times | \n", + "45002 | \n", + "0 | \n", + "8 | \n", + "
10 | \n", + "Hints | \n", + "45002 | \n", + "0 | \n", + "35 | \n", + "
11 | \n", + "Incorrects | \n", + "45002 | \n", + "0 | \n", + "37 | \n", + "
12 | \n", + "Corrects | \n", + "45002 | \n", + "0 | \n", + "51 | \n", + "
13 | \n", + "Avg Corrects | \n", + "45002 | \n", + "0 | \n", + "195 | \n", + "
14 | \n", + "Steps | \n", + "45002 | \n", + "0 | \n", + "31 | \n", + "
15 | \n", + "Avg Assistance Score | \n", + "45002 | \n", + "0 | \n", + "335 | \n", + "
16 | \n", + "Correct First Attempts | \n", + "45002 | \n", + "0 | \n", + "33 | \n", + "
17 | \n", + "Condition | \n", + "0 | \n", + "45002 | \n", + "1 | \n", + "
18 | \n", + "KCs (F2011) | \n", + "45002 | \n", + "0 | \n", + "10 | \n", + "
19 | \n", + "Steps without KCs (F2011) | \n", + "45002 | \n", + "0 | \n", + "31 | \n", + "
20 | \n", + "KC List (F2011) | \n", + "45002 | \n", + "0 | \n", + "170 | \n", + "
21 | \n", + "KCs (Single-KC) | \n", + "45002 | \n", + "0 | \n", + "1 | \n", + "
22 | \n", + "Steps without KCs (Single-KC) | \n", + "45002 | \n", + "0 | \n", + "1 | \n", + "
23 | \n", + "KC List (Single-KC) | \n", + "45002 | \n", + "0 | \n", + "1 | \n", + "
24 | \n", + "KCs (Unique-step) | \n", + "45002 | \n", + "0 | \n", + "32 | \n", + "
25 | \n", + "Steps without KCs (Unique-step) | \n", + "45002 | \n", + "0 | \n", + "16 | \n", + "
26 | \n", + "KC List (Unique-step) | \n", + "45002 | \n", + "0 | \n", + "1470 | \n", + "
\n", + " | Row | \n", + "Anon Student Id | \n", + "Problem Hierarchy | \n", + "Problem Name | \n", + "Problem View | \n", + "Problem Start Time | \n", + "Problem End Time | \n", + "Latency (sec) | \n", + "Steps Missing Start Times | \n", + "Hints | \n", + "Incorrects | \n", + "Corrects | \n", + "Avg Corrects | \n", + "Steps | \n", + "Avg Assistance Score | \n", + "Correct First Attempts | \n", + "KCs (F2011) | \n", + "Steps without KCs (F2011) | \n", + "KC List (F2011) | \n", + "KCs (Unique-step) | \n", + "Steps without KCs (Unique-step) | \n", + "KC List (Unique-step) | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "1 | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "sequence Statics, unit Concentrated Forces and Their Effects, module Introduction to Free Body Diagrams | \n", + "_m2_assess | \n", + "1 | \n", + "2011/9/21 17:35 | \n", + "2011/9/21 17:35 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "9 | \n", + "12 | \n", + "0.571 | \n", + "21 | \n", + "0.429 | \n", + "12 | \n", + "5 | \n", + "0 | \n", + "gravitational_forces, identify_interaction, represent_interaction_cord, represent_interaction_spring, simple_step | \n", + "0 | \n", + "21 | \n", + ". | \n", + "
1 | \n", + "2 | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "sequence Statics, unit Concentrated Forces and Their Effects, module Effects of Force | \n", + "tutor_03_01 | \n", + "1 | \n", + "2011/9/21 17:49 | \n", + "2011/9/21 17:49 | \n", + "9 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "3 | \n", + "1.000 | \n", + "3 | \n", + "0.000 | \n", + "3 | \n", + "1 | \n", + "0 | \n", + "distinguish_rotation_translation | \n", + "3 | \n", + "0 | \n", + "KC523, KC680, KC768 | \n", + "
\n", + " | col_name | \n", + "num_nonull | \n", + "num_null | \n", + "num_unique | \n", + "
---|---|---|---|---|
0 | \n", + "Row | \n", + "45002 | \n", + "0 | \n", + "45002 | \n", + "
1 | \n", + "Anon Student Id | \n", + "45002 | \n", + "0 | \n", + "333 | \n", + "
2 | \n", + "Problem Hierarchy | \n", + "45002 | \n", + "0 | \n", + "27 | \n", + "
3 | \n", + "Problem Name | \n", + "45002 | \n", + "0 | \n", + "300 | \n", + "
4 | \n", + "Problem View | \n", + "45002 | \n", + "0 | \n", + "32 | \n", + "
5 | \n", + "Problem Start Time | \n", + "45002 | \n", + "0 | \n", + "25983 | \n", + "
6 | \n", + "Problem End Time | \n", + "45002 | \n", + "0 | \n", + "25884 | \n", + "
7 | \n", + "Latency (sec) | \n", + "45002 | \n", + "0 | \n", + "1290 | \n", + "
8 | \n", + "Steps Missing Start Times | \n", + "45002 | \n", + "0 | \n", + "8 | \n", + "
9 | \n", + "Hints | \n", + "45002 | \n", + "0 | \n", + "35 | \n", + "
10 | \n", + "Incorrects | \n", + "45002 | \n", + "0 | \n", + "37 | \n", + "
11 | \n", + "Corrects | \n", + "45002 | \n", + "0 | \n", + "51 | \n", + "
12 | \n", + "Avg Corrects | \n", + "45002 | \n", + "0 | \n", + "195 | \n", + "
13 | \n", + "Steps | \n", + "45002 | \n", + "0 | \n", + "31 | \n", + "
14 | \n", + "Avg Assistance Score | \n", + "45002 | \n", + "0 | \n", + "335 | \n", + "
15 | \n", + "Correct First Attempts | \n", + "45002 | \n", + "0 | \n", + "33 | \n", + "
16 | \n", + "KCs (F2011) | \n", + "45002 | \n", + "0 | \n", + "10 | \n", + "
17 | \n", + "Steps without KCs (F2011) | \n", + "45002 | \n", + "0 | \n", + "31 | \n", + "
18 | \n", + "KC List (F2011) | \n", + "45002 | \n", + "0 | \n", + "170 | \n", + "
19 | \n", + "KCs (Unique-step) | \n", + "45002 | \n", + "0 | \n", + "32 | \n", + "
20 | \n", + "Steps without KCs (Unique-step) | \n", + "45002 | \n", + "0 | \n", + "16 | \n", + "
21 | \n", + "KC List (Unique-step) | \n", + "45002 | \n", + "0 | \n", + "1470 | \n", + "
\n", + " | Field | \n", + "Annotation | \n", + "
---|---|---|
0 | \n", + "Row | \n", + "A row counter. | \n", + "
1 | \n", + "Sample | \n", + "The sample that includes this step. If you select more than one sample to export, steps that occur in more than one sample will be duplicated in the export. | \n", + "
2 | \n", + "Anon Student ID | \n", + "The student that performed the step. | \n", + "
3 | \n", + "Problem Hierarchy | \n", + "The location in the curriculum hierarchy where this step occurs. | \n", + "
4 | \n", + "Problem Name | \n", + "The name of the problem in which the step occurs. | \n", + "
5 | \n", + "Problem View | \n", + "The number of times the student encountered the problem so far. This counter increases with each instance of the same problem. Note that problem view increases regardless of whether or not the step was encountered in previous problem views. For example, a step can have a \"Problem View\" of \"3\", indicating the problem was viewed three times by this student, but that same step need not have been encountered by that student in all instances of the problem. If this number does not increase as you expect it to, it might be that DataShop has identified similar problems as distinct: two problems with the same \"Problem Name\" are considered different \"problems\" by DataShop if the following logged values are not identical: problem name, context, tutor_flag (whether or not the problem or activity is tutored) and \"other\" field. For more on the logging of these fields, see the description of the \"problem\" element in the Guide to the Tutor Message Format. For more detail on how problem view is determined, see Determining Problem View. | \n", + "
6 | \n", + "Step Name | \n", + "Formed by concatenating the \"selection\" and \"action\". Also see the glossary entry for \"step\". | \n", + "
7 | \n", + "Step Start Time | \n", + "The step start time is determined one of three ways: If it's the first step of the problem, the step start time is the same as the problem start time If it's a subsequent step, then the step start time is the time of the preceding transaction, if that transaction is within 10 minutes. If it's a subsequent step and the elapsed time between the previous transaction and the first transaction of this step is more than 10 minutes, then the step start time is set to null as it's considered an unreliable value. For a visual example, see the Examples page. | \n", + "
8 | \n", + "First Transaction Time | \n", + "The time of the first transaction toward the step. | \n", + "
9 | \n", + "Correct Transaction Time | \n", + "The time of the correct attempt toward the step, if there was one. | \n", + "
10 | \n", + "Step End Time | \n", + "The time of the last transaction toward the step. | \n", + "
11 | \n", + "Step Duration (sec) | \n", + "The elapsed time of the step in seconds, calculated by adding all of the durations for transactions that were attributed to the step. See the glossary entry for more detail. This column was previously labeled \"Assistance Time\". It differs from \"Assistance Time\" in that its values are derived by summing transaction durations, not finding the difference between only two points in time (step start time and the last correct attempt). | \n", + "
12 | \n", + "Correct Step Duration (sec) | \n", + "The step duration if the first attempt for the step was correct. This might also be described as \"reaction time\" since it's the duration of time from the previous transaction or problem start event to the correct attempt. See the glossary entry for more detail. This column was previously labeled \"Correct Step Time (sec)\". | \n", + "
13 | \n", + "Error Step Duration (sec) | \n", + "The step duration if the first attempt for the step was an error (incorrect attempt or hint request). | \n", + "
14 | \n", + "First Attempt | \n", + "The tutor's response to the student's first attempt on the step. Example values are \"hint\", \"correct\", and \"incorrect\". | \n", + "
15 | \n", + "Incorrects | \n", + "Total number of incorrect attempts by the student on the step. | \n", + "
16 | \n", + "Hints | \n", + "Total number of hints requested by the student for the step. | \n", + "
17 | \n", + "Corrects | \n", + "Total correct attempts by the student for the step. (Only increases if the step is encountered more than once.) | \n", + "
18 | \n", + "Condition | \n", + "The name and type of the condition the student is assigned to. In the case of a student assigned to multiple conditions (factors in a factorial design), condition names are separated by a comma and space. This differs from the transaction format, which optionally has \"Condition Name\" and \"Condition Type\" columns. | \n", + "
19 | \n", + "KC (model_name) | \n", + "(Only shown when the \"Knowledge Components\" option is selected.) Knowledge component(s) associated with the correct performance of this step. In the case of multiple KCs assigned to a single step, KC names are separated by two tildes (\"~~\"). | \n", + "
20 | \n", + "Opportunity (model_name) | \n", + "(Only shown when the \"Knowledge Components\" option is selected.) An opportunity is the first chance on a step for a student to demonstrate whether he or she has learned the associated knowledge component. Opportunity number is therefore a count that increases by one each time the student encounters a step with the listed knowledge component. In the case of multiple KCs assigned to a single step, opportunity number values are separated by two tildes (\"~~\") and are given in the same order as the KC names. Check here to see how opportunity count is computed when Event Type column is present in transaction data. | \n", + "
21 | \n", + "Predicted Error Rate (model_name) | \n", + "A hypothetical error rate based on the Additive Factor Model (AFM) algorithm. A value of \"1\" is a prediction that a student's first attempt will be an error (incorrect attempt or hint request); a value of \"0\" is a prediction that the student's first attempt will be correct. For specifics, see below \"Predicted Error Rate\" and how it's calculated. In the case of multiple KCs assigned to a single step, Datashop implements a compensatory sum across all of the KCs, thus a single value of predicted error rate is provided (i.e., the same predicted error rate for each KC assigned to a step). For more detail on Datashop's implementation for multi-skilled step, see Model Values page. | \n", + "
\n", + " | Row | \n", + "Sample | \n", + "Anon Student Id | \n", + "Problem Hierarchy | \n", + "Problem Name | \n", + "Problem View | \n", + "Step Name | \n", + "Step Start Time | \n", + "First Transaction Time | \n", + "Correct Transaction Time | \n", + "Step End Time | \n", + "Step Duration (sec) | \n", + "Correct Step Duration (sec) | \n", + "Error Step Duration (sec) | \n", + "First Attempt | \n", + "Incorrects | \n", + "Hints | \n", + "Corrects | \n", + "Condition | \n", + "KC (F2011) | \n", + "Opportunity (F2011) | \n", + "Predicted Error Rate (F2011) | \n", + "KC (Single-KC) | \n", + "Opportunity (Single-KC) | \n", + "Predicted Error Rate (Single-KC) | \n", + "KC (Unique-step) | \n", + "Opportunity (Unique-step) | \n", + "Predicted Error Rate (Unique-step) | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "1 | \n", + "All Data | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "sequence Statics, unit Concentrated Forces and Their Effects, module Introduction to Free Body Diagrams | \n", + "_m2_assess | \n", + "1 | \n", + "q1_point1i1 UpdateComboBox | \n", + "2011/9/21 17:35 | \n", + "2011/9/21 17:35 | \n", + "2011/9/21 17:35 | \n", + "2011/9/21 17:35 | \n", + "23.13 | \n", + "23.13 | \n", + ". | \n", + "correct | \n", + "0 | \n", + "0 | \n", + "1 | \n", + ". | \n", + "identify_interaction | \n", + "1 | \n", + "0.3991 | \n", + "Single-KC | \n", + "1 | \n", + "0.4373 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
1 | \n", + "2 | \n", + "All Data | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "sequence Statics, unit Concentrated Forces and Their Effects, module Introduction to Free Body Diagrams | \n", + "_m2_assess | \n", + "1 | \n", + "q1_point3i3 UpdateComboBox | \n", + "2011/9/21 17:35 | \n", + "2011/9/21 17:35 | \n", + "2011/9/21 17:35 | \n", + "2011/9/21 17:35 | \n", + "23.13 | \n", + "23.13 | \n", + ". | \n", + "correct | \n", + "0 | \n", + "0 | \n", + "1 | \n", + ". | \n", + "gravitational_forces | \n", + "1 | \n", + "0.1665 | \n", + "Single-KC | \n", + "2 | \n", + "0.4373 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
\n", + " | Row | \n", + "Problem View | \n", + "Incorrects | \n", + "Hints | \n", + "Corrects | \n", + "Predicted Error Rate (F2011) | \n", + "Opportunity (Single-KC) | \n", + "Predicted Error Rate (Single-KC) | \n", + "Opportunity (Unique-step) | \n", + "Predicted Error Rate (Unique-step) | \n", + "
---|---|---|---|---|---|---|---|---|---|---|
count | \n", + "194947.000000 | \n", + "194947.000000 | \n", + "194947.000000 | \n", + "194947.000000 | \n", + "194947.000000 | \n", + "113992.000000 | \n", + "194947.000000 | \n", + "194947.000000 | \n", + "193043.000000 | \n", + "0.0 | \n", + "
mean | \n", + "97474.000000 | \n", + "1.133154 | \n", + "0.379611 | \n", + "0.143172 | \n", + "0.964072 | \n", + "0.237508 | \n", + "419.751066 | \n", + "0.252233 | \n", + "1.035971 | \n", + "NaN | \n", + "
std | \n", + "56276.495801 | \n", + "0.760515 | \n", + "1.373797 | \n", + "0.852520 | \n", + "0.480346 | \n", + "0.158128 | \n", + "288.365862 | \n", + "0.086406 | \n", + "0.384182 | \n", + "NaN | \n", + "
min | \n", + "1.000000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "0.002900 | \n", + "1.000000 | \n", + "0.038600 | \n", + "1.000000 | \n", + "NaN | \n", + "
25% | \n", + "48737.500000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "1.000000 | \n", + "0.117900 | \n", + "171.000000 | \n", + "0.188100 | \n", + "1.000000 | \n", + "NaN | \n", + "
50% | \n", + "97474.000000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "1.000000 | \n", + "0.201400 | \n", + "382.000000 | \n", + "0.240500 | \n", + "1.000000 | \n", + "NaN | \n", + "
75% | \n", + "146210.500000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "1.000000 | \n", + "0.319500 | \n", + "635.000000 | \n", + "0.294700 | \n", + "1.000000 | \n", + "NaN | \n", + "
max | \n", + "194947.000000 | \n", + "32.000000 | \n", + "413.000000 | \n", + "43.000000 | \n", + "86.000000 | \n", + "0.969300 | \n", + "1410.000000 | \n", + "0.773600 | \n", + "24.000000 | \n", + "NaN | \n", + "
\n", + " | col_name | \n", + "num_nonull | \n", + "num_null | \n", + "num_unique | \n", + "
---|---|---|---|---|
0 | \n", + "Row | \n", + "194947 | \n", + "0 | \n", + "194947 | \n", + "
1 | \n", + "Sample | \n", + "194947 | \n", + "0 | \n", + "1 | \n", + "
2 | \n", + "Anon Student Id | \n", + "194947 | \n", + "0 | \n", + "333 | \n", + "
3 | \n", + "Problem Hierarchy | \n", + "194947 | \n", + "0 | \n", + "27 | \n", + "
4 | \n", + "Problem Name | \n", + "194947 | \n", + "0 | \n", + "300 | \n", + "
5 | \n", + "Problem View | \n", + "194947 | \n", + "0 | \n", + "32 | \n", + "
6 | \n", + "Step Name | \n", + "194947 | \n", + "0 | \n", + "382 | \n", + "
7 | \n", + "Step Start Time | \n", + "194632 | \n", + "315 | \n", + "33098 | \n", + "
8 | \n", + "First Transaction Time | \n", + "194947 | \n", + "0 | \n", + "34578 | \n", + "
9 | \n", + "Correct Transaction Time | \n", + "182132 | \n", + "12815 | \n", + "33501 | \n", + "
10 | \n", + "Step End Time | \n", + "194947 | \n", + "0 | \n", + "34351 | \n", + "
11 | \n", + "Step Duration (sec) | \n", + "194947 | \n", + "0 | \n", + "2521 | \n", + "
12 | \n", + "Correct Step Duration (sec) | \n", + "194947 | \n", + "0 | \n", + "2187 | \n", + "
13 | \n", + "Error Step Duration (sec) | \n", + "194947 | \n", + "0 | \n", + "2105 | \n", + "
14 | \n", + "First Attempt | \n", + "194947 | \n", + "0 | \n", + "3 | \n", + "
15 | \n", + "Incorrects | \n", + "194947 | \n", + "0 | \n", + "32 | \n", + "
16 | \n", + "Hints | \n", + "194947 | \n", + "0 | \n", + "30 | \n", + "
17 | \n", + "Corrects | \n", + "194947 | \n", + "0 | \n", + "17 | \n", + "
18 | \n", + "Condition | \n", + "194947 | \n", + "0 | \n", + "1 | \n", + "
19 | \n", + "KC (F2011) | \n", + "113992 | \n", + "80955 | \n", + "98 | \n", + "
20 | \n", + "Opportunity (F2011) | \n", + "113992 | \n", + "80955 | \n", + "1206 | \n", + "
21 | \n", + "Predicted Error Rate (F2011) | \n", + "113992 | \n", + "80955 | \n", + "7623 | \n", + "
22 | \n", + "KC (Single-KC) | \n", + "194947 | \n", + "0 | \n", + "1 | \n", + "
23 | \n", + "Opportunity (Single-KC) | \n", + "194947 | \n", + "0 | \n", + "1410 | \n", + "
24 | \n", + "Predicted Error Rate (Single-KC) | \n", + "194947 | \n", + "0 | \n", + "317 | \n", + "
25 | \n", + "KC (Unique-step) | \n", + "193043 | \n", + "1904 | \n", + "1179 | \n", + "
26 | \n", + "Opportunity (Unique-step) | \n", + "193043 | \n", + "1904 | \n", + "25 | \n", + "
27 | \n", + "Predicted Error Rate (Unique-step) | \n", + "0 | \n", + "194947 | \n", + "1 | \n", + "
\n", + " | col_name | \n", + "num_nonull | \n", + "num_null | \n", + "num_unique | \n", + "
---|---|---|---|---|
0 | \n", + "Row | \n", + "113817 | \n", + "0 | \n", + "113817 | \n", + "
1 | \n", + "Anon Student Id | \n", + "113817 | \n", + "0 | \n", + "331 | \n", + "
2 | \n", + "Problem Hierarchy | \n", + "113817 | \n", + "0 | \n", + "26 | \n", + "
3 | \n", + "Problem Name | \n", + "113817 | \n", + "0 | \n", + "154 | \n", + "
4 | \n", + "Problem View | \n", + "113817 | \n", + "0 | \n", + "32 | \n", + "
5 | \n", + "Step Name | \n", + "113817 | \n", + "0 | \n", + "240 | \n", + "
6 | \n", + "Step Start Time | \n", + "113817 | \n", + "0 | \n", + "18856 | \n", + "
7 | \n", + "First Transaction Time | \n", + "113817 | \n", + "0 | \n", + "19745 | \n", + "
8 | \n", + "Correct Transaction Time | \n", + "103454 | \n", + "10363 | \n", + "19146 | \n", + "
9 | \n", + "Step End Time | \n", + "113817 | \n", + "0 | \n", + "19623 | \n", + "
10 | \n", + "Step Duration (sec) | \n", + "113817 | \n", + "0 | \n", + "2382 | \n", + "
11 | \n", + "Correct Step Duration (sec) | \n", + "113817 | \n", + "0 | \n", + "2093 | \n", + "
12 | \n", + "Error Step Duration (sec) | \n", + "113817 | \n", + "0 | \n", + "1949 | \n", + "
13 | \n", + "First Attempt | \n", + "113817 | \n", + "0 | \n", + "3 | \n", + "
14 | \n", + "Incorrects | \n", + "113817 | \n", + "0 | \n", + "25 | \n", + "
15 | \n", + "Hints | \n", + "113817 | \n", + "0 | \n", + "25 | \n", + "
16 | \n", + "Corrects | \n", + "113817 | \n", + "0 | \n", + "15 | \n", + "
17 | \n", + "KC (F2011) | \n", + "113817 | \n", + "0 | \n", + "97 | \n", + "
18 | \n", + "Opportunity (F2011) | \n", + "113817 | \n", + "0 | \n", + "1205 | \n", + "
19 | \n", + "Predicted Error Rate (F2011) | \n", + "113817 | \n", + "0 | \n", + "7622 | \n", + "
20 | \n", + "Opportunity (Single-KC) | \n", + "113817 | \n", + "0 | \n", + "1164 | \n", + "
21 | \n", + "Predicted Error Rate (Single-KC) | \n", + "113817 | \n", + "0 | \n", + "315 | \n", + "
22 | \n", + "KC (Unique-step) | \n", + "112869 | \n", + "948 | \n", + "625 | \n", + "
23 | \n", + "Opportunity (Unique-step) | \n", + "112869 | \n", + "948 | \n", + "25 | \n", + "
通过发现,duration中存在一种非数值类型为 '.' ,分析的应该代表0
\n", + "> - 此外,可通过箱型图考虑是否需要去除某些异常点" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['Row', 'Anon Student Id', 'Problem Hierarchy', 'Problem Name', 'Problem View', 'Step Name', 'Step Start Time', 'First Transaction Time', 'Correct Transaction Time', 'Step End Time', 'Step Duration (sec)', 'Correct Step Duration (sec)', 'Error Step Duration (sec)', 'First Attempt', 'Incorrects', 'Hints', 'Corrects', 'KC (F2011)', 'Opportunity (F2011)', 'Predicted Error Rate (F2011)', 'Opportunity (Single-KC)', 'Predicted Error Rate (Single-KC)', 'KC (Unique-step)', 'Opportunity (Unique-step)']\n", + "----------------------------------------------------------------------------------------------------\n", + "['Row', 'Problem View', 'Incorrects', 'Hints', 'Corrects', 'Predicted Error Rate (F2011)', 'Opportunity (Single-KC)', 'Predicted Error Rate (Single-KC)', 'Opportunity (Unique-step)']\n", + "----------------------------------------------------------------------------------------------------\n", + "Row int64\n", + "Anon Student Id object\n", + "Problem Hierarchy object\n", + "Problem Name object\n", + "Problem View int64\n", + "Step Name object\n", + "Step Start Time object\n", + "First Transaction Time object\n", + "Correct Transaction Time object\n", + "Step End Time object\n", + "Step Duration (sec) object\n", + "Correct Step Duration (sec) object\n", + "Error Step Duration (sec) object\n", + "First Attempt object\n", + "Incorrects int64\n", + "Hints int64\n", + "Corrects int64\n", + "KC (F2011) object\n", + "Opportunity (F2011) object\n", + "Predicted Error Rate (F2011) float64\n", + "Opportunity (Single-KC) int64\n", + "Predicted Error Rate (Single-KC) float64\n", + "KC (Unique-step) object\n", + "Opportunity (Unique-step) float64\n", + "dtype: object\n" + ] + } + ], + "source": [ + "print(df_step_clear.columns.tolist())\n", + "print(\"-\"*100)\n", + "print(df_step_clear.describe().columns.tolist()) #有许多object类无法统计分析\n", + "print(\"-\"*100)\n", + "print(df_step_clear.dtypes)" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Step Duration (sec) float64\n", + "Correct Step Duration (sec) float64\n", + "Error Step Duration (sec) float64\n", + "dtype: object\n" + ] + } + ], + "source": [ + "# 把duration中的.修改为0\n", + "rectify_cols = ['Step Duration (sec)', 'Correct Step Duration (sec)', 'Error Step Duration (sec)']\n", + "for col in rectify_cols:\n", + " df_step_clear[col] = df_step_clear[col].apply(lambda x: 0 if x=='.' else x)\n", + " df_step_clear[col] = df_step_clear[col].astype(float)\n", + "print(df_step_clear[rectify_cols].dtypes)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### (2)可视化数据" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "import plotly.express as px\n", + "from plotly.subplots import make_subplots\n", + "import plotly.graph_objs as go" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "\n", + " | Field | \n", + "Annotation | \n", + "
---|---|---|
0 | \n", + "Row | \n", + "A row counter | \n", + "
1 | \n", + "Sample Name | \n", + "The sample that contains the transaction. If a transaction appears in multiple samples, the transaction will be repeated, but with a different sample name. | \n", + "
2 | \n", + "Transaction Id | \n", + "A unique ID that identifies the transaction. Currently used for annotating transactions with custom fields via web services. | \n", + "
3 | \n", + "Anon Student Id | \n", + "DataShop-generated anonymous student ID. To obtain original student identifiers or to learn more about data anonymization, see About data anonymization below. | \n", + "
4 | \n", + "Session Id | \n", + "A dataset-unique string that identifies the user's session with the tutor. | \n", + "
5 | \n", + "Time | \n", + "Time the transaction occurred. For instance, if a student types \"25\" and presses return, the transaction time is at the point in which they press return. | \n", + "
6 | \n", + "Time Zone | \n", + "The local time zone (e.g., EST, PST, US/Eastern). | \n", + "
7 | \n", + "Duration (sec) | \n", + "Duration of the transaction in seconds. This is the time of the current transaction minus that of the preceding transaction or problem start event—whichever is closer in time to the current transaction. If this difference is greater than 10 minutes, or if the prior transaction occurred during a different user session, DataShop reports the duration as null (a dot). If the current transaction is preceded by neither another transaction or a problem start event, duration is shown as null. The duration is formatted without decimal places if the two times used in the calculation were without millisecond precision. | \n", + "
8 | \n", + "Student Response Type | \n", + "The type of attempt made by the student (e.g., \"ATTEMPT\" or \"HINT_REQUEST\"). This is logged in the semantic_event element. | \n", + "
9 | \n", + "Student Response Subtype | \n", + "A more detailed classification of the student attempt. For example, the CTAT software describes actions taken by the tutor on behalf of the student as having subtype \"tutor-performed\". | \n", + "
10 | \n", + "Tutor Response Type | \n", + "The type of response made by the tutor (e.g., \"RESULT\" or \"HINT_MSG\"). | \n", + "
11 | \n", + "Tutor Response Subtype | \n", + "A more detailed classification of the tutor response. | \n", + "
12 | \n", + "Level (level_type) | \n", + "The problem hierarchy name (e.g., \"Understanding Fractions\") of the type specified in the column header (e.g., \"Unit\"). There may be multiple \"Level\" columns if the problem hierarchy is more than one level deep. Level is logged in the level element. | \n", + "
13 | \n", + "Problem Name | \n", + "The name of the problem. Two problems with the same \"Problem Name\" are considered different \"problems\" by DataShop if the following logged values are not identical: problem name, context, tutor_flag (whether or not the problem or activity is tutored) and \"other\" field. These fields are logged in the problem element. | \n", + "
14 | \n", + "Problem View | \n", + "The number of times the student encountered the problem so far. This counter increases with each instance of the same problem. See \"Problem View\" in the \"By Student-Step\" table below. | \n", + "
15 | \n", + "Problem Start Time | \n", + "If the problem start time is not given in the original log data, then it is set to the time of the last transaction of the prior problem. If there is no prior problem for the session, the time of the earliest transaction is used. Earliest transaction time is equivalent to the minimum transaction time for the earliest step of the problem. For more detail on how problem start time is determined, see Determining Problem Start Time. | \n", + "
16 | \n", + "Step Name | \n", + "Formed by concatenating the \"selection\" and \"action\". Also see the glossary entry for \"step\". | \n", + "
17 | \n", + "Attempt at Step | \n", + "As of this transaction, the current number of attempts toward the identified step. | \n", + "
18 | \n", + "Outcome | \n", + "The tutor's evaluation of the student's attempt. For example, \"CORRECT\", \"INCORRECT\", or \"HINT\". This is logged in the action_evaluation element. | \n", + "
19 | \n", + "Selection | \n", + "A description of the interface element(s) that the student selected or interacted with (for example, \"LowestCommonDenominatorCell\"). This is logged in the event_descriptor element. | \n", + "
20 | \n", + "Action | \n", + "A description of the manipulation applied to the selection. | \n", + "
21 | \n", + "Input | \n", + "The input the student submitted (e.g., the text entered, the text of a menu item or a combobox entry). | \n", + "
22 | \n", + "Feedback Text | \n", + "The body of a hint, success, or incorrect action message shown to the student. It is generally a text value, logged in the tutor_advice element. | \n", + "
23 | \n", + "Feedback Classification | \n", + "The type of error (e.g., \"sign error\") or type of hint. | \n", + "
24 | \n", + "Help Level | \n", + "In the case of hierarchical hints, this is the depth of the hint. \"1\", for example, is an initial hint, while \"3\" is the third hint. | \n", + "
25 | \n", + "Total Num Hints | \n", + "The total number of hints available. This is logged in the action_evaluation element. | \n", + "
26 | \n", + "Condition Name | \n", + "The name of the condition (e.g., \"Unworked\"). | \n", + "
27 | \n", + "Condition Type | \n", + "A condition classification (e.g., \"Experimental\", \"Control\"); optional at the time of logging. | \n", + "
28 | \n", + "KC (model_name) | \n", + "The knowledge component for this transaction. It is a member of the knowledge component model named in the column header. One \"KC (model_name)\" column should appear in the export for each KC model in the dataset. | \n", + "
29 | \n", + "KC Category (model_name) | \n", + "The knowledge component \"category\" logged by some tutors. It is a member of the knowledge component model named in the column header. One \"KC Category (model_name)\" column should appear in the export for each KC model in the dataset. | \n", + "
30 | \n", + "School | \n", + "The name of the school where the student used the tutor to create this transaction. | \n", + "
31 | \n", + "Class | \n", + "The name of the class the student was in when he or she used the tutor to create this transaction. | \n", + "
32 | \n", + "CF (custom_field_name) | \n", + "The value of a custom field. This is usually information that did not fit into any of the other logging fields (i.e., any of the other columns), and so was logged in this special container. | \n", + "
33 | \n", + "Event Type | \n", + "Allowed values are \"assess\", \"instruct\" and \"assess_instruct\". Blank is also allowed. Only \"instruct\" and \"assess_instruct\" values are treated as learning opportunities. | \n", + "
\n", + " | Row | \n", + "Sample Name | \n", + "Transaction Id | \n", + "Anon Student Id | \n", + "Session Id | \n", + "Time | \n", + "Time Zone | \n", + "Duration (sec) | \n", + "Student Response Type | \n", + "Student Response Subtype | \n", + "Tutor Response Type | \n", + "Tutor Response Subtype | \n", + "Level (Sequence) | \n", + "Level (Unit) | \n", + "Level (Module) | \n", + "Level (Section1) | \n", + "Problem Name | \n", + "Problem View | \n", + "Problem Start Time | \n", + "Step Name | \n", + "Attempt At Step | \n", + "Is Last Attempt | \n", + "Outcome | \n", + "Selection | \n", + "Action | \n", + "Input | \n", + "Input.1 | \n", + "Feedback Text | \n", + "Feedback Classification | \n", + "Help Level | \n", + "Total Num Hints | \n", + "KC (Single-KC) | \n", + "KC Category (Single-KC) | \n", + "KC (Unique-step) | \n", + "KC Category (Unique-step) | \n", + "KC (F2011) | \n", + "KC Category (F2011) | \n", + "KC (F2011).1 | \n", + "KC Category (F2011).1 | \n", + "KC (F2011).2 | \n", + "KC Category (F2011).2 | \n", + "School | \n", + "Class | \n", + "CF (oli:activityGuid) | \n", + "CF (oli:highStakes) | \n", + "CF (oli:purpose) | \n", + "CF (oli:resourceType) | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "1 | \n", + "All Data | \n", + "2adbe4abefd649d48862d3f62b1abf5e | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:26:36 | \n", + "US/Eastern | \n", + "1 | \n", + "VIEW_PAGE | \n", + "UI Event | \n", + "NaN | \n", + "NaN | \n", + "Statics | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Navigation | \n", + "SelectPageNumber | \n", + "1 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
1 | \n", + "2 | \n", + "All Data | \n", + "4393251e32a6f00502f3f1ef894af8fe | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:35:28 | \n", + "US/Eastern | \n", + "23.13 | \n", + "ATTEMPT | \n", + "NaN | \n", + "RESULT | \n", + "NaN | \n", + "Statics | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "q1_point1i1 UpdateComboBox | \n", + "1.0 | \n", + "1.0 | \n", + "CORRECT | \n", + "q1_point1i1 | \n", + "UpdateComboBox | \n", + "<material>cord c</material> | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Single-KC | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "identify_interaction | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
2 | \n", + "3 | \n", + "All Data | \n", + "e2fb2cb788d10ebaa6f288e0757d1b09 | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:35:28 | \n", + "US/Eastern | \n", + "23.13 | \n", + "ATTEMPT | \n", + "NaN | \n", + "RESULT | \n", + "NaN | \n", + "Statics | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "q1_point3i3 UpdateComboBox | \n", + "1.0 | \n", + "1.0 | \n", + "CORRECT | \n", + "q1_point3i3 | \n", + "UpdateComboBox | \n", + "<material>120 lb</material> | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Single-KC | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "gravitational_forces | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
3 | \n", + "4 | \n", + "All Data | \n", + "e7e150d423862e346dc7e36a95e394e4 | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:35:28 | \n", + "US/Eastern | \n", + "23.13 | \n", + "ATTEMPT | \n", + "NaN | \n", + "RESULT | \n", + "NaN | \n", + "Statics | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "q1_point6i2 UpdateComboBox | \n", + "1.0 | \n", + "1.0 | \n", + "INCORRECT | \n", + "q1_point6i2 | \n", + "UpdateComboBox | \n", + "<material>no interaction</material> | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Single-KC | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "represent_interaction_spring | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
4 | \n", + "5 | \n", + "All Data | \n", + "684b1f770a225f21745c6c4c977ddc32 | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:35:28 | \n", + "US/Eastern | \n", + "23.13 | \n", + "ATTEMPT | \n", + "NaN | \n", + "RESULT | \n", + "NaN | \n", + "Statics | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "q1_point1i2 UpdateComboBox | \n", + "1.0 | \n", + "1.0 | \n", + "CORRECT | \n", + "q1_point1i2 | \n", + "UpdateComboBox | \n", + "<material>up</material> | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Single-KC | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "represent_interaction_cord | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
\n", + " | Row | \n", + "Tutor Response Subtype | \n", + "Problem View | \n", + "Attempt At Step | \n", + "Is Last Attempt | \n", + "Feedback Classification | \n", + "Help Level | \n", + "Total Num Hints | \n", + "KC Category (Single-KC) | \n", + "KC Category (Unique-step) | \n", + "KC Category (F2011) | \n", + "KC Category (F2011).1 | \n", + "KC Category (F2011).2 | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
count | \n", + "361092.000000 | \n", + "0.0 | \n", + "361092.000000 | \n", + "289858.000000 | \n", + "289858.000000 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "
mean | \n", + "180546.500000 | \n", + "NaN | \n", + "1.180192 | \n", + "2.382867 | \n", + "0.658678 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
std | \n", + "104238.426039 | \n", + "NaN | \n", + "0.907172 | \n", + "9.948941 | \n", + "0.474154 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
min | \n", + "1.000000 | \n", + "NaN | \n", + "1.000000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
25% | \n", + "90273.750000 | \n", + "NaN | \n", + "1.000000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
50% | \n", + "180546.500000 | \n", + "NaN | \n", + "1.000000 | \n", + "1.000000 | \n", + "1.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
75% | \n", + "270819.250000 | \n", + "NaN | \n", + "1.000000 | \n", + "2.000000 | \n", + "1.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
max | \n", + "361092.000000 | \n", + "NaN | \n", + "32.000000 | \n", + "427.000000 | \n", + "1.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
\n", + " | col_name | \n", + "num_nonull | \n", + "num_null | \n", + "num_unique | \n", + "
---|---|---|---|---|
0 | \n", + "Row | \n", + "361092 | \n", + "0 | \n", + "361092 | \n", + "
1 | \n", + "Sample Name | \n", + "361092 | \n", + "0 | \n", + "1 | \n", + "
2 | \n", + "Transaction Id | \n", + "361092 | \n", + "0 | \n", + "361092 | \n", + "
3 | \n", + "Anon Student Id | \n", + "361092 | \n", + "0 | \n", + "335 | \n", + "
4 | \n", + "Session Id | \n", + "361092 | \n", + "0 | \n", + "6656 | \n", + "
5 | \n", + "Time | \n", + "361092 | \n", + "0 | \n", + "263172 | \n", + "
6 | \n", + "Time Zone | \n", + "361092 | \n", + "0 | \n", + "1 | \n", + "
7 | \n", + "Duration (sec) | \n", + "361092 | \n", + "0 | \n", + "2565 | \n", + "
8 | \n", + "Student Response Type | \n", + "361092 | \n", + "0 | \n", + "5 | \n", + "
9 | \n", + "Student Response Subtype | \n", + "71234 | \n", + "289858 | \n", + "2 | \n", + "
10 | \n", + "Tutor Response Type | \n", + "289858 | \n", + "71234 | \n", + "3 | \n", + "
11 | \n", + "Tutor Response Subtype | \n", + "0 | \n", + "361092 | \n", + "1 | \n", + "
12 | \n", + "Level (Sequence) | \n", + "361092 | \n", + "0 | \n", + "1 | \n", + "
13 | \n", + "Level (Unit) | \n", + "361092 | \n", + "0 | \n", + "7 | \n", + "
14 | \n", + "Level (Module) | \n", + "361092 | \n", + "0 | \n", + "19 | \n", + "
15 | \n", + "Level (Section1) | \n", + "59480 | \n", + "301612 | \n", + "10 | \n", + "
16 | \n", + "Problem Name | \n", + "361092 | \n", + "0 | \n", + "300 | \n", + "
17 | \n", + "Problem View | \n", + "361092 | \n", + "0 | \n", + "32 | \n", + "
18 | \n", + "Problem Start Time | \n", + "361092 | \n", + "0 | \n", + "46473 | \n", + "
19 | \n", + "Step Name | \n", + "289858 | \n", + "71234 | \n", + "383 | \n", + "
20 | \n", + "Attempt At Step | \n", + "289858 | \n", + "71234 | \n", + "428 | \n", + "
21 | \n", + "Is Last Attempt | \n", + "289858 | \n", + "71234 | \n", + "3 | \n", + "
22 | \n", + "Outcome | \n", + "289858 | \n", + "71234 | \n", + "4 | \n", + "
23 | \n", + "Selection | \n", + "361082 | \n", + "10 | \n", + "287 | \n", + "
24 | \n", + "Action | \n", + "361082 | \n", + "10 | \n", + "10 | \n", + "
25 | \n", + "Input | \n", + "302086 | \n", + "59006 | \n", + "6827 | \n", + "
26 | \n", + "Input.1 | \n", + "1 | \n", + "361091 | \n", + "2 | \n", + "
27 | \n", + "Feedback Text | \n", + "231063 | \n", + "130029 | \n", + "1579 | \n", + "
28 | \n", + "Feedback Classification | \n", + "0 | \n", + "361092 | \n", + "1 | \n", + "
29 | \n", + "Help Level | \n", + "0 | \n", + "361092 | \n", + "1 | \n", + "
30 | \n", + "Total Num Hints | \n", + "0 | \n", + "361092 | \n", + "1 | \n", + "
31 | \n", + "KC (Single-KC) | \n", + "289858 | \n", + "71234 | \n", + "2 | \n", + "
32 | \n", + "KC Category (Single-KC) | \n", + "0 | \n", + "361092 | \n", + "1 | \n", + "
33 | \n", + "KC (Unique-step) | \n", + "283336 | \n", + "77756 | \n", + "1179 | \n", + "
34 | \n", + "KC Category (Unique-step) | \n", + "0 | \n", + "361092 | \n", + "1 | \n", + "
35 | \n", + "KC (F2011) | \n", + "152592 | \n", + "208500 | \n", + "81 | \n", + "
36 | \n", + "KC Category (F2011) | \n", + "0 | \n", + "361092 | \n", + "1 | \n", + "
37 | \n", + "KC (F2011).1 | \n", + "16904 | \n", + "344188 | \n", + "19 | \n", + "
38 | \n", + "KC Category (F2011).1 | \n", + "0 | \n", + "361092 | \n", + "1 | \n", + "
39 | \n", + "KC (F2011).2 | \n", + "6690 | \n", + "354402 | \n", + "9 | \n", + "
40 | \n", + "KC Category (F2011).2 | \n", + "0 | \n", + "361092 | \n", + "1 | \n", + "
41 | \n", + "School | \n", + "361092 | \n", + "0 | \n", + "7 | \n", + "
42 | \n", + "Class | \n", + "361092 | \n", + "0 | \n", + "9 | \n", + "
43 | \n", + "CF (oli:activityGuid) | \n", + "45002 | \n", + "316090 | \n", + "1244 | \n", + "
44 | \n", + "CF (oli:highStakes) | \n", + "45002 | \n", + "316090 | \n", + "3 | \n", + "
45 | \n", + "CF (oli:purpose) | \n", + "44516 | \n", + "316576 | \n", + "4 | \n", + "
46 | \n", + "CF (oli:resourceType) | \n", + "45002 | \n", + "316090 | \n", + "3 | \n", + "
\n", + " | Row | \n", + "Transaction Id | \n", + "Anon Student Id | \n", + "Session Id | \n", + "Time | \n", + "Duration (sec) | \n", + "Student Response Type | \n", + "Student Response Subtype | \n", + "Tutor Response Type | \n", + "Level (Unit) | \n", + "Level (Module) | \n", + "Level (Section1) | \n", + "Problem Name | \n", + "Problem View | \n", + "Problem Start Time | \n", + "Step Name | \n", + "Attempt At Step | \n", + "Is Last Attempt | \n", + "Outcome | \n", + "Selection | \n", + "Action | \n", + "Input | \n", + "Input.1 | \n", + "Feedback Text | \n", + "KC (Single-KC) | \n", + "KC (Unique-step) | \n", + "KC (F2011) | \n", + "KC (F2011).1 | \n", + "KC (F2011).2 | \n", + "School | \n", + "Class | \n", + "CF (oli:activityGuid) | \n", + "CF (oli:highStakes) | \n", + "CF (oli:purpose) | \n", + "CF (oli:resourceType) | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "1 | \n", + "2adbe4abefd649d48862d3f62b1abf5e | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:26:36 | \n", + "1 | \n", + "VIEW_PAGE | \n", + "UI Event | \n", + "NaN | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Navigation | \n", + "SelectPageNumber | \n", + "1 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
1 | \n", + "2 | \n", + "4393251e32a6f00502f3f1ef894af8fe | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:35:28 | \n", + "23.13 | \n", + "ATTEMPT | \n", + "NaN | \n", + "RESULT | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "q1_point1i1 UpdateComboBox | \n", + "1.0 | \n", + "1.0 | \n", + "CORRECT | \n", + "q1_point1i1 | \n", + "UpdateComboBox | \n", + "<material>cord c</material> | \n", + "NaN | \n", + "NaN | \n", + "Single-KC | \n", + "NaN | \n", + "identify_interaction | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
2 | \n", + "3 | \n", + "e2fb2cb788d10ebaa6f288e0757d1b09 | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:35:28 | \n", + "23.13 | \n", + "ATTEMPT | \n", + "NaN | \n", + "RESULT | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "q1_point3i3 UpdateComboBox | \n", + "1.0 | \n", + "1.0 | \n", + "CORRECT | \n", + "q1_point3i3 | \n", + "UpdateComboBox | \n", + "<material>120 lb</material> | \n", + "NaN | \n", + "NaN | \n", + "Single-KC | \n", + "NaN | \n", + "gravitational_forces | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
3 | \n", + "4 | \n", + "e7e150d423862e346dc7e36a95e394e4 | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:35:28 | \n", + "23.13 | \n", + "ATTEMPT | \n", + "NaN | \n", + "RESULT | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "q1_point6i2 UpdateComboBox | \n", + "1.0 | \n", + "1.0 | \n", + "INCORRECT | \n", + "q1_point6i2 | \n", + "UpdateComboBox | \n", + "<material>no interaction</material> | \n", + "NaN | \n", + "NaN | \n", + "Single-KC | \n", + "NaN | \n", + "represent_interaction_spring | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
4 | \n", + "5 | \n", + "684b1f770a225f21745c6c4c977ddc32 | \n", + "Stu_00b2b35fd027e7891e8a1a527125dd65 | \n", + "8dd109e680020ca6016f8e64290b5610 | \n", + "2011-09-21 17:35:28 | \n", + "23.13 | \n", + "ATTEMPT | \n", + "NaN | \n", + "RESULT | \n", + "Concentrated Forces and Their Effects | \n", + "Introduction to Free Body Diagrams | \n", + "NaN | \n", + "_m2_assess | \n", + "1 | \n", + "2011-09-21 17:26:35 | \n", + "q1_point1i2 UpdateComboBox | \n", + "1.0 | \n", + "1.0 | \n", + "CORRECT | \n", + "q1_point1i2 | \n", + "UpdateComboBox | \n", + "<material>up</material> | \n", + "NaN | \n", + "NaN | \n", + "Single-KC | \n", + "NaN | \n", + "represent_interaction_cord | \n", + "NaN | \n", + "NaN | \n", + "Marion Technical College | \n", + "MET2010B-01 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
\n", + " | col_name | \n", + "num_nonull | \n", + "num_null | \n", + "num_unique | \n", + "
---|---|---|---|---|
0 | \n", + "Row | \n", + "361092 | \n", + "0 | \n", + "361092 | \n", + "
1 | \n", + "Transaction Id | \n", + "361092 | \n", + "0 | \n", + "361092 | \n", + "
2 | \n", + "Anon Student Id | \n", + "361092 | \n", + "0 | \n", + "335 | \n", + "
3 | \n", + "Session Id | \n", + "361092 | \n", + "0 | \n", + "6656 | \n", + "
4 | \n", + "Time | \n", + "361092 | \n", + "0 | \n", + "263172 | \n", + "
5 | \n", + "Duration (sec) | \n", + "361092 | \n", + "0 | \n", + "2565 | \n", + "
6 | \n", + "Student Response Type | \n", + "361092 | \n", + "0 | \n", + "5 | \n", + "
7 | \n", + "Student Response Subtype | \n", + "71234 | \n", + "289858 | \n", + "2 | \n", + "
8 | \n", + "Tutor Response Type | \n", + "289858 | \n", + "71234 | \n", + "3 | \n", + "
9 | \n", + "Level (Unit) | \n", + "361092 | \n", + "0 | \n", + "7 | \n", + "
10 | \n", + "Level (Module) | \n", + "361092 | \n", + "0 | \n", + "19 | \n", + "
11 | \n", + "Level (Section1) | \n", + "59480 | \n", + "301612 | \n", + "10 | \n", + "
12 | \n", + "Problem Name | \n", + "361092 | \n", + "0 | \n", + "300 | \n", + "
13 | \n", + "Problem View | \n", + "361092 | \n", + "0 | \n", + "32 | \n", + "
14 | \n", + "Problem Start Time | \n", + "361092 | \n", + "0 | \n", + "46473 | \n", + "
15 | \n", + "Step Name | \n", + "289858 | \n", + "71234 | \n", + "383 | \n", + "
16 | \n", + "Attempt At Step | \n", + "289858 | \n", + "71234 | \n", + "428 | \n", + "
17 | \n", + "Is Last Attempt | \n", + "289858 | \n", + "71234 | \n", + "3 | \n", + "
18 | \n", + "Outcome | \n", + "289858 | \n", + "71234 | \n", + "4 | \n", + "
19 | \n", + "Selection | \n", + "361082 | \n", + "10 | \n", + "287 | \n", + "
20 | \n", + "Action | \n", + "361082 | \n", + "10 | \n", + "10 | \n", + "
21 | \n", + "Input | \n", + "302086 | \n", + "59006 | \n", + "6827 | \n", + "
22 | \n", + "Input.1 | \n", + "1 | \n", + "361091 | \n", + "2 | \n", + "
23 | \n", + "Feedback Text | \n", + "231063 | \n", + "130029 | \n", + "1579 | \n", + "
24 | \n", + "KC (Single-KC) | \n", + "289858 | \n", + "71234 | \n", + "2 | \n", + "
25 | \n", + "KC (Unique-step) | \n", + "283336 | \n", + "77756 | \n", + "1179 | \n", + "
26 | \n", + "KC (F2011) | \n", + "152592 | \n", + "208500 | \n", + "81 | \n", + "
27 | \n", + "KC (F2011).1 | \n", + "16904 | \n", + "344188 | \n", + "19 | \n", + "
28 | \n", + "KC (F2011).2 | \n", + "6690 | \n", + "354402 | \n", + "9 | \n", + "
29 | \n", + "School | \n", + "361092 | \n", + "0 | \n", + "7 | \n", + "
30 | \n", + "Class | \n", + "361092 | \n", + "0 | \n", + "9 | \n", + "
31 | \n", + "CF (oli:activityGuid) | \n", + "45002 | \n", + "316090 | \n", + "1244 | \n", + "
32 | \n", + "CF (oli:highStakes) | \n", + "45002 | \n", + "316090 | \n", + "3 | \n", + "
33 | \n", + "CF (oli:purpose) | \n", + "44516 | \n", + "316576 | \n", + "4 | \n", + "
34 | \n", + "CF (oli:resourceType) | \n", + "45002 | \n", + "316090 | \n", + "3 | \n", + "
通过发现,duration中存在一种非数值类型为 '.' ,分析的应该代表0
\n", - "> - 此外,可通过箱型图考虑是否需要去除某些异常点" + "### Outlier Analysis\n", + "> -It is found that there is a non-numeric type in duration that is '.' , which should represent 0
\n", + "> - In addition, box diagrams can be used to analyze whether some outliers need to be removed" ] }, { @@ -1380,7 +1365,7 @@ } ], "source": [ - "# 把duration中的.修改为0\n", + "# Change . to 0 in \"xxx-duration\"\n", "rectify_cols = ['Step Duration (sec)', 'Correct Step Duration (sec)', 'Error Step Duration (sec)']\n", "for col in rectify_cols:\n", " df_step_clear[col] = df_step_clear[col].apply(lambda x: 0 if x=='.' else x)\n", @@ -1392,85 +1377,58 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "### (2)可视化数据" + "# 3. Data Visualization" ] }, { "cell_type": "code", - "execution_count": 13, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import plotly.express as px\n", "from plotly.subplots import make_subplots\n", - "import plotly.graph_objs as go" + "import plotly.graph_objs as go\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline" ] }, { "cell_type": "code", - "execution_count": 14, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "