[pd.Grouper(key='user'),
pd.Grouper(key='task')]).count()['correct']
cummulativeResult = practiceResultSum.reset_index().groupby(
[pd.Grouper(key='user')]).sum()
# cummulativeResult = practiceResultSum.groupby([pd.Grouper(key='user')]).sum()
cummulativeResult['cumm_practice'] = cummulativeResult[
'correct'] / practiceResult.groupby([pd.Grouper(key='user')
]).count()['date']
cummulativeResult['successPassedRate'] = cummulativeResult['passed'] / (
cummulativeResult['passed'] + cummulativeResult['failed'])
# cummulativeResult = graphLearning.mapNewLabel(cummulativeResult, reLabelIndex)
cummulativeExerciseWeeks.append(cummulativeResult)
assessment_label = assessment.copy()
assessment_label = graphLearning.mapNewLabel(assessment, reLabelIndex)
assessment_label1A = assessment1A.copy()
assessment_label1A = graphLearning.mapNewLabel(assessment1A, reLabelIndex)
assessment_label2A = assessment2A.copy()
assessment_label2A = graphLearning.mapNewLabel(assessment2A, reLabelIndex)
#activity data matrix construction with newPAgeTYpe
workingWeekLog = []
activityDataMatrixWeeks_pageType = []
for w in range(0, 12):
print('Week ' + str(w) + '...')
workingWeekLog.append(weeksEventLog_filtered_pageType[w])
LogPageactivityCountByUser = pd.concat(
workingWeekLog) #weeksEventLog_filtered[w]
LogPageactivityCountByUser = FCAMiner.activityDataMatrixContruct(
[pd.Grouper(key='user'),
pd.Grouper(key='task')]).count()['correct']
cummulativeResult = practiceResultSum.reset_index().groupby(
[pd.Grouper(key='user')]).sum()
# cummulativeResult = practiceResultSum.groupby([pd.Grouper(key='user')]).sum()
cummulativeResult['cumm_practice'] = cummulativeResult[
'correct'] / practiceResult.groupby([pd.Grouper(key='user')
]).count()['date']
cummulativeResult['successPassedRate'] = cummulativeResult['passed'] / (
cummulativeResult['passed'] + cummulativeResult['failed'])
# cummulativeResult = graphLearning.mapNewLabel(cummulativeResult, reLabelIndex)
cummulativeExerciseWeeks.append(cummulativeResult)
assessment_label = assessment.copy()
assessment_label = graphLearning.mapNewLabel(assessment, reLabelIndex)
assessment_label1A = assessment1A.copy()
assessment_label1A = graphLearning.mapNewLabel(assessment1A, reLabelIndex)
assessment_label2A = assessment2A.copy()
assessment_label2A = graphLearning.mapNewLabel(assessment2A, reLabelIndex)
#activity data matrix construction with newPAgeTYpe
workingWeekLog = []
activityDataMatrixWeeks_pageType = []
for w in range(0, 12):
print('Week ' + str(w) + '...')
workingWeekLog.append(weeksEventLog_filtered_pageType[w])
LogPageactivityCountByUser = pd.concat(
workingWeekLog) #weeksEventLog_filtered[w]
LogPageactivityCountByUser = FCAMiner.activityDataMatrixContruct(
elif w in [4,5,6,7]:
studentList = assessment2A.index.astype(str)
else:
studentList = assessment3A.index.astype(str)
temp = temp.loc[temp.index.isin(studentList)]
# temp = graphLearning.mapNewLabel(temp, reLabelIndex)
# temp = temp.drop(['Practice_0-Practice_0'],axis=1)
# if w == 1:
# temp = temp.drop([8])
transitionDataMatrixWeeks.append(temp)
for w in range(0,10):
transitionDataMatrixWeeks[w].index = transitionDataMatrixWeeks[w].index + ['-2020']
for w in range(0,10):
transitionDataMatrixWeeks[w] = graphLearning.mapNewLabel(transitionDataMatrixWeeks[w], reLabelIndex)
transitionDataMatrixWeeks_directFollow_standardised = []
for w in range(0,10):
transitionDataMatrixWeeks_directFollow_standardised.append(dataProcessing.normaliseData(transitionDataMatrixWeeks[w].T))
transitionDataMatrixWeeks_directFollow_normalised = []
for w in range(0,10):
transitionDataMatrixWeeks_directFollow_normalised.append(dataProcessing.normaliseData(transitionDataMatrixWeeks[w].T, 'normalised'))
# correlation processing
corrList = []
corrDistanceList = []
for w in range(0,10):
corrTemp = transitionDataMatrixWeeks_directFollow_standardised[w].corr()
corrList.append(corrTemp)
# ca1162018_transitionDataMatrixWeeks[w]['covid'] = 0
# ca1162019_transitionDataMatrixWeeks[w]['covid'] = 0
# ca1162020_transitionDataMatrixWeeks[w]['covid'] = 1
transitionDataMatrixWeeks.append(
pd.concat([
ca1162018_transitionDataMatrixWeeks[w],
ca1162019_transitionDataMatrixWeeks[w],
ca1162020_transitionDataMatrixWeeks[w]
],
join='inner'))
listIndex = listIndex + list(transitionDataMatrixWeeks[w].index)
listIndex = list(set(listIndex))
reLabelIndex = dataProcessing.reLabelStudentId(listIndex)
for w in range(0, 10):
ca1162018_transitionDataMatrixWeeks[w] = graphLearning.mapNewLabel(
ca1162018_transitionDataMatrixWeeks[w], reLabelIndex)
ca1162019_transitionDataMatrixWeeks[w] = graphLearning.mapNewLabel(
ca1162019_transitionDataMatrixWeeks[w], reLabelIndex)
ca1162020_transitionDataMatrixWeeks[w] = graphLearning.mapNewLabel(
ca1162020_transitionDataMatrixWeeks[w], reLabelIndex)
transitionDataMatrixWeeks[w] = graphLearning.mapNewLabel(
transitionDataMatrixWeeks[w], reLabelIndex)
transitionDataMatrixWeeks_directFollow_standardised = []
for w in range(0, 10):
transitionDataMatrixWeeks_directFollow_standardised.append(
dataProcessing.normaliseData(transitionDataMatrixWeeks[w].T))
ca1162018_activityDataMatrixWeeks_pageTypeWeek = []
ca1162019_activityDataMatrixWeeks_pageTypeWeek = []
ca1162020_activityDataMatrixWeeks_pageTypeWeek = []
workingWeekExcercise = []
cummulativeExerciseWeeks = []
for week in range(0,12):
workingWeekExcercise.append(nonExUploadByWeek[week])
practiceResult = pd.concat(workingWeekExcercise) #nonExUploadByWeek[week]
#adjust number of correct: For each task, number of correct submission/number of submission for that task
practiceResultSum = practiceResult.groupby([pd.Grouper(key='user'),pd.Grouper(key='task')]).sum()
practiceResultSum['correct_adjusted'] = practiceResultSum['correct']/practiceResult.groupby([pd.Grouper(key='user'),pd.Grouper(key='task')]).count()['correct']
cummulativeResult = practiceResultSum.reset_index().groupby([pd.Grouper(key='user')]).sum()
# cummulativeResult = practiceResultSum.groupby([pd.Grouper(key='user')]).sum()
cummulativeResult['cumm_practice'] = cummulativeResult['correct']/practiceResult.groupby([pd.Grouper(key='user')]).count()['date']
cummulativeResult['successPassedRate'] = cummulativeResult['passed']/(cummulativeResult['passed'] + cummulativeResult['failed'])
cummulativeResult = graphLearning.mapNewLabel(cummulativeResult, reLabelIndex)
cummulativeExerciseWeeks.append(cummulativeResult)
a = cummulativeExerciseWeeks[11].corr()
transitionDataMatrixWeeks = []
for w in range(0,12):
temp = pd.read_csv('transitionMatrixStorage_new/transitionDataMatrixWeeks_distance_accumulated_w' + str(w) + '.csv', index_col=0)
if w in [0,1,2,3]:
studentList = assessment1A.index
elif w in [4,5,6,7]:
studentList = assessment2A.index
else:
studentList = assessment3A.index
temp = temp.loc[temp.index.isin(studentList)]
[pd.Grouper(key='user'),
pd.Grouper(key='task')]).count()['correct']
cummulativeResult = practiceResultSum.reset_index().groupby(
[pd.Grouper(key='user')]).sum()
# cummulativeResult = practiceResultSum.groupby([pd.Grouper(key='user')]).sum()
cummulativeResult['cumm_practice'] = cummulativeResult[
'correct'] / practiceResult.groupby([pd.Grouper(key='user')
]).count()['date']
cummulativeResult['successPassedRate'] = cummulativeResult['passed'] / (
cummulativeResult['passed'] + cummulativeResult['failed'])
# cummulativeResult = graphLearning.mapNewLabel(cummulativeResult, reLabelIndex)
cummulativeExerciseWeeks.append(cummulativeResult)
for w in range(0, 12):
cummulativeExerciseWeeks[w] = graphLearning.mapNewLabel(
cummulativeExerciseWeeks[w], reLabelIndex)
assessment_label = assessment.copy()
assessment_label = graphLearning.mapNewLabel(assessment, reLabelIndex)
assessment_label1A = assessment1A.copy()
assessment_label1A = graphLearning.mapNewLabel(assessment1A, reLabelIndex)
assessment_label2A = assessment2A.copy()
assessment_label2A = graphLearning.mapNewLabel(assessment2A, reLabelIndex)
assessment_label3A = assessment3A.copy()
assessment_label3A = graphLearning.mapNewLabel(assessment3A, reLabelIndex)
#read csv iff neeeded
transitionDataMatrixWeeks = []
for w in range(0, 12):
temp = pd.read_csv(