names=['user', 'mark'],
index_col=0)
ex2_excellent1 = examResults2.loc[examResults2['mark'] >= 40]
ex2_weak1 = examResults2.loc[examResults2['mark'] < 40]
examResults3 = pd.read_csv(
'2020-06-29-einstein/marks/2020-ca116-continuous-assessment/2020-ca116-ex3-final.txt',
delimiter=' ',
header=None,
names=['user', 'mark'],
index_col=0)
ex3_excellent1 = examResults3.loc[examResults3['mark'] >= 40]
ex3_weak1 = examResults3.loc[examResults3['mark'] < 40]
#filtered log by activity Type
lectureList = dataProcessing.getLectureList(ca116_eventLog_2019, ['html|py'])
eventLog_ca116_filtered = ca116_eventLog_2019.loc[
ca116_eventLog_2019['description'].str.contains('|'.join(lectureList))]
# ex1_personal_log_1 = dataProcessing.addConceptPageToLog(ex1_personal_log_1)
# eventLog_ca116_filtered = eventLog_ca116_filtered.drop(eventLog_ca116_filtered.loc[eventLog_ca116_filtered['description'].str.contains('http|report|ex|dashboard|graphs.html')].index)
eventLog_ca116_filtered = eventLog_ca116_filtered.drop(
eventLog_ca116_filtered.loc[eventLog_ca116_filtered['concept:name'].isin(
['click-0', 'click-1', 'click-2'])].index)
eventLog_ca116_filtered.loc[
eventLog_ca116_filtered['description'].str.contains('.html|.web'),
'pageType'] = 'Read_Lecture_Note'
eventLog_ca116_filtered.loc[
eventLog_ca116_filtered['description'].str.contains('correct|incorrect'),
'pageType'] = 'Exercise'
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
warnings.filterwarnings("ignore")
# sns.set()
# sns.set_style("whitegrid", {"axes.facecolor": ".9"})
import os
os.environ["PATH"] += os.pathsep + 'C:/Program Files (x86)/Graphviz2.38/bin/'
eventLog_ca116 = pd.read_csv('ca116_eventLog_nonfixed.csv')
eventLog_ca116 = eventLog_ca116.drop([1160345])
eventLog_ca116['time:timestamp'] = pd.to_datetime(
eventLog_ca116['time:timestamp'])
eventLog_ca116 = eventLog_ca116.loc[:, ~eventLog_ca116.columns.str.
contains('^Unnamed')]
lectureList = dataProcessing.getLectureList(eventLog_ca116, ['html|py'])
eventLog_ca116_filtered = eventLog_ca116.loc[
eventLog_ca116['description'].str.contains('|'.join(lectureList))]
# ex1_personal_log_1 = dataProcessing.addConceptPageToLog(ex1_personal_log_1)
# eventLog_ca116_filtered = eventLog_ca116_filtered.drop(eventLog_ca116_filtered.loc[eventLog_ca116_filtered['description'].str.contains('http|report|ex|dashboard|graphs.html')].index)
eventLog_ca116_filtered = eventLog_ca116_filtered.drop(
eventLog_ca116_filtered.loc[eventLog_ca116_filtered['concept:name'].isin(
['click-0', 'click-1', 'click-2'])].index)
eventLog_ca116_filtered.loc[
eventLog_ca116_filtered['description'].str.contains('.html|.web'),
'pageType'] = 'Read_Lecture_Note'
eventLog_ca116_filtered.loc[
eventLog_ca116_filtered['description'].str.contains('correct|incorrect'),
'pageType'] = 'Exercise'
eventLog_ca116_filtered.loc[eventLog_ca116_filtered['description'].str.
def predictionRandomForestProbability(dfActivityMatrixWithResult,
excellentList,
weakList,
practice,
lectureList=[],
pvalue=0.05):
if len(lectureList) == 0:
lectureList = dataProcessing.getLectureList(dfActivityMatrixWithResult)
logPage = dfActivityMatrixWithResult.loc[
dfActivityMatrixWithResult['description'].str.contains(
'|'.join(lectureList))]
# ex1_LogPageIf = dataProcessing.addCompleteTimeToEventLog(ex1_LogPageIf)
# LogPageActivityCountByUser = logPage.groupby([pd.Grouper(key='org:resource'),pd.Grouper(key='concept:name')]).count()
LogPageactivityCountByUser = FCAMiner.activityDataMatrixContruct(logPage)
LogPageactivityCountByUser = LogPageactivityCountByUser.fillna(0)
excellent_LogPageActivityCountByUser = LogPageactivityCountByUser.loc[
LogPageactivityCountByUser.index.isin(excellentList)]
weak_LogPageActivityCountByUser = LogPageactivityCountByUser.loc[
LogPageactivityCountByUser.index.isin(weakList)]
excellent_LogPageActivityCountByUser['result_exam_1'] = 1
weak_LogPageActivityCountByUser['result_exam_1'] = 0
LogPageactivityCountByUser = pd.concat([
excellent_LogPageActivityCountByUser, weak_LogPageActivityCountByUser
])
# cum_practice_col = ['correct_adjusted','successPassedRate'] #,'cumm_practice','successPassedRate'
# LogPageactivityCountByUser = LogPageactivityCountByUser.merge(practice.loc[:,cum_practice_col],
# left_on=LogPageactivityCountByUser.index, right_on=practice.index)
# LogPageactivityCountByUser = LogPageactivityCountByUser.set_index('key_0')
colSelection = [
] #['correct_adjusted','successPassedRate'] #select only col whose p-value <=0.05 with result exam
for col in LogPageactivityCountByUser.columns:
if col not in ['result_exam_1', 'click-3']:
# corr = pearsonr(LogPageactivityCountByUser['result_exam_1'], LogPageactivityCountByUser[col])
# if corr[1] <= pvalue:
# colSelection.append(col)
colSelection.append(col)
if len(colSelection) == 0:
return 'No columns correlated with result_exam_1'
X = LogPageactivityCountByUser[colSelection]
y = LogPageactivityCountByUser['result_exam_1']
# Split dataset into training set and test set
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.20, random_state=1) # 70% training and 30% test
#Create a Gaussian Classifier
clf = RandomForestClassifier(n_estimators=1000)
#Train the model using the training sets y_pred=clf.predict(X_test)
clf.fit(X_train, y_train)
y_pred_proba = clf.predict_proba(X_test)
y_pred = make_decision(y_pred_proba, 0.5)
accuracy_score = metrics.accuracy_score(y_test, y_pred),
f1_score = metrics.f1_score(y_test, y_pred),
precision_score = metrics.precision_score(y_test, y_pred),
recall_score = metrics.recall_score(y_test, y_pred)
roc_auc = metrics.roc_auc_score(y_test, y_pred)
metricsResult = {
'accuracy_score': accuracy_score,
'f1_score': f1_score,
'precision_score': precision_score,
'recall_score': recall_score,
'roc_auc': roc_auc
}
feature_imp = pd.Series(clf.feature_importances_,
index=X.columns).sort_values(ascending=False)
testingData = pd.DataFrame(
columns=['y_test', 'y_pred', 'y_pred_proba_0', 'y_pred_proba_1'])
testingData['y_test'] = y_test
testingData['y_pred'] = y_pred
testingData['y_pred_proba_0'] = y_pred_proba[:, 0]
testingData['y_pred_proba_1'] = y_pred_proba[:, 1]
return [
metricsResult, feature_imp, clf, LogPageactivityCountByUser,
testingData
]
