Then run this script on the above collection
Usage:
python activities_with_lower_completion.py
'''
from collections import defaultdict
from common.base_edx import EdXConnection
from common.generate_csv_report import CSV
# Connect to MongoDB and extra the tracking collection
connection = EdXConnection('user_attempts_per_problem_id')
collection = connection.get_access_to_collection()
cursor = collection['user_attempts_per_problem_id'].find()
result = defaultdict(lambda: defaultdict(int))
for index,document in enumerate(cursor):
# If there is a correct attempts, accept as answered correctly, else accept
#as incorrect only once per student per problem id
if 'correct' in document['attempts']:
result[document['_id']['problem_id']]['correct'] += 1
else:
result[document['_id']['problem_id']]['incorrect'] += 1
csv_result = [[item, result[item]['correct'], result[item]['incorrect']] for item in result]
output = CSV(csv_result, ['Problem Id', 'Correct Count', 'Incorrect Count'], output_file='activities_with_lower_completion.csv')
output.generate_csv()
print(start_event_time)
#when a start event is found set the end event to blank
end_event_time = {'blank'}
continue
#assign all other event types to end
#Note: currently seek_video events count as an end_event
else:
end_event_time = datetime.strptime(item['time'].split('+')[0],
"%Y-%m-%dT%H:%M:%S.%f")
print 'end'
print(end_event_time)
continue
except:
count_errors = count_errors + 1
errors.append([index, item])
#print watch_durations
print
print len(watch_durations)
print errors
output = CSV(watch_durations, [
'Username', 'video_id', 'youtube id (video_code)', 'time_point (seconds)',
'start_event_time', 'end_event_time', 'duration (minutes)'
],
output_file=db_name + 'video_watch_duration.csv',
row_limit=200000)
output.generate_csv()
output_errors = CSV(errors, ['Errors'],
output_file=db_name + 'video_watch_duration_errors.csv',
row_limit=200000)
output_errors.generate_csv()
Usage:
python activities_with_lower_completion.py
'''
from collections import defaultdict
from common.base_edx import EdXConnection
from common.generate_csv_report import CSV
# Connect to MongoDB and extra the tracking collection
connection = EdXConnection('user_attempts_per_problem_id')
collection = connection.get_access_to_collection()
cursor = collection['user_attempts_per_problem_id'].find()
result = defaultdict(lambda: defaultdict(int))
for index, document in enumerate(cursor):
# If there is a correct attempts, accept as answered correctly, else accept
#as incorrect only once per student per problem id
if 'correct' in document['attempts']:
result[document['_id']['problem_id']]['correct'] += 1
else:
result[document['_id']['problem_id']]['incorrect'] += 1
csv_result = [[item, result[item]['correct'], result[item]['incorrect']]
for item in result]
output = CSV(csv_result, ['Problem Id', 'Correct Count', 'Incorrect Count'],
output_file='activities_with_lower_completion.csv')
output.generate_csv()
if item['event_type'] == 'play_video':
start_event_time = datetime.strptime(item['time'].split('+')[0], "%Y-%m-%dT%H:%M:%S.%f")
#get values related to video identification
video = item['event']
video_code = video['code']
video_id = video['id']
time_point = video['currentTime']
print 'start'
print (start_event_time)
#when a start event is found set the end event to blank
end_event_time = {'blank'}
continue
#assign all other event types to end
#Note: currently seek_video events count as an end_event
else:
end_event_time = datetime.strptime(item['time'].split('+')[0], "%Y-%m-%dT%H:%M:%S.%f")
print 'end'
print (end_event_time)
continue
except:
count_errors = count_errors+1
errors.append([index,item])
#print watch_durations
print
print len(watch_durations)
print errors
output = CSV(watch_durations, ['Username','video_id','youtube id (video_code)','time_point (seconds)','start_event_time','end_event_time', 'duration (minutes)'], output_file=db_name+'video_watch_duration.csv', row_limit=200000)
output.generate_csv()
output_errors = CSV(errors, ['Errors'], output_file=db_name+'video_watch_duration_errors.csv', row_limit=200000)
output_errors.generate_csv()