def test_bulk_calculate_course_progress_unlinked_course_error(db, monkeypatch):
"""Tests 'bulk_calculate_course_progress_data' function
The function under test iterates over a set of course enrollment records,
So we create a couple of records to iterate over and mock the collect
function
"""
course_overview = CourseOverviewFactory()
course_enrollments = [
CourseEnrollmentFactory(course_id=course_overview.id) for i in range(2)
]
mapping = {
ce.course_id:
LearnerCourseGradeMetricsFactory(course_id=str(ce.course_id),
user=ce.user,
sections_worked=1,
sections_possible=2)
for ce in course_enrollments
}
def mock_metrics(course_enrollment, **_kwargs):
return mapping[course_enrollment.course_id]
monkeypatch.setattr(
'figures.pipeline.enrollment_metrics.collect_metrics_for_enrollment',
mock_metrics)
with pytest.raises(UnlinkedCourseError) as e_info:
data = bulk_calculate_course_progress_data(course_overview.id)
def test_bulk_calculate_course_progress_data_happy_path(db, monkeypatch):
"""Tests 'bulk_calculate_course_progress_data' function
The function under test iterates over a set of course enrollment records,
So we create a couple of records to iterate over and mock the collect
function
"""
course_overview = CourseOverviewFactory()
course_enrollments = [
CourseEnrollmentFactory(course_id=course_overview.id) for i in range(2)
]
mapping = {
ce.course_id:
LearnerCourseGradeMetricsFactory(course_id=str(ce.course_id),
user=ce.user,
sections_worked=1,
sections_possible=2)
for ce in course_enrollments
}
def mock_metrics(course_enrollment, **_kwargs):
return mapping[course_enrollment.course_id]
monkeypatch.setattr(
'figures.pipeline.enrollment_metrics.get_site_for_course',
lambda val: SiteFactory())
monkeypatch.setattr(
'figures.pipeline.enrollment_metrics.collect_metrics_for_enrollment',
mock_metrics)
data = bulk_calculate_course_progress_data(course_overview.id)
assert data['average_progress'] == 0.5
def extract(self, course_id, date_for, **_kwargs):
"""
defaults = dict(
enrollment_count=data['enrollment_count'],
active_learners_today=data['active_learners_today'],
average_progress=data.get('average_progress', None),
average_days_to_complete=data.get('average_days_to_complete, None'),
num_learners_completed=data['num_learners_completed'],
)
TODO: refactor this class
Add lazy loading method to load course enrollments
- Create a method for each metric field
"""
# We can turn this series of calls into a parallel
# set of calls defined in a ruleset instead of hardcoded here after
# retrieving the core quersets
course_enrollments = get_enrolled_in_exclude_admins(
course_id, date_for,)
data = dict(date_for=date_for, course_id=course_id)
# This is the transform step
# After we get this working, we can then define them declaratively
# we can do a lambda for course_enrollments to get the count
data['enrollment_count'] = course_enrollments.count()
active_learner_ids_today = get_active_learner_ids_today(
course_id, date_for,)
if active_learner_ids_today:
active_learners_today = active_learner_ids_today.count()
else:
active_learners_today = 0
data['active_learners_today'] = active_learners_today
# Average progress
try:
progress_data = bulk_calculate_course_progress_data(course_id=course_id,
date_for=date_for)
data['average_progress'] = progress_data['average_progress']
except Exception: # pylint: disable=broad-except
# Broad exception for starters. Refine as we see what gets caught
# Make sure we set the average_progres to None so that upstream
# does not think things are normal
data['average_progress'] = None
msg = ('FIGURES:FAIL bulk_calculate_course_progress_data'
' date_for={date_for}, course_id="{course_id}"')
logger.exception(msg.format(date_for=date_for, course_id=course_id))
data['average_days_to_complete'] = get_average_days_to_complete(
course_id, date_for,)
data['num_learners_completed'] = get_num_learners_completed(
course_id, date_for,)
return data
def test_bulk_calculate_course_progress_no_enrollments(db, monkeypatch):
"""This tests when there is a new course with no enrollments
"""
monkeypatch.setattr(
'figures.pipeline.enrollment_metrics.get_site_for_course',
lambda val: SiteFactory())
course_overview = CourseOverviewFactory()
data = bulk_calculate_course_progress_data(course_overview.id)
assert data['average_progress'] == 0.0
def extract(self, course_id, date_for=None, **_kwargs):
"""
defaults = dict(
enrollment_count=data['enrollment_count'],
active_learners_today=data['active_learners_today'],
average_progress=data.get('average_progress', None),
average_days_to_complete=data.get('average_days_to_complete, None'),
num_learners_completed=data['num_learners_completed'],
)
TODO: refactor this class
Add lazy loading method to load course enrollments
- Create a method for each metric field
"""
# Update args if not assigned
if not date_for:
date_for = prev_day(
datetime.datetime.utcnow().replace(tzinfo=utc).date())
# We can turn this series of calls into a parallel
# set of calls defined in a ruleset instead of hardcoded here after
# retrieving the core quersets
course_enrollments = get_enrolled_in_exclude_admins(
course_id,
date_for,
)
data = dict(date_for=date_for, course_id=course_id)
# This is the transform step
# After we get this working, we can then define them declaratively
# we can do a lambda for course_enrollments to get the count
data['enrollment_count'] = course_enrollments.count()
active_learner_ids_today = get_active_learner_ids_today(
course_id,
date_for,
)
if active_learner_ids_today:
active_learners_today = active_learner_ids_today.count()
else:
active_learners_today = 0
data['active_learners_today'] = active_learners_today
# Average progress
progress_data = bulk_calculate_course_progress_data(
course_id=course_id, date_for=date_for)
data['average_progress'] = progress_data['average_progress']
data['average_days_to_complete'] = get_average_days_to_complete(
course_id,
date_for,
)
data['num_learners_completed'] = get_num_learners_completed(
course_id,
date_for,
)
return data
def extract(self, course_id, date_for, ed_next=False, **_kwargs):
"""Extracts (collects) aggregated course level data
Args:
course_id (:obj:`str` or :obj:`CourseKey`): The course for which we collect data
date_for (str or date): Deprecated. Was to backfill data.
Specialized TBD backfill data will be called instead.
ed_next (bool, optional): "Enrollment Data Next" flag. If set to `True`
then we collect metrics with our updated workflow. See here:
https://github.com/appsembler/figures/issues/428
Returns:
dict with aggregate course level metrics
```
dict(
enrollment_count=data['enrollment_count'],
active_learners_today=data['active_learners_today'],
average_progress=data.get('average_progress', None),
average_days_to_complete=data.get('average_days_to_complete, None'),
num_learners_completed=data['num_learners_completed'],
)
```
TODO: refactor this class. It doesn't need to be a class. Can be a
standalone function
Add lazy loading method to load course enrollments
- Create a method for each metric field
"""
# We can turn this series of calls into a parallel
# set of calls defined in a ruleset instead of hardcoded here after
# retrieving the core quersets
course_enrollments = get_enrolled_in_exclude_admins(
course_id, date_for,)
data = dict(date_for=date_for, course_id=course_id)
# This is the transform step
# After we get this working, we can then define them declaratively
# we can do a lambda for course_enrollments to get the count
data['enrollment_count'] = course_enrollments.count()
active_learner_ids_today = get_active_learner_ids_today(
course_id, date_for,)
if active_learner_ids_today:
active_learners_today = active_learner_ids_today.count()
else:
active_learners_today = 0
data['active_learners_today'] = active_learners_today
# Average progress
# Progress data cannot be reliable for backfills or for any date prior to yesterday
# without using StudentModuleHistory so we skip getting this data if running
# for a day earlier than previous day (i.e., not during daily update of CDMs),
# especially since it is so expensive to calculate.
# Note that Avg() applied across null and decimal vals for aggregate average_progress
# will correctly ignore nulls
# TODO: Reconsider this if we implement either StudentModuleHistory-based queries
# (if so, you will need to add any types you want to
# StudentModuleHistory.HISTORY_SAVING_TYPES)
# TODO: Reconsider this once we switch to using Persistent Grades
if is_past_date(date_for + relativedelta(days=1)): # more than 1 day in past
data['average_progress'] = None
msg = ('FIGURES:PIPELINE:CDM Declining to calculate average progress for a past date'
' date_for={date_for}, course_id="{course_id}"')
logger.debug(msg.format(date_for=date_for, course_id=course_id))
else:
try:
# This conditional check is an interim solution until we make
# the progress function configurable and able to run Figures
# plugins
if ed_next:
progress_data = calculate_course_progress_next(course_id=course_id)
else:
progress_data = bulk_calculate_course_progress_data(course_id=course_id,
date_for=date_for)
data['average_progress'] = progress_data['average_progress']
except Exception: # pylint: disable=broad-except
# Broad exception for starters. Refine as we see what gets caught
# Make sure we set the average_progres to None so that upstream
# does not think things are normal
data['average_progress'] = None
if ed_next:
prog_func = 'calculate_course_progress_next'
else:
prog_func = 'bulk_calculate_course_progress_data'
msg = ('FIGURES:FAIL {prog_func}'
' date_for={date_for}, course_id="{course_id}"')
logger.exception(msg.format(prog_func=prog_func,
date_for=date_for,
course_id=course_id))
data['average_days_to_complete'] = get_average_days_to_complete(
course_id, date_for,)
data['num_learners_completed'] = get_num_learners_completed(
course_id, date_for,)
return data
def extract(self, course_id, date_for, **_kwargs):
"""
defaults = dict(
enrollment_count=data['enrollment_count'],
active_learners_today=data['active_learners_today'],
average_progress=data.get('average_progress', None),
average_days_to_complete=data.get('average_days_to_complete, None'),
num_learners_completed=data['num_learners_completed'],
)
TODO: refactor this class
Add lazy loading method to load course enrollments
- Create a method for each metric field
"""
# We can turn this series of calls into a parallel
# set of calls defined in a ruleset instead of hardcoded here after
# retrieving the core quersets
course_enrollments = get_enrolled_in_exclude_admins(
course_id,
date_for,
)
data = dict(date_for=date_for, course_id=course_id)
# This is the transform step
# After we get this working, we can then define them declaratively
# we can do a lambda for course_enrollments to get the count
data['enrollment_count'] = course_enrollments.count()
active_learner_ids_today = get_active_learner_ids_today(
course_id,
date_for,
)
if active_learner_ids_today:
active_learners_today = active_learner_ids_today.count()
else:
active_learners_today = 0
data['active_learners_today'] = active_learners_today
# Average progress
# Progress data cannot be reliable for backfills or for any date prior to yesterday
# without using StudentModuleHistory so we skip getting this data if running
# for a day earlier than previous day (i.e., not during daily update of CDMs),
# especially since it is so expensive to calculate.
# Note that Avg() applied across null and decimal vals for aggregate average_progress
# will correctly ignore nulls
# TODO: Reconsider this if we implement either StudentModuleHistory-based queries
# (if so, you will need to add any types you want to
# StudentModuleHistory.HISTORY_SAVING_TYPES)
# TODO: Reconsider this once we switch to using Persistent Grades
if is_past_date(date_for +
relativedelta(days=1)): # more than 1 day in past
data['average_progress'] = None
msg = (
'FIGURES:PIPELINE:CDM Declining to calculate average progress for a past date'
' date_for={date_for}, course_id="{course_id}"')
logger.debug(msg.format(date_for=date_for, course_id=course_id))
else:
try:
progress_data = bulk_calculate_course_progress_data(
course_id=course_id, date_for=date_for)
data['average_progress'] = progress_data['average_progress']
except Exception: # pylint: disable=broad-except
# Broad exception for starters. Refine as we see what gets caught
# Make sure we set the average_progres to None so that upstream
# does not think things are normal
data['average_progress'] = None
msg = ('FIGURES:FAIL bulk_calculate_course_progress_data'
' date_for={date_for}, course_id="{course_id}"')
logger.exception(
msg.format(date_for=date_for, course_id=course_id))
data['average_days_to_complete'] = get_average_days_to_complete(
course_id,
date_for,
)
data['num_learners_completed'] = get_num_learners_completed(
course_id,
date_for,
)
return data
