def compute_total_points(user):
if user.is_teacher:
return None
else:
return (VideoLog.get_points_for_user(user) +
ExerciseLog.get_points_for_user(user) +
ContentLog.get_points_for_user(user))
def compute_total_points(user):
if user.is_teacher:
return None
else:
return (VideoLog.get_points_for_user(user) +
ExerciseLog.get_points_for_user(user) +
ContentLog.get_points_for_user(user))
def update_all_distributed_callback(request):
"""
"""
if request.method != "POST":
raise PermissionDenied("Only POST allowed to this URL endpoint.")
videos = json.loads(request.POST["video_logs"])
exercises = json.loads(request.POST["exercise_logs"])
user = FacilityUser.objects.get(id=request.POST["user_id"])
node_cache = get_node_cache()
# Save videos
n_videos_uploaded = 0
for video in videos:
video_id = video['video_id']
youtube_id = video['youtube_id']
# Only save video logs for videos that we recognize.
if video_id not in node_cache["Content"]:
logging.warn("Skipping unknown video %s" % video_id)
continue
try:
(vl, _) = VideoLog.get_or_initialize(user=user, video_id=video_id) # has to be that video_id, could be any youtube_id
for key,val in video.iteritems():
setattr(vl, key, val)
logging.debug("Saving video log for %s: %s" % (video_id, vl))
vl.save()
n_videos_uploaded += 1
except KeyError: #
logging.error("Could not save video log for data with missing values: %s" % video)
except Exception as e:
error_message = _("Unexpected error importing videos: %(err_msg)s") % {"err_msg": e}
return JsonResponseMessageError(error_message)
# Save exercises
n_exercises_uploaded = 0
for exercise in exercises:
# Only save video logs for videos that we recognize.
if exercise['exercise_id'] not in node_cache['Exercise']:
logging.warn("Skipping unknown video %s" % exercise['exercise_id'])
continue
try:
(el, _) = ExerciseLog.get_or_initialize(user=user, exercise_id=exercise["exercise_id"])
for key,val in exercise.iteritems():
setattr(el, key, val)
logging.debug("Saving exercise log for %s: %s" % (exercise['exercise_id'], el))
el.save()
n_exercises_uploaded += 1
except KeyError:
logging.error("Could not save exercise log for data with missing values: %s" % exercise)
except Exception as e:
error_message = _("Unexpected error importing exercises: %(err_msg)s") % {"err_msg": e}
return JsonResponseMessageError(error_message)
return JsonResponseMessageSuccess(_("Uploaded %(num_exercises)d exercises and %(num_videos)d videos") % {
"num_exercises": n_exercises_uploaded,
"num_videos": n_videos_uploaded,
})
def update_all_distributed_callback(request):
"""
"""
if request.method != "POST":
raise PermissionDenied("Only POST allowed to this URL endpoint.")
videos = json.loads(request.POST["video_logs"])
exercises = json.loads(request.POST["exercise_logs"])
user = FacilityUser.objects.get(id=request.POST["user_id"])
node_ids = [node.get("id") for node in get_content_items()]
# Save videos
n_videos_uploaded = 0
for video in videos:
video_id = video['video_id']
youtube_id = video['youtube_id']
# Only save video logs for videos that we recognize.
if video_id not in node_ids:
logging.warn("Skipping unknown video %s" % video_id)
continue
try:
(vl, _) = VideoLog.get_or_initialize(user=user, video_id=video_id) # has to be that video_id, could be any youtube_id
for key,val in video.iteritems():
setattr(vl, key, val)
logging.debug("Saving video log for %s: %s" % (video_id, vl))
vl.save()
n_videos_uploaded += 1
except KeyError: #
logging.error("Could not save video log for data with missing values: %s" % video)
except Exception as e:
error_message = _("Unexpected error importing videos: %(err_msg)s") % {"err_msg": e}
return JsonResponseMessageError(error_message, status=500)
# Save exercises
n_exercises_uploaded = 0
for exercise in exercises:
# Only save video logs for videos that we recognize.
if exercise['exercise_id'] not in node_ids:
logging.warn("Skipping unknown video %s" % exercise['exercise_id'])
continue
try:
(el, _) = ExerciseLog.get_or_initialize(user=user, exercise_id=exercise["exercise_id"])
for key,val in exercise.iteritems():
setattr(el, key, val)
logging.debug("Saving exercise log for %s: %s" % (exercise['exercise_id'], el))
el.save()
n_exercises_uploaded += 1
except KeyError:
logging.error("Could not save exercise log for data with missing values: %s" % exercise)
except Exception as e:
error_message = _("Unexpected error importing exercises: %(err_msg)s") % {"err_msg": e}
return JsonResponseMessageError(error_message, status=500)
return JsonResponseMessageSuccess(_("Uploaded %(num_exercises)d exercises and %(num_videos)d videos") % {
"num_exercises": n_exercises_uploaded,
"num_videos": n_videos_uploaded,
})
def before_scenario(context, scenario):
base_before_scenario(context, scenario)
if "with_progress" in context.tags:
user = FacilityUser.objects.get(username=context.user,
facility=getattr(
context, "facility", None))
exercises = random.sample(get_exercise_cache().keys(), 2)
for exercise in exercises:
log = ExerciseLog(
exercise_id=exercise,
user=user,
streak_progress=50,
attempts=15,
latest_activity_timestamp=datetime.datetime.now())
log.save()
context.exercises = exercises
videos = random.sample(get_content_cache().keys(), 2)
for video in videos:
log = VideoLog(youtube_id=video,
video_id=video,
user=user,
total_seconds_watched=100,
points=600,
latest_activity_timestamp=datetime.datetime.now())
log.save()
context.videos = videos
def _setup(self, num_logs=50, **kwargs):
super(OneHundredRandomLogUpdates, self)._setup(**kwargs)
node_cache = get_node_cache()
try:
self.user = FacilityUser.objects.get(username=self.username)
except:
#take username from ExerciseLog
all_exercises = ExerciseLog.objects.all()
self.user = FacilityUser.objects.get(id=all_exercises[0].user_id)
print self.username, " not in FacilityUsers, using ", self.user
self.num_logs = num_logs
#give the platform a chance to cache the logs
ExerciseLog.objects.filter(user=self.user).delete()
for x in range(num_logs):
while True:
ex_idx = int(self.random.random() *
len(node_cache["Exercise"].keys()))
ex_id = node_cache["Exercise"].keys()[ex_idx]
if not ExerciseLog.objects.filter(user=self.user,
exercise_id=ex_id):
break
ex = ExerciseLog(user=self.user, exercise_id=ex_id)
ex.save()
self.exercise_list = ExerciseLog.objects.filter(user=self.user)
self.exercise_count = self.exercise_list.count()
VideoLog.objects.filter(user=self.user).delete()
for x in range(num_logs):
while True:
vid_idx = int(self.random.random() *
len(node_cache["Content"].keys()))
vid_id = node_cache["Content"].keys()[vid_idx]
if not VideoLog.objects.filter(user=self.user,
video_id=vid_id):
break
vid = VideoLog(user=self.user, video_id=vid_id)
vid.save()
self.video_list = VideoLog.objects.filter(user=self.user)
self.video_count = self.video_list.count()
def _setup(self, num_logs=50, **kwargs):
super(OneHundredRandomLogUpdates, self)._setup(**kwargs)
node_cache = get_node_cache()
try:
self.user = FacilityUser.objects.get(username=self.username)
except:
#take username from ExerciseLog
all_exercises = ExerciseLog.objects.all()
self.user = FacilityUser.objects.get(id=all_exercises[0].user_id)
print self.username, " not in FacilityUsers, using ", self.user
self.num_logs = num_logs
#give the platform a chance to cache the logs
ExerciseLog.objects.filter(user=self.user).delete()
for x in range(num_logs):
while True:
ex_idx = int(self.random.random() * len(node_cache["Exercise"].keys()))
ex_id = node_cache["Exercise"].keys()[ex_idx]
if not ExerciseLog.objects.filter(user=self.user, exercise_id=ex_id):
break
ex = ExerciseLog(user=self.user, exercise_id=ex_id)
ex.save()
self.exercise_list = ExerciseLog.objects.filter(user=self.user)
self.exercise_count = self.exercise_list.count()
VideoLog.objects.filter(user=self.user).delete()
for x in range(num_logs):
while True:
vid_idx = int(self.random.random() * len(node_cache["Content"].keys()))
vid_id = node_cache["Content"].keys()[vid_idx]
if not VideoLog.objects.filter(user=self.user, video_id=vid_id):
break
vid = VideoLog(user=self.user, video_id=vid_id)
vid.save()
self.video_list = VideoLog.objects.filter(user=self.user)
self.video_count = self.video_list.count()
def update_all_central_callback(request):
"""
Callback after authentication.
Parses out the request token verification.
Then finishes the request by getting an auth token.
"""
if not "ACCESS_TOKEN" in request.session:
finish_auth(request)
exercises = get_api_resource(request, "/api/v1/user/exercises")
videos = get_api_resource(request, "/api/v1/user/videos")
node_cache = get_node_cache()
# Collate videos
video_logs = []
for video in videos:
# Assume that KA videos are all english-language, not dubbed (for now)
video_id = youtube_id = video.get('video', {}).get('youtube_id', "")
# Only save videos with progress
if not video.get('seconds_watched', None):
continue
# Only save video logs for videos that we recognize.
if video_id not in node_cache["Video"]:
logging.warn("Skipping unknown video %s" % video_id)
continue
try:
video_logs.append({
"video_id": video_id,
"youtube_id": youtube_id,
"total_seconds_watched": video['seconds_watched'],
"points": VideoLog.calc_points(video['seconds_watched'], video['duration']),
"complete": video['completed'],
"completion_timestamp": convert_ka_date(video['last_watched']) if video['completed'] else None,
})
logging.debug("Got video log for %s: %s" % (video_id, video_logs[-1]))
except KeyError: #
logging.error("Could not save video log for data with missing values: %s" % video)
# Collate exercises
exercise_logs = []
for exercise in exercises:
# Only save exercises that have any progress.
if not exercise.get('last_done', None):
continue
# Only save video logs for videos that we recognize.
slug = exercise.get('exercise', "")
if slug not in node_cache['Exercise']:
logging.warn("Skipping unknown video %s" % slug)
continue
try:
completed = exercise['streak'] >= 10
basepoints = node_cache['Exercise'][slug][0]['basepoints']
exercise_logs.append({
"exercise_id": slug,
"streak_progress": min(100, 100 * exercise['streak']/10), # duplicates logic elsewhere
"attempts": exercise['total_done'],
"points": ExerciseLog.calc_points(basepoints, ncorrect=exercise['streak'], add_randomness=False), # no randomness when importing from KA
"complete": completed,
"attempts_before_completion": exercise['total_done'] if not exercise['practiced'] else None, #can't figure this out if they practiced after mastery.
"completion_timestamp": convert_ka_date(exercise['proficient_date']) if completed else None,
})
logging.debug("Got exercise log for %s: %s" % (slug, exercise_logs[-1]))
except KeyError:
logging.error("Could not save exercise log for data with missing values: %s" % exercise)
# POST the data back to the distributed server
try:
dthandler = lambda obj: obj.isoformat() if isinstance(obj, datetime.datetime) else None
logging.debug("POST'ing to %s" % request.session["distributed_callback_url"])
response = requests.post(
request.session["distributed_callback_url"],
cookies={ "csrftoken": request.session["distributed_csrf_token"] },
data = {
"csrfmiddlewaretoken": request.session["distributed_csrf_token"],
"video_logs": json.dumps(video_logs, default=dthandler),
"exercise_logs": json.dumps(exercise_logs, default=dthandler),
"user_id": request.session["distributed_user_id"],
}
)
logging.debug("Response (%d): %s" % (response.status_code, response.content))
except requests.exceptions.ConnectionError as e:
return HttpResponseRedirect(set_query_params(request.session["distributed_redirect_url"], {
"message_type": "error",
"message": _("Could not connect to your KA Lite installation to share Khan Academy data."),
"message_id": "id_khanload",
}))
except Exception as e:
return HttpResponseRedirect(set_query_params(request.session["distributed_redirect_url"], {
"message_type": "error",
"message": _("Failure to send data to your KA Lite installation: %s") % e,
"message_id": "id_khanload",
}))
try:
json_response = json.loads(response.content)
if not isinstance(json_response, dict) or len(json_response) != 1:
# Could not validate the message is a single key-value pair
raise Exception(_("Unexpected response format from your KA Lite installation."))
message_type = json_response.keys()[0]
message = json_response.values()[0]
except ValueError as e:
message_type = "error"
message = unicode(e)
except Exception as e:
message_type = "error"
message = _("Loading json object: %s") % e
# If something broke on the distribute d server, we are SCREWED.
# For now, just show the error to users.
#
# Ultimately, we have a message, would like to share with the distributed server.
# if response.status_code != 200:
# return HttpResponseServerError(response.content)
return HttpResponseRedirect(set_query_params(request.session["distributed_redirect_url"], {
"message_type": message_type,
"message": message,
"message_id": "id_khanload",
}))
def generate_fake_video_logs(
facility_user=None, topics=topics, start_date=datetime.datetime.now() - datetime.timedelta(days=30 * 6)
):
"""Add video logs for the given topics, for each of the given users.
If no users are given, they are created.
If no topics exist, they are taken from the list at the top of this file."""
date_diff = datetime.datetime.now() - start_date
video_logs = []
# It's not a user: probably a list.
# Recursive case
if not hasattr(facility_user, "username"):
# It's NONE :-/ generate the users first!
if not facility_user:
(facility_user, _, _) = generate_fake_facility_users()
for topic in topics:
for user in facility_user:
video_logs.append(generate_fake_video_logs(facility_user=user, topics=[topic], start_date=start_date))
# Actually generate!
else:
# First, make videos for the associated logs
# Then make some unassociated videos, to simulate both exploration
# and watching videos without finishing.
# Get (or create) user type
try:
user_settings = json.loads(facility_user.notes)
except:
user_settings = sample_user_settings()
facility_user.notes = json.dumps(user_settings)
try:
facility_user.save()
except Exception as e:
logging.error("Error saving facility user: %s" % e)
date_diff_started = datetime.timedelta(
seconds=datediff(date_diff, units="seconds") * user_settings["time_in_program"]
) # when this user started in the program, relative to NOW
# contains the video duration key
video_cache = get_content_cache()
for topic in topics:
videos = get_topic_videos(topic_id=topic)
exercises = get_topic_exercises(topic_id=topic)
exercise_ids = [ex["id"] if "id" in ex else ex["name"] for ex in exercises]
exercise_logs = ExerciseLog.objects.filter(user=facility_user, id__in=exercise_ids)
# Probability of watching a video, irrespective of the context
p_video_outer = probability_of("video", user_settings=user_settings)
logging.debug(
"# videos: %d; p(videos)=%4.3f, user settings: %s\n"
% (len(videos), p_video_outer, json.dumps(user_settings))
)
for video in videos:
p_completed = probability_of("completed", user_settings=user_settings)
# If we're just doing random videos, fine.
# If these videos relate to exercises, then suppress non-exercise-related videos
# for this user.
p_video = p_video_outer # start with the context-free value
did_exercise = False
if exercise_logs.count() > 0:
# 5x less likely to watch a video if you haven't done the exercise,
if "related_exercise" not in video:
p_video /= 5 # suppress
# 5x more likely to watch a video if they've done the exercise
# 2x more likely to have finished it.
else:
exercise_log = ExerciseLog.objects.filter(
user=facility_user, id=video["related_exercise"]["id"]
)
did_exercise = exercise_log.count() != 0
if did_exercise:
p_video *= 5
p_completed *= 2
# Do the sampling
if p_video < random.random():
continue
# didn't watch it
elif p_completed > random.random():
pct_completed = 100.0
else: # Slower students will use videos more. Effort also important.
pct_completed = 100.0 * min(
1.0,
sqrt(
random.random()
* sqrt(
user_settings["effort_level"]
* user_settings["time_in_program"]
/ sqrt(user_settings["speed_of_learning"])
)
),
)
# get the video duration on the video cache
video_id = video.get("id", "")
video_duration = 0
if video_id and video_cache:
video_item = video_cache.get(video_id, None)
if video_item:
video_duration = video_item.get("duration", 0)
# Compute quantities based on sample
total_seconds_watched = int(video_duration * pct_completed / 100.0)
points = int(750 * pct_completed / 100.0)
# Choose a rate of videos, based on their effort level.
# Compute the latest possible start time.
# Then sample a start time between their start time
# and the latest possible start_time
if did_exercise:
# More jitter if you learn fast, less jitter if you try harder (more diligent)
date_jitter = datetime.timedelta(
days=max(0, random.gauss(1, user_settings["speed_of_learning"] / user_settings["effort_level"]))
)
date_completed = exercise_log[0].completion_timestamp - date_jitter
else:
rate_of_videos = (
0.66 * user_settings["effort_level"] + 0.33 * user_settings["speed_of_learning"]
) # exercises per day
time_for_watching = total_seconds_watched
time_delta_completed = datetime.timedelta(
seconds=random.randint(
int(time_for_watching), int(datediff(date_diff_started, units="seconds"))
)
)
date_completed = datetime.datetime.now() - time_delta_completed
try:
vlog = VideoLog.objects.get(user=facility_user, video_id=video_id)
except VideoLog.DoesNotExist:
logging.info(
"Creating video log: %-12s: %-45s (%4.1f%% watched, %d points)%s"
% (
facility_user.first_name,
video["title"],
pct_completed,
points,
" COMPLETE on %s!" % date_completed if pct_completed == 100 else "",
)
)
youtube_id = video.get("youtube_id", video_id)
vlog = VideoLog(
user=facility_user,
video_id=video_id,
youtube_id=youtube_id,
total_seconds_watched=total_seconds_watched,
points=points,
complete=(pct_completed == 100.0),
completion_timestamp=date_completed,
latest_activity_timestamp=date_completed,
)
try:
vlog.save() # avoid userlog issues
except Exception as e:
logging.error("Error saving video log: %s" % e)
continue
video_logs.append(vlog)
return video_logs
def generate_fake_video_logs(facility_user=None,
topics=topics,
start_date=datetime.datetime.now() -
datetime.timedelta(days=30 * 6)):
"""Add video logs for the given topics, for each of the given users.
If no users are given, they are created.
If no topics exist, they are taken from the list at the top of this file."""
own_device = Device.get_own_device()
date_diff = datetime.datetime.now() - start_date
video_logs = []
# It's not a user: probably a list.
# Recursive case
if not hasattr(facility_user, "username"):
# It's NONE :-/ generate the users first!
if not facility_user:
(facility_user, _, _) = generate_fake_facility_users()
for topic in topics:
for user in facility_user:
video_logs.append(
generate_fake_video_logs(facility_user=user,
topics=[topic],
start_date=start_date))
# Actually generate!
else:
# First, make videos for the associated logs
# Then make some unassociated videos, to simulate both exploration
# and watching videos without finishing.
# Get (or create) user type
try:
user_settings = json.loads(facility_user.notes)
except:
user_settings = sample_user_settings()
facility_user.notes = json.dumps(user_settings)
try:
facility_user.save()
except Exception as e:
logging.error("Error saving facility user: %s" % e)
date_diff_started = datetime.timedelta(
seconds=datediff(date_diff, units="seconds") *
user_settings["time_in_program"]
) # when this user started in the program, relative to NOW
for topic in topics:
videos = get_topic_videos(topic_id=topic)
exercises = get_topic_exercises(topic_id=topic)
exercise_ids = [
ex["id"] if "id" in ex else ex['name'] for ex in exercises
]
exercise_logs = ExerciseLog.objects.filter(user=facility_user,
id__in=exercise_ids)
# Probability of watching a video, irrespective of the context
p_video_outer = probability_of("video",
user_settings=user_settings)
logging.debug(
"# videos: %d; p(videos)=%4.3f, user settings: %s\n" %
(len(videos), p_video_outer, json.dumps(user_settings)))
for video in videos:
p_completed = probability_of("completed",
user_settings=user_settings)
# If we're just doing random videos, fine.
# If these videos relate to exercises, then suppress non-exercise-related videos
# for this user.
p_video = p_video_outer # start with the context-free value
did_exercise = False
if exercise_logs.count() > 0:
# 5x less likely to watch a video if you haven't done the exercise,
if "related_exercise" not in video:
p_video /= 5 # suppress
# 5x more likely to watch a video if they've done the exercise
# 2x more likely to have finished it.
else:
exercise_log = ExerciseLog.objects.filter(
user=facility_user,
id=video["related_exercise"]["id"])
did_exercise = exercise_log.count() != 0
if did_exercise:
p_video *= 5
p_completed *= 2
# Do the sampling
if p_video < random.random():
continue
# didn't watch it
elif p_completed > random.random():
pct_completed = 100.
else: # Slower students will use videos more. Effort also important.
pct_completed = 100. * min(
1.,
sqrt(random.random() *
sqrt(user_settings["effort_level"] *
user_settings["time_in_program"] /
sqrt(user_settings["speed_of_learning"]))))
# Compute quantities based on sample
total_seconds_watched = int(video["duration"] * pct_completed /
100.)
points = int(750 * pct_completed / 100.)
# Choose a rate of videos, based on their effort level.
# Compute the latest possible start time.
# Then sample a start time between their start time
# and the latest possible start_time
if did_exercise:
# More jitter if you learn fast, less jitter if you try harder (more diligent)
date_jitter = datetime.timedelta(days=max(
0,
random.gauss(
1, user_settings["speed_of_learning"] /
user_settings["effort_level"])))
date_completed = exercise_log[
0].completion_timestamp - date_jitter
else:
rate_of_videos = 0.66 * user_settings[
"effort_level"] + 0.33 * user_settings[
"speed_of_learning"] # exercises per day
time_for_watching = total_seconds_watched
time_delta_completed = datetime.timedelta(
seconds=random.randint(
int(time_for_watching),
int(datediff(date_diff_started, units="seconds"))))
date_completed = datetime.datetime.now(
) - time_delta_completed
try:
vlog = VideoLog.objects.get(user=facility_user,
video_id=video["id"])
except VideoLog.DoesNotExist:
logging.info(
"Creating video log: %-12s: %-45s (%4.1f%% watched, %d points)%s"
% (
facility_user.first_name,
video["title"],
pct_completed,
points,
" COMPLETE on %s!" %
date_completed if pct_completed == 100 else "",
))
vlog = VideoLog(
user=facility_user,
video_id=video["id"],
youtube_id=video["youtube_id"],
total_seconds_watched=total_seconds_watched,
points=points,
complete=(pct_completed == 100.),
completion_timestamp=date_completed,
)
try:
vlog.save(update_userlog=False) # avoid userlog issues
except Exception as e:
logging.error("Error saving video log: %s" % e)
continue
video_logs.append(vlog)
return video_logs
