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 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