def analyze(cls, last_day=None):
""" Run cooccurrence analysis for the last day with all its intervals. """
param_last_day = last_day
# Run for previous day
if not last_day: # Parameter last_day should be the required day at 00:00:00
last_day = datetime.combine(
(datetime.now() - timedelta(days=1)).date(),
datetime.min.time())
# Get last day at 23:59:59
last_day = last_day + timedelta(days=1) - timedelta(
seconds=1) # This works because Python's sum is immutable
# Run for last N days.
for delta in ConfigurationManager().get_list('cooccurrence_deltas'):
# Calculate start date from delta
start_date = datetime.combine(
(last_day - timedelta(days=int(delta))).date(),
datetime.min.time())
# Run cooccurrence analysis
cls.get_logger().info(
f'Starting cooccurrence analysis for last {delta} days.')
cls.analyze_cooccurrence_for_window(start_date, last_day)
cls.get_logger().info(
f'Cooccurrence analysis for last {delta} days done.')
# Run usage analysis as soon as possible
HashtagUsageService.calculate_topics_hashtag_usage(param_last_day)
UserTopicService().init_process_with_date(
DateUtils.today() if not param_last_day else param_last_day +
timedelta(days=1))
def calculate_topics_hashtag_usage(cls, end_date=None):
""" Calculate the usage of all hashtags in today showable topics and the total usage of the topic itself. """
supporters = cls.__generate_supporters_map()
date = DateUtils.today() if not end_date else end_date + timedelta(
days=1)
# End time is yesterday at 23:59:59
end_time = date - timedelta(seconds=1)
# Run for different intervals of dates
for delta in ConfigurationManager().get_list(
'showable_cooccurrence_deltas'):
# Calculate start date from delta
start_date = datetime.combine(
(end_time - timedelta(days=int(delta))).date(),
datetime.min.time())
# Calculate data
cls.get_logger().info(
f'Starting hashtag usage calculation for {delta} days window.')
cls.calculate_hashtag_usage(start_date,
end_time,
interval='days',
supporters=supporters)
# Log finish for time checking
cls.get_logger().info(
f'Hashtag usage calculation finished for {delta} days window.')
# Log finish for time checking
cls.get_logger().info('Hashtag usage calculation finished.')
# Once we've analyzed hashtags, topic usage calculations are just additions
cls.get_logger().info('Starting topic usage calculation.')
# Run for different intervals of dates
for delta in ConfigurationManager().get_list(
'showable_cooccurrence_deltas'):
# Calculate start date from delta
start_date = datetime.combine(
(end_time - timedelta(days=int(delta))).date(),
datetime.min.time())
# Calculate data
cls.get_logger().info(
f'Starting topic usage calculation for {delta} days window.')
cls.calculate_topic_usage(start_date, end_time, interval='days')
# Log finish for time checking
cls.get_logger().info(
f'Topic usage calculation finished for {delta} days window.')
# Log finish for time checking
cls.get_logger().info('Topic usage calculation finished.')
def store(self, data):
# Generate document
data['date'] = DateUtils.today()
# Store document
self.collection.insert_one(data)