def classify(self, objekts=None, attribute_name=None):
""" Run :meth:`classify_one` on each member of :param:`objekts`.
Returns a ``dict`` of the form:
{
u'duration': <the duration in seconds, as integer>,
},
}
"""
start_time = pytime.time()
seen_objects = 0
error_types = {}
if objekts is None:
objekts = self.iterables
if attribute_name is None:
attribute_name = self.attribute_name
assert objekts is not None
assert attribute_name is not None
for objekt in objekts:
error = self.classify_one(getattr(objekt, attribute_name), objekt)
error_types[error] = error_types.setdefault(error, 0) + 1
seen_objects += 1
return {
u'duration': pytime.time() - start_time,
u'seen_objects': seen_objects,
u'error_types': error_types,
u'stored_instances': self.stored_instances,
}
def classify(self, objekts=None, attribute_name=None):
""" Run :meth:`classify_one` on each member of :param:`objekts`.
Returns a ``dict`` of the form:
{
u'duration': <the duration in seconds, as integer>,
},
}
"""
start_time = pytime.time()
seen_objects = 0
error_types = {}
if objekts is None:
objekts = self.iterables
if attribute_name is None:
attribute_name = self.attribute_name
assert objekts is not None
assert attribute_name is not None
for objekt in objekts:
error = self.classify_one(getattr(objekt, attribute_name), objekt)
error_types[error] = error_types.setdefault(error, 0) + 1
seen_objects += 1
return {
u'duration': pytime.time() - start_time,
u'seen_objects': seen_objects,
u'error_types': error_types,
u'stored_instances': self.stored_instances,
}
def feed_distribution_by_last_fetch():
""" compute and group feeds by last_fetch delta from now. """
start_time = pytime.time()
# open_feeds = Feed.objects(Q(closed=False) | Q(closed__exists=False))
open_feeds_count = Feed.objects.filter(closed__ne=True).count()
lower_value = None
loop_count = 0
fetched_feeds = 0
delta_lengths = (
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL / 6),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL / 2),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL * 2),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL * 6),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL * 12),
timedelta(days=1),
timedelta(days=2),
timedelta(days=3),
timedelta(days=4),
timedelta(days=5),
timedelta(days=6),
timedelta(days=7),
timedelta(days=10),
None
)
results = {}
for delta in delta_lengths:
upper_value = (now() - delta) if delta else None
if lower_value is None:
kwargs = {'last_fetch__gt': upper_value}
elif upper_value is None:
kwargs = {'last_fetch__lte': lower_value}
else:
kwargs = {'last_fetch__lte': lower_value,
'last_fetch__gt': upper_value}
feeds = Feed.objects(**kwargs)
count = feeds.count()
percent = float(count * 100.0 / open_feeds_count)
avg_fi = sum(f.fetch_interval for f in feeds) * 1.0 / (count or 1.0)
results[loop_count] = [
feeds,
count,
percent,
lower_value,
upper_value,
avg_fi,
]
fetched_feeds += count
lower_value = upper_value
loop_count += 1
results['meta'] = {'fetched_feeds': fetched_feeds,
'open_feeds_count': open_feeds_count,
'duration': pytime.time() - start_time,
'loop_count': loop_count}
return results
def feed_distribution_by_last_fetch():
""" compute and group feeds by last_fetch delta from now. """
start_time = pytime.time()
# open_feeds = Feed.objects(Q(closed=False) | Q(closed__exists=False))
open_feeds_count = Feed.objects.filter(closed__ne=True).count()
lower_value = None
loop_count = 0
fetched_feeds = 0
delta_lengths = (timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL / 6),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL / 2),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL * 2),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL * 6),
timedelta(seconds=config.FEED_FETCH_DEFAULT_INTERVAL *
12), timedelta(days=1), timedelta(days=2),
timedelta(days=3), timedelta(days=4), timedelta(days=5),
timedelta(days=6), timedelta(days=7), timedelta(days=10),
None)
results = {}
for delta in delta_lengths:
upper_value = (now() - delta) if delta else None
if lower_value is None:
kwargs = {'last_fetch__gt': upper_value}
elif upper_value is None:
kwargs = {'last_fetch__lte': lower_value}
else:
kwargs = {
'last_fetch__lte': lower_value,
'last_fetch__gt': upper_value
}
feeds = Feed.objects(**kwargs)
count = feeds.count()
percent = float(count * 100.0 / open_feeds_count)
avg_fi = sum(f.fetch_interval for f in feeds) * 1.0 / (count or 1.0)
results[loop_count] = [
feeds,
count,
percent,
lower_value,
upper_value,
avg_fi,
]
fetched_feeds += count
lower_value = upper_value
loop_count += 1
results['meta'] = {
'fetched_feeds': fetched_feeds,
'open_feeds_count': open_feeds_count,
'duration': pytime.time() - start_time,
'loop_count': loop_count
}
return results
