def partition_ids(old_true_positive,
old_true_negative,
classifier=event_classifier.classified_event_from_fb_event):
success = set()
fail = set()
a = time.time()
for i, (id, fb_event) in enumerate(processing.all_fb_data(combined_ids)):
if not i % 10000: print 'Processing ', i
if i < START_EVENT:
continue
if END_EVENT and i > END_EVENT:
break
result = classifier(fb_event)
result.classify()
if result.is_dance_event():
success.add(id)
if id in old_true_negative:
handle_new_false_positive(id, result)
else:
# To print out failures, to see if there's any way we can better detect them
#if id in good_ids:
# print id, fb_event['info'].get('name')
# print result.found_dance_matches, result.found_event_matches, result.found_wrong_matches
fail.add(id)
if id in old_true_positive:
handle_new_false_negative(id, result)
print 'Time per event: %s' % (1.0 * (time.time() - a) /
(max(END_EVENT, i) - START_EVENT))
return fail, success
def partition_ids(old_true_positive, old_true_negative, classifier=event_classifier.classified_event_from_fb_event):
success = set()
fail = set()
a = time.time()
for i, (id, fb_event) in enumerate(processing.all_fb_data(combined_ids)):
if not i % 10000: print 'Processing ', i
if i < START_EVENT:
continue
if END_EVENT and i > END_EVENT:
break
result = classifier(fb_event)
result.classify()
if result.is_dance_event():
success.add(id)
if id in old_true_negative:
handle_new_false_positive(id, result)
else:
# To print out failures, to see if there's any way we can better detect them
#if id in good_ids:
# print id, fb_event['info'].get('name')
# print result.found_dance_matches, result.found_event_matches, result.found_wrong_matches
fail.add(id)
if id in old_true_positive:
handle_new_false_negative(id, result)
print 'Time per event: %s' % (1.0 * (time.time() - a) / (max(END_EVENT, i) - START_EVENT))
return fail, success
def partition_ids():
for i, (id, fb_event) in enumerate(processing.all_fb_data([], filename='local_data/PotentialFBEvents.csv')):
e = event_classifier.get_classified_event(fb_event)
result = event_auto_classifier.is_battle(e)
if result[0]:
success(e, fb_event, result)
else:
failure(e, fb_event, result)
def mp_partition_ids(ids, classifier=lambda x: False):
pool = multiprocessing.Pool(processes=multiprocessing.cpu_count(), initializer=init_worker)
print "Generating data..."
data = [(classifier, x) for x in processing.all_fb_data(ids)]
print "Running multiprocessing classifier..."
async_results = pool.map_async(mp_classify, data, chunksize=100)
# We need to specify a timeout to get(), so that KeyboardInterrupt gets delivered properly.
results = async_results.get(9999999)
print "Multiprocessing classifier completed."
successes = set(x[1] for x in results if x[0])
fails = set(x[1] for x in results if not x[0])
return successes, fails
def partition_ids(ids, classifier=lambda x: False):
successes = set()
fails = set()
for i, (id, fb_event) in enumerate(processing.all_fb_data(ids)):
if not i % 10000: print 'Processing ', i
result = classifier(fb_event)
if result:
successes.add(id)
#if id not in good_ids:
# # false positive
# add_counts(false_positive_counts, fb_event)
else:
fails.add(id)
#if id not in bad_ids:
# # false negative
# add_counts(false_negative_counts, fb_event)
#if id in good_ids:
# add_counts(good_counts, fb_event)
#else:
# add_counts(bad_counts, fb_event)
return successes, fails
rules[name] = var_value
return rules
# These are the regexes that will be our feature detectors
named_rules = {}
named_rules.update(get_magic_rules(rules))
named_rules.update(get_magic_rules(keywords))
named_rules['nlp.rules.MANUAL_DANCE[grammar.STRONG]'] = rules.MANUAL_DANCE[grammar.STRONG]
named_rules['nlp.rules.MANUAL_DANCE[grammar.STRONG_WEAK]'] = rules.MANUAL_DANCE[grammar.STRONG_WEAK]
named_rules['nlp.rules.MANUAL_DANCER[grammar.STRONG]'] = rules.MANUAL_DANCER[grammar.STRONG]
named_rules['nlp.rules.MANUAL_DANCER[grammar.STRONG_WEAK]'] = rules.MANUAL_DANCER[grammar.STRONG_WEAK]
named_rules_list = sorted(named_rules.items())
all_ids = processing.load_all_ids()
training_data = processing.load_classified_ids(all_ids)
loaded_data = processing.all_fb_data(all_ids)
print 'loaded ids'
class Bunch(object):
pass
train = Bunch()
def process(fb_event):
return '%s\n\n%s' % (fb_event['info'].get('name'), fb_event['info'].get('description'))
c = event_auto_classifier.is_auto_add_event(e)
result = c.result
else:
result = event_auto_classifier.is_auto_notadd_event(e)
# classified as good, but not supposed to be in the good set of ids:
if result[0] and fb_event['info']['id'] not in training_data.good_ids:
# false positive
print fb_event['info']['id'], result
if not full_run:
print fb_event['info']['id'], result
return result[0]
a = time.time()
print "Running auto classifier..."
fb_data = processing.all_fb_data(trial_ids)
# Input fb_data is [(id, fb_event), (id, fb_event)]
# Result will be positive ids and negative ids
classifier_data = processing.partition_data(fb_data, classifier=basic_match)
print "done, %d seconds" % (time.time() - a)
score_card = processing.ClassifierScoreCard(training_data, classifier_data, positive_classifier)
print "Found %s true-positives, %s false-positives" % (len(score_card.true_positives), len(score_card.false_positives))
print "Leaves %s to be manually-classified" % (len(score_card.false_negatives))
if full_run:
score_card.write_to_disk('scratch/')
for id in score_card.false_positives:
print 'F', id
named_rules.update(get_magic_rules(rules))
named_rules.update(get_magic_rules(keywords))
named_rules['nlp.rules.MANUAL_DANCE[grammar.STRONG]'] = rules.MANUAL_DANCE[
grammar.STRONG]
named_rules[
'nlp.rules.MANUAL_DANCE[grammar.STRONG_WEAK]'] = rules.MANUAL_DANCE[
grammar.STRONG_WEAK]
named_rules['nlp.rules.MANUAL_DANCER[grammar.STRONG]'] = rules.MANUAL_DANCER[
grammar.STRONG]
named_rules[
'nlp.rules.MANUAL_DANCER[grammar.STRONG_WEAK]'] = rules.MANUAL_DANCER[
grammar.STRONG_WEAK]
named_rules_list = sorted(named_rules.items())
all_ids = processing.load_all_ids()
training_data = processing.load_classified_ids(all_ids)
loaded_data = processing.all_fb_data(all_ids)
print 'loaded ids'
class Bunch(object):
pass
train = Bunch()
def process(fb_event):
return '%s\n\n%s' % (fb_event['info'].get('name'),
fb_event['info'].get('description'))