def create_author_feature(feature_name, author_guid, attribute_value, window_start, window_end):
feature = AuthorFeatures()
feature.author_guid = author_guid
feature.attribute_name = feature_name
feature.attribute_value = attribute_value
feature.window_start = window_start
feature.window_end = window_end
return feature
def _create_feature(self, feature, id_val, result, suffix=u''):
author_feature = AuthorFeatures()
author_feature.author_guid = id_val
author_feature.window_start = self._window_start
author_feature.window_end = self._window_end
subclass_name = self.__class__.__name__
author_feature.attribute_name = unicode(subclass_name + "_" + feature + suffix)
author_feature.attribute_value = result
return author_feature
def _create_feature(self, feature, id_val, result, suffix=''):
author_feature = AuthorFeatures()
author_feature.author_guid = id_val
author_feature.window_start = self._window_start
author_feature.window_end = self._window_end
subclass_name = self.__class__.__name__
author_feature.attribute_name = '{}_{}{}'.format(subclass_name, feature, suffix)
author_feature.attribute_value = str(result)
return author_feature
def _create_author_feature_with_name(self, author_guid, value, feature_name):
author_feature = AuthorFeatures()
author_feature.author_guid = author_guid
author_feature.window_start = date('2010-01-01 00:00:00')
author_feature.window_end = date('2020-01-01 23:59:59')
author_feature.attribute_name = feature_name
author_feature.attribute_value=value
self._authors_to_author_features_dict[author_guid].append(author_feature)
self._db.update_author_features((author_feature))
self._db.session.commit()
def run_and_create_author_feature(self, author, feature, posts, id_val,
feature_name):
try:
result = getattr(self, feature)(posts=posts, author=author)
author_feature = AuthorFeatures()
author_feature.author_guid = id_val
author_feature.window_start = self._window_start
author_feature.window_end = self._window_end
author_feature.attribute_name = unicode(feature_name)
author_feature.attribute_value = result
return author_feature
except Exception as e:
info_msg = e.message
logging.error(info_msg + feature)
def run_and_create_author_feature_with_given_value(self, author, value,
feature_name):
try:
result = value
author_feature = AuthorFeatures()
author_feature.author_guid = author
author_feature.window_start = self._window_start
author_feature.window_end = self._window_end
author_feature.attribute_name = unicode(feature_name)
author_feature.attribute_value = result
return author_feature
except Exception as e:
info_msg = e.message
logging.error(info_msg + str(value))
def run_and_create_author_feature(self, kwargs, id_val, feature):
try:
result = getattr(self, feature)(**kwargs)
author_feature = AuthorFeatures()
author_feature.author_guid = id_val
author_feature.window_start = self._window_start
author_feature.window_end = self._window_end
subclass_name = self.__class__.__name__
author_feature.attribute_name = unicode(subclass_name + "_" + feature)
author_feature.attribute_value = result
return author_feature
except Exception as e:
info_msg = e.message
logging.error(info_msg)
def execute(self):
start_time = time.time()
info_msg = "execute started for " + self.__class__.__name__
logging.info(info_msg)
post_topics_map = self._db.get_single_post_per_author_topic_mapping()
total = len(post_topics_map)
processed = 0
authors_features = []
for tuple in post_topics_map:
author_guid = tuple[0]
for topic in range(1, len(tuple)):
probability = tuple[topic]
author_feature = AuthorFeatures()
author_feature.author_guid = author_guid
author_feature.window_start = self._window_start
author_feature.window_end = self._window_end
author_feature.attribute_name = unicode('probability_topic_' +
str(topic))
author_feature.attribute_value = probability
authors_features.append(author_feature)
processed += 1
print("\r processed authors " + str(processed) + " from " +
str(total),
end="")
if authors_features:
print('\n Beginning merging author_features objects')
counter = 0
for author_features_row in authors_features:
counter += 1
self._db.update_author_features(author_features_row)
if counter == 100:
print("\r " + str(self.__class__.__name__) +
" merging author-features objects",
end="")
self._db.commit()
counter = 0
if counter != 0:
self._db.commit()
print('Finished merging author_features objects')
end_time = time.time()
diff_time = end_time - start_time
print('execute finished in ' + str(diff_time) + ' seconds')