def execute(self, window_start=None):
self._word_vector_dict = self._db.get_word_vector_dictionary(self._table_name)
for target1, target2 in self._pairs_targets:
features = []
target1_tuples = self._get_records_by_target_dict(target1)
target2_tuples = self._get_records_by_target_dict(target2)
for id in target1_tuples:
dif_set1, dif_set2 = self.get_word_differences(id, target1_tuples, target2_tuples)
for aggregation_function in self._aggregation_functions:
try:
dif1_word_embedding, dif2_word_embedding, subtraction_vec = self._get_differential_vectors(
aggregation_function, dif_set1, dif_set2)
feature_name = self._get_feature_names(target1, target2, aggregation_function)
features = features + Vector_Operations.create_author_feature_for_each_dimention(
subtraction_vec, feature_name, id, self._window_start, self._window_end,
self.__class__.__name__ + '_')
features = features + self.create_distance_features(id, aggregation_function,
dif1_word_embedding,
dif2_word_embedding, target1, target2, self.__class__.__name__ + '_')
except Exception as e1:
logging.info(e1)
self._db.add_author_features(features)
def execute(self, window_start=None):
for targeted_fields_dict in self._targeted_fields_for_embedding:
source_id_target_elements_dict = self._get_source_id_target_elements(
targeted_fields_dict)
source_id_document_tuples = self._create_documents(
source_id_target_elements_dict)
msg = "\rStarting training doc2vec"
print(msg, end='')
model = self._train_doc2vec_model(source_id_document_tuples)
msg = "\rFinishing training doc2vec"
print(msg, end='')
targeted_table = targeted_fields_dict['source']['table_name']
targeted_field_name = targeted_fields_dict['destination']['table_name'] + "-" \
+ targeted_fields_dict['destination']['target_field']
model_type = "{0}_dimensions_{1}_window_size".format(
self._num_of_dimensions, self._window_size_doc2vec)
source_ids = source_id_target_elements_dict.keys()
counter = 0
authors_features = []
for i, source_id in enumerate(source_ids):
msg = "\rExtracting doc2vec features: {0}/{1}:{2}".format(
i, len(source_ids), source_id)
print(msg, end="")
counter += 1
if counter % self._max_objects_without_saving == 0:
self._db.add_author_features(authors_features)
self._db.session.commit()
source_id_vector = model[source_id]
feature_name = model_type + '_' + targeted_table + "_" + targeted_field_name
dimentions_feature_for_author = Vector_Operations.create_author_feature_for_each_dimention(
source_id_vector, feature_name, source_id,
self._window_start, self._window_end, self._prefix)
authors_features = authors_features + dimentions_feature_for_author
self._db.add_author_features(authors_features)
self._db.session.commit()