def get_features_array(self,
prop_graphs,
micro_features,
macro_features,
news_source=None,
label=None,
file_dir="data/features",
use_cache=False):
function_refs = []
file_name = self.get_dump_file_name(news_source, micro_features,
macro_features, label, file_dir)
data_file = Path(file_name)
if use_cache and data_file.is_file():
return pickle.load(open(file_name, "rb"))
if micro_features:
function_refs.extend(self.get_micro_feature_method_references())
if len(function_refs) == 0:
return None
all_features = []
for idx in range(len(function_refs)):
features_set = get_sample_feature_value(prop_graphs,
function_refs[idx])
all_features.append(features_set)
feature_array = np.transpose(get_numpy_array(all_features))
pickle.dump(feature_array, open(file_name, "wb"))
return feature_array
def get_prop_graphs_min_time_to_reach_level_2(news_graphs: list, edge_type=None):
return get_sample_feature_value(news_graphs, get_min_time_to_reach_level_2)
def get_prop_graphs_num_unique_user_under_level_4(prop_graphs, edge_type=RETWEET_EDGE):
return get_sample_feature_value(prop_graphs, get_num_unique_users_under_level_4)
def get_prop_graphs_max_breadth(prop_graphs, edge_type=RETWEET_EDGE):
return get_sample_feature_value(prop_graphs, get_breadth_at_each_level)
def get_prop_graphs_fraction_of_cascades_with_replies(prop_graphs, edge_type=RETWEET_EDGE):
return get_sample_feature_value(prop_graphs, get_fraction_of_cascades_with_replies)
def get_prop_graphs_fraction_of_bot_users_retweeting(prop_graphs: tweet_node, edge_type=None):
return get_sample_feature_value(prop_graphs, get_fraction_of_bot_users_retweeting)
def get_prop_graphs_num_bot_users_retweeting(prop_graphs: tweet_node, edge_type=None):
global user_id_bot_score_dict
return get_sample_feature_value(prop_graphs, get_num_bot_users)
def get_prop_graphs_ratio_of_retweet_to_reply(prop_graphs, edge_type=None):
return get_sample_feature_value(prop_graphs, get_ratio_of_retweet_to_reply)
def get_prop_graphs_num_user_retweet_and_reply(prop_graphs, edge_type=None):
return get_sample_feature_value(prop_graphs, get_num_user_retweet_and_reply)
def get_prop_graphs_num_of_cascades_with_retweets(prop_graphs, edge_type=RETWEET_EDGE):
return get_sample_feature_value(prop_graphs, get_num_of_cascades_with_retweets)