def preprocess_feature_data(dataset, raw_data_folder, preprocessed_data_folder, feature_raw_data_file, number_of_nodes):
source_file_path = raw_data_folder + "/" + dataset + "-" + feature_raw_data_file + ".mtx"
target_file_path = preprocessed_data_folder + "/" + feature_raw_data_file + ".tsv"
matrix = read_feature_raw_data_file(source_file_path, number_of_nodes)
scipy_sparse_to_csv(target_file_path, matrix, separator="\t", directed=True, numbering="matlab")
def make_labelling(dataset, raw_data_folder, preprocessed_data_folder):
node_file_path = raw_data_folder + "/" + dataset + ".ids"
file_row_gen = get_file_row_generator(node_file_path, " ")
user_twitter_id_list = list()
for file_row in file_row_gen:
if file_row[0] == "":
break
else:
user_twitter_id_list.append(int(file_row[0]))
id_to_node = dict(zip(user_twitter_id_list, range(len(user_twitter_id_list))))
user_twitter_id_list = set(user_twitter_id_list)
core_file_path = raw_data_folder + "/" + dataset + ".communities"
file_row_gen = get_file_row_generator(core_file_path, ",")
row = list()
col = list()
category_counter = 0
for file_row in file_row_gen:
id_list = list()
first_id = file_row[0].strip().split(" ")
first_id = id_to_node[int(first_id[1])]
id_list.append(first_id)
for id in file_row[1:]:
id_list.append(id_to_node[int(id)])
row.extend(id_list)
col.extend(category_counter*np.ones(len(id_list), dtype=np.int32))
category_counter += 1
row = np.array(row, dtype=np.int32)
col = np.array(col, dtype=np.int32)
data = np.ones_like(row, dtype=np.int8)
node_label_matrix = spsp.coo_matrix((data, (row, col)), shape=(len(user_twitter_id_list), category_counter))
target_path = preprocessed_data_folder + "/" + "node_label_matrix" + ".tsv"
scipy_sparse_to_csv(target_path, node_label_matrix, separator="\t", directed=True, numbering="matlab")
def make_labelling(dataset, raw_data_folder, preprocessed_data_folder):
node_file_path = raw_data_folder + "/" + dataset + ".ids"
file_row_gen = get_file_row_generator(node_file_path, " ")
user_twitter_id_list = list()
for file_row in file_row_gen:
if file_row[0] == "":
break
else:
user_twitter_id_list.append(int(file_row[0]))
id_to_node = dict(zip(user_twitter_id_list, range(len(user_twitter_id_list))))
user_twitter_id_list = set(user_twitter_id_list)
core_file_path = raw_data_folder + "/" + dataset + ".core"
file_row_gen = get_file_row_generator(core_file_path, " ")
core_user_twitter_id_list = list()
for file_row in file_row_gen:
if file_row[0] == "":
break
else:
core_user_twitter_id_list.append(int(file_row[0]))
core_user_twitter_id_list = user_twitter_id_list.intersection(core_user_twitter_id_list)
non_core_user_twitter_id_set = user_twitter_id_list.difference(core_user_twitter_id_list)
row = [id_to_node[id] for id in core_user_twitter_id_list] + [id_to_node[id] for id in non_core_user_twitter_id_set]
row = np.array(row, dtype=np.int32)
col = [1 for id in core_user_twitter_id_list] + [0 for id in non_core_user_twitter_id_set]
col = np.array(col, dtype=np.int32)
data = np.ones(len(user_twitter_id_list), dtype=np.int8)
node_label_matrix = spsp.coo_matrix((data, (row, col)), shape=(len(user_twitter_id_list), 2))
target_path = preprocessed_data_folder + "/" + "node_label_matrix" + ".tsv"
scipy_sparse_to_csv(target_path, node_label_matrix, separator="\t", directed=True, numbering="matlab")
def make_implicit_graphs(preprocessed_data_folder, simple_undirected_implicit_graph_folder):
####################################################################################################################
# Read graphs.
####################################################################################################################
# Read follow graph.
source_path = preprocessed_data_folder + "/" + "followedby" + ".tsv"
follow_graph = read_adjacency_matrix(source_path, "\t", "matlab")
follow_graph = follow_graph.transpose()
# Read mention graph.
source_path = preprocessed_data_folder + "/" + "mentionedby" + ".tsv"
mention_graph = read_adjacency_matrix(source_path, "\t", "matlab")
mention_graph = mention_graph.transpose()
# Read retweet graph.
source_path = preprocessed_data_folder + "/" + "retweetedby" + ".tsv"
retweet_graph = read_adjacency_matrix(source_path, "\t", "matlab")
retweet_graph = retweet_graph.transpose()
####################################################################################################################
# Simple undirected implicit graphs.
####################################################################################################################
target_path = simple_undirected_implicit_graph_folder + "/" + "follow_graph" + ".tsv"
simple_undirected_follow_graph = (follow_graph + follow_graph.transpose())/2
scipy_sparse_to_csv(target_path, simple_undirected_follow_graph, separator="\t", directed=False, numbering="matlab")
target_path = simple_undirected_implicit_graph_folder + "/" + "mention_graph" + ".tsv"
simple_undirected_mention_graph = (mention_graph + mention_graph.transpose())/2
scipy_sparse_to_csv(target_path, simple_undirected_mention_graph, separator="\t", directed=False, numbering="matlab")
target_path = simple_undirected_implicit_graph_folder + "/" + "retweet_graph" + ".tsv"
simple_undirected_retweet_graph = (retweet_graph + retweet_graph.transpose())/2
scipy_sparse_to_csv(target_path, simple_undirected_retweet_graph, separator="\t", directed=False, numbering="matlab")
gc.collect()
####################################################################################################################
# Multiview graphs.
####################################################################################################################
target_path = simple_undirected_implicit_graph_folder + "/" + "fol_men_graph" + ".tsv"
simple_undirected_fol_men_graph = (follow_graph + follow_graph.transpose() +
mention_graph + mention_graph.transpose())/4
scipy_sparse_to_csv(target_path, simple_undirected_fol_men_graph, separator="\t", directed=False, numbering="matlab")
target_path = simple_undirected_implicit_graph_folder + "/" + "men_ret_graph" + ".tsv"
simple_undirected_men_ret_graph = (mention_graph + mention_graph.transpose() +
retweet_graph + retweet_graph.transpose())/4
scipy_sparse_to_csv(target_path, simple_undirected_men_ret_graph, separator="\t", directed=False, numbering="matlab")
target_path = simple_undirected_implicit_graph_folder + "/" + "fol_ret_graph" + ".tsv"
simple_undirected_fol_ret_graph = (follow_graph + follow_graph.transpose() +
retweet_graph + retweet_graph.transpose())/4
scipy_sparse_to_csv(target_path, simple_undirected_fol_ret_graph, separator="\t", directed=False, numbering="matlab")
target_path = simple_undirected_implicit_graph_folder + "/" + "fol_men_ret_graph" + ".tsv"
simple_undirected_fol_men_ret_graph = (follow_graph + follow_graph.transpose() +
mention_graph + mention_graph.transpose() +
retweet_graph + retweet_graph.transpose())/6
scipy_sparse_to_csv(target_path, simple_undirected_fol_men_ret_graph, separator="\t", directed=False, numbering="matlab")
