import sys
import os
import fileio
import gspan
if __name__ == '__main__':
print 'Database: ', sys.argv[1]
database = fileio.read_file(sys.argv[1])
print 'Number Graphs Read: ', len(database)
print 'Support: ', sys.argv[2],
minsup = int((float(sys.argv[2]) * len(database)))
print minsup
database, freq, trimmed, flabels = gspan.trim_infrequent_nodes(
database, minsup)
database = fileio.read_file(sys.argv[1], frequent=freq)
print 'Trimmed ', len(trimmed), ' labels from the database'
print flabels
gspan.project(database, freq, minsup, flabels)
else:
cons = (ml_cons, cl_cons[: num_constraints - len_ml_cons])
for m in model:
for length in [5]:
scores = {names[0]: [], names[1]: [], names[2]: []}
times = []
for k in xrange(0, k_fold):
train_file = output_file_train + str(k) + ".txt"
test_file = output_file_test + str(k) + ".txt"
database_train = fileio.read_file(train_file)
print "Number Graphs Read: ", len(database_train)
minsup = int((float(min_sup) * len(database_train)))
print minsup
database_train, freq, trimmed, flabels = gspan.trim_infrequent_nodes(database_train, minsup)
database_train = fileio.read_file(train_file, frequent=freq)
train_labels = np.array(graph_labels_train[k])
tik = datetime.utcnow()
pattern_set_global = []
class_index = 1
# for class_index in xrange(num_classes):
H, L, L_hat, n_graphs, n_pos, n_neg, pos_index, neg_index, graph_id_to_list_id = fileio.preproscessing(
database_train, class_index, labels_mapping, m
)
X_train, pattern_set_global = gspan.project(
database_train,
freq,
minsup,
flabels,
def Gspan(support): database = fileio.read_file(r"database.txt") minsup = int((float(support)*len(database))) database, freq, trimmed, flabels = gspan.trim_infrequent_nodes(database, minsup) database = fileio.read_file(r"database.txt", frequent = freq) gspan.project(database, freq, minsup, flabels)
