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,
length,
H,
L,
L_hat,
n_graphs,
n_pos,
n_neg,
pos_index,
class_index,
neg_index,
graph_id_to_list_id,
mapper=id_to_uri,
labels=labels_mapping,
model=m,
constraints=cons,
)
# for p in pattern_set:
# if p not in pattern_set_global:
# pattern_set_global.append(p)
# if m == "top-k":
# break
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)
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)
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) 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)