parser = argparse.ArgumentParser()
parser.add_argument('-content_file', help='The path to the content file.')
parser.add_argument('-cites_file', help='The path to the cites file.')
parser.add_argument('-classifier',
default='sklearn.naive_bayes.MultinomialNB',
help='The underlying classifier.')
parser.add_argument('-num_folds',
type=int,
default=10,
help='The number of folds.')
args = parser.parse_args()
graph, domain_labels = load_linqs_data(args.content_file, args.cites_file)
kf = KFold(n=len(graph.node_list),
n_folds=args.num_folds,
shuffle=True,
random_state=42)
accuracies = []
cm = None
for train, test in kf:
clf = LocalClassifier(args.classifier)
clf.fit(graph, train)
y_pred = clf.predict(graph, test)
y_true = [graph.node_list[t].label for t in test]
print 'Cites File: %s' % args.cites_file
print 'Aggregator: %s' %args.aggregate
if(args.directed):
Dir='Directed'
else:
Dir='Undirected'
print 'Directed : %s' %Dir
if(args.dont_use_node_attributes):
Att='Without Node attributes'
else:
Att='With Node Attributes'
print 'Attributes: %s' %Att
print 'classifier:%s' %args.classifier
graph, domain_labels = load_linqs_data(args.content_file, args.cites_file)
#budget=[0.1, 0.2, 0.3, 0.4, 0.6, 0.7, 0.8, 0.9]
budget=[0.8]
n=range(len(graph.node_list))
ica_accuracies = defaultdict(list)
for t in range(args.num_trials):
for b in budget:
train, test = train_test_split(n, train_size=b, random_state=t)
# True labels
y_true=[graph.node_list[t].label for t in test]
local_clf=LocalClassifier(args.classifier)