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]
accuracies.append(accuracy_score(y_true, y_pred))
if cm is None:
cm = confusion_matrix(y_true, y_pred, labels=domain_labels)
else:
cm += confusion_matrix(y_true, y_pred, labels=domain_labels)
print accuracies
print "Mean accuracy: %0.4f +- %0.4f" % (np.mean(accuracies),
np.std(accuracies))
print cm
conditional_map = {}
X = []
for a in train_indices:
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]
accuracies.append(accuracy_score(y_true, y_pred))
if cm is None:
cm = confusion_matrix(y_true, y_pred, labels = list(domain_labels))
else:
cm += confusion_matrix(y_true, y_pred, labels = list(domain_labels))
print accuracies
print "Mean accuracy: %0.4f +- %0.4f" % (np.mean(accuracies), np.std(accuracies))
print cm
if not args.dont_evaluate_local:
local_accuracies = defaultdict(list)
relational_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]
if not args.dont_evaluate_local:
# local classifier fit and test
local_clf = LocalClassifier(args.classifier)
local_clf.fit(graph, train)
local_y_pred = local_clf.predict(graph, test)
local_accuracy = accuracy_score(y_true, local_y_pred)
local_accuracies[b].append(local_accuracy)
# relational classifier fit and test
agg = pick_aggregator(args.aggregate, domain_labels, args.directed)
relational_clf = RelationalClassifier(
args.classifier, agg, not args.dont_use_node_attributes)
relational_clf.fit(graph, train)
conditional_node_to_label_map = create_map(graph, train)
relational_y_pred = relational_clf.predict(
graph, test, conditional_node_to_label_map)
relational_accuracy = accuracy_score(y_true, relational_y_pred)
relational_accuracies[b].append(relational_accuracy)
if not args.dont_evaluate_local:
local_accuracies = defaultdict(list)
relational_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]
if not args.dont_evaluate_local:
# local classifier fit and test
local_clf=LocalClassifier(args.classifier)
local_clf.fit(graph,train)
local_y_pred=local_clf.predict(graph,test)
local_accuracy=accuracy_score(y_true, local_y_pred)
local_accuracies[b].append(local_accuracy)
# relational classifier fit and test
agg=pick_aggregator(args.aggregate,domain_labels,args.directed)
relational_clf=RelationalClassifier(args.classifier, agg, not args.dont_use_node_attributes)
relational_clf.fit(graph,train)
conditional_node_to_label_map=create_map(graph,train)
relational_y_pred=relational_clf.predict(graph,test,conditional_node_to_label_map)
relational_accuracy=accuracy_score(y_true,relational_y_pred)
relational_accuracies[b].append(relational_accuracy)
