def fungo_test_wrapper(name='cellcycle_FUN'):
X_train, X_test, train_ids, test_ids, id2doc, nodes = read_fungo(name)
X_train, X_test = np.array(X_train), np.array(X_test)
id2doc_train = id2doc
args = conf()
# id2doc_train = filter_ancestors(id2doc, nodes)
tree = Tree(args, train_ids, test_ids, id2doc=id2doc_train, id2doc_a=id2doc, nodes=nodes, rootname='Top')
mlb = MultiLabelBinarizer(classes=tree.class_idx)
Y_train = mlb.fit_transform([tree.id2doc_ancestors[docid]['class_idx'] for docid in train_ids])
Y_test = mlb.transform([tree.id2doc_ancestors[docid]['class_idx'] for docid in test_ids])
return X_train, Y_train, X_test, Y_test
def fungo_test(data_name):
X_train, X_test, train_ids, test_ids, id2doc, nodes = read_fungo(data_name)
Y_train = [id2doc[bid]['categories'] for bid in train_ids]
Y_test = [id2doc[bid]['categories'] for bid in test_ids]
# Actually here Y is not used. We use id2doc for labels.
mlb = MultiLabelBinarizer()
Y = mlb.fit_transform(np.concatenate([Y_train, Y_test]))
Y_train = Y[:len(Y_train)]
Y_test = Y[-len(Y_test):]
return X_train, Y_train, X_test, Y_test, train_ids, test_ids
save_minibatch(logger,
args,
word_index,
X_test,
test_ids,
32,
name='test_nyt')
tree = Tree(args,
train_ids,
test_ids,
id2doc=id2doc_train,
id2doc_a=id2doc,
nodes=nodes,
rootname='Top')
elif 'FUN' in args.dataset or 'GO' in args.dataset:
X_train, _, train_ids, test_ids, id2doc, nodes = read_fungo(args.dataset)
if args.filter_ancestors:
id2doc_train = filter_ancestors(id2doc, nodes)
else:
id2doc_train = id2doc
tree = Tree(args,
train_ids,
test_ids,
id2doc=id2doc_train,
id2doc_a=id2doc,
nodes=nodes,
rootname='Top')
else:
logger.error('No such dataset: {}'.format(args.dataset))
exit(1)
if args.stat_check: