word_vecs_rand, word_vecs, word_cab, sentence_max_len, revs = X[0], X[
1], X[2], X[3], X[4]
print('load data finish. . .')
# configuration tf
filter_sizes = [3, 4, 5]
filter_numbers = 100
embedding_size = 300
# use word2vec or not
W = word_vecs_rand
if args.wordvec_flag:
W = word_vecs
pass
# pdb.set_trace()
word_ids, W_list = process_data.getWordsVect(W)
# use static train or not
static_falg = args.static_flag
# use shuffer the data or not
shuffer_falg = args.shuffer_flag
#交叉验证
results = []
for index in tqdm(range(10)):
#打调试断点
# pdb.set_trace()
# train_x, train_y, test_x, test_y = process_data.get_train_test_data1(W,revs,index,sentence_max_len,default_values=0.0,vec_size=300)
train_x, train_y, test_x, test_y = process_data.get_train_test_data2(
word_ids, revs, index, sentence_max_len)
# step3 create TextCNN model
text_cnn = TextCNN(W_list, shuffer_falg, static_falg, filter_numbers,
# 混淆矩阵
print("Confusion Matrix...")
cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
print(cm)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
if __name__ == '__main__':
if len(sys.argv) != 2 or sys.argv[1] not in ['train', 'test']:
raise ValueError("""usage: python run_rnn.py [train / test]""")
print('Configuring RNN model...')
print('load data. . .')
X = pickle.load(open(train_data, 'rb'))
df, word_vecs, word_cab_num, sentence_max_len, class_num = X[0], X[1], X[2], X[3], X[4]
config = TRNNConfig(sentence_max_len, class_num, word_cab_num)
word_ids, W_list = process_data.getWordsVect(config, word_vecs)
model = TextRNN(config, W_list, False) #默认不训练词向量
if sys.argv[1] == 'train':
train()
else:
test()