print(
metrics.classification_report(y_test_cls,
y_pred_cls,
target_names=categories))
# 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...')
config = TRNNConfig()
if not os.path.exists(vocab_dir):
build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
config.vocab_size = len(words)
model = TextRNN(config)
if sys.argv[1] == 'train':
train()
else:
test()
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_cnn.py [train / test]""")
print('Configuring CNN model...')
config = TCNNConfig()
if not os.path.exists(vocab_dir_c): # 如果不存在字表，重建
data_loader.build_vocab(train_dir, vocab_dir_c, config.vocab_size_c)
if not os.path.exists(vocab_dir_w): # 如果不存在词汇表，重建
data_loader_wordlevel.build_vocab(train_dir, vocab_dir_w,
config.vocab_size_w)
categories, cat_to_id = data_loader.read_category()
characters, character_to_id = data_loader.read_vocab(vocab_dir_c)
words, word_to_id = data_loader_wordlevel.read_vocab(vocab_dir_w)
config.vocab_size_c = len(characters)
config.vocab_size_w = len(words)
# max_train = data_loader.get_maxlength(train_dir)
# max_val = data_loader.get_maxlength(val_dir)
# # 用所有集合中最大的序列长度
# temp_val = max(max_train, max_val)
# # 如果有的集合中序列长度超过了1014，就还是用1014吧
# print("最长长度： %i" % temp_val)
# # config.seq_length = min(temp_val, 1500)
def init_vocab(config):
if not os.path.exists(config.vocab_dir): # 如果不存在词汇表，重建
print('build vocabulary')
build_vocab(config.train_dir, config.vocab_dir, config.vocab_size)
config.words, config.word_to_id = read_vocab(config.vocab_dir)
config.vocab_size = len(config.words)
# save_file_stratified('data/qwdata/shuffle-try3/classified_table_ms.txt', 'data/qwdata/ms-ygscplusssdqw-clean',categories)
# print(len(open('data/betadata2-711depart/train.txt', 'r', encoding='utf-8').readlines()))
# print(len(open('data/betadata2-711depart/val.txt', 'r', encoding='utf-8').readlines()))
# print(len(open('data/betadata2-711depart/test.txt', 'r', encoding='utf-8').readlines()))
# write_files_together(ms_file_path='data\\qwdata\\ms-ssd',
# ms_label='data\\qwdata\\classifier_ms.csv',
# xs_file_path='data\\qwdata\\new-xs-zkss-ajjbkq',
# xs_label='data\\qwdata\\classifier_xs.csv')
config = TCNNConfig()
config.vocab_size_w = 200000
config.vocab_size_c = 200000
if not os.path.exists(vocab_dir_c): # 如果不存在字表，重建
data_loader.build_vocab(all_data_dir, vocab_dir_c, config.vocab_size_c)
if not os.path.exists(vocab_dir_w): # 如果不存在词汇表，重建
data_loader_wordlevel.build_vocab(all_data_dir, vocab_dir_w, config.vocab_size_w)
# categories, cat_to_id = data_loader.read_category()
# characters, character_to_id = data_loader.read_vocab(vocab_dir_c)
# words, word_to_id = data_loader_wordlevel.read_vocab(vocab_dir_w)
# config.vocab_size_c = len(characters)
# config.vocab_size_w = len(words)
#
# config.seq_length_c = 1500
# config.seq_length_w = 800
# data_convert()
# stratified_cross('data\\10-fold-original-data\\data-convert',
