feed_dict=feed_dict)
# 评估
print("Precision, Recall and F1-Score...")
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__':
print('Configuring CNN model...')
if not os.path.exists(vocab_dir): # 如果不存在词汇表，重建
build_vocab(train_dir, vocab_dir, args.VOCAB_SIZE)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
args.VOCAB_SIZE = len(words)
model = TextCNN(args)
if args.DO_TRAIN:
train()
if args.DO_TEST:
test()
# 评估
print("Precision, Recall and F1-Score...")
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): # 如果不存在词汇表，重建
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()
val_dir = os.path.join(base_dir, 'cnewsval.txt')
vocab_dir = os.path.join(base_dir, 'cnewsvocab.txt')
vector_word_dir= os.path.join(base_dir, 'vector_word.txt')#vector_word trained by word2vec
vector_word_npz=os.path.join(base_dir, 'vector_word.npz')# save vector_word to numpy file
#最佳验证结果保存路径
save_dir = 'HOME\mydata\lstm\checkpoints'
save_path = os.path.join(save_dir, 'best_validation')
#获取词典
'''build_vocab(train_dir,vocab_dir)
_,word_to_id=read_vocab(vocab_dir)
categories,cat_to_id=read_category()
config=TRNNConfig()
model=TextRNN(config)'''
config=TRNNConfig()
build_vocab(train_dir,vocab_dir)
words,word_to_id=read_vocab(vocab_dir)
categories,cat_to_id=read_category()
config.vocab_size = len(words)
if not os.path.exists(vector_word_npz):
export_word2vec_vectors(word_to_id, vector_word_dir, vector_word_npz)
config.pre_trianing = get_training_word2vec_vectors(vector_word_npz)
model=TextRNN(config)
init=tf.global_variables_initializer()
def get_time_dif(start_time):
"""获取已使用时间"""
end_time = time.time()
time_dif = end_time - start_time
return timedelta(seconds=int(round(time_dif)))
