save_path = os.path.join(save_dir, 'best_validation') # 最佳验证结果保存路径
# tf.reset_default_graph()
print('Configuring CNN model...')
config = TCNNConfig()
if not os.path.exists(vocab_dir): # 如果不存在词汇表，重建
print("no vocabulary file, need to generate it ")
generate_w2v()
# categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
config.vocab_size = len(words)
# trans vector file to numpy file
if not os.path.exists(word_vector_dir):
print("no pretrained w2v exists, generate the w2v")
generate_w2v()
else:
print("load w2v embeddings")
config.pre_training = pd.read_csv(word_vector_dir,
header=None,
index_col=None).values
model = TextCNN(config)
if sys.argv[1] == 'train' and len(sys.argv) == 3:
train(filename=sys.argv[2])
elif sys.argv[1] == 'train' and len(sys.argv) == 2:
train()
elif sys.argv[1] == 'test':
test()
else:
raise ValueError(
"""usage: python run_cnn.py [train / test] [train/test file]""")
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 CNN model...')
config = TCNNConfig()
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)
config.pre_training = np.load(pre_training)
model = TextCNN(config)
if sys.argv[1] == 'train':
train()
else:
test()
