def predict():
with open(map_path, "rb") as f:
word_to_id, cat_to_id, seq_length, num_classes = pickle.load(f)
id_to_cat = {v: k for k, v in cat_to_id.items()}
config = TRNNConfig()
config.num_classes = num_classes
config.vocab_size = len(word_to_id)
model = TextRNN(config)
session = tf.Session()
session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=session, save_path=save_path) # 读取保存的模型
while True:
line = input("请输入测试句子:")
data_id = [[
word_to_id[x] for x in list(native_content(line))
if x in word_to_id
]]
x_pad = kr.preprocessing.sequence.pad_sequences(data_id, seq_length)
y_pred_cls = session.run(model.y_pred_cls,
feed_dict={
model.input_x: x_pad,
model.keep_prob: 1.0
})
print('sentence : {}, prdict intent : {}'.format(
line, id_to_cat[y_pred_cls[0]]))
a = 1
# 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()
# 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()
for f in F1:
print('\t'.join(['%0.1f'%f[0],str(f[2]),str(f[3]),str(f[4]),str(f[5])]))
return auc,F1
if __name__ == '__main__':
tf.reset_default_graph()
base_dir = sys.argv[1]
save_dir = sys.argv[2]
ckpt_dir = sys.argv[3]
train_dir = os.path.join(base_dir, 'train.txt')
test_dir = os.path.join(base_dir, 'test.txt')
val_dir = os.path.join(base_dir, 'val.txt')
vocab_dir = os.path.join(base_dir, 'vocab.txt')
predict_dir = os.path.join(base_dir, 'predict.txt')
save_path = os.path.join(save_dir, 'best_validation') # 最佳验证结果保存路径
if len(sys.argv)>4:
option = sys.argv[4]
else:
option = 'train'
print('Configuring RNN model...')
config = TRNNConfig()
tokenizer = Tokenizer(vocab_dir)
config.vocab_size = len(tokenizer.vocab)
model = TextRNN(config)
print('参数总量：%d'%np.sum([np.prod(v.get_shape().as_list()) for v in tf.trainable_variables()]))
if option == 'train':
iter = batch_iter(train_dir, tokenizer, epochs=config.num_epochs)
iter_test = batch_iter_test(val_dir, tokenizer)
train()
else:
test()
