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 = TCNNConfig()
config.num_classes = num_classes
config.vocab_size = len(word_to_id)
model = TextCNN(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 = str(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
base_dir = 'data/' + data_dir + '/' + t_name
classes = sys.argv[5].split('-')
train_dir = os.path.join(base_dir, 'train.csv')
test_dir = os.path.join(base_dir, 'test.csv')
val_dir = os.path.join(base_dir, 'dev.csv')
vocab_dir = os.path.join('data/data_orginal/' + t_name, 'vocab.csv')
if not os.path.exists(vocab_dir): # 如果不存在词汇表，重建
print(' vocab_dir not exists: ', vocab_dir)
build_vocab('data/data_orginal/' + t_name + '/whole.csv',
vocab_dir, config.vocab_size)
categories, cat_to_id = read_category(classes)
words, word_to_id = read_vocab(vocab_dir)
config.vocab_size = len(words)
config.num_classes = len(classes)
mode_name = 'textcnn'
save_dir = 'checkpoints/' + t_name + '/' + mode_name + '_' + t_name + "_" + data_dir + '_' + t_th + 'th'
save_path = os.path.join(save_dir, 'best_validation') # 最佳验证结果保存路径
model = TextCNN(config)
if sys.argv[1] == 'train':
train()
else:
test()
else:
print(
'usage: parameters are less than 4: python file, number of running the task, task name'
)
# 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_cnn.py [train / test]""")
print('Configuring CNN model...')
config = TCNNConfig()
print('CNN config:', config)
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(problem)
print('categories:', categories)
words, word_to_id = read_vocab(vocab_dir)
config.vocab_size = len(words)
config.num_classes = len(categories)
model = TextCNN(config)
if sys.argv[1] == 'train':
train()
else:
test()
if __name__ == '__main__':
# predict(); exit()
# if len(sys.argv) != 2 or sys.argv[1] not in ['train', 'test']:
# raise ValueError("""usage: python run_cnn.py [train / test / predict]""")
d = 'data/cnews/'
train_dir = d + 'sen_class.train'
test_dir = d + 'sen_class.test'
val_dir = d + 'sen_class.val'
vocab_dir = d + 'sen_class.vocab'
print('Configuring CNN model...')
config = TCNNConfig()
labels = build_vocab(train_dir, test_dir, val_dir, vocab_dir,
config.vocab_size)
config.num_classes = len(labels)
categories, cat_to_id = read_category(labels)
words, word_to_id = read_vocab(vocab_dir)
config.vocab_size = len(words)
model = TextCNN(config)
print('labels: {}, vocabulary size: {}'.format(config.num_classes,
len(words)))
with open(map_path, "wb") as f:
pickle.dump(
[word_to_id, cat_to_id, config.seq_length, config.num_classes], f)
train()
exit()
if sys.argv[1] == 'train':
train()
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): # 如果不存在词汇表，重建
build_vocab(train_dir, vocab_dir, config.vocab_size)
# w2v = get_word_embedding(w2v_path, vocab_dir, config.embedding_dim)
# config.w2v = w2v
# print(w2v)
# print(config.w2v)
categories, cat_to_id = read_category(categories_dir)
id_to_cat = {v: k for k, v in cat_to_id.items()}
words, word_to_id = read_vocab(vocab_dir)
#print('loading word embedding...')
#embeddings = get_embeddings('./datasets/w2v.txt',vocab_dir,word_to_id)
#embeddings = pickle.load(open('./datasets/embeddings.pkl','rb'))
#config.embedding_dim = len(embeddings[0])
config.num_classes = len(cat_to_id)
config.vocab_size = len(words)
config.is_w2v = False
#config.w2v = embeddings
model = TextCNN(config)
if sys.argv[1] == 'train':
train()
else:
test()
