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
def __init__(self):
self.config = TRNNConfig()
self.categories, self.cat_to_id = read_category()
self.words, self.word_to_id = read_vocab(vocab_dir)
self.config.vocab_size = len(self.words)
self.model = TextRNN(self.config)
self.session = tf.Session()
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=self.session, save_path=save_path) # 读取保存的模型
def __init__(self):
self.config = TRNNConfig()
self.categories, self.cat_to_id = read_category()
self.words = np.load('./datas/dict_token.npy')
self.word_to_id = np.load('./datas/token_to_id.npy').tolist()
self.config.vocab_size = len(self.words)
self.model = TextRNN(self.config)
self.session = tf.Session()
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=self.session, save_path=save_path) # 读取保存的模型
def __init__(self):
self.config = TRNNConfig()
self.categories = categories
self.cat_to_id = cat_to_id
self.words = words
self.word_to_id = word_to_id
self.config.vocab_size = len(self.words)
self.model = TextRNN(self.config)
self.session = sess
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=self.session, save_path=rnn_save_path) # 读取保存的模型
def read_example(filename_queue):
"""Read one example from filename_queue"""
config = TRNNConfig()
reader = tf.TFRecordReader()
key, value = reader.read(filename_queue)
features = tf.parse_single_example(value, features={"title_len": tf.FixedLenFeature([1], tf.int64),
"title": tf.FixedLenFeature([config.seq_length], tf.int64),
"label": tf.FixedLenFeature([config.seq_length], tf.float32),
"frame_weight": tf.FixedLenFeature([config.seq_length], tf.float32),
})
title_len = tf.cast(features["title_len"], tf.int32)
title = tf.cast(features["title"], tf.int32)
label = tf.cast(features["label"], tf.float32)
frame_weight = tf.cast(features["frame_weight"], tf.float32)
return title_len, title, label, frame_weight
def __init__(self):
with open(map_path, "rb") as f:
self.word_to_id, self.cat_to_id, self.seq_length, self.num_classes = pickle.load(
f)
self.id_to_cat = {v: k for k, v in self.cat_to_id.items()}
if model_type == 'cnn':
self.config = TCNNConfig()
self.config.num_classes = self.num_classes
self.config.vocab_size = len(self.word_to_id)
self.model = TextCNN(self.config)
else:
self.config = TRNNConfig()
self.config.num_classes = self.num_classes
self.config.vocab_size = len(self.word_to_id)
self.model = TextRNN(self.config)
self.session = tf.Session()
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=self.session, save_path=save_path) # 读取保存的模型
def load_model(self):
sess = tf.Session()
print('Configuring CNN model...')
config = TRNNConfig()
cnn_model = TextRNN(config)
saver = tf.train.Saver()
params_file = tf.train.latest_checkpoint(self.model_dir)
saver.restore(sess, params_file)
categories, cat_to_id = read_category()
vocab_dir = 'cnews/cnews.vocab.txt'
words, word_to_id = read_vocab(vocab_dir)
self.words = words
self.word_to_id = word_to_id
self.categories = categories
self.cat_to_id = cat_to_id
self.cnn_model = cnn_model
self.sess = sess
print(self.cnn_model)
print(self.sess)
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]""")
conn = pymysql.connect(host='localhost',
user='******',
passwd='sasa',
db='text_clf',
charset='utf8')
cur = conn.cursor()
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_vec = read_category()
#words, word_to_id = read_vocab(vocab_dir)
#config.vocab_size = len(words)
model = TextRNN(config, get_embedding())
print('training')
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()
test_dir = os.path.join(base_dir, 'cnewstest.txt')
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 = r'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)))
print(cm)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
if __name__ == '__main__':
if len(sys.argv) != 3 or sys.argv[1] not in [
'train', 'test'
] or sys.argv[2] not in ['char', 'word']:
raise ValueError(
"""usage: python run_cnn.py [train / test] [char / word]""")
print('Configuring RNN model...')
if sys.argv[2] == 'char':
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()
else:
print("train on word embedding...")
config = TRNNConfig()
config.seq_length = 400
# 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 RNN model...',sys.argv)
if len(sys.argv) == 6 and sys.argv[1] in ['train', 'test']:
config = TRNNConfig()
t_name = sys.argv[3]
t_th = sys.argv[2]
data_dir = sys.argv[4]
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)
print(len(test_docs))
train_file.close()
test_file = open(rnn.test_dir, 'w')
for test_doc in test_docs:
temp = test_doc.split(',')
test_data_X.append(corpus[int(temp[0]) - 1])
test_data_Y.append(temp[1])
string = corpus[int(temp[0]) - 1].replace('\n',
'').replace('\t', '')
test_file.write(temp[1] + '\t' + string + '\n')
print('Configuring RNN model...')
test_file.close()
rnn.config = TRNNConfig()
#if not os.path.exists(rnn.vocab_dir): #if no vocab, build it
build_vocab_words(rnn.train_dir, rnn.vocab_dir, rnn.config.vocab_size)
rnn.categories, rnn.cat_to_id, rnn.id_to_cat = read_category()
rnn.words, rnn.word_to_id = read_vocab(rnn.vocab_dir)
rnn.config.vocab_size = len(rnn.words)
#select a subset of word vectors
rnn.missing_dir = os.path.join(rnn.base_dir,
key + '.' + sub_key + '.missing.txt')
missing_words_file = open(rnn.missing_dir, 'w')
sub_embeddings = np.random.uniform(
-0.0, 0.0, (rnn.config.vocab_size, embedding_dim))
count = 0
for i in range(0, rnn.config.vocab_size):
if (rnn.words[i] in word_vector_map
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()
# 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()
# 构建英文和中文的词表、字表
if not os.path.exists(vocab_cn): # 中文词汇表2370个，重建
# 中文是分好词的，我需要把他处理成一个一个的字
build_vocab(train_cnx, vocab_cn, config.vocab_size)
if not os.path.exists(vocab_en): # 英文词汇表5000个，重建
build_vocab(train_eny, vocab_en, config.vocab_size)
# 开始映射words to id
words_cn, word_to_id_cn = read_vocab(vocab_cn)
words_en, word_to_id_en = read_vocab(vocab_en)
config.vocab_size_cn = len(words_cn)
config.vocab_size_en = len(words_en)
def test():
print('Configuring RNN model...')
config = TRNNConfig()
config.dropout_keep_prob = 1.0
config.num_epochs = 1
start_time = time.time()
config.batch_size = 10
count = 0
# 配置GPU内存分配方式
tfconfig = tf.ConfigProto(log_device_placement=True)
tfconfig.gpu_options.allow_growth = True
tfconfig.gpu_options.per_process_gpu_memory_fraction = 0.6
fw = file(config.test_dir_output, "w")
with tf.Graph().as_default(), tf.Session(config=tfconfig) as sess:
test_dir_list = os.listdir(config.test_dir_tf)
test_dir_list = [
os.path.join(config.test_dir_tf, i) for i in test_dir_list
]
queueTest = tf.train.string_input_producer(
test_dir_list, num_epochs=config.num_epochs)
text, title_len, title, label, frame_weight = read_example_test(
queueTest)
text_batch, title_len_batch, title_batch, label_batch, frame_weight_batch = tf.train.batch(
[text, title_len, title, label, frame_weight],
batch_size=config.batch_size,
capacity=50000,
num_threads=1)
with tf.variable_scope("model",
initializer=tf.random_uniform_initializer(
-1 * 1, 1)):
model = TextRNN(config=config,
input_x_len=title_len_batch,
input_x=title_batch,
input_y=label_batch,
frame_weight=frame_weight_batch)
fetches = [text_batch, model.input_x_len, model.y_pred, model.input_y]
feed_dict = {}
# init
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
sess.run(init_op)
# 配置 Saver
saver = tf.train.Saver()
saver.restore(sess=sess, save_path=config.modelPath) # 读取保存的模型
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
if not os.path.exists(config.save_dir):
os.makedirs(config.save_dir)
try:
while not coord.should_stop():
texts, x_len, y_pred, y_test = sess.run(fetches,
feed_dict=feed_dict)
texts = "".join(texts.values).split("\n")
for i in range(len(texts) - 1):
score = [str(int(j * 100))
for j in y_test[i]][:x_len[i][0]]
y_test_i = " ".join(score)
score = [str(int(j * 100))
for j in y_pred[i]][:x_len[i][0]]
y_pred_i = " ".join(score)
fw.write(texts[i] + "\ttarget:\t" + y_test_i +
"\tpredict\t" + y_pred_i + "\n")
count = count + 1
if count % 10000 == 0:
print(count)
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
coord.request_stop()
coord.join(threads)
fw.close()
def train():
print('Configuring RNN model...')
config = TRNNConfig()
config.dropout_keep_prob = 1.0
start_time = time.time()
# config.batch_size = 10
total_batch = 0 # 总批次
best_mse_val = 99999999 # 最佳验证集准确率
best_loss_val = 99999999 # 最佳验证集准确率
last_improved = 0 # 记录上一次提升批次
require_improvement = 5000 # 如果超过1000轮未提升，提前结束训练
count = 0
tensorboard_dir = config.tensorboard_dir
# 配置GPU内存分配方式
tfconfig = tf.ConfigProto(log_device_placement=True)
tfconfig.gpu_options.allow_growth = True
tfconfig.gpu_options.per_process_gpu_memory_fraction = 0.6
with tf.Graph().as_default(), tf.Session(config=tfconfig) as sess:
train_dir_list = os.listdir(config.train_dir_tf)
train_dir_list = [
os.path.join(config.train_dir_tf, i) for i in train_dir_list
]
queueTrain = tf.train.string_input_producer(
train_dir_list, num_epochs=config.num_epochs)
title_len, title, label, frame_weight = read_example(queueTrain)
title_len_batch, title_batch, label_batch, frame_weight_batch = tf.train.batch(
[title_len, title, label, frame_weight],
batch_size=config.batch_size,
capacity=100000,
num_threads=1)
with tf.variable_scope("model",
initializer=tf.random_uniform_initializer(
-1 * 1, 1)):
model = TextRNN(config=config,
input_x_len=title_len_batch,
input_x=title_batch,
input_y=label_batch,
frame_weight=frame_weight_batch)
tf.summary.scalar("loss", model.loss)
tf.summary.scalar("mse", model.mse)
merged_summary = tf.summary.merge_all()
writer = tf.summary.FileWriter(tensorboard_dir, sess.graph)
fetches = [model.loss, model.mse]
feed_dict = {}
# init
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
sess.run(init_op)
# 配置 Saver
saver = tf.train.Saver(write_version=saver_pb2.SaverDef.V1)
if not config.retraining:
saver.restore(sess=sess, save_path=config.modelPath) # 读取保存的模型
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
if not os.path.exists(config.save_dir):
os.makedirs(config.save_dir)
try:
while not coord.should_stop():
# Run training steps or whatever
# titles, labels = sess.run([title_batch, label_batch])
if total_batch % config.save_per_batch == 0:
# 每多少轮次将训练结果写入tensorboard scalar
s = sess.run(merged_summary, feed_dict)
writer.add_summary(s, total_batch)
if total_batch % config.print_per_batch == 0:
# 每多少轮次输出在训练集和验证集上的性能
loss_val, mse_val = sess.run(fetches, feed_dict)
if mse_val < best_mse_val or loss_val < best_loss_val:
# 保存最好结果
best_mse_val = mse_val
best_loss_val = loss_val
last_improved = total_batch
improved_str = '*'
# saver.save(sess=sess, save_path=config.save_path)
if total_batch % config.save_per_batch == 0:
saver.save(sess,
config.save_path + '_%03d' %
(total_batch / config.save_per_batch),
write_meta_graph=False)
else:
improved_str = ''
time_dif = get_time_dif(start_time)
msg = 'Iter: {0:>6}, Val Loss: {1:>6.5}, Mse: {2:>6.5}, Time: {3} {4}'
print(
msg.format(total_batch, loss_val, mse_val, time_dif,
improved_str))
# print(embedding_inputs)
sess.run(model.optim, feed_dict)
total_batch += 1
if total_batch - last_improved > require_improvement:
# 验证集正确率长期不提升，提前结束训练
print("No optimization for a long time, auto-stopping...")
coord.should_stop()
break # 跳出循环
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
coord.request_stop()
coord.join(threads)
# 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()
# 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...')
print('load data. . .')
X = pickle.load(open(train_data, 'rb'))
df, word_vecs, word_cab_num, sentence_max_len, class_num = X[0], X[1], X[2], X[3], X[4]
config = TRNNConfig(sentence_max_len, class_num, word_cab_num)
word_ids, W_list = process_data.getWordsVect(config, word_vecs)
model = TextRNN(config, W_list, False) #默认不训练词向量
if sys.argv[1] == 'train':
train()
else:
test()
