def __init__(self):
self.config = TCNNConfig()
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 = TextCNN(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 = TCNNConfig()
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 = TextCNN(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):
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, config.vocab_size)
self.categories, cat_to_id = read_category()
words, self.word_to_id = read_vocab(vocab_dir)
self.table = pd.read_excel('predict_check_data.xls')
category_set = list(set(self.table['name'].tolist()))
self.config = TCNNConfig(len(list(category_set)))
self.config.vocab_size = len(words)
self.model = TextCNN(self.config)
self.categories = list(set(self.table['name'].tolist()))
self.categories.sort(key=self.table['name'].tolist().index)
def __init__(self):
self.config = TextCNNConfig()
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 = TextCNN(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
self.meta_graph_def = sm.loader.load(self.session,
tags=[sm.tag_constants.SERVING],
export_dir=pd_path)
signature = self.meta_graph_def.signature_def
x_tensor_name = signature[signature_key].inputs['input_x'].name
kp_tensor_name = signature[signature_key].inputs['keep_prob'].name
y_tensor_name = signature[signature_key].outputs['output'].name
self.x = self.session.graph.get_tensor_by_name(x_tensor_name)
self.kp = self.session.graph.get_tensor_by_name(kp_tensor_name)
self.y = self.session.graph.get_tensor_by_name(y_tensor_name)
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()
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)
dataNums = [16, 32, 64, 128, 256]
for i in dataNums:
if i == 0:
continue
g1 = tf.Graph()
sess1 = tf.Session(graph=g1)
with sess1.as_default():
with g1.as_default():
model = TextCNN(config, batch_size=i)
train()
test()
plt.plot(xx, yy1)
plt.title('train loss')
plt.show()
msg = 'Iter: {0:>6}, Train Loss: {1:>6.2}, Train Acc: {2:>7.2%},' \
+ ' Val Loss: {3:>6.2}, Val Acc: {4:>7.2%}, Time: {5} {6}'
print(
msg.format(total_batch, loss_train, acc_train, loss_val,
acc_val, time_dif, improved_str))
session.run(model.optim, feed_dict=feed_dict) # 运行优化
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...")
flag = True
break # 跳出循环
if flag: # 同上
break
if __name__ == '__main__':
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)
categories, cat_to_id = read_category()
words, word2id = read_vocab(vocab_dir)
config.vocab_size = len(words)
model = TextCNN(config)
train()
rnn.vocab_dir = os.path.join(rnn.base_dir,
key + '.' + sub_key + '.vocab.txt')
test_docs = test_sub_dic[sub_key]
test_data_Y = []
print(len(test_docs))
for test_doc in test_docs:
temp = test_doc.split(',')
test_data_Y.append(temp[1])
print('Configuring CNN model...')
rnn.config = TRNNConfig()
#if not os.path.exists(cnn.vocab_dir): #if no vocab, build it
build_vocab_words(rnn.all_dir, rnn.vocab_dir, rnn.config.vocab_size)
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
): # word_vector_map.has_key(cnn.words[i])
count = count
sub_embeddings[i] = word_vector_map.get(rnn.words[i])
else:
msg = 'Iter: {0:>6}, Train Loss: {1:>6.2}, Train Acc: {2:>7.2%},' \
+ ' Val Loss: {3:>6.2}, Val Acc: {4:>7.2%}, Time: {5} {6}'
print(
msg.format(total_batch, loss_train, acc_train, loss_val,
acc_val, time_dif, improved_str))
session.run(train_op, feed_dict=feed_dict) # 运行优化
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...")
flag = True
break # 跳出循环
if flag: # 同上
break
if __name__ == '__main__':
model = TextCNN()
config = model.config
file_config, _ = Config().parse.parse_known_args()
print('Configuring CNN model...')
if not os.path.exists(file_config.vocab_path): # 如果不存在词汇表，重建
build_vocab(file_config.train_path, file_config.vocab_path,
config.vocab_size)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(file_config.vocab_path)
config.vocab_size = len(words)
train(model, file_config)
# 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()
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_path): # 如果不存在词汇表，重建
build_vocab(train_path, vocab_path, config.vocab_size)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_path)
config.vocab_size = len(words)
model = TextRNN(config)
if sys.argv[1] == 'train':
train()
else:
test()
test_data_X.append(corpus[int(temp[0]) - 1])
test_data_Y.append(temp[1])
string = corpus[int(temp[0]) - 1]
#string = expand_abbr(string)
str_to_write = string
test_file.write(temp[1] + '\t' + str_to_write + '\n')
all_file.write(temp[1] + '\t' + str_to_write + '\n')
print('Configuring CNN model...')
test_file.close()
all_file.close()
cnn.config = TCNNConfig()
#if not os.path.exists(cnn.vocab_dir): #if no vocab, build it
build_vocab_words(cnn.all_dir, cnn.vocab_dir, cnn.config.vocab_size)
cnn.words, cnn.word_to_id = read_vocab(cnn.vocab_dir)
cnn.config.vocab_size = len(cnn.words)
#select a subset of word vectors
cnn.missing_dir = os.path.join(cnn.base_dir,
key + '.' + sub_key + '.missing.txt')
missing_words_file = open(cnn.missing_dir, 'w')
sub_embeddings = np.random.uniform(
-0.0, 0.0, (cnn.config.vocab_size, embedding_dim))
count = 0
for i in range(0, cnn.config.vocab_size):
if (cnn.words[i] in word_vector_map
): #word_vector_map.has_key(cnn.words[i])
count = count
sub_embeddings[i] = word_vector_map.get(cnn.words[i])
else:
# 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() # 读取配置文件
if not os.path.exists(
vocab_dir): # 如果不存在词汇表，用train_dir中频率最高的vocab_size-1个词构建词汇表
build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_id = read_category() # 读分类list 和 分类-id 字典
words, word_to_id = read_vocab(vocab_dir) # 读词汇表list 和 words-id 字典
config.vocab_size = len(words) # 词汇表大小重新设定
model = TextCNN(config)
if sys.argv[1] == 'train':
train()
elif sys.argv[1] == 'test':
test()
else:
raise ValueError("""usage: python run_cnn.py [train / test]""")
def train(model,data):
if
print("Configuring TensorBoard and Saver...")
# 配置 Tensorboard，重新训练时，请将tensorboard文件夹删除，不然图会覆盖
tensorboard_dir = 'tensorboard/textcnn'
if not os.path.exists(tensorboard_dir):
os.makedirs(tensorboard_dir)
tf.summary.scalar("loss", model.loss)
tf.summary.scalar("accuracy", model.acc)
merged_summary = tf.summary.merge_all()
writer = tf.summary.FileWriter(tensorboard_dir)
# 配置 Saver
saver = tf.train.Saver()
if not os.path.exists(save_dir):
os.makedirs(save_dir)
print("Loading training and validation data...")
# 载入训练集与验证集
start_time = time.time()
x_train, y_train = process_file(train_dir, word_to_id, cat_to_id, config.seq_length)
x_val, y_val = process_file(val_dir, word_to_id, cat_to_id, config.seq_length)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
# 创建session
session = tf.Session()
session.run(tf.global_variables_initializer())
writer.add_graph(session.graph)
print('Training and evaluating...')
start_time = time.time()
total_batch = 0 # 总批次
best_acc_val = 0.0 # 最佳验证集准确率
last_improved = 0 # 记录上一次提升批次
require_improvement = 1000 # 如果超过1000轮未提升，提前结束训练
flag = False
for epoch in range(config.num_epochs):
print('Epoch:', epoch + 1)
batch_train = batch_iter(x_train, y_train, config.batch_size)
for x_batch, y_batch in batch_train:
feed_dict = feed_data(x_batch, y_batch, config.dropout_keep_prob)
if total_batch % config.save_per_batch == 0:
# 每多少轮次将训练结果写入tensorboard scalar
s = session.run(merged_summary, feed_dict=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
feed_dict[model.keep_prob] = 1.0
loss_train, acc_train = session.run([model.loss, model.acc], feed_dict=feed_dict)
loss_val, acc_val = evaluate(session, x_val, y_val) # todo
if acc_val > best_acc_val:
# 保存最好结果
best_acc_val = acc_val
last_improved = total_batch
saver.save(sess=session, save_path=save_path)
improved_str = '*'
else:
improved_str = ''
time_dif = get_time_dif(start_time)
msg = 'Iter: {0:>6}, Train Loss: {1:>6.2}, Train Acc: {2:>7.2%},' \
+ ' Val Loss: {3:>6.2}, Val Acc: {4:>7.2%}, Time: {5} {6}'
print(msg.format(total_batch, loss_train, acc_train, loss_val, acc_val, time_dif, improved_str))
session.run(model.optim, feed_dict=feed_dict) # 运行优化
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...")
flag = True
break # 跳出循环
if flag: # 同上
break
def test():
print("Loading test data...")
start_time = time.time()
x_test, y_test = process_file(test_dir, word_to_id, cat_to_id, config.seq_length)
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
print('Testing...')
loss_test, acc_test = evaluate(session, x_test, y_test)
msg = 'Test Loss: {0:>6.2}, Test Acc: {1:>7.2%}'
print(msg.format(loss_test, acc_test))
batch_size = 128
data_len = len(x_test)
num_batch = int((data_len - 1) / batch_size) + 1
y_test_cls = np.argmax(y_test, 1)
y_pred_cls = np.zeros(shape=len(x_test), dtype=np.int32) # 保存预测结果
for i in range(num_batch): # 逐批次处理
start_id = i * batch_size
end_id = min((i + 1) * batch_size, data_len)
feed_dict = {
model.input_x: x_test[start_id:end_id],
model.keep_prob: 1.0
}
y_pred_cls[start_id:end_id] = session.run(model.y_pred_cls, 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__':
#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)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
config.vocab_size = len(words)
model = TextCNN(config)
#if sys.argv[1] == 'train':
# train()
#else:
# test()
train()
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__':
# 输入参数 train 和 test 表示训练与测试
# 需要在命令行运行 python run_cnn.py <train>|<test>
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() # 获得TCNNConfig设置，TCNNConfig表示CNN配置参数
if not os.path.exists(vocab_dir): # 如果不存在词汇表，重建 单词表长度5000，是train里面出现最频繁的5000个单词
build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_id = read_category() # read_category()获取目录，cat_to_id 标签:序号的字典
words, word_to_id = read_vocab(vocab_dir) # 将词汇表的各个单词编号
config.vocab_size = len(words) # 更新词汇表长度
model = TextCNN(config) # 构建CNN模型，很重要
if sys.argv[1] == 'train':
train()
else:
test()
cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
print(cm)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
return y_pred_cls
if __name__ == '__main__':
if len(sys.argv) != 2 or sys.argv[1] not in ['train', 'test']:
raise ValueError("""usage: python run_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)
categories, cat_to_id, id_to_cat = read_category()
words, word_to_id = read_vocab(vocab_dir)
entities, entity_to_id = read_vocab(entity_vocab_dir)
config.vocab_size = len(words)
config.entity_vocab_size = len(entities)
word_embeddings = np.random.uniform(-0.0, 0.0, (config.vocab_size, 100))
entity_embeddings = np.random.uniform(-0.0, 0.0,
(config.entity_vocab_size, 200))
model = TextCNN(config, word_embeddings, entity_embeddings)
if sys.argv[1] == 'train':
train()
else:
test()
test_data_X.append(corpus[int(temp[0]) - 1])
test_data_Y.append(temp[1])
string = corpus[int(temp[0]) - 1]
str_to_write = string
test_file.write(temp[1] + '\t' + str_to_write + '\n')
all_file.write(temp[1] + '\t' + str_to_write + '\n')
test_file.close()
all_file.close()
print('Configuring CNN model...')
cnn.config = TCNNConfig()
build_vocab_words(cnn.all_dir, cnn.vocab_dir, cnn.config.vocab_size)
cnn.words, cnn.word_to_id = read_vocab(cnn.vocab_dir)
cnn.config.vocab_size = len(cnn.words)
#select a subset of word vectors
cnn.missing_dir = os.path.join(cnn.base_dir,
key + '.' + sub_key + '.missing.txt')
missing_words_file = open(cnn.missing_dir, 'w')
word_embeddings = np.random.uniform(
-0.0, 0.0, (cnn.config.vocab_size, word_embedding_dim))
count = 0
for i in range(0, cnn.config.vocab_size):
if (cnn.words[i] in word_vector_map
): #word_vector_map.has_key(cnn.words[i])
word_embeddings[i] = word_vector_map.get(cnn.words[i])
else:
count = count + 1
