def data_convert():
x_c, y = data_loader.process_file(all_data_dir, character_to_id, cat_to_id, config.seq_length_c)
x_w, _ = data_loader_wordlevel.process_file(all_data_dir, word_to_id, cat_to_id, config.seq_length_w)
file_x_c_id = open('data\\10-fold-original-data\\data-convert\\x_c_id.txt','w',encoding='utf-8')
file_x_w_id = open('data\\10-fold-original-data\\data-convert\\x_w_id.txt','w',encoding='utf-8')
file_y_id = open('data\\10-fold-original-data\\data-convert\\y_id.txt','w',encoding='utf-8')
for data in x_c:
print(len(data))
for i in data:
file_x_c_id.write(str(i) + ' ')
file_x_c_id.write('\n')
for data in x_w:
print(len(data))
for i in data:
file_x_w_id.write(str(i) + ' ')
file_x_w_id.write('\n')
for data in y:
print(len(data))
for i in data:
file_y_id.write(str(i) + ' ')
file_y_id.write('\n')
file_x_c_id.close()
file_x_w_id.close()
file_y_id.close()
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)
sequence_length_vector = [
get_sequence_length() for x in range(end_id - start_id)
]
feed_dict = {
model.input_x: x_test[start_id:end_id],
model.keep_prob: 1.0,
model.sequence_length_vector: sequence_length_vector
}
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)
def train():
print('Configuring TensorBoard and Saver...')
# 配置Tensorboard ，重新训练时请将tensorboard文件夹删除,不然会覆盖
tensorboard_dir = 'tensorboard/textrnn'
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 train and validationn data...')
# 载入训练集合验证集
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)
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 evaluting...')
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 # 如果草错1000轮未提升，提前结束训练
flag = False
for epoch in range(config.num_rpochs):
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:
# 每多少轮将训练结果写入tensorboard scalar
s = sesion.run(merged_summary, feed_dict=feed_dict)
if total_batch % config.print_per_batch == 0:
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 = evalute(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:{:>6},Train Loss:{:>6.2},Train Acc:{:>7.2%}," + 'Val Loss:{:>6.2}, Val Acc:{:>7.2%} ,Time:{} {}'
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)
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
if flag:
break
def train(config, model):
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
tf.summary.scalar("loss", model.loss)
tf.summary.scalar("accuracy", model.acc)
merged_summary = tf.summary.merge_all()
writer = tf.summary.FileWriter(config.tensorboard_dir)
# 配置 Saver
saver = tf.train.Saver()
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(config.train_dir, config.word_to_id,
config.cat_to_id, config.seq_length)
x_val, y_val = process_file(config.val_dir, config.word_to_id,
config.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(model, 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, model, x_val, y_val)
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=config.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
