def upload():
#msg2=None
# Get the name of the uploaded files
uploaded_files = request.files.getlist("file[]")
#filenames = []
for file in uploaded_files:
# Check if the file is one of the allowed types/extensions
if file and allowed_file(file.filename):
# Make the filename safe, remove unsupported chars
filename = secure_filename(file.filename)
# Move the file form the temporal folder to the upload
# folder we setup
#shutil.rmtree('File_to_validate')
#os.makedirs('File_to_validate')
file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))
#else:
#msg2='Please select a valid extension (.xls or .xlsx)'
#shutil.rmtree('Report')
#os.makedirs('Report')
prodata.process_file(path=os.path.join(app.config['UPLOAD_FOLDER']),company=app.config['COMPANY_FOLDER'],report=os.path.join(app.config['DOWNLOAD_FOLDER']),history=os.path.join(app.config['ITSM_FOLDER']))
filenames=os.listdir(app.config['DOWNLOAD_FOLDER'])
#filenames.append(filename)
text = open(app.config['DOWNLOAD_FOLDER']+'/issues.txt', 'r+')
content = text.read()
text.close()
# Save the filename into a list, we'll use it later
# Redirect the user to the uploaded_file route, which
# will basicaly show on the browser the uploaded file
# Load an html page with a link to each uploaded file
return render_template('multi_files_upload.html', filenames=filenames,text=content)#,msg2=msg2)
def upload():
msg2=None
# Get the name of the uploaded files
uploaded_files = request.files.getlist("file[]")
for file in uploaded_files:
# Check if the file is one of the allowed types/extensions
if file and allowed_file(file.filename):
# Make the filename safe, remove unsupported chars
filename = secure_filename(file.filename)
# Move the file form the temporal folder to the upload
file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))
msg2='blabla'
else:
msg2='Please select a valid extension (.xls or .xlsx)'
return render_template('multi_upload_index.html',msg2=msg2)
if len(os.listdir(app.config['UPLOAD_FOLDER']))>0:
prodata.process_file(path=os.path.join(app.config['UPLOAD_FOLDER']),company=app.config['COMPANY_NAME_FOLDER'],report=os.path.join(app.config['DOWNLOAD_FOLDER']),history=os.path.join(app.config['ITSM_FOLDER']))
filenames=os.listdir(app.config['DOWNLOAD_FOLDER'])
text = open(app.config['DOWNLOAD_FOLDER']+'/issues.txt', 'r+',encoding='utf8')
content = text.read()
text.close()
shutil.rmtree(app.config['COMPANY_NAME_FOLDER'])
# Redirect the user to the uploaded_file route, which
# will basicaly show on the browser the uploaded file
# Load an html page with a link to each uploaded file
return render_template('multi_files_upload.html', filenames=filenames,text=content,msg2=msg2)
def upload():
ID_FOLDER = session['filename']
ITSM_FOLDER = ID_FOLDER + '/ITSM_sites/'
UPLOAD_FOLDER = ID_FOLDER + '/Files_to_validate/'
DOWNLOAD_FOLDER = ID_FOLDER + '/Report/'
os.makedirs(DOWNLOAD_FOLDER)
if len(os.listdir(UPLOAD_FOLDER)) > 0:
process_data.process_file(path=UPLOAD_FOLDER,
company=ID_FOLDER.split('_')[0],
report=DOWNLOAD_FOLDER,
history=ITSM_FOLDER)
filenames = os.listdir(DOWNLOAD_FOLDER)
text = open(DOWNLOAD_FOLDER + 'issues.txt', 'r+', encoding='utf8')
content = text.read()
text.close()
return render_template('multi_files_upload.html',
filenames=filenames,
text=content)
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)
from tqdm import tqdm, trange
import pickle
import numpy as np
import torch
from torch.utils.data import DataLoader, RandomSampler
from torch.utils.data.distributed import DistributedSampler
from tokenization_unilm import UnilmTokenizer, WhitespaceTokenizer
from modeling_unilm import UnilmForSeq2SeqDecode, UnilmConfig
from process_data import process_file, make_conll_format, TEST_FILE, test_data
import utils_seq2seq
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
test_sentence_all, test_question_all, test_answers_all = process_file(
TEST_FILE)
make_conll_format(test_sentence_all, test_question_all, test_answers_all,
test_data)
ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys())
for conf in (UnilmConfig, )), ())
MODEL_CLASSES = {'unilm': (UnilmConfig, UnilmForSeq2SeqDecode, UnilmTokenizer)}
logging.basicConfig(
format='%(asctime)s - %(levelname)s - %(name)s - %(message)s',
datefmt='%m/%d/%Y %H:%M:%S',
level=logging.INFO)
my_logger = logging.getLogger(__name__)
def detokenize(tk_list):
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()
train_x, train_y = process_file(train_dir, word_to_id, cat_to_id, config.seq_length)
x_train, x_val, y_train, y_val = train_test_split(train_x, train_y)
# 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.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.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
