def read_imdb3(data_dir):
"""读取数据集文本序列和标签"""
data, labels = [], []
tag=0
new_file='F:\sampledatakb\train\pos'
for file in os.listdir(data_dir):
filenamedir=os.path.join(data_dir, file)
with open(filenamedir, 'rb') as f:
# join用来做路径拼接
review = f.read()
data=review[0:1024]
print(data[0:4])
# print(data[2])
file_name = os.path.join(new_file, file)
with open(file_name, 'w+', encoding='utf-8') as f:
for data1 in data:
# print(data1)
f.write(chr(data1))
f.close()
print("成功写入文件")
# print(review[0])
data_dir='F:\smapledata\train\pos'
