我正在尝试运行这个笔记本，它是一个问答系统的实现。运行第 8 个单元后：
challenges = {
# QA1 with 10,000 samples
'single_supporting_fact_10k': 'tasks_1-20_v1-2/en-10k/qa1_single-supporting-fact_{}.txt',
# QA2 with 10,000 samples
'two_supporting_facts_10k': 'tasks_1-20_v1-2/en-10k/qa2_two-supporting-facts_{}.txt',
}
challenge_type = 'single_supporting_fact_10k'
challenge = challenges[challenge_type]
print('Extracting stories for the challenge:', challenge_type)
train_stories = get_stories(tar.extractfile(challenge.format('train')))
test_stories = get_stories(tar.extractfile(challenge.format('test')))
我收到此错误：
AttributeError：“NoneType”对象没有属性“strip”
它在这些功能中使用了拆分：
def tokenize(sent):
return [ x.strip() for x in re.split('(\W+)?', sent) if x.strip()]
def parse_stories(lines, only_supporting=False):
'''Parse stories provided in the bAbi tasks format
If only_supporting is true, only the sentences
that support the answer are kept.
'''
data = []
story = []
for line in lines:
line = line.decode('utf-8').strip()
nid, line = line.split(' ', 1)
nid = int(nid)
if nid == 1:
story = []
if '\t' in line:
q, a, supporting = line.split('\t')
q = tokenize(q)
substory = None
if only_supporting:
# Only select the related substory
supporting = map(int, supporting.split())
substory = [story[i - 1] for i in supporting]
else:
# Provide all the substories
substory = [x for x in story if x]
data.append((substory, q, a))
story.append('')
else:
sent = tokenize(line)
story.append(sent)
return data
def get_stories(f, only_supporting=False, max_length=None):
data = parse_stories(f.readlines(), only_supporting=only_supporting)
flatten = lambda data: reduce(lambda x, y: x + y, data)
data = [(flatten(story), q, answer) for story, q, answer in data if not max_length or len(flatten(story)) < max_length]
return data
我不知道缺少什么以及如何修复它。