Traceback (most recent call last): File "C:\Program Files\JetBrains\PyCharm Community Edition 2023.1.1\plugins\python-ce\helpers\pydev\pydevconsole.py", line 364, in runcode coro = func() File "<input>", line 3, in <module> File "C:\Users\13974\AppData\Local\Programs\Python\Python310\lib\site-packages\gensim\corpora\dictionary.py", line 78, in __init__ self.add_documents(documents, prune_at=prune_at) File "C:\Users\13974\AppData\Local\Programs\Python\Python310\lib\site-packages\gensim\corpora\dictionary.py", line 204, in add_documents self.doc2bow(document, allow_update=True) # ignore the result, here we only care about updating token ids File "C:\Users\13974\AppData\Local\Programs\Python\Python310\lib\site-packages\gensim\corpora\dictionary.py", line 241, in doc2bow raise TypeError("doc2bow expects an array of unicode tokens on input, not a single string") TypeError: doc2bow expects an array of unicode tokens on input, not a single string

这个错误是因为 `doc2bow` 函数期望输入一个unicode token的数组，而不是单一的字符串。你需要将输入的文档分词并转换为一个token数组，然后再传递给 `doc2bow` 函数。你可以用如下的代码完成这个操作：

from gensim.corpora.dictionary import Dictionary

# 假设你的文档已经存储在一个名为 documents 的数组中
# 分词并创建一个token列表
tokens_list = [doc.split() for doc in documents]

# 创建词典
dictionary = Dictionary(tokens_list)

# 将文档转换为词袋表示
corpus = [dictionary.doc2bow(tokens) for tokens in tokens_list]

这样就可以将文档转换为词袋表示了。注意，这里使用的是gensim库中的 `Dictionary` 和 `doc2bow` 函数。