python nltk中文_使用NLTK的FreqDist

我试图使用Python获得一组文档的频率分布。由于某种原因，我的代码无法工作，并产生以下错误：Traceback (most recent call last):

File "C:\Documents and Settings\aschein\Desktop\freqdist", line 32, in

fd = FreqDist(corpus_text)

File "C:\Python26\lib\site-packages\nltk\probability.py", line 104, in __init__

self.update(samples)

File "C:\Python26\lib\site-packages\nltk\probability.py", line 472, in update

self.inc(sample, count=count)

File "C:\Python26\lib\site-packages\nltk\probability.py", line 120, in inc

self[sample] = self.get(sample,0) + count

TypeError: unhashable type: 'list'

你能帮忙吗？

这是目前为止的代码：import os

import nltk

from nltk.probability import FreqDist

#The stop=words list

stopwords_doc = open("C:\\Documents and Settings\\aschein\\My Documents\\stopwords.txt").read()

stopwords_list = stopwords_doc.split()

stopwords = nltk.Text(stopwords_list)

corpus = []

#Directory of documents

directory = "C:\\Documents and Settings\\aschein\\My Documents\\comments"

listing = os.listdir(directory)

#append all documents in directory into a single 'document' (list)

for doc in listing:

doc_name = "C:\\Documents and Settings\\aschein\\My Documents\\comments\\" + doc

input = open(doc_name).read()

input = input.split()

corpus.append(input)

#Turn list into Text form for NLTK

corpus_text = nltk.Text(corpus)

#Remove stop-words

for w in corpus_text:

if w in stopwords:

corpus_text.remove(w)

fd = FreqDist(corpus_text)