Question

当我执行以下代码时

import networkx as nx
import numpy as np
from nltk.tokenize.punkt import PunktSentenceTokenizer
from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer

def textrank(document):
    sentence_tokenizer = PunktSentenceTokenizer()
    sentences = sentence_tokenizer.tokenize(document)

    bow_matrix = CountVectorizer().fit_transform(sentences)
    normalized = TfidfTransformer().fit_transform(bow_matrix)

    similarity_graph = normalized * normalized.T

    nx_graph = nx.from_scipy_sparse_matrix(similarity_graph)
    scores = nx.pagerank(nx_graph)
    return sorted(((scores[i],s) for i,s in enumerate(sentences)), reverse=True)

fp = open("QC")    
txt = fp.read()
sents = textrank(txt)
print sents

我收到以下错误

Traceback (most recent call last):
  File "Textrank.py", line 44, in <module>
    sents = textrank(txt)
  File "Textrank.py", line 10, in textrank
    sentences = sentence_tokenizer.tokenize(document)
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 1237, in tokenize
    return list(self.sentences_from_text(text, realign_boundaries))
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 1285, in sentences_from_text
    return [text[s:e] for s, e in self.span_tokenize(text, realign_boundaries)]
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 1276, in span_tokenize
    return [(sl.start, sl.stop) for sl in slices]
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 1316, in _realign_boundaries
    for sl1, sl2 in _pair_iter(slices):
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 311, in _pair_iter
    for el in it:
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 1291, in _slices_from_text
    if self.text_contains_sentbreak(context):
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 1337, in text_contains_sentbreak
    for t in self._annotate_tokens(self._tokenize_words(text)):
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 1472, in _annotate_second_pass
    for t1, t2 in _pair_iter(tokens):
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 310, in _pair_iter
    prev = next(it)
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 577, in _annotate_first_pass
    for aug_tok in tokens:
  File "/usr/local/lib/python2.7/dist-packages/nltk/tokenize/punkt.py", line 542, in _tokenize_words
    for line in plaintext.split('\n'):
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe2 in position 9: ordinal not in range(128)

我在Ubuntu中执行代码。为了得到文本，我推荐了这个网站 https://uwaterloo.ca/institute-for-quantum-computing/quantum-computing-101。我创建了一个文件QC（而不是QC.txt）并将段落中的数据复制粘贴到文件中。请帮我解决错误。谢谢

Answer 1

请尝试以下方法适用于您。

import networkx as nx
import numpy as np
import sys

reload(sys)
sys.setdefaultencoding('utf8')

from nltk.tokenize.punkt import PunktSentenceTokenizer
from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer

def textrank(document):
    sentence_tokenizer = PunktSentenceTokenizer()
    sentences = sentence_tokenizer.tokenize(document)

    bow_matrix = CountVectorizer().fit_transform(sentences)
    normalized = TfidfTransformer().fit_transform(bow_matrix)

    similarity_graph = normalized * normalized.T

    nx_graph = nx.from_scipy_sparse_matrix(similarity_graph)
    scores = nx.pagerank(nx_graph)
    return sorted(((scores[i],s) for i,s in enumerate(sentences)), reverse=True)

fp = open("QC")    
txt = fp.read()
sents = textrank(txt.encode('utf-8'))
print sents

UnicodeDecodeError：＆＃39; ascii＆＃39;编解码器无法解码Textranking代码中的字节

1 个答案: