Python sklearn值错误：词汇表为空

Question

我试图模拟一个以前完成的项目，我遇到了一个CountVectorizer函数的麻烦。下面是与该问题相关的代码。在

from __future__ import division
import nltk, textmining, pprint, re, os.path 
#import numpy as np
from nltk.corpus import gutenberg
import fileinput

list = ["carmilla.txt", "pirate-caribbee.txt", "rider-sage.txt"]

for l in list:
    f = open(l)
    raw1 = f.read()
    print "<-----Here goes nothing"
    head = raw1[:680]
    foot = raw1[157560:176380]
    content = raw1[680:157560]
    print "Done---->"

content=[re.sub(r'[\']', '', text)for text in content]
content=[re.sub(r'[^\w\s\.]', ' ', text) for text in content]

print content

propernouns = []
for story in content:
    propernouns = propernouns+re.findall(r'Mr.[\s][\w]+', story)
    propernouns = propernouns+re.findall(r'Mrs.[\s][\w]+', story)
    propernouns = propernouns+re.findall(r'Ms.[\s][\w]+', story)
    propernouns = propernouns+re.findall(r'Miss.[\s][\w]+', story)

propernouns = set(propernouns)
print "\nNumber of proper nouns: " + str(len(propernouns))
print "\nExamples from our list of proper nouns: "+str(sorted(propernouns))

#Strip all of the above out of text
for word in propernouns:
    content = [re.sub(" "+word+" "," ",story) for story in content]

import string
content = [story.translate(string.maketrans("",""), "_.0123456789")]

print "\n[2] -----Carmilla Text-----"
print content

#Prepare a list of stopwords
f1 = open('stopwords.txt', 'r')
f2 = open('stopwords2.txt', 'w')
for line in f1:
    f2.write(line.replace('\n', ' '))
    f1.close()
    f2.close()

stopfile = open('stopwords2.txt')

print "Examples of stopwords: "
print stopfile.read()

from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(stop_words = stopfile , min_df=1)
stories_tdm = cv.fit_transform(content).toarray()

执行此操作没有完成，我得到以下错误：

^{pr2}$

我不知道该去哪里，因为我试着用另一个文件替换“content”作为测试，它表明我没有使用stopfile。。我好像不能让它正常工作。还有其他人遇到过这个问题吗？我错过了一些简单的事情吗？在

Answer 1

请记住正确关闭文件。f.close()无处，f2.close()不应缩进，f1.close()

我想这可以解决你的问题。在

for l in list:
    f = open(l)
    raw1 = f.read()
    print "<  -Here goes nothing"
    head = raw1[:680]
    foot = raw1[157560:176380]
    content = raw1[680:157560]
    print "Done  >"
    f.close()

。。。在

^{2}$

编辑 我又看到了两个问题：

一个是： 内容=[故事.翻译(字符串.maketrans（“，”“），”0123456789“）]

此缩进级别不存在story变量，因此请澄清这一点。在

另一个问题是stop_words可能是string、alist或{}。在string的情况下，唯一支持的值是'english'。但是，在您的情况下，您将传递一个文件句柄：

stopfile = open('stopwords2.txt')
#...
cv = CountVectorizer(stop_words = stopfile , min_df=1)

您应该做的是将stopfile中的所有文本转换为字符串列表。 替换此项：

#Prepare a list of stopwords
f1 = open('stopwords.txt', 'r')
f2 = open('stopwords2.txt', 'w')
for line in f1:
    f2.write(line.replace('\n', ' '))
    f1.close()
    f2.close()

stopfile = open('stopwords2.txt')

print "Examples of stopwords: "
print stopfile.read()

from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(stop_words = stopfile , min_df=1)

有了这个：

#Prepare a list of stopwords
f1 = open('stopwords.txt', 'r')
stoplist = []
for line in f1:
    nextlist = line.replace('\n', ' ').split()
    stoplist.extend(nextlist)
f1.close()

print "Examples of stopwords: "
print stoplist


from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(stop_words = stoplist, min_df=1)