我正在尝试模拟以前完成的项目,并且我遇到了CountVectorizer函数的问题。以下是与该问题相关的代码。
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()
执行此操作无法完成,我收到了以下错误:
Traceback (most recent call last):
File "C:\Users\mnate_000\workspace\de.vogella.python.third\src\TestFile_EDIT.py", line 84, in <module>
stories_tdm = cv.fit_transform(content).toarray()
File "C:\Users\mnate_000\Anaconda\lib\site-packages\sklearn\feature_extraction\text.py", line 780, in fit_transform
vocabulary, X = self._count_vocab(raw_documents, self.fixed_vocabulary)
File "C:\Users\mnate_000\Anaconda\lib\site-packages\sklearn\feature_extraction\text.py", line 727, in _count_vocab
raise ValueError("empty vocabulary; perhaps the documents only"
**ValueError: empty vocabulary; perhaps the documents only contain stop words**
我不知道该往哪里去,因为我已经尝试过更换内容&#34;使用另一个文件作为测试,它确定我没有使用停止文件..我似乎无法让它正常运行。还有其他人遇到过这个问题吗?我错过了一些简单的东西吗?
答案 0 :(得分:0)
请记得正确关闭文件。 f.close()
无处,f2.close()
不应缩进,f1.close()
我认为这可能会解决您的问题。
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()
...
#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()
修改强> 我还看到了另外两个问题:
一个是这样的: content = [story.translate(string.maketrans(“”,“”),“_ 0.0123456789”)]
此缩进级别不存在story
变量,因此请澄清。
另一个问题是stop_words
可能是string
,list
或None
。对于string
,唯一支持的值为'english'
。但是,在您的情况下,您传递文件句柄:
stopfile = open('stopwords2.txt')
#...
cv = CountVectorizer(stop_words = stopfile , min_df=1)
您应该做的是将stopfile
中的所有文字转换为字符串列表。
替换这个:
#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)