值错误：可对原始文本文档进行迭代，接​​收到字符串对象TFIDF矢量化

编程问答 2022-06-03

问题描述

我已经做了很多尝试来找出问题所在，但仍然会出现错误。我不知道为什么！ ＃库已导入

import pandas as pd
import numpy as np
import nltk
import sklearn
from sklearn import svm
from sklearn.model_selection import train_test_split
from nltk.probability import Freqdist
from collections import Counter
from nltk import word_tokenize,sent_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import matplotlib.pyplot as pt
import string 
from wordcloud import WordCloud
from PIL import Image
from nltk import pos_tag
from sklearn.feature_extraction.text import TfidfVectorizer
import re
from nltk.corpus import wordnet
from nltk.tag import pos_tag#Libraries imported
import pandas as pd
import numpy as np
import nltk
import sklearn
from sklearn import svm
from sklearn.model_selection import train_test_split
from nltk.probability import Freqdist
from collections import Counter
from nltk import word_tokenize,sent_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import matplotlib.pyplot as pt
import string 
from wordcloud import WordCloud
from PIL import Image
from nltk import pos_tag
from sklearn.feature_extraction.text import TfidfVectorizer
import re
from nltk.corpus import wordnet
from nltk.tag import pos_tag

TR_DS=pd.read_csv("D:\DataSet\Training_Dataset.csv")
TR_DS.drop(["title","date","subject"],axis=1,inplace=True)#Delete unnecessary columns
TR_DS.isnull().any()
TR_DS.head()

#text column with small letters
news_text=TR_DS['text'].str.lower()

#Remove Punctuations
news_text=news_text.str.replace(r'[^\w\d\s]',' ')

#Remove Digits
news_text=news_text.str.replace('\d+','')
        
#Tokenization (Text as Words)
def tokenize(text):
    tokens= re.split('\W+',text)  
    return tokens
news_text=news_text.apply(lambda x : word_tokenize(x.lower()))  

#Remove StopWords
stop_words=stopwords.words("english")
def remove_stopwords(text):
    text = [word for word in text if word not in stop_words]
    return text
news_text=news_text.apply(lambda x: remove_stopwords(x))

#Lemmatization Words in stem Form
WordNetLemmatizer = nltk.WordNetLemmatizer()
def lemmer(text):
    text = [WordNetLemmatizer.lemmatize(word,pos='v') for word in text]
    return text
news_text=news_text.apply(lambda x: lemmer(x))
print(news_text)

输出 

 0 [reuters,man,accuse,tackle,u,senator,ran... 1      [washington,reuters,republican,senators,... 2      [reuters,proposals,republicans,repeal,r... 3      [reuters,tax,plan,senate,r... 4      [washington,americans,likely,belie...
                             ...                         295    [donald,trump,kick,hispanic,heritage,mont... 296    [us,even,conservatives,kNow,donald,... 297    [take,office,repeatedly,take... 298    [sunday,august,th,salt,lake,city,police,... 299    [u,rep,tim,murphy,staunch,pro,life,repu... Name: text,Length: 300,dtype: object
tfidf_vect = TfidfVectorizer(max_features=5000,ngram_range = (1,2))
def TFIDF(text):
    text = [tfidf_vect.fit(word) for word in text]
    return text
news_text=news_text.apply(lambda x: TFIDF(x))

**错误

ValueError                                Traceback (most recent call last) <ipython-input-232-886e227564fb> in <module>
      4     text = [tfidf_vect.fit(word) for word in text]
      5     return text
----> 6 news_text=news_text.apply(lambda x: TFIDF(x))

c:\users\mahad maqsood\appdata\local\programs\python\python39\lib\site-packages\pandas\core\series.py in apply(self,func,convert_dtype,args,**kwds)    4210             else:    4211                 values = self.astype(object)._values
-> 4212                 mapped = lib.map_infer(values,f,convert=convert_dtype)    4213     4214         if len(mapped) and isinstance(mapped[0],Series):

pandas\_libs\lib.pyx in pandas._libs.lib.map_infer()

<ipython-input-232-886e227564fb> in <lambda>(x)
      4     text = [tfidf_vect.fit(word) for word in text]
      5     return text
----> 6 news_text=news_text.apply(lambda x: TFIDF(x))

<ipython-input-232-886e227564fb> in TFIDF(text)
      2 tfidf_vect = TfidfVectorizer()
      3 def TFIDF(text):
----> 4     text = [tfidf_vect.fit(word) for word in text]
      5     return text
      6 news_text=news_text.apply(lambda x: TFIDF(x))

<ipython-input-232-886e227564fb> in <listcomp>(.0)
      2 tfidf_vect = TfidfVectorizer()
      3 def TFIDF(text):
----> 4     text = [tfidf_vect.fit(word) for word in text]
      5     return text
      6 news_text=news_text.apply(lambda x: TFIDF(x))

c:\users\mahad maqsood\appdata\local\programs\python\python39\lib\site-packages\sklearn\feature_extraction\text.py in fit(self,raw_documents,y)    1816         self._check_params()    1817         self._warn_for_unused_params()
-> 1818         X = super().fit_transform(raw_documents)    1819         self._tfidf.fit(X)    1820         return self

c:\users\mahad maqsood\appdata\local\programs\python\python39\lib\site-packages\sklearn\feature_extraction\text.py in fit_transform(self,y)    1186         # TfidfVectorizer.    1187         if isinstance(raw_documents,str):
-> 1188             raise ValueError(    1189                 "Iterable over raw text documents expected,"    1190                 "string object received.")

ValueError: Iterable over raw text documents expected,string object received.

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）

data-sciencemachine-learningnlppython-3.9