我需要您的帮助,我正在进行文本挖掘,文本分类,并且当我要将单词列表转换为字符串时,因为countvec不能与列表一起使用,所以我报错
Data['FilteredArticle']=0.0
for i in range (0,Data.shape[0]):
DS=nlp(Data['Titre-Article'][i])
Data['FilteredArticle'][i]=[ w for w in DS if w.is_alpha and not w.is_stop and not w.is_punct and len(w)>3]
from sklearn.model_selection import train_test_split
X_train, X_valid, y_train, y_valid = train_test_split(Data.FilteredArticle , Data.classe)
Xtrain=" ".join(X_train)
count_vect = CountVectorizer(analyzer='word', token_pattern=r'\w{1,}')
count_vect.fit(X_train)
TypeError跟踪(最近一次通话) 在 ----> 1 Xtrain =“” .join(X_train)
TypeError:序列项0:预期的str实例,找到列表enter image description here