如何解决多项式 NB 的维数不匹配
from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(FinalList)
print(vectorizer.get_feature_names())
print(X.shape)
data["sentiment"]=data["sentiment"].map(dict(positive=1,negative=0))
data.head(5)
y= data["sentiment"]
x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=2020)
clf = MultinomialNB()
clf.fit(x_train,y_train)
y_head_train = clf.predict(x_train)
y_head_test=clf.predict(x_test)
print(accuracy_score(y_head_train,y_train))
print(accuracy_score(y_head_test,y_test))
Newlist=Tokenization(post_df['text'])
Newlistlist = list(filter(None,Newlist))
vectorizer = TfidfVectorizer(vocabulary=vectorizer.vocabulary_)
NewText = vectorizer.fit_transform(Newlist)
print(vectorizer.get_feature_names())
print(NewText.shape)
y_NewText = clf.predict(NewText)
我遇到的问题与下面相同，我该如何解决尺寸不匹配错误..？谢谢。 scikit-learn ValueError: dimension mismatch
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。
