python sklearn 文本分类

docs = ['你好喜欢你','ni hao wo xi huan ni','我 爱 你','你 不 可 以 放 弃 我','你 好']
docs1 = ['nihao wo xi huan ni','你 好']

#文本向量化
from sklearn.feature_extraction.text import CountVectorizer
count = CountVectorizer(analyzer='char')
bag = count.fit_transform(docs)
bag1 = count.transform(docs1)

#模型
#k-近邻
y = [1,2,3,4,5]
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier (n_neighbors=1) #
knn.fit(bag,y) #拟合
print(knn.predict(bag1))
#逻辑回归
from sklearn.linear_model import LogisticRegression
clf = LogisticRegression(max_iter= 1000)
clf.fit(bag,y)
print(clf.predict(bag1))