ML之NB&LoR：利用NB(朴素贝叶斯)、LoR(逻辑斯蒂回归)算法(+TfidfVectorizer)对Rotten Tomatoes影评数据集进行文本情感分析—五分类预测

输出结果

设计思路

核心代码

tf = TfidfVectorizer(

   analyzer='word',

   ngram_range=(1,4),

#     stop_words=stop_words,

   max_features=150000

)

x_train,x_test,y_train,y_test = train_test_split(x,y,random_state=1234)

x_train = tf.transform(x_train)

x_test = tf.transform(x_test)

classifier = MultinomialNB()

classifier.fit(x_train,y_train)

lg = LogisticRegression(C=4, dual=True)

lg.fit(x_train,y_train)