Content_Based.py 文件源码

def get_vectorizer(self, ngram_range=(1, 3), min_df=2, max_df=1.0):
        """
        Define a binary CountVectorizer (Feature Presence) using n-grams and min and max document frequency
        :param ngram_range: n-grams are created for all numbers within this range
        :param min_df: min document frequency of features
        :param max_df: max document frequency of features
        :return:
        """
        if self.is_weight == 'FP':#Feature Presence
            vectorizer = CountVectorizer(ngram_range=ngram_range,
                                         tokenizer=self.tokenize,
                                         min_df=min_df,
                                         max_df=max_df,
                                         binary=True,
                                         stop_words='english')

        if self.is_weight == 'TF-IDF':#Feature Presence    
            vectorizer = TfidfVectorizer(ngram_range=ngram_range,
                                        tokenizer=self.tokenize,
                                         min_df=min_df, 
                                         max_df=max_df, 
                                         binary=True,
                                         stop_words='english')
        return vectorizer