bm25Matcher.py 文件源码

def calculateIDF(self):

        # ???????????????
        if len(self.wordset) == 0:
            self.buildWordSet()
        if len(self.words_location_record) == 0:
            self.buildWordLocationRecord()

        # ?? idf
        for word in self.wordset:
            self.words_idf[word] = math.log2((self.D + .5)/(self.words_location_record[word] + .5))