句子相似 BM25 python 实现

 

 

 

# -*- coding: utf-8 -*-

import math


class BM25(object):


    def __init__(self, docs):
        """
        
        :param docs: 分好词的list
        """
        self.D = len(docs)
        self.avgdl = sum([len(doc)+0.0 for doc in docs]) / self.D
        self.docs = docs
        self.f = []
        self.df = {}
        self.idf = {}
        self.k1 = 1.5
        self.b = 0.75
        self.init()

    def init(self):
        for doc in self.docs:
            tmp = {}
            for word in doc:
                if not word in tmp:
                    tmp[word] = 0
                tmp[word] += 1
            self.f.append(tmp)
            for k