#! /usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2021/11/12 15:44
"""
我们再写一遍这个算法；
"""
from icecream import ic
import jieba
import jieba.analyse
from gensim import corpora
from gensim import models
from gensim import similarities
from collections import defaultdict
def similarity_fun(doc_list):
# 1.首先我们需要对其进行分词，二维列表放词语
texts = [list(jieba.cut(i)) for i in doc_list]
ic(texts)
# 2.接下来要对词语进行标号
dictionary = corpora.Dictionary(texts)
ic(dictionary.token2id) #这个只是让你看一下，待会调用的是封装的他
# 3.标号以后，要将其 转化为数字
corpus = [dictionary.doc2bow(text) for text in texts]
ic(corpus)
# 4.创建模型
tfidf = models.TfidfModel(corpus)
ic(tfidf)
# 5.将整个语料库转化为tfidf表示方法
corpus_tfidf = tfidf[corpus]
ic(corpus_tfidf)
# 6.创建相似度索引
index = similarities.MatrixSimilarity(corpus_tfidf)
ic(index)
# 7.计算单个词语的相似度
words_sims = [tfidf[obj] for obj in corpus]
ic(words_sims)
# 8.计算句子之间的相似度
texts_sims = [index[obj] for obj in words_sims]
ic(texts_sims)
if __name__ == "__main__":
doc_list = [
"楚枫不是楚枫",
"楚枫是人"
]
doc_list = [
"楚枫有五颗仙灵草",
"楚月没有仙灵草",
"楚枫喜欢楚月"
]
similarity_fun(doc_list=doc_list)View Code
-----------------------------------------------------------------------------------------------------------------------------------------
