word2vec文本相似度找出相似的文本，计算与之相似文本个数，语料库

首先，建立自己的语料库

def ylk(x):
    seg = jieba.cut(x, cut_all=False)
    with open('D://listTwo.txt', 'a',encoding='utf-8')as f:
        for word in seg:
            f.write(word+" ")
        f.write('\n')

训练模型

from gensim.models.word2vec import LineSentence, Word2Vec
#加载语料库
sentences = LineSentence("D://listTwo.txt")
model = Word2Vec(sentences, min_count=1, iter=1000)
model.save("D://w2v.mod")

比较相似

target = "D:/listTwo.txt"
model ="D://w2v.mod"
model_w2v = Word2Vec.load(model)

candidates = []
with open(target, encoding='utf-8')as f:
    for line in f:
        candidates.append(line.strip().split()) #将语料放到列表中便于操作
        
def xsd(text):
    words = list(jieba.cut(text.strip())) #分词
    flag = False
    res = []
    index = 0
    for candidate in candidates:
        # print("candidate", candidate)
        for c in candidate:
            if c not in model_w2v.wv.vocab:
                print("candidate word %s not in dict. skip this turn" % c)
                flag = True
        if flag:
            break
        score = model_w2v.n_similarity(words, candidate)
    
            res.append(index)
        index += 1
    return (len(res),res)
    #返回列表中与这句话形似的文本的个数和相似的有哪些