import gensim

outp1 = 'D:\python_noweightpathway\TIA\docmodel'
file = open(u'D:\python_noweightpathway\TIA\TIAxmmc.txt', encoding='utf-8')
# fileghdjid = open(u'D:\python_noweightpathway\TIA\TIA.txt', encoding='utf-8')
# ghdjids = []
# for ghdjid in fileghdjid:
#     ghdjids.append(ghdjid)
# i = 0
# for line in file:
 

#     LabeledSentence(words=line.split(), labels=['SENT_%s' % ghdjids[i]])
#     i = i + 1
documents = gensim.models.doc2vec.TaggedLineDocument(file)
model = gensim.models.Doc2Vec(documents, size=100, window=8, min_count=100, workers=8)
model.save(outp1)

讀取模型

import gensim

model=gensim.models.Doc2Vec.load
 
("D:\python_noweightpathway\TIA\docmodel")
print(model.docvecs.most_similar(4))
print(model.docvecs.similarity(2,12))

文向量其實跟詞向量的模型一樣，只不過是訓練的時候把文件id也作為一個詞進行訓練，這樣文件id就學習到了文件下面每一個詞的資訊，就會生成一個文向量。