使用 Python 进行词嵌入：docc

import re
import numpy as np

from gensim.models import doc2vec
from gensim.models.doc2vec import taggeddocument
from nltk.corpus import gutenberg
from multiprocessing import pool
from scipy import spatial

sentences = list(gutenberg.sents('shakespeare-hamlet.txt'))   # import the corpus and convert into a list

print('type of corpus: ', type(sentences))
print('length of corpus: ', len(sentences))

print(sentences[0])    # title, author, and year
print(sentences[1])
print(sentences[10])

for i in range(len(sentences)):
    sentences[i] = [word.lower() for word in sentences[i] if re.match('^[a-za-z]+', word)]  
print(sentences[0])    # title, author, and year
print(sentences[1])
print(sentences[10])

for i in range(len(sentences)):
    sentences[i] = taggeddocument(words = sentences[i], tags = ['sent{}'.format(i)])    # converting each sentence into a taggeddocument
sentences[0]

model = doc2vec(documents = sentences,dm = 1, size = 100, min_count = 1, iter = 10, workers = pool()._processes)

model.init_sims(replace = true)

model.save('doc2vec_model')
model = doc2vec.load('doc2vec_model')

model.most_similar('hamlet')

v1 = model['king']
v2 = model['queen']

# define a function that computes cosine similarity between two words
def cosine_similarity(v1, v2):
    return 1 - spatial.distance.cosine(v1, v2)

cosine_similarity(v1, v2)