word2vector java使用_word2vector调用

1.word2vec模型训练

import jieba.analyse

import jieba

import os

from gensim.models.word2vec import Word2Vec

dirname = './data/LCQMC'

sentence = []

words = []

for filename in os.listdir(dirname):

with open(os.path.join(dirname, filename), 'r') as lcqmc:

for line in lcqmc:

linedict = eval(line)   #将json字符串转化为json对象

word = linedict['sentence1']

pos = linedict['sentence2']

sentence.append(word)

sentence.append(pos)

with open('./data/data_text', 'r') as f:

for line in f:

sentence.append(line)

print("data_text size:", len(sentence))#sentence存放所有要训练的语料

for string in sentence:

temp = list(string)

str = ''

for ch in temp:

str = str+ch+' '

# print(str)

words.append(str)

#size指定训练的字表示向量大小

model = Word2Vec(words, size=128, window=4, min_count=1, sg=1, workers=2)

model.save('./data/word2vecModel')  #将训练好的模型存放在该代码文件下data目录中word2vecModel文件中

2.word2vec模型的调用

model = Word2Vec.load('./gensim_word2vec/data/word2vecModel')

def wordToVector(words):

result = []

for senarr in words:

temp = []

for i in range(30):  #将一句语句设置固定长度30字，下标低于30的字向量从模型中取，超过的获取128的列向量

if i < len(senarr):

word_vec = model[senarr[i]]  #获取字向量

else:

word_vec = [0 for _ in range(128)]

word_vec = np.asarray(word_vec)

temp.append(word_vec)

# temp = np.asarray(temp)

result.append(temp)

return result