Table of Contents
针对结巴分词Memory Error的两种解决方式
一、背景
最近,在使用Gensim Word2vec根据特定语料训练近义词模型,模型训练输入语料要求是分词之后的文件。使用结巴jieba对原始语料文件进行分词,在分词过程中,由于语料文件太大,将近五千万的数据量,出现了Memory Error问题。针对此问题,提供以下两种解决方式。同时,代码中展示了分词时对词语词性的筛选,停用词及标点符号的过滤。最后,附上根据分词文件进行模型训练代码。
二、解决方式
解决思路:一是在读取文件数据时避免一次性全部加载数据,单线程按行加载处理数据;二是将存储有大数据量的一个文件拆分为多个,多线程并行分词。
2.1 第一种按行加载处理数据的解决方案代码
# -*- coding: utf-8 -*-
""" 由原始文本进行分词后保存到新的文件 """
import jieba
import numpy as np
import jieba.posseg as pseg
import re
filePath='/data/work/keyword/work_data/work_title_description.csv'
fileSegWordDonePath ='/data/work/keyword/work_cutdata/corpus_line.txt'
#停用词加载
stop_word_path = '/data/work/keyword/keyword_extraction-master/data/stopWord.txt'
def stopwordslist(filepath):
stopwords = [line.strip() for line in open(filepath, 'rb').readlines()]
return stopwords
# 打印中文列表
def PrintListChinese(list):
for i in range(len(list)):
print (list[i])
# 读取文件内容到列表
fileTrainRead = []
with open(filePath,'r') as fileTrainRaw:
for line in fileTrainRaw: # 按行读取文件
fileTrainRead.append(line)
# jieba分词后保存在列表中
fileTrainSeg=[]
jieba.enable_paddle()
stopwords = stopwordslist(stop_word_path) # 这里加载停用词的路径
outstr = ''
for i in range(len(fileTrainRead)):
for x in pseg.cut(fileTrainRead[i][0:],use_paddle=True):
#下方判断表示选取指定词性词语
if x.flag == 'n' or x.flag == 'nw' or x.flag == 'nz' or x.flag.startswith('TIME') or x.flag.startswith('t'):
if x.word not in stopwords:
#去除标点符号
y = re.sub(r"[0-9\s+\.\!\/_,$%^*()?;;:-【】+\"\']+|[+——!,;:。?、~@#¥%……&*()]+", " ", x.word)
if y != '\t':
outstr += y
outstr += " "
if i % 100 == 0:
print(i)
fileTrainSeg.append([outstr])
# 保存分词结果到文件中
with open(fileSegWordDonePath,'w',encoding='utf-8') as fW:
for i in range(len(fileTrainSeg)):
fW.write(fileTrainSeg[i][0])
fW.write('\n')
复制代码
## 2.2 第二种将存储有大数据量的一个文件拆分为多个的解决方案代码
复制代码
# -*-coding:utf-8 -*-
import jieba.analyse
import jieba
import os
import jieba.posseg as pseg
jieba.enable_parallel(4)
raw_data_path = '/data/work/keyword/work_data/'
cut_data_path = '/data/work/keyword/work_cutdata/'
stop_word_path = '/data/work/keyword/keyword_extraction-master/data/stopWord.txt'
def stopwordslist(filepath):
stopwords = [line.strip() for line in open(filepath, 'rb').readlines()]
return stopwords
def cut_word(raw_data_path, cut_data_path ):
#读取该路径下的多个数据文件
data_file_list = os.listdir(raw_data_path)
corpus = ''
temp = 0
for file in data_file_list:
with open(raw_data_path + file,'rb') as f:
print(temp+1)
temp +=1
document = f.read()
document_cut = jieba.cut(document, cut_all=False)
result = ' '.join(document_cut)
corpus += result
with open(cut_data_path + 'corpus.txt', 'w+', encoding='utf-8') as f:
f.write(corpus) # 读取的方式和写入的方式要一致
stopwords = stopwordslist(stop_word_path) # 加载停用词的路径
with open(cut_data_path + 'corpus.txt', 'r', encoding='utf-8') as f:
document_cut = f.read()
outstr = ''
for word in document_cut:
if word not in stopwords:
if word != '\t':
outstr += word
outstr += " "
with open(cut_data_path + 'corpus1.txt', 'w+', encoding='utf-8') as f:
f.write(outstr) # 读取的方式和写入的方式要一致
if __name__ == "__main__":
cut_word(raw_data_path, cut_data_path )
复制代码
#三、使用Gensim Word2vec训练模型
""" gensim word2vec获取词向量 """
import warnings
import logging
import os.path
import sys
import multiprocessing
import gensim
from gensim.models import Word2Vec
from gensim.models.word2vec import LineSentence
# 忽略警告
warnings.filterwarnings(action='ignore', category=UserWarning, module='gensim')
if __name__ == '__main__':
program = os.path.basename(sys.argv[0]) # 读取当前文件的文件名
logger = logging.getLogger(program)
logging.basicConfig(format='%(asctime)s: %(levelname)s: %(message)s',level=logging.INFO)
logger.info("running %s" % ' '.join(sys.argv))
# inp为输入语料, outp1为输出模型, outp2为vector格式的模型
inp = '/data/work/keyword/work_cutdata/corpus_line.txt'
out_model = '/data/work/keyword/word2vec_model/work_title_description.model'
out_vector = '/data/work/keyword/word2vec_model/work_title_description.vector'
# 训练skip-gram模型
model = Word2Vec(LineSentence(inp), size=50, window=5, min_count=5,
workers=multiprocessing.cpu_count())
# 保存模型
model.save(out_model)
# 保存词向量
model.wv.save_word2vec_format(out_vector, binary=False)
复制代码
四、总结
在开发过程中,最终使用第一种按行读取文件数据的方式进行分词并训练得到模型。第二种方式读取的是目录下的多个文件,测试时分了20个文件分别读取,Memory Error问题不再出现。
参考:
评论前必须登录!
注册