需要写个小脚本给不会编程的同事用,大致是他们自己编写检索条件然后去运行脚本得出结果。
检索条件类似这种:虚汗 or ((怕 or 畏) and (寒 or 冷))
目前试了两种,in 方式( func1 )和正则匹配( func2 ) 测试语料 1220 条,花费时间:
func1 运行时间:26.843648433685303
func2 运行时间:46.992613554000854
当语料很大,检索条件量很多(或者嵌套很多)。效率感觉不怎么理想? 问问有没思路改进一下效率,或者有没更好的方法思路。
相关代码文件 链接: https://pan.baidu.com/s/1c2llxlu 密码: v7ia
代码下面贴出了自己写的
# -*- coding=utf-8 -*-
import os
import re
import time
import pandas as pd
from pandas import DataFrame
from itertools import permutations
def str_to_list(p):
""" 处理字符串转换成列表
如:虚汗 or ((怕 or 畏) and (寒 or 冷))
结果:['虚汗','or',[['怕','or','畏'],'and',['寒','or','冷']]]
"""
p = re.sub('([^\(\)()\s(?:and|or)]+|(?:and|or))','"\\1",',p)
p = p.replace('(','[').replace('(','[').replace(')','],').replace(')','],')
p = '[%s]' % p
return eval(p)
def list_to_regex(p):
""" 处理列表转换成正则表达式
递归方法
如:['虚汗','or',[['怕','or','畏'],'and',['寒','or','冷']]]
结果:(虚汗|((怕|畏).*?(寒|冷)|(寒|冷).*?(怕|畏)))
"""
tempP = [list_to_regex(x) if isinstance(x,list) else x
for x in p
if x not in ['or','and']]
if 'and' in p:
tempP = permutations(tempP) #生成排列
return '(%s)' % '|'.join(['.*?'.join(x) for x in tempP])
else:
return '(%s)' % '|'.join(tempP)
def match_sentence(p,sentence):
"""转成 in 的方式去匹配句子"""
words = p.replace(' ','').replace(',','').replace('(','(').replace(')',')').replace('and',',and,').replace('or',',or,').replace('(',',(,').replace(')',',),').split(',')
scriptStr = [w if w in 'and or ()' \
else '"%s" in "%s"' % (w,sentence) for w in words]
if eval(' '.join(scriptStr)):
return True
return False
def func1(patternFile,sentenceFile):
"""
转成正则再去匹配
patternFile -- 含有检索条件的文件名
sentenceFile -- 语料文件名
"""
dfS = pd.read_excel(sentenceFile)
dfP = pd.read_excel(patternFile)
#编译好的正则列表
regexList = [re.compile(list_to_regex(str_to_list(x))) for x in dfP.ix[:,-1]]
resultFile = 'result1.txt'
for senIdx in dfS.index:
for i,patt in enumerate(regexList):
keyword = dfP.ix[i,-2]
sentence = dfS.ix[senIdx,-1]
if patt.search(sentence):
r = dfP.ix[[i],:-1]
with open(resultFile,'a',encoding='utf-8') as f:
f.write('%s\t%s\n' % (keyword, sentence))
def func2(patternFile,sentenceFile):
"""
转成 in 的方式再去匹配
patternFile -- 含有检索条件的文件名
sentenceFile -- 语料文件名
"""
dfS = pd.read_excel(sentenceFile)
dfP = pd.read_excel(patternFile)
resultFile = 'result2.txt'
for senIdx in dfS.index:
for pattIdx in dfP.index:
keyword = dfP.ix[pattIdx,-2]
sentence = dfS.ix[senIdx,-1]
if match_sentence(dfP.ix[pattIdx,-1],sentence):
with open(resultFile,'a',encoding='utf-8') as f:
f.write('%s\t%s\n' % (keyword, sentence))
if __name__ == '__main__':
"""测试"""
patternFile = '检索条件_测试.xlsx'
sentenceFile = '语料_测试.xlsx'
t1 = time.time()
func2(patternFile,sentenceFile)
t2 = time.time()
print('func2 运行时间:',t2-t1)
1
patx 2018-01-02 02:00:18 +08:00
用全文检索引擎会好一点吧
|