for line in ds:
line = re.sub('\n', '', line)
ds_cs.append(line)
ryzd = []
output = []
for emrtxt in emrtxts:
f = open(emrtxt, 'r', errors="ignore") #中文加入errors
emrpath = os.path.basename(emrtxt)
emrpath = os.path.splitext(emrpath)[0] #提取目录
pattern = r'\s*\d+、+\s?(.*)'
c = re.compile(pattern)
for line in f.readlines():
line1 = line.strip('\n')
line2 = ''.join(line1)
line2 = line2.strip()
line3 = c.findall(line2)
line3 = ''.join(line3)
line4 = str(line3)
out = line4
out = re.sub(r'右侧|两侧|双侧|左侧|右|左|双', '', out)
out = re.sub(r'肺肺', '肺', out)
out = re.sub('（.*?）', '', out)
out = re.sub(r'很高危|极高危', '', out)
out = re.sub(r'/?|？', '', out)
for ds in ds_cs:
if EMRdef.SBS(out, ds) > 0.8:
output.append(out)
output = EMRdef.delre(output)
EMRdef.text_save(u'D:\python\EMR\jbml.txt', output1)
#-*- coding: UTF-8 -*-
#根据给药方式和剂量剂型分词
import os
import EMRdef
import string
import re
pattern = r',|;|\*|`|\[|\]|<|>|\?|"|\{|\}|!|@|#|\$|%|\^|&|=|，|。|：|；|‘|’|\+|\-|【|】| \)|\( |（|）|·|！|、|…' #清除标点
c = open(r'C:\Users\Administrator\Desktop\quanbu.txt', 'r',
errors="ignore") #给药剂量加剂型加给药方式词典
b = open(r'C:\Users\Administrator\Desktop\tc.txt', 'r',
errors="ignore") #给药剂量词典
crl = c.readlines()
brl = b.readlines()
test_out = []
for cl in crl:
cl = re.sub('\n', '', cl)
for bl in brl:
bl = re.sub('\n', '', bl)
if cl == bl:
test_out.append(cl)
adult_a = EMRdef.delre(test_out)
EMRdef.text_save(r'C:\Users\Administrator\Desktop\output.txt', adult_a)
ds_cs = []
for line in ds:
line = re.sub('\n', '', line)
ds_cs.append(line)
ryzd = []
output = []
for emrtxt in emrtxts:
f = open(emrtxt, 'r', errors="ignore") #中文加入errors
emrpath = os.path.basename(emrtxt)
emrpath = os.path.splitext(emrpath)[0] #提取目录
pattern = r'\s*\d+、+\s?(.*)'
c = re.compile(pattern)
for line in f.readlines():
line1 = line.strip('\n')
line2 = ''.join(line1)
line2 = line2.strip()
line3 = c.findall(line2)
line3 = ''.join(line3)
line4 = str(line3)
out = line4
out = re.sub(r'右侧|两侧|双侧|左侧|右|左|双', '', out)
out = re.sub(r'肺肺', '肺', out)
out = re.sub('（.*?）', '', out)
out = re.sub(r'很高危|极高危', '', out)
for ds in ds_cs:
if EMRdef.SBS(out, ds) > 0.8:
output.append(out)
output = EMRdef.delre(output)
output1 = '\n'.join(output)
EMRdef.text_save(u'D:\python\EMR\jbml.txt', adult_c)
ds_cs = []
for line in ds:
line = re.sub('\n', '', line)
ds_cs.append(line)
ryzd = []
output = []
for emrtxt in emrtxts:
f = open(emrtxt, 'r', errors="ignore") #中文加入errors
emrpath = os.path.basename(emrtxt)
emrpath = os.path.splitext(emrpath)[0] #提取目录
pattern = r'\s*\d+、+\s?(.*)'
c = re.compile(pattern)
for line in f.readlines():
line1 = line.strip('\n')
line2 = ''.join(line1)
line2 = line2.strip()
line3 = c.findall(line2)
line3 = ''.join(line3)
line4 = str(line3)
out = line4
out = re.sub(r'右侧|两侧|双侧|左侧|右|左|双', '', out)
out = re.sub(r'肺肺', '肺', out)
out = re.sub('（.*?）', '', out)
out = re.sub(r'很高危|极高危', '', out)
for ds in ds_cs:
if EMRdef.SBS(out, ds) > 0.8:
output.append(out)
output = EMRdef.delre(output)
output1 = '\n'.join(output)
EMRdef.text_save(u'D:\python\EMR\967yw.txt', adult_c)
import time
import math
import os
import sys
import os, os.path, shutil
import codecs
import EMRdef
import re
emrtxts = EMRdef.txttq(u'D:\DeepLearning ER\EHRzlgc4') #txt目录提取
a_out = []
pattern = r',|;|\'|`|\[|\]|<|>|\?|"|\{|\}|!|@|#|\$|%|\^|&|=|＞|，|。|：|＜|；|‘|’|【|】|（|）|·|！|\*|\/|…' #清除标点
for emrtxt in emrtxts:
f = open(emrtxt, 'r', errors="ignore") #中文加入errors
emrtxt = os.path.basename(emrtxt)
emrtxt_str = re.findall(r'(^.+?)\_', emrtxt) #提取ID
emrtxt = "".join(emrtxt_str) #转成str
#txtp=txtp.decode('utf-8')
for line in f.readlines():
line = re.sub(' ', '', line) #删除空格
line = re.sub('\.', '', line) #删除.
line = re.sub('×', '', line) #删除.
a = EMRdef.tq_bnum(line)
a_end = "".join(a) #转成str
a_end = re.split(pattern, a_end)
a_end = "".join(a_end) #转成str
a_end = re.sub(' ', '', a_end) #删除空格
a_out.append(a_end)
adult_a = EMRdef.delre(a_out)
EMRdef.text_save('D:\python\EMR\hyxm.txt', adult_a)
