# if one_case_chara[10] == '3':
# sign = 1
break
subtlety_ave = getAve(store_subtlety)
internalStructure_ave = getAve(store_internalStructure)
calcification_ave = getAve(store_calcification)
sphericity_ave = getAve(store_sphericity)
margin_ave = getAve(store_margin)
lobulation_ave = getAve(store_lobulation)
spiculation_ave = getAve(store_spiculation)
texture_ave = getAve(store_texture)
malignancy_ave = getAve(store_malignancy)
item.append(subtlety_ave)
item.append(internalStructure_ave)
item.append(calcification_ave)
item.append(sphericity_ave)
item.append(margin_ave)
item.append(lobulation_ave)
item.append(spiculation_ave)
item.append(texture_ave)
item.append(malignancy_ave)
if sign == 1:
count += 1
# csvTools.writeCSV('malignancy.csv', item)
# print('count ', count)
# print('len ', len(list3))
csvTools.writeCSV('malignancy.csv', list3_2)
<texture>5</texture>
<malignancy>5</malignancy>
'''
tree = ET.parse(basedir + xmlfile)
root = tree.getroot()
for child in root:
# print('child')
# print(child.tag[20:len(child.tag)])
if 'readingSession' in child.tag:
for leave in child:
if 'unblindedReadNodule' in leave.tag:
for dot in leave:
if 'characteristics' in dot.tag:
temp_for_nodule = []
for dottemp in leave:
if 'noduleID' in dottemp.tag:
# print(dottemp.text)
temp_for_nodule.append(scan[:14])
temp_for_nodule.append(dottemp.text)
if 'characteristics' in dottemp.tag:
# print('=====')
for chara in dottemp:
# print(chara.text)
temp_for_nodule.append(chara.text)
noudle_chara_list.append(temp_for_nodule)
print(len(noudle_chara_list))
csvTools.writeCSV('nodule_chara_list.csv', noudle_chara_list)
import csvTools
bacteriapath = '/home/wangqiuli/Data/pneumonia/BacteriaScreened/'
funguspath = '/home/wangqiuli/Data/pneumonia/FungusScreened/'
bacFilelist = os.listdir(bacteriapath)
funFilelist = os.listdir(funguspath)
print(len(bacFilelist))
print(len(funFilelist))
baclines = []
funlines = []
for onebac in bacFilelist:
baclines.append(str(onebac) + ',bacter')
for onefun in funFilelist:
funlines.append(str(onefun) + ',fungus')
import random
random.shuffle(baclines)
random.shuffle(funlines)
alllines = baclines + funlines
random.shuffle(alllines)
csvTools.writeCSV('label/all.csv', alllines)
csvTools.writeCSV('label/bacter.csv', baclines)
csvTools.writeCSV('label/fungus.csv', funlines)
print('Done CSV!')
# print(len(metadata))
# print(metadata[4])
if metadata[4] == 'CT':
ctdata = []
ctdata.append(metadata[1])
Patient_Id.append(metadata[1])
ctdata.append(metadata[9])
Series_UID.append(metadata[9])
CTList.append(ctdata)
sign += 1
print(len(CTList))
print(len(Patient_Id))
print(len(Series_UID))
csvTools.writeCSV('PatientId_SeriesUID.csv', CTList)
patients = os.listdir(basedir)
scan = []
for patient in patients:
idlist1 = os.listdir(basedir + patient)
for level1 in idlist1:
idlist2 = os.listdir(basedir + patient + '/' + level1)
for level2 in idlist2:
if level2 in Series_UID:
temp = patient + '/' + level1 + '/' + level2 + '\n'
scan.append(temp)
print(scan[:10])
file_object = open('id_scan.txt', 'w')
file_object.writelines(scan)
from pyltp import SentenceSplitter
from pyltp import Segmentor
import csvTools
import re
from string import digits
from zhon.hanzi import punctuation
from tqdm import tqdm
import os
contexts = csvTools.readCSV('transformedlistd.csv')
complaint = ""
for onecontext in contexts:
temp = onecontext[-1]
# print(temp)
temp += ' '
complaint += temp
# print(complaint)
source_vocab = list(set(complaint.split()))
source_int_to_vocab = {idx: word for idx, word in enumerate(source_vocab)}
vocab = []
# print(source_int_to_vocab)
for one in source_int_to_vocab:
key = one
content = source_int_to_vocab[one]
temp = [key, content]
vocab.append(temp)
csvTools.writeCSV('vocab.csv', vocab)