def words_list(filepath):
wordslist = []
with open(filepath, mode = 'r',encoding = 'utf-8') as init_file:
for words_rec in init_file.readlines():
Aword = StringSplit.stringsplit(words_rec.strip(),(' ','|'))
wordslist.append(Aword[0])
return wordslist
def wordlist(Atext, split_list=' '): #split_list （单词间的分隔符以及需要过滤字符，默认为空格）
word_list = {}
for Aword in StringSplit.stringsplit(Atext, split_list):
lower_word = Aword.lower()
if (lower_word not in word_list):
word_list[lower_word] = 1
else:
word_list[lower_word] = word_list[lower_word] + 1
return word_list
def readWords(filepath):
with open(filepath, mode='rb') as read_file:
Words_list = []
BOM = read_file.read(3)
for word_rec in read_file.readlines():
Aword = StringSplit.stringsplit(
word_rec.decode('utf-8').strip(',').strip(), ',')
# print(Aword)
Aword_NM = {}
for word_NM in Aword[2:]:
word_no_me = StringSplit.stringsplit(word_NM, '.')
# print(word_no_me)
try:
Aword_NM[word_no_me[0] + '.'] = word_no_me[1]
except IndexError:
Aword_NM['other nominal'] = word_no_me[0]
Words_list.append(EnglishWord(Aword[0], Aword[1], Aword_NM))
return Words_list
from LearnModule import StringSplit
import json
infilePath = r'F:\memory\python-learning\learning2017\ESP_project\data_news\搜狐新闻语料库.json'
outfilePath = r'F:\memory\python-learning\learning2017\ESP_project\data_news\NewsCalsses.json'
NewsCalsses = {}
TotalCount = 0
with open(infilePath, mode='r', encoding='utf-8') as infile:
for aline in infile.readlines():
TotalCount += 1
try:
alineJson = json.loads(aline.strip())
except:
print('OrderId:%d -- %s' % (TotalCount, aline))
if ('url' in alineJson.keys()):
OneCalss = StringSplit.stringsplit(
StringSplit.stringsplit(alineJson['url'], '/')[1], '.')[0]
if (OneCalss not in NewsCalsses.keys()):
NewsCalsses[OneCalss] = alineJson['url']
if (TotalCount % 1000 == 0):
print('===== %d =====' % TotalCount)
print('=====在 %d 条数据中,类型读取结束 %d 个新闻类型=====' % (TotalCount, len(NewsCalsses)))
with open(outfilePath, mode='w', encoding='utf-8') as outfile:
for key in NewsCalsses:
outfile.write('%s\t%s' % (key, NewsCalsses[key]))
outfile.write('\n')
# for AClass in NewsCalsses:
# print(AClass)
#
# Acount = String_func.StrExtractNum(NBACschools[1],1)[0]
# print('%d: %d' %(i,Acount))
# i += 1
# NBACcount = NBACcount + Acount
for Arec in NBACschools[2:]:
if(Arec != '-' and Arec != ''):
# print(Arec.strip())
NBACSchoolList.append(Arec.strip())
# print('NBACCount = %d' %NBACcount)
# print('Count of NBACShool is %d' %(len(NBACSchoolList)))
# ========== 读取高等学校学科创新引智计划高校信息 ==========
P111schoolList = []
for Aschool in readCSV(datafilepath4,'utf-8'):
P111schools = StringSplit.stringsplit(Aschool[0],(':','、'))
# Acount = String_func.StrExtractNum(P111schools[0], 1)[0]
# print('%d: %d' %(i,Acount))
# i += 1
# NBACcount = NBACcount + Acount
for Arec in P111schools[1:]:
if (Arec != '-' and Arec != ''):
# print(Arec.strip())
P111schoolList.append(Arec.strip())
# print('NBACCount = %d' %NBACcount)
# print('Count of NBACShool is %d' %(len(P111schoolList)))
# ========== 读取985和211高校信息 ==========
HighSchoolCPinfo = {}
for Aschool in readCSV(datafilepath2,'GBK')[2:]:
data = {
'tableNames': 'officialdocs',
'size': 5000,
# 'query': 'title:石沉大海',
'field': 'record_type'
}
conn.request(method="POST", url="http://192.168.10.179:9095/api/MssSearchApi/searchByQuery", headers=headerdata,
body=parse.urlencode(data))
# 获取全部分析结果,转成json格式
get_result = json.loads(conn.getresponse().read().decode('utf-8'))
result_list = get_result['obj']['hits']['hits']
DocTypeList = []
splitstr = ['〔','第']
for Adata in result_list:
# print(Adata['_source']['symbol_of_document_lssuing'])
try:
AdocType = StringSplit.stringsplit(Adata['_source']['symbol_of_document_lssuing'],splitstr)[0]
except:
AdocType = ''
if(AdocType not in DocTypeList):
print(Adata['_source']['symbol_of_document_lssuing'])
DocTypeList.append(AdocType)
for Adata in DocTypeList:
print(Adata)
AfileName = FileName[0]
if (ischinese(AfileName)):
FileRecord['title'] = AfileName
else:
FileRecord['title'] = OutFiles[Findex].strip().decode(
'utf-8') + '_' + AfileName
if (Findex < len(OutFiles) - 1):
Findex += 1
else:
Findex = 0
FileRecord['file_suffix'] = FileName[1].strip('.').lower()
FileRecord['fileformat'] = FileRecord['file_suffix']
# ===============================设置文件路径相关属性==============================
SetFilePath = StringSplit.stringsplit(alineJson['文件路径'], '\\')
FilePath = ''
for Apath in SetFilePath[1:]:
FilePath = os.path.join(FilePath, Apath)
FileRecord['fileURL'] = FilePath
# ===============================设置文件所属分类==============================
FileCat = ''
for Apath in SetFilePath[2:-1]:
FileCat = FileCat + '//' + Apath
FileRecord['FilesCat'] = FileCat
# ===============================设置文件其他属性==============================
if ('备注' in AfileKey):
FileRecord['content'] = alineJson['备注'].strip()
elif (key == '作者'):
FileRecord['authors'] = alineJson[key]
elif (key == '文件大小'):
FileRecord['filesize'] = SetFileSize(int(alineJson[key]))
elif (key == '创建时间'):
FileRecord['edittime'] = FormatTime(alineJson[key])
elif (key == '修改时间'):
FileRecord['pubtime'] = FormatTime(alineJson[key])
FileRecord['belongdep'] = Data_normalization.SetDepartment(
deplist)
FileRecord['filename'] = FilePathList[fileindex][1]
FileName = os.path.splitext(FilePathList[fileindex][1])
# =========================================================
FilePathSet = StringSplit.stringsplit(
FilePathList[fileindex][0], '\\')
FilePath = ''
FilesCat = ''
for xpath in FilePathSet[3:]:
FilePath = os.path.join(FilePath, xpath)
for xpath in FilePathSet[4:]:
FilesCat = FilesCat + '//' + xpath
FileRecord['fileURL'] = os.path.join(
FilePath, FilePathList[fileindex][1])
FileRecord['FilesCat'] = FilesCat
FileRecord['title'] = FileName[0]
FileRecord['file_suffix'] = FileName[1].strip('.').lower()
FileRecord['fileformat'] = SetFileFormat(
FileRecord['file_suffix'])
FileRecord['viewcounts'] = random.randint(0, 117)
mode='rb') as imagesfile:
# OutImagesFiles = imagesfile.readlines()
for IFile in ImageFilesName:
if (IFile[2] != []):
for Afile in IFile[2]:
AimageFile['filename'] = Afile
AFileName, AFileSuffix = os.path.splitext(Afile)
if (ischinese(Afile)):
AimageFile['title'] = AFileName
else:
AimageFile['title'] = OutFiles[Findex].strip().decode(
'utf-8') + '_' + AFileName
AimageFile['file_suffix'] = AFileSuffix.strip('.')
FilePathSet = StringSplit.stringsplit(IFile[0], '\\')
FilePath = ''
FilesCat = ''
for xpath in FilePathSet[3:]:
FilePath = os.path.join(FilePath, xpath)
for xpath in FilePathSet[4:]:
FilesCat = FilesCat + '//' + xpath
AimageFile['fileURL'] = os.path.join(FilePath, Afile)
AimageFile['FilesCat'] = FilesCat
AimageFile['belongdep'] = SetDepartment(deplist)
AimageFile['viewcounts'] = random.randint(0, 163)
if (Findex < len(OutFiles) - 1):
Findex = Findex + 1
else:
Findex = 0
while (True):
if (alineStr[0] == '('):
while (alineStr[0] != ')'):
alineStr = alineStr[1:]
alineStr = alineStr[1:]
else:
break
AKLdata['content'] = alineStr
elif (key == 'question'):
AKLdata['title'] = alineJson[key]
elif (key == 'author'):
AKLdata['author'] = alineJson[key]
elif (key == 'tags'):
AKLdata['keywords'] = alineJson[key]
elif (key == 'answer_time'):
AKLdata['pubtime'] = StringSplit.stringsplit(
alineJson[key], 'T')[0]
AKLdata['viewcounts'] = random.randint(0, 83)
AKLdata['subjectCat'] = Data_normalization.SetCatlog(catlog)
AKLdata['belongdep'] = Data_normalization.SetDepartment(deplist)
# ============以下为给该条新闻随机分配一个附件============
appendixFilePath = Data_normalization.SetAppendixFiles(
appendixfilesPath, n)
if (appendixFilePath != ''):
n = n + 1
AKLdata['appendix_URL'] = appendixFilePath
AKLdata['appendix_filenames'] = [
os.path.basename(x) for x in appendixFilePath
]
else:
# -*- coding: utf-8 -*-
import random
from LearnModule import StringSplit
usernamelist = []
with open('F:\documents\python\learning2017\program data\测试用人员名单.dat',
mode='rb') as outfile:
outfile.readline()
for aline in outfile.readlines():
aline_decode = aline.decode('utf-8').strip()
Auser = StringSplit.stringsplit(aline_decode, '\t')
# print(Auser)
inserttag = 1
try:
username = Auser[3]
except IndexError as e:
print('%s-->第%s条有问题' % (e, Auser[0]))
inserttag = 0
except TypeError as e:
print('有问题')
inserttag = 0
if (inserttag):
usernamelist.append(username)
usernameset = set()
usernamelistlen = len(usernamelist)
while (len(usernameset) < 121):
usernameset.add(usernamelist[random.randint(0, usernamelistlen - 1)])
CurrentTable = PokerTable(initTableParameter(),[''] * 4, [''] * 4,menutext)
CurrentTable.ShowTable()
while (not ifVictory(CurrentTable.GamePokersList)):
GameOperating = input('请按上述菜单输入操作指令')
if(GameOperating.lower() == 'q'):
print('游戏结束 ! ')
break
elif(GameOperating.lower() == 'r'):
print('开始一局新游戏 ！')
CurrentTable = PokerTable(initTableParameter(), [''] * 4, [''] * 4, menutext)
CurrentTable.ShowTable()
else:
Operation = StringSplit.stringsplit(GameOperating,('(',')',','))
# print(Operation)
if(Operation[0] == '1'): #输入1（列号A，列号B,牌数N），表示将游戏区A列最下面的一组牌N张移动到游戏区B列最下面，N不输则为1张
ExcuteTag = 1
if(len(Operation) == 3):
MoveCount = 1
elif(len(Operation) == 4):
MoveCount = Operation[3]
else:
print('请按上述菜单要求输入正确的操作指令')
ExcuteTag = 0
if(ExcuteTag):
if(Game2Game(CurrentTable.GamePokersList,CurrentTable.TempPokersList,Operation[1],Operation[2],MoveCount)):
CurrentTable.ShowTable()
def time2seconds(time):
h, m, s = StringSplit.stringsplit(time, ':') #用分隔符“:”拆分成时、分、秒
return int(h) * 3600 + int(m) * 60 + int(s)
# -*- coding: utf-8 -*-
from LearnModule import StringSplit
KLcatlist = []
with open('F:/documents/python/learning2017/ESP_project/data_knowledge/学科分类11.dat', mode = 'rb') as infile:
for aline in infile.readlines():
aline_decode = aline.decode('utf-8').strip()
if(aline_decode != ''):
Arecord = StringSplit.stringsplit(aline_decode,' ')
# print(Arecord)
if(len(Arecord[0]) == 2):
Acatlvl1 = Arecord[1]
if(len(Arecord[0]) == 4):
Acatlvl2 = Arecord[1]
if(len(Arecord[0]) == 6):
Acatlvl3 = Arecord[1]
Acatlog = Acatlvl1 + '\\' + Acatlvl2 + '\\' + Acatlvl3
KLcatlist.append(Acatlog)
with open('F:/documents/python/learning2017/ESP_project/data_knowledge/学科分类22.dat', mode = 'wb') as outfile:
for arecord in KLcatlist:
outfile.write(arecord.encode('utf-8'))
outfile.write('\n'.encode('utf-8'))
# ClassNO_Split = []
test_txt_temp = []
# ZT_Class_dict = {}
with open('C:/Users/flyingaura/Desktop/test.txt', 'rb') as init_file:
for fline in init_file.readlines():
# fline.strip()
# print(fline)
fline_decode = fline.decode('utf-8')
# print(fline_decode)
if (fline_decode.strip() != ''):
test_txt_temp.append(fline_decode.strip())
# 对从文件中读出来的数据做处理
test_txt_temp.pop(0)
for key in test_txt_temp:
fline_split.append(StringSplit.stringsplit(key, '\t'))
for Kstring in fline_split:
if (len(Kstring) == 1):
ZTNo_List.append(ZTNo_source(Kstring[0], '', ''))
elif (len(Kstring) == 2):
for ZTkey in StringSplit.stringsplit(Kstring[1], ';'):
ZTNo_List.append(ZTNo_source(Kstring[0], ZTkey, ''))
else:
ZTNo_temp = StringSplit.stringsplit(Kstring[1], ';')
ZTNo_name = StringSplit.stringsplit(Kstring[2], ';')
for i in range(len(ZTNo_temp)):
if (i < len(ZTNo_name)):
ZTNo_List.append(
ZTNo_source(Kstring[0], ZTNo_temp[i], ZTNo_name[i]))
else:
ZTNo_List.append(ZTNo_source(Kstring[0], ZTNo_temp[i], ''))
# -*-coding: utf-8 -*-
# 将分析出来的新闻类型转化为中文
from LearnModule import StringSplit
infilepath = r'F:\memory\python-learning\learning2017\ESP_project\data_news\NewsCalsses.json'
RestClasses = []
with open(infilepath, mode='r', encoding='utf-8') as infile:
for aline in infile.readlines():
if ('auto' in StringSplit.stringsplit(aline, '\t')[1]):
continue
else:
print(aline)
RestClasses.append(aline)
# print(len(RestClasses))
alias_street_list.append(self.street[:filter_index])
if (alias_street_list):
return alias_street_list
else:
return None
toponymy_list = []
the_towns = '-'
with open('C:/Users/flyingaura/Desktop/昌平区.dat', mode='rb') as in_file:
the_province = '北京市'
the_city = in_file.readline().decode('utf-8').strip()
for rec in in_file.readlines():
rec_data = rec.decode('utf-8').strip()
if ('\t' in rec_data):
rec_TS = StringSplit.stringsplit(rec_data, '\t')
the_towns = rec_TS[0]
rec_street = rec_TS[1].strip('\"')
else:
rec_street = rec_data.strip('\"')
if (rec_street):
for the_street in StringSplit.stringsplit(rec_street, '、'):
rec_toponymy = toponymy(the_province, the_city, the_towns,
the_street)
toponymy_list.append(rec_toponymy)
# for rec_ty in toponymy_list:
# print('============ %s' %rec_ty.street)
province_list = []
# -*- coding: utf-8 -*-
from LearnModule import StringSplit
with open('C:/Users/flyingaura/Desktop/test.txt', mode='rb') as wordsfile:
wordsfile.readline()
# print(wordsfile.readline().decode('utf-8'))
all_words = []
for line in wordsfile.readlines():
for word in StringSplit.stringsplit(
line.decode('utf-8').strip(), (',', ' ', '.', '-')):
all_words.append(word.lower())
print('The count of Speech Words is: %d' % len(all_words))
print(list(all_words))
unique_words = {}
for aword in all_words:
if (aword not in unique_words.keys()):
unique_words[aword] = all_words.count(aword)
print('the count of unique words in this speech is : %d ' % len(unique_words))
for keys in sorted(unique_words, key=lambda x: unique_words[x], reverse=True):
print('%s : %d ' % (keys, unique_words[keys]))
if(tagList[i] < Sep_tagList[i]):
tag_name = 'tag' + chr(ord('A') + i)
BadDiag_wrong[tag_name] = BadDiag_wrong[tag_name] + 1
return (GoodDiag_wrong,BadDiag_wrong)
# ================ 主程序 =====================
AllData = []
# 从文件中读取所有学习数据
with open('C:/Users/flyingaura/Desktop/breast-cancer-wisconsin.data', mode = 'rb') as Datafile:
for Aline in Datafile.readlines():
Adata = []
save_tag = 1
Aline_decode = Aline.decode('utf-8').strip()
for x in StringSplit.stringsplit(Aline_decode,','):
try:
Adata.append(int(x))
except ValueError:
save_tag = 0
break
if(save_tag):
AllData.append(breast_data(Adata[0],Adata[1],Adata[2],Adata[3],Adata[4], Adata[5],
Adata[6],Adata[7],Adata[8],Adata[9],Adata[10]))
# 随机选取400组做为训练语料，剩下的做为测试语料
ML_indexList = set()
ML_count = 400
DataCount = len(AllData)
print(DataCount)
if(DataCount < 400):
def get_duty(self):
return self.duty
def get_mobilephone(self):
return self.mobilephone
def get_email(self):
return self.email
# --------从文件中读所有人名---------
person_list = []
with open('C:/Users/flyingaura/Desktop/Chinese_surname.txt','rb') as person_file:
# 按行读取每个人的基本信息，并保存到person_list列表里
for one in person_file.readlines():
OnePerson = StringSplit.stringsplit(one.strip().decode('utf-8'), '\t')
Pinfo_temp = ['','','','']
for i in range(len(OnePerson)):
Pinfo_temp[i] = OnePerson[i]
personinfo = person_info(Pinfo_temp[0],Pinfo_temp[1],Pinfo_temp[2],Pinfo_temp[3])
person_list.append(personinfo)
person_list.pop(0)
# 开始分析
sur_list = []
# 把所有的姓都取出来!
for person_key in person_list:
sur_list.append(get_surname(person_key.get_name()))
# print(sur_list)
# 对姓进行统计
index_sur = []
# ================ 主程序 =====================
# AllData = []
breastPatientList = []
# 从文件中读取所有学习数据
with open('G:/memory/python-learning/learning2017/program data/breast-cancer-wisconsin.data', mode = 'rb') as Datafile:
for Aline in Datafile.readlines():
# breastAttrList = []
# save_tag = 1
Aline_decode = Aline.decode('utf-8').strip()
APatientData = StringSplit.stringsplit(Aline_decode,',')
try:
breastAttrList = [[int(x),'',0] for x in APatientData[1:-1]]
except ValueError as e:
print('ValueError --> 参数错误，该参数无法转换为数值')
continue
ABpatient = breast_patients(0,[],'')
ABpatient.patientID = APatientData[0]
ABpatient.breastAttrList = breastAttrList
if(APatientData[-1] == '2'):
ABpatient.diagResult = 'Good'
elif(APatientData[-1] == '4'):
ABpatient.diagResult = 'Bad'
else:
ABpatient.diagResult = 'UnKnown'
# 对模块的使用测试
# -*- coding: utf-8 -*-
import sys
import math
import functools
from LearnModule import Module_test
from LearnModule import StringSplit
from LearnModule import String_func
print('the module\'s note is :', Module_test.__doc__)
print('the module\'s author is :', Module_test.__author__)
print('the module\' edit time is : ', StringSplit.__edittime__)
# Module_test.test()
StrList = 'aaa,acb.923asd,88sdfffdd.,sdfk__sldf,1sdfjjj,asiw2,ddd,AFD'
# 先进行字符串拆分
StrNList = StringSplit.stringsplit(StrList, (',', 's'))
# 给每个字符串加上分隔符
for StrN in StrNList:
print(String_func.StringAddVal(StrN, '***'))
# -*- coding: utf-8 -*-
# 整理公司通讯录，生成完整的组织机构
from LearnModule import StringSplit
OrgList = []
with open('C:/Users/flyingaura/Desktop/公司通讯录数据（开发用）.dat',
mode='rb') as outfile:
for aline in outfile.readlines():
aline_decode = aline.decode('utf-8')
OrgList.append(StringSplit.stringsplit(aline_decode.strip(), '\t'))
# print(OrgList)
OrgNameList = []
OrgTemp = []
for unit in OrgList:
if (unit == None):
unit = []
OrgName = ''
if (len(unit) > 1):
for alevel in unit:
OrgName = OrgName + '\\' + alevel
OrgNameList.append(OrgName)
OrgTemp = unit[:-1]
elif (len(unit) == 1):
if (OrgTemp == []):
OrgName = OrgName + '\\' + unit[0]
else:
for alevel in OrgTemp:
# print(alevel)
OrgName = OrgName + '\\' + alevel
n = 0 #分配附件用的起始值
with open(
'F:/documents/python/learning2017/ESP_project/data_news/origin_news.json',
mode='rb') as infile: #origin_news
StripStr = '安卓网 > \t\t\t\t科技频道 \t\t\t\t\t\t\t\t\t \t\t\t\t\t\t\t\t\t > 互联\t\t\t\t\t\t\t \t\t <!-- //头部 ---> \t \t\t\t \t\t\t\t \t\t\t\t\t'
for Aline in infile.readlines():
Aline_decode = Aline.decode('utf-8').strip()
AlineJson = json.loads(Aline_decode)
# print(AlineJson)
for key in AlineJson:
# print(key)
if (key == '标题'):
AnormalData['title'] = AlineJson[key]
elif (key == '正文内容'):
try:
AnormalData['content'] = StringSplit.stringsplit(
AlineJson[key].strip(StripStr), '\t')[-1]
except TypeError as e:
print(AlineJson[key].strip(StripStr))
elif (key == '链接'):
AnormalData['Original_address'] = AlineJson[key]
AnormalData['pubtime'] = SetPubtime(20150101, '00:00:00',
random.randint(0, 730),
random.randint(0, 24 * 3600))
AnormalData['belongdep'] = SetDepartment(deplist)
AnormalData['viewcounts'] = random.randint(0, 76)
AnormalData['source'] = SetSource(sourcelist)
AnormalData['NewsCat'] = SetCatlog(catlog)
#============以下为给该条新闻随机分配一个附件============
# 打开梭哈扑克牌面文件 showhand_pokers.dat
with open('C:/Users/flyingauraHome/Desktop/showhand_pokers.dat',
mode='r') as showhandfile:
showhandfile.readline()
#===========================开始计算各种牌面类型===========================
start_time = time.time()
print(
'============== Showhand Pokers Aggregations by Ranks! Now Starting Calculation @ %s =============='
% time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(start_time)))
showhand_count = 0
for line in showhandfile.readlines(
): #每一行:[A(1),Heart] [A(1),Spade] [A(1),Diamond] [A(1),Club] [2(2),Heart]
error_tag = 0
onehand = []
for mpoker in StringSplit.stringsplit(
line.strip(), ('[', ']', '\t')): #分解成5个独立的poker牌字符串:A(1),Heart
ppoker = StringSplit.stringsplit(
mpoker, ('(', ')', ',')) #每个poker牌字符串分解成poker的三种属性:A,1,Heart
try:
onehand.append(Apoker(int(ppoker[1]), ppoker[2]))
except ValueError as e:
print('ValueError:%s' % e)
error_tag = 1
# showhand_count = showhand_count - 1
# for onepoker in onehand:
# print('[%s(%d),%s]' % (onepoker.Value_show(), onepoker.Pvalue, onepoker.Pflower), end='\t')
# print('\n')
if (error_tag):
continue
straight_tag = 0
pairs_poker = count_pairs(onehand)
def FormatTime(xtime):
Ftime = StringSplit.stringsplit(xtime, ('T', 'Z'))
return Ftime[0] + ' ' + Ftime[1]
def readCSV(filepath, reqcode='utf-8'):
with open(filepath, mode='r', encoding=reqcode) as infile:
datalist = []
for aline in csv.reader(infile):
datalist.append(aline)
return datalist
DataDistrList = []
for aline in readCSV(filepath):
DataRec = {}
if (not aline[0].isdigit()):
DataDistr = StringSplit.stringsplit(aline[0], ('（', '）'))
try:
DataRec[DataDistr[0]] = String_func.StrExtractNum(DataDistr[1],
1)[0]
except IndexError:
continue
DataDistrList.append(DataRec)
with open(r'F:\documents\python\learning2017\program data\高校相关数据\高校按省分布.dat',
mode='w',
encoding='utf-8') as outfile:
for Arec in DataDistrList:
for key in Arec:
outfile.write('%s\t%d' % (key, Arec[key]))
outfile.write('\n')