def standardizing():
datapath = 'MergedDataSecond.csv'
resultList = []
with open(datapath, 'r', encoding='utf-8') as f:
data_csv = csv.DictReader(f)
for row in data_csv:
dictTemp = {}
timeUnStandard = (row['\ufeff年月日时分'])
dataString = timeUnStandard[0:10]
hourString = timeUnStandard[11:13]
minuteString = timeUnStandard[13:]
timeStandard = dataString + ' ' + hourString + ':' + minuteString + ':' + '00'
dictTemp['时间'] = timeStandard
timeDatetime = datetime.strptime(timeStandard, '%Y-%m-%d %H:%M:%S')
area = row['area'].upper()
if area != 'Y' and timeDatetime.month == 4:
dictTemp['区域'] = area
# dictTemp[]
dictTemp['气温'] = row['气温']
dictTemp['风向'] = row['风向']
dictTemp['风速'] = row['风速']
dictTemp['雨量'] = row['雨量']
dictTemp['AQI'] = row['AQI']
dictTemp['空气质量'] = row['AIRQUALITY']
resultList.append(dictTemp)
print(dictTemp)
# print(dictTemp)
hearders = ['时间', '区域', '气温', '风向', '风速', '雨量', 'AQI', '空气质量']
filename = '清洗完毕天气与空气质量总表'
writeData(resultList, headers=hearders, filename=filename)
def merge():
trafficDataPath = '公交出租总表.csv'
AirAndPollutionDataPath = '清洗完毕天气与空气质量总表.csv'
dataList = []
trafficFile = open(trafficDataPath, 'r', encoding='utf-8')
traffic_csv = csv.DictReader(trafficFile)
for trafficDataRow in traffic_csv:
# print(trafficDataRow)
mergeDictTemp = {}
trafficTimeTemp = datetime.strptime(trafficDataRow['时间'],
'%Y-%m-%d %H:%M:%S')
trafficArea = trafficDataRow['区域']
mergeDictTemp['时间'] = trafficTimeTemp
mergeDictTemp['区域'] = trafficArea
mergeDictTemp['出租车数量'] = trafficDataRow['出租车数量']
mergeDictTemp['公交车数量'] = trafficDataRow['公交车数量']
with open(AirAndPollutionDataPath, 'r', encoding='utf-8') as AirFile:
air_csv = csv.DictReader(AirFile)
flag = 0
for airDataRow in air_csv:
# print(airDataRow)
if airDataRow['时间'] != '时间':
airTimeTemp = datetime.strptime(airDataRow['时间'],
'%Y-%m-%d %H:%M:%S')
airArea = airDataRow['区域']
# 相等 则存入数据
if trafficTimeTemp == airTimeTemp and trafficArea == airArea:
flag = 1
# print(airDataRow)
print(trafficDataRow)
mergeDictTemp['气温'] = airDataRow['气温']
mergeDictTemp['风向'] = airDataRow['风向']
mergeDictTemp['风速'] = airDataRow['风速']
mergeDictTemp['雨量'] = airDataRow['雨量']
mergeDictTemp['AQI'] = airDataRow['AQI']
mergeDictTemp['空气质量'] = airDataRow['空气质量']
print(mergeDictTemp)
dataList.append(mergeDictTemp)
# print('**')
break
if flag == 0:
# print(trafficDataRow)
print()
print('***')
headers = [
'时间', '区域', '出租车数量', '公交车数量', '气温', '风向', '风速', '雨量', 'AQI', '空气质量'
]
fileName = '汇合的表格'
writeData(dataList, headers, fileName)
def deleteDateOfB():
'''
除掉表中的B区数据
:return:
'''
cleanedList = []
busDataPath = '公交与出租.csv'
with open(busDataPath, 'r', encoding='utf-8') as f:
data_csv = csv.DictReader(f)
for row in data_csv:
if row['区域'] != 'B':
cleanedList.append(row)
dataHeaders = ['时间', '区域', '出租车数量', '公交车数量']
fileName = '公交出租总表'
writeData(cleanedList, dataHeaders, fileName)
def getBusTimeAndCount(area, timeHeader):
dataPath = '公交数据/' + area + '.csv'
print('正在打开...', dataPath)
busCountList = [{'时间': 0, '区域': 0, '数量': 0}]
with open(dataPath, 'r', encoding='utf-8') as f:
data_csv = csv.DictReader(f)
for row in data_csv:
# print(row['2015-01-01 07:00:53'])
busRealTime = datetime.strptime(row[timeHeader],
'%Y-%m-%d %H:%M:%S') # 真实时间
if busRealTime.month == 4: # 只计算四月的
busDict = {}
busStandardTime = standardTime(busRealTime)
busDict['区域'] = area
busDict['时间'] = busStandardTime
if busDict['时间'] is None:
if busRealTime.day == 30 and (busRealTime.month == 4 or 6
or 9 or 11):
busDict['时间'] = datetime(year=busRealTime.year,
month=busRealTime.month + 1,
day=1)
else:
busDict['时间'] = datetime(year=busRealTime.year,
month=busRealTime.month,
day=busRealTime.day + 1)
# print(busDict)
flag = 0 # 是否找到
for busCount in busCountList:
if busCount['时间'] == busDict['时间'] and busCount[
'区域'] == busDict['区域']:
print('区域与时间相等')
print('本次循环的出租车信息(taxiDict):', busDict)
print('List中对应的出租车信息(taxiCount):', busCount)
busCountTemp = busCount['数量']
busCount['数量'] = busCountTemp + 1
flag = 1
break
if flag == 0:
busDict['数量'] = 1
busCountList.append(busDict)
f.close()
dataHeaders = ['时间', '区域', '数量']
fileName = '公交车数量' + area + '区域数据'
writeData(busCountList, dataHeaders, fileName)
def mergeData():
taxiDataPath = '出租车数量总表.csv'
taxiFile = open(taxiDataPath, 'r', encoding='utf-8')
mergedList = []
taxi_csv = csv.DictReader(taxiFile)
for taxiRow in taxi_csv:
# 正常存入时间 区域 出租车数量
mergedDictTemp = {}
areaTemp = taxiRow['区域']
# print(taxiRow['时间'] + ':00')
timeTemp = datetime.strptime(taxiRow['时间']+':00', '%Y/%m/%d %H:%M:%S') # 转化为datatime格式
mergedDictTemp['时间'] = timeTemp
mergedDictTemp['区域'] = areaTemp
mergedDictTemp['出租车数量'] = taxiRow['数量']
# 根据区域检查公交车数量是否齐全
busDataPath = '公交车数量数据/公交车数量' + areaTemp + '区域数据.csv'
# print('此时的公交车区域为:::', areaTemp)
if areaTemp != 'B':
with open(busDataPath, 'r', encoding='utf-8') as busFile:
bus_csv = csv.DictReader(busFile)
busFlag = 0
for busRow in bus_csv:
# 时间转化为datatime格式
if busRow['时间'] != '0' and busRow['时间'] != '时间':
busTime = datetime.strptime(busRow['时间'], '%Y-%m-%d %H:%M:%S')
if timeTemp == busTime:
mergedDictTemp['公交车数量'] = busRow['数量']
busFlag = 1
if busFlag == 0:
print('公交车数据不全,现在的数据状态为:::', mergedDictTemp)
mergedDictTemp['公交车数量'] = 0
print('之后的状态', mergedDictTemp)
mergedList.append(mergedDictTemp)
dataHeaders = ['时间', '区域', '出租车数量', '公交车数量']
fileName = '公交与出租'
writeData(mergedList, dataHeaders, fileName)