视频1 视频21 视频41 视频61 视频文章1 视频文章21 视频文章41 视频文章61 推荐1 推荐3 推荐5 推荐7 推荐9 推荐11 推荐13 推荐15 推荐17 推荐19 推荐21 推荐23 推荐25 推荐27 推荐29 推荐31 推荐33 推荐35 推荐37 推荐39 推荐41 推荐43 推荐45 推荐47 推荐49 关键词1 关键词101 关键词201 关键词301 关键词401 关键词501 关键词601 关键词701 关键词801 关键词901 关键词1001 关键词1101 关键词1201 关键词1301 关键词1401 关键词1501 关键词1601 关键词1701 关键词1801 关键词1901 视频扩展1 视频扩展6 视频扩展11 视频扩展16 文章1 文章201 文章401 文章601 文章801 文章1001 资讯1 资讯501 资讯1001 资讯1501 标签1 标签501 标签1001 关键词1 关键词501 关键词1001 关键词1501 专题2001
python处理csv数据的方法
2020-11-27 14:32:02 责编:小采
文档


本文实例讲述了python处理csv数据的方法。分享给大家供大家参考。具体如下:

Python代码:

代码如下:


#coding=utf-8
__author__ = 'dehua.li'
from datetime import *
import datetime
import csv
import sys
import time
import string
import os
import os.path
import pylab as plt
rootdir='/nethome/dehua.li/orderlifeCycleData/xingzheng'
writeFileDir="/nethome/dehua.li/orderlifeMyWork/xingzheng/csv"
heyueFile="/nethome/dehua.li/orderlifeCycleData/heyue_150128.csv"
ms_acked="1"
msg=[]
ex=[]
def getTheDate(date):
[filenamePart1,filenamePart2]=string.split(filename,'.')
[filenamePart11,filenamePart12,filenamePart13]=string.split(filenamePart1,'_')
return filenamePart13
LocalTime=datetime.datetime.fromtimestamp(time.mktime(time.strptime("2014-11-04 20:59:59","%Y-%m-%d %H:%M:%S")))
for parent,dirname,filenames in os.walk(rootdir):
for filename in filenames:
fileNameWrite=os.path.join(writeFileDir,filename)
print fileNameWrite
csvfile00=open(fileNameWrite,'wb')
writer1=csv.writer(csvfile00)
writer1.writerow(['FeedCode','OrderId','Status','LocalTime','Time','Exchange'])
fileName=os.path.join(parent,filename)
[filenamePart1,filenamePart2]=string.split(filename,'.')
[filenamePart11,filenamePart12,filenamePart13]=string.split(filenamePart1,'_')
#filenamePart11_filenamePart12_filenamePart13.filenamePart2:dongzheng_orderlifeCycleData_20150111.csv
print fileName
with open(fileName,'rb') as csvfile:
reader=csv.reader(csvfile)
CsvItem=[row for row in reader]
for item in CsvItem:
if item[3]=='TPO':
#print " filter TPO "
continue
if item[12]=='Sent':
[tm_local,ms_local]=string.split(item[15],'.')
[tm_localup,ms_localup]=string.split(item[19],'.')
LocalTime=datetime.datetime.fromtimestamp(time.mktime(time.strptime(tm_local,"%Y-%m-%d %H:%M:%S")))
LocalUpdate=datetime.datetime.fromtimestamp(time.mktime(time.strptime(tm_localup,"%Y-%m-%d %H:%M:%S")))
tm=int(((LocalTime-LocalUpdate).seconds))*1000
ms_sent=str(int(ms_local)-int(ms_localup)+tm)
if int(ms_sent)>10*60*1000:
print "ms_sent>600000"
continue
if(int(ms_local)-int(ms_localup)+tm)<0:
print 'wrong1'
msg=[]
msg.append(item[0])
msg.append(item[1])
msg.append(item[12])
msg.append(item[15])
msg.append(ms_sent)
with open(heyueFile,'rb') as csvfile1:
reader=csv.reader(csvfile1)
CsvItem=[row for row in reader]
for Item in CsvItem:
if Item[1]==item[0]:
msg.append(Item[3])
writer1.writerow(msg)
#print 'write ok'
ex=Item[3]
break
csvfile1.close()
with open(fileName,'rb') as csvfile22:
reader=csv.reader(csvfile22)
CsvItem2=[row for row in reader]
for item_ in CsvItem2:
if item_[12]=='Acked' and item_[1]==item[1]:
[tm_local2,ms_local2]=string.split(item_[15],'.')
LocalTime2=datetime.datetime.fromtimestamp(time.mktime(time.strptime(tm_local2,"%Y-%m-%d %H:%M:%S")))
tm2=int(((LocalTime2-LocalTime).seconds))*1000
ms_acked=str(int(ms_local2)-int(ms_local)+tm2)
if int(ms_acked)>10*60*1000:
print "MSacked>600000"
continue
msg=[]
msg.append(item_[0])
msg.append(item_[1])
msg.append(item_[12])
msg.append(item_[15])
msg.append(ms_acked)
with open(heyueFile,'rb') as csvfile111:
reader=csv.reader(csvfile111)
CsvItem=[row for row in reader]
for Item in CsvItem:
if Item[1]==item[0]:
msg.append(Item[3])
writer1.writerow(msg)
#print 'write ok'
break
#print "write ok"
csvfile22.close()
csvfile.close()
csvfile00.close()

代码如下:


#coding=utf-8
#__author__ = 'dehua.li'
from datetime import *
import datetime
import csv
import sys
import time
import string
import os
import os.path
import pylab as plt
def median(lst):
even = (0 if len(lst) % 2 else 1) + 1
half = (len(lst) - 1) / 2
return sum(sorted(lst)[half:half + even]) / float(even)
def mean(lst):
if len(lst)==0:
return 0
return sum(lst)/len(lst)
nightLine="21:01:00"
morningLine="09:01:00"
def getTheDate(date):
[filenamePart1,filenamePart2]=string.split(filename,'.')
[filenamePart11,filenamePart12,filenamePart13]=string.split(filenamePart1,'_')
return filenamePart13
def afterOneMin(time):
[tm_local,ms_local]=string.split(time,'.')
[ymd,hms]=string.split(tm_local,' ')
flag=0
if hms>"21:01:00":
flag=1
elif hms>"09:01:00" and hms<"20:00:00":
flag=1
elif hms>"00:00:00" and hms<"05:00:00":
flag=1
return flag
rootdir="/nethome/dehua.li/orderlifeMyWork/xingzheng/csv"
#csvfileMaxMin = open('e:\dehua.li\csv\__xingzhenMaxMin.csv','wb')
#writer1 = csv.writer(csvfileMaxMin)
#writer1.writerow(['FeedCode','date','SentMaxTime','SentMaxLocalTime','SentMinTime','SentMinLocalTime','SentMeanTime','SentMedian','AckedMaxTime','AckedMaxLocalTime','AckedMinTime','AckedMinLocalTime','AckedMeanTime','AckedMedianTime','Exchange'])
#writer1.writerow(['FeedCode','date','SentMaxTime','SentMinTime','SentMeanTime','SentMedian','AckedMaxTime','AckedMinTime','AckedMeanTime','AckedMedianTime','Exchange'])
msg=[]
codeList=list()
orderList=list()
itemSentList=[]
itemAckedList=[]
feedCode=[]
exchange=[]
zhengshangSentMedian=0
zhengshangSentMean=0
zhengshangAckedMedian=0
zhengshangAckedMean=0
dashangSentMedian=0
dashangSentMean=0
dashangAckedMedian=0
dashangAckedMean=0
shangqiSentMedian=0
shangqiSentMean=0
shangqiAckedMedian=0
shangqiAckedMean=0
zhongjinSentMedian=0
zhongjinSentMean=0
zhongjinAckedMedian=0
zhongjinAckedMean=0
zhengshangSent=[]
zhengshangAcked=[]
dashangSent=[]
dashangAcked=[]
shangqiSent=[]
shangqiAcked=[]
zhongjinSent=[]
zhongjinAcked=[]
zhengshangSentMedianAll=[]
zhengshangSentMeanAll=[]
zhengshangAckedMedianAll=[]
zhengshangAckedMeanAll=[]
dashangSentMedianAll=[]
dashangSentMeanAll=[]
dashangAckedMedianAll=[]
dashangAckedMeanAll=[]
shangqiSentMedianAll=[]
shangqiSentMeanAll=[]
shangqiAckedMedianAll=[]
shangqiAckedMeanAll=[]
zhongjinSentMedianAll=[]
zhongjinSentMeanAll=[]
zhongjinAckedMedianAll=[]
zhongjinAckedMeanAll=[]
zhengshang='0'
dashang='0'
shangqi='0'
zhongjin='0'
with open('/nethome/dehua.li/orderlifeCycleData/heyue_150128.csv','rb') as csvfile:
reader=csv.reader(csvfile)
csvItem=[row for row in reader]
zhengshang=csvItem[300][3]
dashang=csvItem[5][3]
shangqi=csvItem[165][3]
zhongjin=csvItem[435][3]
#for item in csvItem:
# if item[3]==zhengshang:
# print item
for parent,dirname,filenames in os.walk(rootdir):
for filename in filenames:
fileName=os.path.join(rootdir,filename)
csvfile1=open(fileName,'rb')
reader=csv.reader(csvfile1)
CsvItem=[row for row in reader]
for item in CsvItem:
if item[0]=='FeedCode':
continue
if item[0] not in codeList:
codeList.append(item[0])
#print CsvItem[15]
if len(item)<=5:
print fileName
print item
print '++++++++++++++++++++++++++++++'
#if afterOneMin(item[3])==0:
# print item[3]
# continue
if item[5]==zhengshang and item[2]=='Sent':
zhengshangSent.append(int(item[4]))
elif item[5]==zhengshang and item[2]=='Acked':
zhengshangAcked.append(int(item[4]))
elif item[5]==dashang and item[2]=='Sent':
dashangSent.append(int(item[4]))
elif item[5]==dashang and item[2]=='Acked':
dashangAcked.append(int(item[4]))
elif item[5]==shangqi and item[2]=='Sent':
shangqiSent.append(int(item[4]))
if int(item[4])>=600000:
print "------------"
print item
elif item[5]==shangqi and item[2]=='Acked':
shangqiAcked.append(int(item[4]))
elif item[5]==zhongjin and item[2]=='Sent':
zhongjinSent.append(int(item[4]))
elif item[5]==zhongjin and item[2]=='Acked':
zhongjinAcked.append(int(item[4]))
else:
print "wrong info"
print item
if mean(shangqiSent)>420000:
print sum(shangqiSent)
print len(shangqiSent)
print item
print fileName
print shangqiSent
zhengshangSentMedian=median(zhengshangSent)
zhengshangSentMean=mean(zhengshangSent)
zhengshangAckedMedian=median(zhengshangAcked)
zhengshangAckedMean=mean(zhengshangAcked)
dashangSentMedian=median(dashangSent)
dashangSentMean=mean(dashangSent)
dashangAckedMedian=median(dashangAcked)
dashangAckedMean=mean(dashangAcked)
shangqiSentMedian=median(shangqiSent)
shangqiSentMean=mean(shangqiSent)
shangqiAckedMedian=median(shangqiAcked)
shangqiAckedMean=mean(shangqiAcked)
zhongjinSentMedian=median(zhongjinSent)
zhongjinSentMean=mean(zhongjinSent)
zhongjinAckedMedian=median(zhongjinAcked)
zhongjinAckedMean=mean(zhongjinAcked)
#if mean(shangqiSent)>70:
# print '================================'
# print fileName
#print codeList
'''
for listItem in codeList:
itemSentList=[]
itemAckedList=[]
for item in CsvItem:
if item[0]==listItem and item[2]=='Sent':
itemSentList.append(int(item[4]))
exchange=item[5]
elif item[0]==listItem and item[2]=='Acked':
itemAckedList.append(int(item[4]))
#print itemSentList
itemMaxSent=max(itemSentList)
itemMinSent=min(itemSentList)
itemAvgSent=sum(itemSentList)/len(itemSentList)
itemMaxAcked=max(itemAckedList)
itemMinAcked=min(itemAckedList)
itemAvgAcked=sum(itemAckedList)/len(itemAckedList)
SentMedian=median(itemSentList)
AckedMedian=median(itemAckedList)
msg=[]
msg.append(listItem) #0
msg.append("2015/01/14") #1
msg.append(itemMaxSent) #2
msg.append(itemMinSent) #3
msg.append(itemAvgSent) #4
msg.append(SentMedian) #5
msg.append(itemMaxAcked) #6
msg.append(itemMinAcked) #7
msg.append(itemAvgAcked) #8
msg.append(AckedMedian) #9
msg.append(exchange) #10
if len(msg)>15:
print "------------------------------"
print msg
writer1.writerow(msg)
'''
zhengshangSentMedianAll.append(zhengshangSentMedian)
zhengshangSentMeanAll.append(zhengshangSentMean)
zhengshangAckedMedianAll.append(zhengshangAckedMedian)
zhengshangAckedMeanAll.append(zhengshangAckedMean)
dashangSentMedianAll.append(dashangSentMedian)
dashangSentMeanAll.append(dashangSentMean)
dashangAckedMedianAll.append(dashangAckedMedian)
dashangAckedMeanAll.append(dashangAckedMean)
shangqiSentMedianAll.append(shangqiSentMedian)
shangqiSentMeanAll.append(shangqiSentMean)
shangqiAckedMedianAll.append(shangqiAckedMedian)
shangqiAckedMeanAll.append(shangqiAckedMean)
zhongjinSentMedianAll.append(zhongjinSentMedian)
zhongjinSentMeanAll.append(zhongjinSentMean)
zhongjinAckedMedianAll.append(zhongjinAckedMedian)
zhongjinAckedMeanAll.append(zhongjinAckedMean)
plt.figure(1)
plt.figure(2)
plt.figure(3)
plt.figure(4)
plt.figure(1)
plt.title('SentMean r-zhengshang b-dashang,green-shangqi grey-zhongjin')
plt.plot(range(1,len(zhengshangSentMeanAll)+1),zhengshangSentMeanAll,'r')
plt.plot(range(1,len(dashangSentMeanAll)+1),dashangSentMeanAll,'b')
plt.plot(range(1,len(shangqiSentMeanAll)+1),shangqiSentMeanAll,'g')
plt.plot(range(1,len(zhongjinSentMeanAll)+1),zhongjinSentMeanAll,'grey')
plt.savefig('/nethome/dehua.li/orderlifeMyWork/xingzheng/data_noTPO_in10minutes/SentMean.png')
plt.figure(2)
plt.title('SentMedian r-zhengshang b-dashang,green-shangqi grey-zhongjin')
plt.plot(range(1,len(zhengshangSentMedianAll)+1),zhengshangSentMedianAll,'r')
plt.plot(range(1,len(dashangSentMedianAll)+1),dashangSentMedianAll,'b')
plt.plot(range(1,len(shangqiSentMedianAll)+1),shangqiSentMedianAll,'g')
plt.plot(range(1,len(zhongjinSentMedianAll)+1),zhongjinSentMedianAll,'grey')
plt.savefig('/nethome/dehua.li/orderlifeMyWork/xingzheng/data_noTPO_in10minutes/SentMedian.png')
plt.figure(3)
plt.title('AckedMean r-zhengshang b-dashang,green-shangqi grey-zhongjin')
plt.plot(range(1,len(zhengshangAckedMeanAll)+1),zhengshangAckedMeanAll,'r')
plt.plot(range(1,len(dashangAckedMeanAll)+1),dashangAckedMeanAll,'b')
plt.plot(range(1,len(shangqiAckedMeanAll)+1),shangqiAckedMeanAll,'g')
plt.plot(range(1,len(zhongjinAckedMeanAll)+1),zhongjinAckedMeanAll,'grey')
plt.savefig('/nethome/dehua.li/orderlifeMyWork/xingzheng/data_noTPO_in10minutes/AckedMean.png')
plt.figure(4)
plt.title('AckedMedian r-zhengshang b-dashang,green-shangqi grey-zhongjin')
plt.plot(range(1,len(zhengshangAckedMedianAll)+1),zhengshangAckedMedianAll,'r')
plt.plot(range(1,len(dashangAckedMedianAll)+1),dashangAckedMedianAll,'b')
plt.plot(range(1,len(shangqiAckedMedianAll)+1),shangqiAckedMedianAll,'g')
plt.plot(range(1,len(zhongjinAckedMedianAll)+1),zhongjinAckedMedianAll,'grey')
plt.savefig('/nethome/dehua.li/orderlifeMyWork/xingzheng/data_noTPO_in10minutes/AckedMedian.png')
plt.show()
print 'over'

希望本文所述对大家的Python程序设计有所帮助。

下载本文
显示全文
专题