python pandas 对时间序列文件处理的实例

import pandas as pd
from numpy import *
import matplotlib.pylab as plt
import copy

def read(filename):
 dat=pd.read_csv(filename,iterator=True)
 loop = True
 chunkSize = 1000000
 R=[]
 while loop:
  try:
   data = dat.get_chunk(chunkSize)
   data=data.loc[:,'B':'C'] # 切片
   data=data[data.B==855]  #条件选择
   data['C']=pd.to_datetime(data['C']) # 转换成时间格式
   data=data.set_index(['C'])    # 设置索引
   data.loc[:,'D']=array([1]*len(data)) #增加一列
   data=data.resample('D').sum() #按天求和
   data=data.loc[:,'D'] #截取
   data.fillna(0) #填充缺失值
   R.append(data)
  except StopIteration:
   loop = False
   print ("Iteration is stopped.")
 R.to_csv('855_pay.csv') # 保存

def read2(filename):
 reader=pd.read_csv(filename,iterator=True)
 loop = True
 chunkSize = 100000
 chunks = []
 while loop:
  try:
   chunk = reader.get_chunk(chunkSize)
   chunks.append(chunk)
  except StopIteration:
   loop = False
   print ("Iteration is stopped.")
 df = pd.concat(chunks, ignore_index=True)
 return df

def read3save(filename):
 dat=pd.read_csv(filename)
 #data = dat.get_chunk(chunkSize)
 data=dat.loc[:,'B':'C'] # 切片
 data=data[data.B==855]#条件选择
 print(shape(data))
 data['C']=pd.to_datetime(data['C']) # 转换成时间格式
 data=data.set_index(['C'])# 设置索引
 if len(data)==0:
  return
 data.loc[:,'D']=array([1]*len(data)) #增加一列
 data=data.resample('D').sum() #按天求和
 data=data.loc[:,'D'] #截取
 data.fillna(0) #填充缺失值
 data.to_csv('855_pay.csv',mode='a') # 保存

def loadDataSet(fileName, delim='\t'):
 fr = open(fileName)
 stringArr = [line.strip().split(delim) for line in fr.readlines()]
 datArr = [list(map(float,line)) for line in stringArr]
 return mat(datArr)

def getShopData():
 fr = open('shopInfo.txt')
 shopID = [line.strip().split('\n') for line in fr.readlines()]
 # datArr = [list(map(float,line))for line in stringArr]
 for i in range(1,9):
  name="user_pay.001.00%d"%i
  dat=pd.read_csv(name)
  #data = dat.get_chunk(chunkSize)
  data=dat.loc[:,'B':'C'] # 切片
  for factor in shopID:
   data=data[data.B==int(str(factor[0]))]#条件选择
   print(shape(data))
   if len(data)==0: continue
   data['C']=pd.to_datetime(data['C']) # 转换成时间格式
   data=data.set_index(['C'])# 设置索引
   data.loc[:,'D']=array([1]*len(data)) #增加一列
   data=data.resample('D').sum() #按天求和
   data=data.loc[:,'D'] #截取
   data.fillna(0) #填充缺失值
   s=str(factor[0])
   savename='D:\python\data\%s_pay.csv'%s
   data.to_csv(savename,mode='a') # 保存
   del dat
 print("over")

def tset(filename):
 dat=pd.read_csv(filename)
 #data = dat.get_chunk(chunkSize)
 data=dat.loc[:,'B':'C'] # 切片
 data=data[data.B==855]#条件选择
 print(shape(data))
 data['C']=pd.to_datetime(data['C']) # 转换成时间格式
 data=data.set_index(['C'])# 设置索引
 if len(data)==0:
  return
 data.loc[:,'D']=array([1]*len(data)) #增加一列
 data=data.resample('D').sum() #按天求和
 data=data.loc[:,'D'] #截取
 data.fillna(0) #填充缺失值
 #data.to_csv('855_pay.csv',mode='a') # 保存
 s='my'
 savename='D:\python\data\%s_pay.csv'%s
 data.to_csv(savename,mode='a') # 保存
  
def getShopData2(filename):
  import csv
 # fr = open('shopInfo.txt')
  # shopID = [line.strip().split('\n') for line in fr.readlines()]
 # datArr = [list(map(float,line))for line in stringArr]
 #for i in range(1,9):
 #name="user_pay.001.00%d"%i
  dat=pd.read_csv(filename)
  #data = dat.get_chunk(chunkSize)
  data=dat.loc[:,'B':'C'] # 切片
  data['C']=pd.to_datetime(data['C']) # 转换成时间格式
  data=data.set_index(['C'])# 设置索引
  data.loc[:,'D']=array([1]*len(data)) #增加一列
  for i in range(1,2001):
   d=copy.copy(data)
   d=d[data.B==i]#条件选择
   #print(shape(d))
   print(i)
   if len(d)==0: continue
   d=d.resample('D').sum() #按天求和
   d=d.loc[:,'D'] #截取
   d.fillna(0) #填充缺失值
   s=str(i)
   #print(s)
   savename='D:\python\data2\%s_pay.csv'%s
   c=open(savename,'a')
   writer=csv.writer(c)
   writer.writerow(['C','D'])
   c.close()
   d.to_csv(savename,mode='a') # 保存
   # del dat
   print("over")
def formatData():
  #fr = open('shopInfo.txt')
  #shopID = [line.strip().split('\n') for line in fr.readlines()]
 # datArr = [list(map(float,line))for line in stringArr]
  #data = dat.get_chunk(chunkSize)
  for i in range(1,2001):
   s=str(i)
   print(s)
   name='D:\python\data2\%s_pay.csv'%s
   dat=pd.read_csv(name)
   data['C']=pd.to_datetime(data['C']) # 转换成时间格式
   data=data.set_index(['C'])# 设置索引
   data=data.resample('D').sum() #按天求和
   data.fillna(0) #填充缺失值
   savename='D:\python\data3\%s_pay.csv'%s
   data.to_csv(savename,mode='w') # 保存
   del dat
   print("over")