數據讀入與寫出(命令行交互)
1.讀文件輸出文件
import sys
def main(argv):
#input_file='/home/vitamin/bigdata/code/python/part-00000'
#output_file='/home/vitamin/bigdata/code/python/out1'
input_file=argv[1]
output_file1=argv[2]
output_file2=argv[3]
cnt=0
fin = open(input_file)
fout1=open(output_file1, mode='w+')
fout2=open(output_file2, mode='w+')
while 1:
lines=fin.readlines(10000)
if not lines :
print 'user num:'+str(cnt)
sys.exit()
for line in lines:
tks=line.split('\t')
if len(tks)<3:
continue
if(cnt<258):
fout1.write(tks[1])
fout2.write(tks[2])
cnt=cnt+1
if __name__=='__main__':
#sys.argv 用來接收命令行參數,python命令之後都,都被接收到sys.argv列表中
if len(sys.argv)!=4:
print 'usage: python getuser.py inputfile outfilesmall outfullfile'
main(sys.argv)
print 'Job done...'
2.讀取目錄(並從中分割出類別信息)
from os import listdir
# 得到目錄下所有的文件名
trainingFileList=listdir('trainingDigits')
m=len(trainingFileList)
for i in range(m):
fileNameStr=trainingFileList[i]
fileStr=fileNameStr.split('.')[0]
classNumStr=int(fileStr.split('_')[0])
print classNumStr
3.讀文件內容到矩陣中
從文本文件中處理得到實值矩陣
import numpy as np
fr=open('datingTestSet2.txt')
arrayOfLines=fr.readlines()
numberOfLines=len(arrayOfLines)
returnMat=np.zeros((numberOfLines,3))
index=0
for line in arrayOfLines:
line=line.strip()
listFromLine=line.split('\t')
returnMat[index,:]=listFromLine[0:3]
index+=1
print returnMat