python读取大文件

d={}

a_in = open("testfile.txt", "r")

for line in a_in:
    columnssplit = line.rstrip().split("\t")
    d[columnssplit[0]]=columnssplit[1]

a_in.close()

ID_test = open("correlation.txt", "r")

for line in ID_test:
    s = line.rstrip().split("\t")
    if s[1] in d:
        print s[0]+"\t"+d[s[1]]
ID_test.close()

## Here is another example

f = open("test.txt", "r")  
while True:  
    line = f.readline()  
    if line:   #  或者用 if line != "":
        print line  
    else:  
        break  
f.close()

import pandas as pd

df1 = pd.read_csv("test.txt", header = None, sep='\t')

# 打印前三行
print df1[:3]

# 选取前三行的 前三列， 使用df.loc

df2 = df1.loc[:3, [0, 1, 2]]

print df2

# 替换第三列的部分内容

col3 = df2.apply(lambda r: r[2].replace("KH","TF"), axis=1)

# 合并第一列和替换后的第三列内容

df3 = pd.concat([df2[0], col3], axis = 1)

print df3