12.pandas 读取与写入文件

import numpy as np
import pandas as pd
from pandas import Series,DataFrame
from numpy import nan as NA
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']

读取csv

# pd.read_csv() 默认 逗号为分隔符 ，默认首行作为 columnsName
pd.read_csv('data/ex1.csv')

a	b	c	d	message
0	1	2	3	4	hello
1	5	6	7	8	world
2	9	10	11	12	foo

# pd..read_table()也可以读取，但是要指定分隔符参数sep=''
pd.read_table('data/ex1.csv',sep=',')

a	b	c	d	message
0	1	2	3	4	hello
1	5	6	7	8	world
2	9	10	11	12	foo

# 读取没有明显列名称的文件，不需要让首行作为列，用参数header=None
df2=pd.read_csv('data/ex2.csv',header=None)
df2

0	1	2	3	4
0	1	2	3	4	hello
1	5	6	7	8	world
2	9	10	11	12	foo

# 自d义列名称读取 参数names=[]
# names给几列，就会从最后向前读几列数据，剩下的都是index
# 超出就是nan
df3=pd.read_csv('data/ex2.csv',names=['aa','bb','cc','dd','message','nn'])
df3

aa	bb	cc	dd	message	nn
0	1	2	3	4	hello	NaN
1	5	6	7	8	world	NaN
2	9	10	11	12	foo	NaN

# 设置行索引 index_col='某个列name'
df4=pd.read_csv('data/ex2.csv',
                names=['aa','bb','cc','dd','message'],
               index_col='message'
               )
df4

aa	bb	cc	dd
message				
hello	1	2	3	4
world	5	6	7	8
foo	9	10	11	12

# 多列的值作为行索引
df5=pd.read_csv('data/csv_mindex.csv',
               index_col=['key1'