Pandas - 数据的加载、存储与解析

---

Pandas加载数据

import pandas as pd
from pandas import DataFrame,Series
import sys

• read_csv 从文件,URl,文件型对象中加载带分隔符的数据,默认分隔符为逗号(,)
• read_table 从文件,URl,文件型对象中加载带分隔符的数据,默认分隔符为制表符(\t)

pd.read_csv('ex1.csv')

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

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

#pandas加载没有标题的数据
pd.read_csv('ex2.csv',header=None)

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

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

#手动指定列名
pd.read_csv('ex2.csv',names =['a','b','c','d','message'])

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

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

#加载csv数据并制定一列数据并指定一列为行索引
pd.read_csv('ex2.csv',
            names =['a','b','c','d','message'],
           index_col='message')

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

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

#加载数据,创建层次化索引数据结构
parsed = pd.read_csv('csv_mindex.csv',index_col=['key1','key2'])
parsed

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

		value1	value2
key1	key2
one	a	1	2
	b	3	4
	c	5	6
	d	7	8
two	a	9	10
	b	11	12
	c	13	14
	d	15	16

#若CSV文件的分隔符是不规则的,可采取正则来进行分割
pd.read_csv('ex3.csv',sep='\s+')

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

	A	B	C
aaa	-0.264438	-1.026059	-0.619500
bbb	0.927272	0.302904	-0.032399
ccc	-0.264273	-0.386314	-0.217601
ddd	-0.871858	-0.348382	1.100491

#读取带有无效数据行的文件
pd.read_csv('ex4.csv',skiprows=[0,2,3])

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

	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_csv('ex5.csv',na_values=['world'])#na_values选定数据集里的某些值为None

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

	something	a	b	c	d	message
0	one	1	2	3.0	4	NaN
1	two	5	6	NaN	8	NaN
2	three	9	10	11.0	12	foo

#加载csv数据,并按列指定不同的None值
sen = {'message':['foo','NA'],'something':['two']}
data_ex5 = pd.read_csv('ex5.csv',na_values=sen)
data_ex5

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

	something	a	b	c	d	message
0	one	1	2	3.0	4	NaN
1	NaN	5	6	NaN	8	world
2	three	9	10	11.0	12	NaN

Pandas存储数据

df = DataFrame({'name':['Rachel','Zack','Daniel'],
               'age':[15,22,35],
               'gemder':['F','M','M'],
               'job':['student','killer','doctor']})
df

.dataframe thead tr:only-child th { text-align: right; } .dataframe thead th { text-align: left; } .dataframe tbody tr th { vertical-align: top; }

	age	gemder	job	name
0	15	F	student	Rachel
1	22	M	killer	Zack
2	35	M	doctor	Daniel

#将数据写入到文件
df.to_csv('Angelsof.csv',sep='\t')

#将写入的结果在控制台输出sys.stdout
df.to_csv(sys.stdout,sep='\t')

    age gemder  job name
0   15  F   student Rachel
1   22  M   killer  Zack
2   35  M   doctor  Daniel

#将数据写入到csv文件中,不保存行索引和列索引
df.to_csv(sys.stdout,index=False,header=False)

15,F,student,Rachel
22,M,killer,Zack
35,M,doctor,Daniel

#写入CSV文件,并替换NaN值
data_ex5.to_csv(sys.stdout,na_rep=0)

,something,a,b,c,d,message
0,one,1,2,3.0,4,0
1,0,5,6,0,8,world
2,three,9,10,11.0,12,0

#只保存部分数据
df.to_csv(sys.stdout,columns=['name'])

,name
0,Rachel
1,Zack
2,Daniel