ch6：数据载入，存储及文件格式

数据的读取, 保存

import numpy as np
import pandas as pd
np.random.seed(12345)
import matplotlib.pyplot as plt
plt.rc('figure', figsize=(10, 6))
np.set_printoptions(precision=4, suppress=True)

读取csv,txt文件

df = pd.read_csv('examples/ex1.csv')
df

	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('examples/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

pd.read_csv('examples/ex2.csv', header=None)

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

命名表头

pd.read_csv('examples/ex2.csv', names=['a', 'b', 'c', 'd', 'message'])

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

list(open('examples/ex3.txt'))

['            A         B         C\n',
 'aaa -0.264438 -1.026059 -0.619500\n',
 'bbb  0.927272  0.302904 -0.032399\n',
 'ccc -0.264273 -0.386314 -0.217601\n',
 'ddd -0.871858 -0.348382  1.100491\n']

result = pd.read_table('examples/ex3.txt', sep='\s+')
result

	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

result = pd.read_csv('examples/ex5.csv')
result

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

数据部分读取

1.很多行时，只展示10行

result = pd.read_csv('examples/ex6.csv')
result

	one	two	three	four	key
0	0.467976	-0.038649	-0.295344	-1.824726	L
1	-0.358893	1.404453	0.704965	-0.200638	B
2	-0.501840	0.659254	-0.421691	-0.057688	G
3	0.204886	1.074134	1.388361	-0.982404	R
4	0.354628	-0.133116	0.283763	-0.837063	Q
...	...	...	...	...	...
9995	2.311896	-0.417070	-1.409599	-0.515821	L
9996	-0.479893	-0.650419	0.745152	-0.646038	E
9997	0.523331	0.787112	0.486066	1.093156	K
9998	-0.362559	0.598894	-1.843201	0.887292	G
9999	-0.096376	-1.012999	-0.657431	-0.573315	0

10000 rows × 5 columns

2.只读取前五行

pd.read_csv('examples/ex6.csv', nrows=5)

	one	two	three	four	key
0	0.467976	-0.038649	-0.295344	-1.824726	L
1	-0.358893	1.404453	0.704965	-0.200638	B
2	-0.501840	0.659254	-0.421691	-0.057688	G
3	0.204886	1.074134	1.388361	-0.982404	R
4	0.354628	-0.133116	0.283763	-0.837063	Q

3.使用chunksize分块处理大型csv文件

chunker = pd.read_csv('examples/ex6.csv', chunksize=1000)

tot = pd.Series([])
for piece in chunker:
    tot = tot.add(piece['key'].value_counts(), fill_value=0)

tot = tot.sort_values(ascending=False)

显示前十的计数结果

tot[:10]

E    368.0
X    364.0
L    346.0
O    343.0
Q    340.0
M    338.0
J    337.0
F    335.0
K    334.0
H    330.0
dtype: float64

将数据导出

data = pd.read_csv('examples/ex5.csv')
data

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

data.to_csv('examples/out.csv')

1.sys:如果需要更好的控制输出，而print不能满足需求，sys.stdout，sys.stdin，sys.stderr就是你需要的。

import sys
data.to_csv(sys.stdout, sep='|')

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

data.to_csv(sys.stdout, na_rep='NULL')

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

2.去除空值和索引

data.to_csv(sys.stdout, index=False, header=False)

one,1,2,3.0,4,
two,5,6,,8,world
three,9,10,11.0,12,foo

3.自动生成日期序列

dates = pd.date_range('1/1/2000', periods=7)
ts = pd.Series(np.arange(7), index=dates)
ts.to_csv('examples/tseries.csv')

读取csv

import csv
f = open('examples/ex7.csv')
reader = csv.reader(f)

for line in reader:
    print(line)

['a', 'b', 'c']
['1', '2', '3']
['1', '2', '3']

JSON 数据

obj = """
{"name": "Wes",
 "places_lived": ["United States", "Spain", "Germany"],
 "pet": null,
 "siblings": [{"name": "Scott", "age": 30, "pets": ["Zeus", "Zuko"]},
              {"name": "Katie", "age": 38,
               "pets": ["Sixes", "Stache", "Cisco"]}]
}
"""

type(obj)

str

json.loads将字符转为字典

import json
result = json.loads(obj)
result

{'name': 'Wes',
 'places_lived': ['United States', 'Spain', 'Germany'],
 'pet': None,
 'siblings': [{'name': 'Scott', 'age': 30, 'pets': ['Zeus', 'Zuko']},
  {'name': 'Katie', 'age': 38, 'pets': ['Sixes', 'Stache', 'Cisco']}]}

type(result)

dict

json.loads将字典转为字符

asjson = json.dumps(result)
asjson

'{"name": "Wes", "places_lived": ["United States", "Spain", "Germany"], "pet": null, "siblings": [{"name": "Scott", "age": 30, "pets": ["Zeus", "Zuko"]}, {"name": "Katie", "age": 38, "pets": ["Sixes", "Stache", "Cisco"]}]}'

type(asjson)

str

读取json数据

data = pd.read_json('examples/example.json')
data

	a	b	c
0	1	2	3
1	4	5	6
2	7	8	9

print(data.to_json())

{"a":{"0":1,"1":4,"2":7},"b":{"0":2,"1":5,"2":8},"c":{"0":3,"1":6,"2":9}}

type(data.to_json())

str

读取excel文件

xlsx = pd.ExcelFile('examples/ex1.xlsx')

pd.read_excel(xlsx, 'Sheet1')

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

frame = pd.read_excel('examples/ex1.xlsx', 'Sheet1')
frame

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