> 多維的pandas.Series

import pandas as pd 
import numpy as np
data = {
    'color':['blue', 'green', 'yellow', 'red', 'white'],
    'object':['ball', 'pen', 'pencil', 'paper', 'mug'],
    'price':[1.2, 1.0, 0.6, 0.9, 1.7]
}

frame = pd.DataFrame(data)
frame

color	object	price
0	blue	ball	1.2
1	green	pen	1.0
2	yellow	pencil	0.6
3	red	paper	0.9
4	white	mug	1.7

# 指定列名讀取
frame2 = pd.DataFrame(data, columns=['object'
 
, 'price'])
frame2

object	price
0	ball	1.2
1	pen	1.0
2	pencil	0.6
3	paper	0.9
4	mug	1.7

# 修改索引
frames3 = pd.DataFrame(data, index=['one'
 
, 'two', 'three', 'four', 'five'])
frames3

color	object	price
one	blue	ball	1.2
two	green	pen	1.0
three	yellow	pencil	0.6
four	red	paper	0.9
five	white	mug	1.7

frame4 = pd.DataFrame(np.arange(16).reshape(4,4),
                     index=['one', 'two', 'three', 'four'],
                     columns=['blue', 'green', 'yellow', 'red'])
frame4

blue	green	yellow	red
one	0	1	2	3
two	4	5	6	7
three	8	9	10	11
four	12	13	14	15

### 選取資料

frame4.columns

Index([‘blue’, ‘green’, ‘yellow’, ‘red’], dtype=’object’)

frame4.index

Index([‘one’, ‘two’, ‘three’, ‘four’], dtype=’object’)

frame4.values

array([[ 0, 1, 2, 3], [ 4, 5, 6, 7], [ 8, 9, 10, 11], [12, 13, 14, 15]])

frame4.red

one 3 two 7 three 11 four 15 Name: red, dtype: int64

# frame4.ix[2] ix方法已經不能使用了
frame4.iloc[:,2]

one 2 two 6 three 10 four 14 Name: yellow, dtype: int64

# 行->列
frame4['red'][3]

15 ### 賦值

frame

color	object	price
0	blue	ball	1.2
1	green	pen	1.0
2	yellow	pencil	0.6
3	red	paper	0.9
4	white	mug	1.7

frame.index.name = "id"
frame.columns.name = "item"
frame

item	color	object	price
id
0	blue	ball	1.2
1	green	pen	1.0
2	yellow	pencil	0.6
3	red	paper	0.9
4	white	mug	1.7

frame['new'] = 12
frame

item	color	object	price	new
id
0	blue	ball	1.2	12
1	green	pen	1.0	12
2	yellow	pencil	0.6	12
3	red	paper	0.9	12
4	white	mug	1.7	12

frame['new'] = [1.2, 2.3, 3.5, 5.8, 9.6]
frame

item	color	object	price	new
id
0	blue	ball	1.2	1.2
1	green	pen	1.0	2.3
2	yellow	pencil	0.6	3.5
3	red	paper	0.9	5.8
4	white	mug	1.7	9.6

### numpy.array->pandas.DataFrame

ser = pd.Series(np.arange(5))
ser

0 0 1 1 2 2 3 3 4 4 dtype: int64

frame['new'] = ser
frame

item	color	object	price	new
id
0	blue	ball	1.2	0
1	green	pen	1.0	1
2	yellow	pencil	0.6	2
3	red	paper	0.9	3
4	white	mug	1.7	4

### 元素所屬關係

frame.isin([1.0,'pen'])

item	color	object	price	new
id
0	False	False	False	False
1	False	True	True	True
2	False	False	False	False
3	False	False	False	False
4	False	False	False	False

frame[frame.isin([1.0,'pen'])]

item	color	object	price	new
id
0	NaN	NaN	NaN	NaN
1	NaN	pen	1.0	1.0
2	NaN	NaN	NaN	NaN
3	NaN	NaN	NaN	NaN
4	NaN	NaN	NaN	NaN

### 刪除一列

del frame['new']
frame

item	color	object	price
id
0	blue	ball	1.2
1	green	pen	1.0
2	yellow	pencil	0.6
3	red	paper	0.9
4	white	mug	1.7

### 篩選

frame4

blue	green	yellow	red
one	0	1	2	3
two	4	5	6	7
three	8	9	10	11
four	12	13	14	15

frame4[frame4<12]

blue	green	yellow	red
one	0.0	1.0	2.0	3.0
two	4.0	5.0	6.0	7.0
three	8.0	9.0	10.0	11.0
four	NaN	NaN	NaN	NaN

### 巢狀字典生成DataFrame

nestdict = {'red':{2012:22, 2013:33},
            'white':{2011:13, 2012:22, 2013:16},
            'blue':{2011:17, 2012:27, 2013:18}}
frame5 = pd.DataFrame(nestdict)
frame5

blue	red	white
2011	17	NaN	13
2012	27	22.0	22
2013	18	33.0	16

### 轉置

frame5.T

2011	2012	2013
blue	17.0	27.0	18.0
red	NaN	22.0	33.0
white	13.0	22.0	16.0

nestdict = {'red':{2012:22, 2013:33},
            'white':{2011:13, 2012:22, 2013:16},
            'blue':{2011:17, 2012:27, 2013:18}}
frame5 = pd.DataFrame(nestdict)
frame5

blue	red	white
2011	17	NaN	13
2012	27	22.0	22
2013	18	33.0	16