pandas基礎知識（index）

jupyter notebook文件地址

import pandas as pd
import numpy as np
ser = pd.Series([5, 0, 3, 8, 4], index=['red', 'blue', 'yellow', 'yellow', 'blue'])
ser.index

Index(['red', 'blue', 'yellow', 'yellow', 'blue'], dtype='object')

重複標籤

ser

red       5
blue      0
yellow    3
yellow    8
blue      4
dtype: int64

ser.idxmin()

‘blue’

ser.idxmax()

‘yellow’

ser.blue

blue    0
blue    4
dtype: int64

# 判斷索引是否有重複
ser.index.is_unique

False

更換索引

ser = pd.Series([5, 0, 3, 8, 4], index=['one', 'two', 'three', 'four', 'five'])
ser

one 5 two 0 three 3 four 8 five 4 dtype: int64

# 產生一個新的對象
ser.reindex(['three', 'two', 'one', 'five', 'four'])

three 3 two 0 one 5 five 4 four 8 dtype: int64

# two變成six
ser.reindex(['three', 'six', 'one', 'five', 'four'])

three 3.0 six NaN one 5.0 five 4.0 four 8.0 dtype: float64

ser2 = pd.Series([1, 5, 6, 3], index=[0, 3, 5, 6])
ser2

0 1 3 5 5 6 6 3 dtype: int64

ser2.reindex(range(6), method='ffill')

0 1 1 1 2 1 3 5 4 5 5 6 dtype: int64

ser2.reindex(range(6), method='bfill')

0 1 1 5 2 5 3 5 4 6 5 6 dtype: int64

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

frame.reindex(range(5, 0, -1),method='ffill', columns=['one', 'two', 'three'])

	one	two	three
5	mug	1.7	1.7
4	mug	1.7	1.7
3	paper	0.9	0.9
2	pencil	0.6	0.6
1	pen	1.0	1.0

刪除（drop）

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

# 刪除行
frame.drop([1])

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

# 刪除列 用關鍵字axis指定
frame.drop(['price'], axis=1)

	color	object
0	blue	ball
1	green	pen
2	yellow	pencil
3	red	paper
4	white	mug