用groupby 配合unstack,可以实现pivot_table

# 读取flights数据集
flights = pd.read_csv('data/flights.csv')
flights

	MONTH	DAY	WEEKDAY	AIRLINE	ORG_AIR	DEST_AIR	SCHED_DEP	DEP_DELAY	AIR_TIME	DIST	SCHED_ARR	ARR_DELAY	DIVERTED	CANCELLED
0	1	1	4	WN	LAX	SLC	1625	58.0	94.0	590	1905	65.0	0	0
1	1	1	4	UA	DEN	IAD	823	7.0	154.0	1452	1333	-13.0	0	0
2	1	1	4	MQ	DFW	VPS	1305	36.0	85.0	641	1453	35.0	0	0
3	1	1	4	AA	DFW	DCA	1555	7.0	126.0	1192	1935	-7.0	0	0
4	1	1	4	WN	LAX	MCI	1720	48.0	166.0	1363	2225	39.0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
58487	12	31	4	AA	SFO	DFW	515	5.0	166.0	1464	1045	-19.0	0	0
58488	12	31	4	F9	LAS	SFO	1910	13.0	71.0	414	2050	4.0	0	0
58489	12	31	4	OO	SFO	SBA	1846	-6.0	46.0	262	1956	-5.0	0	0
58490	12	31	4	WN	MSP	ATL	525	39.0	124.0	907	855	34.0	0	0
58491	12	31	4	OO	SFO	BOI	859	5.0	73.0	522	1146	-1.0	0	0

58492 rows × 14 columns

# 用pivot_table方法求出每条航线每个始发地的被取消的航班总数
fp = flights.pivot_table(index='AIRLINE',columns='ORG_AIR',values='CANCELLED',
                         aggfunc='sum', fill_value=0).round(2)
fp.head()

ORG_AIR	ATL	DEN	DFW	IAH	LAS	LAX	MSP	ORD	PHX	SFO
AIRLINE
AA	3	4	86	3	3	11	3	35	4	2
AS	0	0	0	0	0	0	0	0	0	0
B6	0	0	0	0	0	0	0	0	0	1
DL	28	1	0	0	1	1	4	0	1	2
EV	18	6	27	36	0	0	6	53	0	0

# groupby聚合不能直接复现这张表。需要先按所有index和columns的列聚合
fg = flights.groupby(['AIRLINE', 'ORG_AIR'])['CANCELLED'].sum()
fg.head()
'''
AIRLINE  ORG_AIR
AA       ATL         3
         DEN         4
         DFW        86
         IAH         3
         LAS         3
Name: CANCELLED, dtype: int64
'''

# 再使用unstack，将ORG_AIR这层索引作为列名
fg_unstack = fg.unstack('ORG_AIR', fill_value=0)
fg_unstack.head()

ORG_AIR	ATL	DEN	DFW	IAH	LAS	LAX	MSP	ORD	PHX	SFO
AIRLINE
AA	3	4	86	3	3	11	3	35	4	2
AS	0	0	0	0	0	0	0	0	0	0
B6	0	0	0	0	0	0	0	0	0	1
DL	28	1	0	0	1	1	4	0	1	2
EV	18	6	27	36	0	0	6	53	0	0

# 判断两个方式是否等价
fg_unstack = fg.unstack('ORG_AIR', fill_value=0)
fp.equals(fg_unstack)
#True

import numpy as np
# 先实现一个稍微复杂的透视表
fp2 = flights.pivot_table(index=['AIRLINE', 'MONTH'],
                                   columns=['ORG_AIR', 'CANCELLED'],
                                   values=['DEP_DELAY', 'DIST'],
                                   aggfunc=[np.mean, np.sum],
                                   fill_value=0)
fp2.head()

	mean											...	sum
		DEP_DELAY										...	DIST
	ORG_AIR	ATL		DEN		DFW		IAH		LAS		...	LAX		MSP		ORD		PHX		SFO
	CANCELLED	0	1	0	1	0	1	0	1	0	1	...	0	1	0	1	0	1	0	1	0	1
AIRLINE	MONTH
AA	1	-3.250000	0	7.062500	0	11.977591	-3.0	9.750000	0	32.375000	0	...	135921	2475	7281	0	129334	0	21018	0	33483	0
	2	-3.000000	0	5.461538	0	8.756579	0.0	1.000000	0	-3.055556	0	...	113483	5454	5040	0	120572	5398	17049	868	32110	2586
	3	-0.166667	0	7.666667	0	15.383784	0.0	10.900000	0	12.074074	0	...	131836	1744	14471	0	127072	802	25770	0	43580	0
	4	0.071429	0	20.266667	0	10.501493	0.0	6.933333	0	27.241379	0	...	170285	0	4541	0	152154	4718	17727	0	51054	0
	5	5.777778	0	23.466667	0	16.798780	0.0	3.055556	0	2.818182	0	...	167484	0	6298	0	110864	1999	11164	0	40233	0

5 rows × 80 columns

# 用groupby和unstack复现上面的方法
flights.groupby(['AIRLINE', 'MONTH', 'ORG_AIR', 'CANCELLED'])['DEP_DELAY', 'DIST']\
.agg(['mean', 'sum']) \
.unstack(['ORG_AIR', 'CANCELLED'], fill_value=0) \
.swaplevel(0, 1, axis='columns') \
.head()

	mean											...	sum
		DEP_DELAY										...	DIST
	ORG_AIR	ATL		DEN		DFW		IAH		LAS		...	LAX		MSP		ORD		PHX		SFO
	CANCELLED	0	1	0	1	0	1	0	1	0	1	...	0	1	0	1	0	1	0	1	0	1
AIRLINE	MONTH
AA	1	-3.250000	0.0	7.062500	0.0	11.977591	-3.0	9.750000	0.0	32.375000	0.0	...	135921	2475	7281	0	129334	0	21018	0	33483	0
	2	-3.000000	NaN	5.461538	NaN	8.756579	NaN	1.000000	NaN	-3.055556	NaN	...	113483	5454	5040	0	120572	5398	17049	868	32110	2586
	3	-0.166667	NaN	7.666667	0.0	15.383784	NaN	10.900000	0.0	12.074074	0.0	...	131836	1744	14471	0	127072	802	25770	0	43580	0
	4	0.071429	0.0	20.266667	0.0	10.501493	NaN	6.933333	0.0	27.241379	0.0	...	170285	0	4541	0	152154	4718	17727	0	51054	0
	5	5.777778	0.0	23.466667	NaN	16.798780	NaN	3.055556	NaN	2.818182	0.0	...	167484	0	6298	0	110864	1999	11164	0	40233	0

5 rows × 80 columns