20  Siub - Intro

from siuba import _, group_by, summarize
from siuba.data import mtcars

(mtcars
  >> group_by(_.cyl)
  >> summarize(avg_hp = _.hp.mean())
  )

	cyl	avg_hp
0	4	82.636364
1	6	122.285714
2	8	209.214286

20.1 Filter Rows

from siuba import _, filter, group_by
from siuba.data import mtcars

mtcars >> filter(_.cyl == 4, _.gear == 5)

	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
26	26.0	4	120.3	91	4.43	2.140	16.7	0	1	5	2
27	30.4	4	95.1	113	3.77	1.513	16.9	1	1	5	2

mtcars >> filter((_.cyl == 4) | (_.gear == 5))

	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
2	22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1
7	24.4	4	146.7	62	3.69	3.190	20.00	1	0	4	2
8	22.8	4	140.8	95	3.92	3.150	22.90	1	0	4	2
17	32.4	4	78.7	66	4.08	2.200	19.47	1	1	4	1
18	30.4	4	75.7	52	4.93	1.615	18.52	1	1	4	2
19	33.9	4	71.1	65	4.22	1.835	19.90	1	1	4	1
20	21.5	4	120.1	97	3.70	2.465	20.01	1	0	3	1
25	27.3	4	79.0	66	4.08	1.935	18.90	1	1	4	1
26	26.0	4	120.3	91	4.43	2.140	16.70	0	1	5	2
27	30.4	4	95.1	113	3.77	1.513	16.90	1	1	5	2
28	15.8	8	351.0	264	4.22	3.170	14.50	0	1	5	4
29	19.7	6	145.0	175	3.62	2.770	15.50	0	1	5	6
30	15.0	8	301.0	335	3.54	3.570	14.60	0	1	5	8
31	21.4	4	121.0	109	4.11	2.780	18.60	1	1	4	2

20.2 Select

import pandas as pd

pd.set_option("display.max_rows", 5)

from siuba import _, select
from siuba.data import penguins

penguins

	species	island	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g	sex	year
0	Adelie	Torgersen	39.1	18.7	181.0	3750.0	male	2007
1	Adelie	Torgersen	39.5	17.4	186.0	3800.0	female	2007
...	...	...	...	...	...	...	...	...
342	Chinstrap	Dream	50.8	19.0	210.0	4100.0	male	2009
343	Chinstrap	Dream	50.2	18.7	198.0	3775.0	female	2009

344 rows × 8 columns

#  select a column to keep is to refer to it by name or position.
select(penguins, _.species, _.island, 6, -1)

	species	island	sex	year
0	Adelie	Torgersen	male	2007
1	Adelie	Torgersen	female	2007
...	...	...	...	...
342	Chinstrap	Dream	male	2009
343	Chinstrap	Dream	female	2009

344 rows × 4 columns