filter

In [1]:

# https://dplyr.tidyverse.org/reference/filter.html
%run nb_helpers.py
from datar.data import starwars
from datar.all import *

nb_header(filter)

# https://dplyr.tidyverse.org/reference/filter.html %run nb_helpers.py from datar.data import starwars from datar.all import * nb_header(filter)

Try this notebook on binder.

★ filter_

¶

Filter a data frame based on conditions¶

The original API:
https://dplyr.tidyverse.org/reference/filter.html

Args:¶

  _data: A data frame
  *conditions: Conditions to filter by.
  _preserve: If True, keep grouping variables even if they are not used.

Returns:¶

  The subset dataframe

In [2]:

filter(starwars, f.species == "Human")

filter(starwars, f.species == "Human")

Out[2]:

	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
0	Luke Skywalker	172.0	77.0	blond	fair	blue	19.0	male	masculine	Tatooine	Human
3	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
4	Leia Organa	150.0	49.0	brown	light	brown	19.0	female	feminine	Alderaan	Human
5	Owen Lars	178.0	120.0	brown, grey	light	blue	52.0	male	masculine	Tatooine	Human
6	Beru Whitesun lars	165.0	75.0	brown	light	blue	47.0	female	feminine	Tatooine	Human
8	Biggs Darklighter	183.0	84.0	black	light	brown	24.0	male	masculine	Tatooine	Human
9	Obi-Wan Kenobi	182.0	77.0	auburn, white	fair	blue-gray	57.0	male	masculine	Stewjon	Human
10	Anakin Skywalker	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
11	Wilhuff Tarkin	180.0	NaN	auburn, grey	fair	blue	64.0	male	masculine	Eriadu	Human
13	Han Solo	180.0	80.0	brown	fair	brown	29.0	male	masculine	Corellia	Human
16	Wedge Antilles	170.0	77.0	brown	fair	hazel	21.0	male	masculine	Corellia	Human
17	Jek Tono Porkins	180.0	110.0	brown	fair	blue	NaN	male	masculine	Bestine IV	Human
19	Palpatine	170.0	75.0	grey	pale	yellow	82.0	male	masculine	Naboo	Human
20	Boba Fett	183.0	78.2	black	fair	brown	31.5	male	masculine	Kamino	Human
23	Lando Calrissian	177.0	79.0	black	dark	brown	31.0	male	masculine	Socorro	Human
24	Lobot	175.0	79.0	none	light	blue	37.0	male	masculine	Bespin	Human
26	Mon Mothma	150.0	NaN	auburn	fair	blue	48.0	female	feminine	Chandrila	Human
27	Arvel Crynyd	NaN	NaN	brown	fair	brown	NaN	male	masculine	NaN	Human
30	Qui-Gon Jinn	193.0	89.0	brown	fair	blue	92.0	male	masculine	NaN	Human
32	Finis Valorum	170.0	NaN	blond	fair	blue	91.0	male	masculine	Coruscant	Human
40	Shmi Skywalker	163.0	NaN	black	fair	brown	72.0	female	feminine	Tatooine	Human
47	Mace Windu	188.0	84.0	none	dark	brown	72.0	male	masculine	Haruun Kal	Human
56	Gregar Typho	185.0	85.0	black	dark	brown	NaN	male	masculine	Naboo	Human
57	Cordé	157.0	NaN	brown	light	brown	NaN	female	feminine	Naboo	Human
58	Cliegg Lars	183.0	NaN	brown	fair	blue	82.0	male	masculine	Tatooine	Human
62	Dormé	165.0	NaN	brown	light	brown	NaN	female	feminine	Naboo	Human
63	Dooku	193.0	80.0	white	fair	brown	102.0	male	masculine	Serenno	Human
64	Bail Prestor Organa	191.0	NaN	black	tan	brown	67.0	male	masculine	Alderaan	Human
65	Jango Fett	183.0	79.0	black	tan	brown	66.0	male	masculine	Concord Dawn	Human
70	Jocasta Nu	167.0	NaN	white	fair	blue	NaN	female	feminine	Coruscant	Human
78	Raymus Antilles	188.0	79.0	brown	light	brown	NaN	male	masculine	Alderaan	Human
81	Finn	NaN	NaN	black	dark	dark	NaN	male	masculine	NaN	Human
82	Rey	NaN	NaN	brown	light	hazel	NaN	female	feminine	NaN	Human
83	Poe Dameron	NaN	NaN	brown	light	brown	NaN	male	masculine	NaN	Human
86	Padmé Amidala	165.0	45.0	brown	light	brown	46.0	female	feminine	Naboo	Human

In [3]:

filter(starwars, f.mass > 1000)

filter(starwars, f.mass > 1000)

Out[3]:

	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
15	Jabba Desilijic Tiure	175.0	1358.0	NaN	green-tan, brown	orange	600.0	hermaphroditic	masculine	Nal Hutta	Hutt

In [4]:

# Conditions connected by & or | have to wrapped, since == has lower priority than & does
filter(starwars, (f.hair_color == "none") & (f.eye_color == "black"))

# Conditions connected by & or | have to wrapped, since == has lower priority than & does filter(starwars, (f.hair_color == "none") & (f.eye_color == "black"))

Out[4]:

	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
29	Nien Nunb	160.0	68.0	none	grey	black	NaN	male	masculine	Sullust	Sullustan
45	Gasgano	122.0	NaN	none	white, blue	black	NaN	male	masculine	Troiken	Xexto
49	Kit Fisto	196.0	87.0	none	green	black	NaN	male	masculine	Glee Anselm	Nautolan
54	Plo Koon	188.0	80.0	none	orange	black	22.0	male	masculine	Dorin	Kel Dor
68	Lama Su	229.0	88.0	none	grey	black	NaN	male	masculine	Kamino	Kaminoan
69	Taun We	213.0	NaN	none	grey	black	NaN	female	feminine	Kamino	Kaminoan
75	Shaak Ti	178.0	57.0	none	red, blue, white	black	NaN	female	feminine	Shili	Togruta
80	Tion Medon	206.0	80.0	none	grey	black	NaN	male	masculine	Utapau	Pau'an
84	BB8	NaN	NaN	none	none	black	NaN	none	masculine	NaN	Droid

In [5]:

filter(starwars, (f.hair_color == "none") | (f.eye_color == "black"))

filter(starwars, (f.hair_color == "none") | (f.eye_color == "black"))

Out[5]:

	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
3	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
14	Greedo	173.0	74.0	NaN	green	black	44.0	male	masculine	Rodia	Rodian
21	IG-88	200.0	140.0	none	metal	red	15.0	none	masculine	NaN	Droid
22	Bossk	190.0	113.0	none	green	red	53.0	male	masculine	Trandosha	Trandoshan
24	Lobot	175.0	79.0	none	light	blue	37.0	male	masculine	Bespin	Human
25	Ackbar	180.0	83.0	none	brown mottle	orange	41.0	male	masculine	Mon Cala	Mon Calamari
29	Nien Nunb	160.0	68.0	none	grey	black	NaN	male	masculine	Sullust	Sullustan
31	Nute Gunray	191.0	90.0	none	mottled green	red	NaN	male	masculine	Cato Neimoidia	Neimodian
33	Jar Jar Binks	196.0	66.0	none	orange	orange	52.0	male	masculine	Naboo	Gungan
34	Roos Tarpals	224.0	82.0	none	grey	orange	NaN	male	masculine	Naboo	Gungan
35	Rugor Nass	206.0	NaN	none	green	orange	NaN	male	masculine	Naboo	Gungan
38	Sebulba	112.0	40.0	none	grey, red	orange	NaN	male	masculine	Malastare	Dug
41	Darth Maul	175.0	80.0	none	red	yellow	54.0	male	masculine	Dathomir	Zabrak
42	Bib Fortuna	180.0	NaN	none	pale	pink	NaN	male	masculine	Ryloth	Twi'lek
43	Ayla Secura	178.0	55.0	none	blue	hazel	48.0	female	feminine	Ryloth	Twi'lek
44	Dud Bolt	94.0	45.0	none	blue, grey	yellow	NaN	male	masculine	Vulpter	Vulptereen
45	Gasgano	122.0	NaN	none	white, blue	black	NaN	male	masculine	Troiken	Xexto
46	Ben Quadinaros	163.0	65.0	none	grey, green, yellow	orange	NaN	male	masculine	Tund	Toong
47	Mace Windu	188.0	84.0	none	dark	brown	72.0	male	masculine	Haruun Kal	Human
49	Kit Fisto	196.0	87.0	none	green	black	NaN	male	masculine	Glee Anselm	Nautolan
51	Adi Gallia	184.0	50.0	none	dark	blue	NaN	female	feminine	Coruscant	Tholothian
52	Saesee Tiin	188.0	NaN	none	pale	orange	NaN	male	masculine	Iktotch	Iktotchi
53	Yarael Poof	264.0	NaN	none	white	yellow	NaN	male	masculine	Quermia	Quermian
54	Plo Koon	188.0	80.0	none	orange	black	22.0	male	masculine	Dorin	Kel Dor
55	Mas Amedda	196.0	NaN	none	blue	blue	NaN	male	masculine	Champala	Chagrian
59	Poggle the Lesser	183.0	80.0	none	green	yellow	NaN	male	masculine	Geonosis	Geonosian
67	Dexter Jettster	198.0	102.0	none	brown	yellow	NaN	male	masculine	Ojom	Besalisk
68	Lama Su	229.0	88.0	none	grey	black	NaN	male	masculine	Kamino	Kaminoan
69	Taun We	213.0	NaN	none	grey	black	NaN	female	feminine	Kamino	Kaminoan
71	Ratts Tyerell	79.0	15.0	none	grey, blue	unknown	NaN	male	masculine	Aleen Minor	Aleena
72	R4-P17	96.0	NaN	none	silver, red	red, blue	NaN	none	feminine	NaN	Droid
73	Wat Tambor	193.0	48.0	none	green, grey	unknown	NaN	male	masculine	Skako	Skakoan
74	San Hill	191.0	NaN	none	grey	gold	NaN	male	masculine	Muunilinst	Muun
75	Shaak Ti	178.0	57.0	none	red, blue, white	black	NaN	female	feminine	Shili	Togruta
76	Grievous	216.0	159.0	none	brown, white	green, yellow	NaN	male	masculine	Kalee	Kaleesh
79	Sly Moore	178.0	48.0	none	pale	white	NaN	NaN	NaN	Umbara	NaN
80	Tion Medon	206.0	80.0	none	grey	black	NaN	male	masculine	Utapau	Pau'an
84	BB8	NaN	NaN	none	none	black	NaN	none	masculine	NaN	Droid

In [6]:

filter(starwars, f.hair_color == "none", f.eye_color == "black")

filter(starwars, f.hair_color == "none", f.eye_color == "black")

Out[6]:

	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
29	Nien Nunb	160.0	68.0	none	grey	black	NaN	male	masculine	Sullust	Sullustan
45	Gasgano	122.0	NaN	none	white, blue	black	NaN	male	masculine	Troiken	Xexto
49	Kit Fisto	196.0	87.0	none	green	black	NaN	male	masculine	Glee Anselm	Nautolan
54	Plo Koon	188.0	80.0	none	orange	black	22.0	male	masculine	Dorin	Kel Dor
68	Lama Su	229.0	88.0	none	grey	black	NaN	male	masculine	Kamino	Kaminoan
69	Taun We	213.0	NaN	none	grey	black	NaN	female	feminine	Kamino	Kaminoan
75	Shaak Ti	178.0	57.0	none	red, blue, white	black	NaN	female	feminine	Shili	Togruta
80	Tion Medon	206.0	80.0	none	grey	black	NaN	male	masculine	Utapau	Pau'an
84	BB8	NaN	NaN	none	none	black	NaN	none	masculine	NaN	Droid

In [8]:

starwars >> filter(f.mass > mean(f.mass))

starwars >> filter(f.mass > mean(f.mass))

Out[8]:

	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
3	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
5	Owen Lars	178.0	120.0	brown, grey	light	blue	52.0	male	masculine	Tatooine	Human
12	Chewbacca	228.0	112.0	brown	unknown	blue	200.0	male	masculine	Kashyyyk	Wookiee
15	Jabba Desilijic Tiure	175.0	1358.0	NaN	green-tan, brown	orange	600.0	hermaphroditic	masculine	Nal Hutta	Hutt
17	Jek Tono Porkins	180.0	110.0	brown	fair	blue	NaN	male	masculine	Bestine IV	Human
21	IG-88	200.0	140.0	none	metal	red	15.0	none	masculine	NaN	Droid
22	Bossk	190.0	113.0	none	green	red	53.0	male	masculine	Trandosha	Trandoshan
67	Dexter Jettster	198.0	102.0	none	brown	yellow	NaN	male	masculine	Ojom	Besalisk
76	Grievous	216.0	159.0	none	brown, white	green, yellow	NaN	male	masculine	Kalee	Kaleesh
77	Tarfful	234.0	136.0	brown	brown	blue	NaN	male	masculine	Kashyyyk	Wookiee

In [ ]:

starwars >> group_by(f.gender) >> filter(f.mass > mean(f.mass, na_rm=True))

starwars >> group_by(f.gender) >> filter(f.mass > mean(f.mass, na_rm=True))

Out[ ]:

	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
0	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
1	Owen Lars	178.0	120.0	brown, grey	light	blue	52.0	male	masculine	Tatooine	Human
2	Beru Whitesun lars	165.0	75.0	brown	light	blue	47.0	female	feminine	Tatooine	Human
3	Chewbacca	228.0	112.0	brown	unknown	blue	200.0	male	masculine	Kashyyyk	Wookiee
4	Jabba Desilijic Tiure	175.0	1358.0	NaN	green-tan, brown	orange	600.0	hermaphroditic	masculine	Nal Hutta	Hutt
5	Jek Tono Porkins	180.0	110.0	brown	fair	blue	NaN	male	masculine	Bestine IV	Human
6	IG-88	200.0	140.0	none	metal	red	15.0	none	masculine	NaN	Droid
7	Bossk	190.0	113.0	none	green	red	53.0	male	masculine	Trandosha	Trandoshan
8	Ayla Secura	178.0	55.0	none	blue	hazel	48.0	female	feminine	Ryloth	Twi'lek
9	Luminara Unduli	170.0	56.2	black	yellow	blue	58.0	female	feminine	Mirial	Mirialan
10	Zam Wesell	168.0	55.0	blonde	fair, green, yellow	yellow	NaN	female	feminine	Zolan	Clawdite
11	Shaak Ti	178.0	57.0	none	red, blue, white	black	NaN	female	feminine	Shili	Togruta
12	Grievous	216.0	159.0	none	brown, white	green, yellow	NaN	male	masculine	Kalee	Kaleesh
13	Tarfful	234.0	136.0	brown	brown	blue	NaN	male	masculine	Kashyyyk	Wookiee

TibbleGrouped: gender (n=2)

In [ ]:

# To refer to column names that are stored as strings, use `f[...]`:
vars = c("mass", "height")
cond = c(80, 150)
starwars >> \
  filter(
    f[vars[0]] > cond[0],
    f[vars[1]] > cond[1]
  )

# To refer to column names that are stored as strings, use `f[...]`: vars = c("mass", "height") cond = c(80, 150) starwars >> \ filter( f[vars[0]] > cond[0], f[vars[1]] > cond[1] )

Out[ ]:

	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
3	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
5	Owen Lars	178.0	120.0	brown, grey	light	blue	52.0	male	masculine	Tatooine	Human
8	Biggs Darklighter	183.0	84.0	black	light	brown	24.0	male	masculine	Tatooine	Human
10	Anakin Skywalker	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
12	Chewbacca	228.0	112.0	brown	unknown	blue	200.0	male	masculine	Kashyyyk	Wookiee
15	Jabba Desilijic Tiure	175.0	1358.0	NaN	green-tan, brown	orange	600.0	hermaphroditic	masculine	Nal Hutta	Hutt
17	Jek Tono Porkins	180.0	110.0	brown	fair	blue	NaN	male	masculine	Bestine IV	Human
21	IG-88	200.0	140.0	none	metal	red	15.0	none	masculine	NaN	Droid
22	Bossk	190.0	113.0	none	green	red	53.0	male	masculine	Trandosha	Trandoshan
25	Ackbar	180.0	83.0	none	brown mottle	orange	41.0	male	masculine	Mon Cala	Mon Calamari
30	Qui-Gon Jinn	193.0	89.0	brown	fair	blue	92.0	male	masculine	NaN	Human
31	Nute Gunray	191.0	90.0	none	mottled green	red	NaN	male	masculine	Cato Neimoidia	Neimodian
34	Roos Tarpals	224.0	82.0	none	grey	orange	NaN	male	masculine	Naboo	Gungan
47	Mace Windu	188.0	84.0	none	dark	brown	72.0	male	masculine	Haruun Kal	Human
48	Ki-Adi-Mundi	198.0	82.0	white	pale	yellow	92.0	male	masculine	Cerea	Cerean
49	Kit Fisto	196.0	87.0	none	green	black	NaN	male	masculine	Glee Anselm	Nautolan
56	Gregar Typho	185.0	85.0	black	dark	brown	NaN	male	masculine	Naboo	Human
67	Dexter Jettster	198.0	102.0	none	brown	yellow	NaN	male	masculine	Ojom	Besalisk
68	Lama Su	229.0	88.0	none	grey	black	NaN	male	masculine	Kamino	Kaminoan
76	Grievous	216.0	159.0	none	brown, white	green, yellow	NaN	male	masculine	Kalee	Kaleesh
77	Tarfful	234.0	136.0	brown	brown	blue	NaN	male	masculine	Kashyyyk	Wookiee