bind

In [1]:

# https://dplyr.tidyverse.org/reference/bind.html
%run nb_helpers.py

from datar.data import starwars
from datar.all import *

nb_header(bind_rows, bind_cols, book='bind')

# https://dplyr.tidyverse.org/reference/bind.html %run nb_helpers.py from datar.data import starwars from datar.all import * nb_header(bind_rows, bind_cols, book='bind')

Try this notebook on binder.

★ bind_rows

¶

Bind rows of give dataframes¶

Original APIs https://dplyr.tidyverse.org/reference/bind.html

Args:¶

  *data: Dataframes to combine
  _id: The name of the id columns
  _copy: If False, do not copy data unnecessarily.
    Original API does not support this. This argument will be
    passed by to pandas.concat() as copy argument.

  **kwargs: A mapping of dataframe, keys will be used as _id col.

Returns:¶

  The combined dataframe

★ bind_cols

¶

Bind columns of give dataframes¶

Note that unlike dplyr, mismatched dimensions are allowed and
missing rows will be filled with NAs

Args:¶

  *data: Dataframes to bind
  _name_repair: treatment of problematic column names:
    - "minimal": No name repair or checks, beyond basic existence,

    - "unique": Make sure names are unique and not empty,

    - "check_unique": (default value), no name repair,       but check they are unique,

    - "universal": Make the names unique and syntactic

    - a function: apply custom name repair

  _copy: If False, do not copy data unnecessarily.
    Original API does not support this. This argument will be
    passed by to pandas.concat() as copy argument.

Returns:¶

  The combined dataframe

In [2]:

one = starwars >> slice(c[:4])
two = starwars >> slice(c[9:12])

one >> bind_rows(two)

one = starwars >> slice(c[:4]) two = starwars >> slice(c[9:12]) one >> bind_rows(two)

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
1	C-3PO	167.0	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	Droid
2	R2-D2	96.0	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	Droid
3	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
4	Obi-Wan Kenobi	182.0	77.0	auburn, white	fair	blue-gray	57.0	male	masculine	Stewjon	Human
5	Anakin Skywalker	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
6	Wilhuff Tarkin	180.0	NaN	auburn, grey	fair	blue	64.0	male	masculine	Eriadu	Human

In [3]:

bind_rows([one, two])

bind_rows([one, two])

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>
0	Luke Skywalker	172.0	77.0	blond	fair	blue	19.0	male	masculine	Tatooine	Human
1	C-3PO	167.0	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	Droid
2	R2-D2	96.0	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	Droid
3	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
4	Obi-Wan Kenobi	182.0	77.0	auburn, white	fair	blue-gray	57.0	male	masculine	Stewjon	Human
5	Anakin Skywalker	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
6	Wilhuff Tarkin	180.0	NaN	auburn, grey	fair	blue	64.0	male	masculine	Eriadu	Human

In [4]:

bind_rows([one, two], [two, one])

bind_rows([one, two], [two, one])

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>
0	Luke Skywalker	172.0	77.0	blond	fair	blue	19.0	male	masculine	Tatooine	Human
1	C-3PO	167.0	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	Droid
2	R2-D2	96.0	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	Droid
3	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
4	Obi-Wan Kenobi	182.0	77.0	auburn, white	fair	blue-gray	57.0	male	masculine	Stewjon	Human
5	Anakin Skywalker	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
6	Wilhuff Tarkin	180.0	NaN	auburn, grey	fair	blue	64.0	male	masculine	Eriadu	Human
7	Obi-Wan Kenobi	182.0	77.0	auburn, white	fair	blue-gray	57.0	male	masculine	Stewjon	Human
8	Anakin Skywalker	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
9	Wilhuff Tarkin	180.0	NaN	auburn, grey	fair	blue	64.0	male	masculine	Eriadu	Human
10	Luke Skywalker	172.0	77.0	blond	fair	blue	19.0	male	masculine	Tatooine	Human
11	C-3PO	167.0	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	Droid
12	R2-D2	96.0	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	Droid
13	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human

In [5]:

tibble(a=1, b=2) >> bind_rows(tibble(a=3, b=4))

tibble(a=1, b=2) >> bind_rows(tibble(a=3, b=4))

Out[5]:

	a	b
	<int64>	<int64>
0	1	2
1	3	4

In [6]:

tibble(a=1, b=2) >> bind_rows(
    tibble(a=[3, 4], b=[5, 6]),
    tibble(a=7, b=8)
)

tibble(a=1, b=2) >> bind_rows( tibble(a=[3, 4], b=[5, 6]), tibble(a=7, b=8) )

Out[6]:

	a	b
	<int64>	<int64>
0	1	2
1	3	5
2	4	6
3	7	8

In [7]:

bind_rows([one, two], _id = "id")

bind_rows([one, two], _id = "id")

Out[7]:

	id	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<int64>	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
0	0	Luke Skywalker	172.0	77.0	blond	fair	blue	19.0	male	masculine	Tatooine	Human
1	0	C-3PO	167.0	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	Droid
2	0	R2-D2	96.0	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	Droid
3	0	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
4	1	Obi-Wan Kenobi	182.0	77.0	auburn, white	fair	blue-gray	57.0	male	masculine	Stewjon	Human
5	1	Anakin Skywalker	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
6	1	Wilhuff Tarkin	180.0	NaN	auburn, grey	fair	blue	64.0	male	masculine	Eriadu	Human

In [9]:

# If we need a name for one
bind_rows(a=one, b=two, _id = "id")

# If we need a name for one bind_rows(a=one, b=two, _id = "id")

Out[9]:

	id	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
0	a	Luke Skywalker	172.0	77.0	blond	fair	blue	19.0	male	masculine	Tatooine	Human
1	a	C-3PO	167.0	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	Droid
2	a	R2-D2	96.0	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	Droid
3	a	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
4	b	Obi-Wan Kenobi	182.0	77.0	auburn, white	fair	blue-gray	57.0	male	masculine	Stewjon	Human
5	b	Anakin Skywalker	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
6	b	Wilhuff Tarkin	180.0	NaN	auburn, grey	fair	blue	64.0	male	masculine	Eriadu	Human

In [10]:

bind_rows(**{"group 1": one, "group 2": two}, _id = "groups")

bind_rows(**{"group 1": one, "group 2": two}, _id = "groups")

Out[10]:

	groups	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<object>	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
0	group 1	Luke Skywalker	172.0	77.0	blond	fair	blue	19.0	male	masculine	Tatooine	Human
1	group 1	C-3PO	167.0	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	Droid
2	group 1	R2-D2	96.0	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	Droid
3	group 1	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
4	group 2	Obi-Wan Kenobi	182.0	77.0	auburn, white	fair	blue-gray	57.0	male	masculine	Stewjon	Human
5	group 2	Anakin Skywalker	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
6	group 2	Wilhuff Tarkin	180.0	NaN	auburn, grey	fair	blue	64.0	male	masculine	Eriadu	Human

In [11]:

tibble(x=range(3)) >> bind_rows(
    tibble(y=range(4))
)

tibble(x=range(3)) >> bind_rows( tibble(y=range(4)) )

Out[11]:

	x	y
	<float64>	<float64>
0	0.0	NaN
1	1.0	NaN
2	2.0	NaN
3	NaN	0.0
4	NaN	1.0
5	NaN	2.0
6	NaN	3.0

In [12]:

# NAs filled for missed rows
tibble(x=range(3)) >> bind_cols(
    tibble(y=range(2))
)

# NAs filled for missed rows tibble(x=range(3)) >> bind_cols( tibble(y=range(2)) )

Out[12]:

	x	y
	<int64>	<float64>
0	0	0.0
1	1	1.0
2	2	NaN

In [13]:

tibble(x = range(3)) >> bind_cols(tibble())

tibble(x = range(3)) >> bind_cols(tibble())

Out[13]:

	x
	<int64>
0	0
1	1
2	2

In [14]:

one >> bind_cols(two)

one >> bind_cols(two)

[2022-12-02 13:42:54][datar][WARNING] New names:
[2022-12-02 13:42:54][datar][WARNING] * 'name' -> 'name__0'
[2022-12-02 13:42:54][datar][WARNING] * 'height' -> 'height__1'
[2022-12-02 13:42:54][datar][WARNING] * 'mass' -> 'mass__2'
[2022-12-02 13:42:54][datar][WARNING] * 'hair_color' -> 'hair_color__3'
[2022-12-02 13:42:54][datar][WARNING] * 'skin_color' -> 'skin_color__4'
[2022-12-02 13:42:54][datar][WARNING] * 'eye_color' -> 'eye_color__5'
[2022-12-02 13:42:54][datar][WARNING] * 'birth_year' -> 'birth_year__6'
[2022-12-02 13:42:54][datar][WARNING] * 'sex' -> 'sex__7'
[2022-12-02 13:42:54][datar][WARNING] * 'gender' -> 'gender__8'
[2022-12-02 13:42:54][datar][WARNING] * 'homeworld' -> 'homeworld__9'
[2022-12-02 13:42:54][datar][WARNING] * 'species' -> 'species__10'
[2022-12-02 13:42:54][datar][WARNING] * 'name' -> 'name__11'
[2022-12-02 13:42:54][datar][WARNING] * 'height' -> 'height__12'
[2022-12-02 13:42:54][datar][WARNING] * 'mass' -> 'mass__13'
[2022-12-02 13:42:54][datar][WARNING] * 'hair_color' -> 'hair_color__14'
[2022-12-02 13:42:54][datar][WARNING] * 'skin_color' -> 'skin_color__15'
[2022-12-02 13:42:54][datar][WARNING] * 'eye_color' -> 'eye_color__16'
[2022-12-02 13:42:54][datar][WARNING] * 'birth_year' -> 'birth_year__17'
[2022-12-02 13:42:54][datar][WARNING] * 'sex' -> 'sex__18'
[2022-12-02 13:42:54][datar][WARNING] * 'gender' -> 'gender__19'
[2022-12-02 13:42:54][datar][WARNING] * 'homeworld' -> 'homeworld__20'
[2022-12-02 13:42:54][datar][WARNING] * 'species' -> 'species__21'

Out[14]:

	name__0	height__1	mass__2	hair_color__3	skin_color__4	eye_color__5	birth_year__6	sex__7	gender__8	homeworld__9	...	height__12	mass__13	hair_color__14	skin_color__15	eye_color__16	birth_year__17	sex__18	gender__19	homeworld__20	species__21
	<object>	<float64>	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<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	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	C-3PO	167.0	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	R2-D2	96.0	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
9	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	182.0	77.0	auburn, white	fair	blue-gray	57.0	male	masculine	Stewjon	Human
10	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	188.0	84.0	blond	fair	blue	41.9	male	masculine	Tatooine	Human
11	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	180.0	NaN	auburn, grey	fair	blue	64.0	male	masculine	Eriadu	Human

7 rows × 22 columns