select

In [1]:

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

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

nb_header(select)

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

Try this notebook on binder.

★ select

¶

Select columns from a data frame.¶

See original API
https://dplyr.tidyverse.org/reference/select.html

Args:¶

  _data: A data frame
  *args: A list of columns to select
  **kwargs: A list of columns to select

Returns:¶

  A data frame with only the selected columns

In [2]:

starwars >> select(f.height)

starwars >> select(f.height)

Out[2]:

	height
	<float64>
0	172.0
1	167.0
2	96.0
3	202.0
...	...
4	150.0
82	NaN
83	NaN
84	NaN
85	NaN
86	165.0

87 rows × 1 columns

In [3]:

iris >> pivot_longer(f['Sepal_Length'])

iris >> pivot_longer(f['Sepal_Length'])

Out[3]:

	Petal_Length	Petal_Width	Sepal_Width	Species	name	value
	<float64>	<float64>	<float64>	<object>	<object>	<float64>
0	1.4	0.2	3.5	setosa	Sepal_Length	5.1
1	1.4	0.2	3.0	setosa	Sepal_Length	4.9
2	1.3	0.2	3.2	setosa	Sepal_Length	4.7
3	1.5	0.2	3.1	setosa	Sepal_Length	4.6
...	...	...	...	...	...	...
4	1.4	0.2	3.6	setosa	Sepal_Length	5.0
145	5.2	2.3	3.0	virginica	Sepal_Length	6.7
146	5.0	1.9	2.5	virginica	Sepal_Length	6.3
147	5.2	2.0	3.0	virginica	Sepal_Length	6.5
148	5.4	2.3	3.4	virginica	Sepal_Length	6.2
149	5.1	1.8	3.0	virginica	Sepal_Length	5.9

150 rows × 6 columns

In [4]:

starwars >> select(f.homeworld, f.height, f.mass)

starwars >> select(f.homeworld, f.height, f.mass)

Out[4]:

	homeworld	height	mass
	<object>	<float64>	<float64>
0	Tatooine	172.0	77.0
1	Tatooine	167.0	75.0
2	Naboo	96.0	32.0
3	Tatooine	202.0	136.0
...	...	...	...
4	Alderaan	150.0	49.0
82	NaN	NaN	NaN
83	NaN	NaN	NaN
84	NaN	NaN	NaN
85	NaN	NaN	NaN
86	Naboo	165.0	45.0

87 rows × 3 columns

In [5]:

iris >> pivot_longer(c(f['Sepal_Length'], f['Petal_Length']))

iris >> pivot_longer(c(f['Sepal_Length'], f['Petal_Length']))

Out[5]:

	Petal_Width	Sepal_Width	Species	name	value
	<float64>	<float64>	<object>	<object>	<float64>
0	0.2	3.5	setosa	Sepal_Length	5.1
1	0.2	3.0	setosa	Sepal_Length	4.9
2	0.2	3.2	setosa	Sepal_Length	4.7
3	0.2	3.1	setosa	Sepal_Length	4.6
...	...	...	...	...	...
4	0.2	3.6	setosa	Sepal_Length	5.0
295	2.3	3.0	virginica	Petal_Length	5.2
296	1.9	2.5	virginica	Petal_Length	5.0
297	2.0	3.0	virginica	Petal_Length	5.2
298	2.3	3.4	virginica	Petal_Length	5.4
299	1.8	3.0	virginica	Petal_Length	5.1

300 rows × 5 columns

In [6]:

starwars >> select(c[f.name:f.mass])

starwars >> select(c[f.name:f.mass])

Out[6]:

	name	height
	<object>	<float64>
0	Luke Skywalker	172.0
1	C-3PO	167.0
2	R2-D2	96.0
3	Darth Vader	202.0
...	...	...
4	Leia Organa	150.0
82	Rey	NaN
83	Poe Dameron	NaN
84	BB8	NaN
85	Captain Phasma	NaN
86	Padmé Amidala	165.0

87 rows × 2 columns

In [7]:

starwars >> select(~c[f.name:f.mass])

starwars >> select(~c[f.name:f.mass])

Out[7]:

	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
	<float64>	<object>	<object>	<object>	<float64>	<object>	<object>	<object>	<object>
0	77.0	blond	fair	blue	19.0	male	masculine	Tatooine	Human
1	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	Droid
2	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	Droid
3	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
...	...	...	...	...	...	...	...	...	...
4	49.0	brown	light	brown	19.0	female	feminine	Alderaan	Human
82	NaN	brown	light	hazel	NaN	female	feminine	NaN	Human
83	NaN	brown	light	brown	NaN	male	masculine	NaN	Human
84	NaN	none	none	black	NaN	none	masculine	NaN	Droid
85	NaN	unknown	unknown	unknown	NaN	NaN	NaN	NaN	NaN
86	45.0	brown	light	brown	46.0	female	feminine	Naboo	Human

87 rows × 9 columns

In [8]:

iris >> select(~c(f['Sepal_Length'], f['Petal_Length']))

iris >> select(~c(f['Sepal_Length'], f['Petal_Length']))

Out[8]:

	Sepal_Width	Petal_Width	Species
	<float64>	<float64>	<object>
0	3.5	0.2	setosa
1	3.0	0.2	setosa
2	3.2	0.2	setosa
3	3.1	0.2	setosa
...	...	...	...
4	3.6	0.2	setosa
145	3.0	2.3	virginica
146	2.5	1.9	virginica
147	3.0	2.0	virginica
148	3.4	2.3	virginica
149	3.0	1.8	virginica

150 rows × 3 columns

In [9]:

iris >> select(~ends_with("Width"))

iris >> select(~ends_with("Width"))

Out[9]:

	Sepal_Length	Petal_Length	Species
	<float64>	<float64>	<object>
0	5.1	1.4	setosa
1	4.9	1.4	setosa
2	4.7	1.3	setosa
3	4.6	1.5	setosa
...	...	...	...
4	5.0	1.4	setosa
145	6.7	5.2	virginica
146	6.3	5.0	virginica
147	6.5	5.2	virginica
148	6.2	5.4	virginica
149	5.9	5.1	virginica

150 rows × 3 columns

In [10]:

iris >> select(starts_with("Petal") & ends_with("Width"))

iris >> select(starts_with("Petal") & ends_with("Width"))

Out[10]:

	Petal_Width
	<float64>
0	0.2
1	0.2
2	0.2
3	0.2
...	...
4	0.2
145	2.3
146	1.9
147	2.0
148	2.3
149	1.8

150 rows × 1 columns

In [11]:

iris >> select(starts_with("Petal") | ends_with("Width"))

iris >> select(starts_with("Petal") | ends_with("Width"))

Out[11]:

	Petal_Length	Petal_Width	Sepal_Width
	<float64>	<float64>	<float64>
0	1.4	0.2	3.5
1	1.4	0.2	3.0
2	1.3	0.2	3.2
3	1.5	0.2	3.1
...	...	...	...
4	1.4	0.2	3.6
145	5.2	2.3	3.0
146	5.0	1.9	2.5
147	5.2	2.0	3.0
148	5.4	2.3	3.4
149	5.1	1.8	3.0

150 rows × 3 columns

In [12]:

iris >> select(starts_with("Petal") & ~ends_with("Width"))

iris >> select(starts_with("Petal") & ~ends_with("Width"))

Out[12]:

	Petal_Length
	<float64>
0	1.4
1	1.4
2	1.3
3	1.5
...	...
4	1.4
145	5.2
146	5.0
147	5.2
148	5.4
149	5.1

150 rows × 1 columns

In [13]:

# select last column
iris >> select(-1)

# select last column iris >> select(-1)

Out[13]:

	Species
	<object>
0	setosa
1	setosa
2	setosa
3	setosa
...	...
4	setosa
145	virginica
146	virginica
147	virginica
148	virginica
149	virginica

150 rows × 1 columns

In [14]:

iris >> select(c[1:3])

iris >> select(c[1:3])

Out[14]:

	Sepal_Width	Petal_Length
	<float64>	<float64>
0	3.5	1.4
1	3.0	1.4
2	3.2	1.3
3	3.1	1.5
...	...	...
4	3.6	1.4
145	3.0	5.2
146	2.5	5.0
147	3.0	5.2
148	3.4	5.4
149	3.0	5.1

150 rows × 2 columns

In [15]:

# drop last column
iris >> select(~c(-1))

# drop last column iris >> select(~c(-1))

Out[15]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width
	<float64>	<float64>	<float64>	<float64>
0	5.1	3.5	1.4	0.2
1	4.9	3.0	1.4	0.2
2	4.7	3.2	1.3	0.2
3	4.6	3.1	1.5	0.2
...	...	...	...	...
4	5.0	3.6	1.4	0.2
145	6.7	3.0	5.2	2.3
146	6.3	2.5	5.0	1.9
147	6.5	3.0	5.2	2.0
148	6.2	3.4	5.4	2.3
149	5.9	3.0	5.1	1.8

150 rows × 4 columns