group_map

In [2]:

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

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

nb_header(group_map)

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

Try this notebook on binder.

★ group_map

¶

Apply a function to each group¶

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

Args:¶

  _data: A grouped frame
  _f: A function to apply to each group.
  *args: Additional arguments to pass to func.
  _keep: If True, keep the grouping variables in the output.
  **kwargs: Additional keyword arguments to pass to func.

Returns:¶

  A list of results

In [3]:

list(
  mtcars >> \
  group_by(f.cyl) >> \
  group_map(lambda df: df >> head(2))
)

list( mtcars >> \ group_by(f.cyl) >> \ group_map(lambda df: df >> head(2)) )

Out[3]:

[        mpg      disp      hp      drat  ...      vs      am    gear    carb
   <float64> <float64> <int64> <float64>  ... <int64> <int64> <int64> <int64>
 0      21.0     160.0     110       3.9  ...       0       1       4       4
 1      21.0     160.0     110       3.9            0       1       4       4
 
 [2 rows x 10 columns],
         mpg      disp      hp      drat  ...      vs      am    gear    carb
   <float64> <float64> <int64> <float64>  ... <int64> <int64> <int64> <int64>
 0      22.8     108.0      93      3.85  ...       1       1       4       1
 1      24.4     146.7      62      3.69            1       0       4       2
 
 [2 rows x 10 columns],
         mpg      disp      hp      drat  ...      vs      am    gear    carb
   <float64> <float64> <int64> <float64>  ... <int64> <int64> <int64> <int64>
 0      18.7     360.0     175      3.15  ...       0       0       3       2
 1      14.3     360.0     245      3.21            0       0       3       4
 
 [2 rows x 10 columns]]

In [4]:

mtcars >> \
  group_by(f.cyl) >> \
  group_modify(lambda df: df >> head(2))

mtcars >> \ group_by(f.cyl) >> \ group_modify(lambda df: df >> head(2))

Out[4]:

	cyl	mpg	disp	hp	drat	wt	qsec	vs	am	gear	carb
	<int64>	<float64>	<float64>	<int64>	<float64>	<float64>	<float64>	<int64>	<int64>	<int64>	<int64>
0	6	21.0	160.0	110	3.90	2.620	16.46	0	1	4	4
1	6	21.0	160.0	110	3.90	2.875	17.02	0	1	4	4
0	4	22.8	108.0	93	3.85	2.320	18.61	1	1	4	1
1	4	24.4	146.7	62	3.69	3.190	20.00	1	0	4	2
0	8	18.7	360.0	175	3.15	3.440	17.02	0	0	3	2
1	8	14.3	360.0	245	3.21	3.570	15.84	0	0	3	4

TibbleGrouped: cyl (n=3)

In [5]:

list(
  iris >> \
  group_by(f.Species) >> \
  group_map(lambda df: quantile(df['Petal_Length'], probs=c(0.25, 0.5, 0.75)))
)

list( iris >> \ group_by(f.Species) >> \ group_map(lambda df: quantile(df['Petal_Length'], probs=c(0.25, 0.5, 0.75))) )

Out[5]:

[array([1.4  , 1.5  , 1.575]),
 array([4.  , 4.35, 4.6 ]),
 array([5.1  , 5.55 , 5.875])]

In [6]:

iris >> \
  group_by(f.Species) >> \
  group_walk(lambda df: print(df.shape))

iris >> \ group_by(f.Species) >> \ group_walk(lambda df: print(df.shape))

(50, 4)
(50, 4)
(50, 4)

In [7]:

mtcars >> \
  group_modify(lambda df: df >> head(2))

mtcars >> \ group_modify(lambda df: df >> head(2))

Out[7]:

	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
	<float64>	<int64>	<float64>	<int64>	<float64>	<float64>	<float64>	<int64>	<int64>	<int64>	<int64>
Mazda RX4	21.0	6	160.0	110	3.9	2.620	16.46	0	1	4	4
Mazda RX4 Wag	21.0	6	160.0	110	3.9	2.875	17.02	0	1	4	4

In [ ]: