count

In [1]:

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

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

nb_header(count, tally, add_count, add_tally)

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

Try this notebook on binder.

★ count

¶

Count the number of rows in each group¶

Original API:
https://dplyr.tidyverse.org/reference/count.html

Args:¶

  _data: A data frame
  *args: Variables, or functions of variables.
    Use desc() to sort a variable in descending order.

  wt: A variable or function of variables to weight by.
  sort: If TRUE, the result will be sorted by the count.
  name: The name of the count column.
  _drop: If False, keep grouping variables even if they are not used.
    Original API does not support this.

  **kwargs: Name-value pairs that apply with mutate

Returns:¶

  A data frame with the same number of rows as the number of groups.
  The output has the following properties:
    All rows appear in the output, but (usually) in a different place.
    Columns are not modified.
    Groups are not modified.
    Data frame attributes are preserved.

★ tally

¶

Count the number of rows in each group¶

Original API:
https://dplyr.tidyverse.org/reference/count.html

Args:¶

  _data: A data frame
  wt: A variable or function of variables to weight by.
  sort: If TRUE, the result will be sorted by the count.
  name: The name of the count column.

Returns:¶

  A data frame with the same number of rows as the number of groups.
  The output has the following properties:
    All rows appear in the output, but (usually) in a different place.
    Columns are not modified.
    Groups are not modified.
    Data frame attributes are preserved.

★ add_count

¶

Add a count column to a data frame¶

Original API:
https://dplyr.tidyverse.org/reference/count.html

Args:¶

  _data: A data frame
  *args: Variables, or functions of variables.
    Use desc() to sort a variable in descending order.

  wt: A variable or function of variables to weight by.
  sort: If TRUE, the result will be sorted by the count.
  name: The name of the count column.
  **kwargs: Name-value pairs that apply with mutate

Returns:¶

  A data frame with the same number of rows as the number of groups.
  The output has the following properties:
    All rows appear in the output, but (usually) in a different place.
    Columns are not modified.
    Groups are not modified.
    Data frame attributes are preserved.

★ add_tally

¶

Add a count column to a data frame¶

Original API:
https://dplyr.tidyverse.org/reference/count.html

Args:¶

  _data: A data frame
  wt: A variable or function of variables to weight by.
  sort: If TRUE, the result will be sorted by the count.
  name: The name of the count column.

Returns:¶

  A data frame with the same number of rows as the number of groups.
  The output has the following properties:
    All rows appear in the output, but (usually) in a different place.
    Columns are not modified.
    Groups are not modified.
    Data frame attributes are preserved.

In [2]:

starwars >> count(f.species)

starwars >> count(f.species)

Out[2]:

	species	n
	<object>	<int64>
0	Human	35
1	Droid	6
2	Wookiee	2
3	Rodian	1
4	Hutt	1
5	Yoda's species	1
6	Trandoshan	1
7	Mon Calamari	1
8	Ewok	1
9	Sullustan	1
10	Neimodian	1
11	Gungan	3
12	NaN	4
13	Toydarian	1
14	Dug	1
15	Zabrak	2
16	Twi'lek	2
17	Vulptereen	1
18	Xexto	1
19	Toong	1
20	Cerean	1
21	Nautolan	1
22	Tholothian	1
23	Iktotchi	1
24	Quermian	1
25	Kel Dor	1
26	Chagrian	1
27	Geonosian	1
28	Mirialan	2
29	Clawdite	1
30	Besalisk	1
31	Kaminoan	2
32	Aleena	1
33	Skakoan	1
34	Muun	1
35	Togruta	1
36	Kaleesh	1
37	Pau'an	1

In [3]:

starwars >> count(f.species, sort=True)

starwars >> count(f.species, sort=True)

Out[3]:

	species	n
	<object>	<int64>
0	Human	35
1	Droid	6
2	NaN	4
3	Gungan	3
4	Twi'lek	2
5	Zabrak	2
6	Kaminoan	2
7	Mirialan	2
8	Wookiee	2
9	Besalisk	1
10	Clawdite	1
11	Iktotchi	1
12	Skakoan	1
13	Muun	1
14	Geonosian	1
15	Chagrian	1
16	Togruta	1
17	Kel Dor	1
18	Quermian	1
19	Aleena	1
20	Tholothian	1
21	Xexto	1
22	Cerean	1
23	Toong	1
24	Kaleesh	1
25	Vulptereen	1
26	Dug	1
27	Toydarian	1
28	Neimodian	1
29	Sullustan	1
30	Ewok	1
31	Mon Calamari	1
32	Trandoshan	1
33	Yoda's species	1
34	Hutt	1
35	Rodian	1
36	Nautolan	1
37	Pau'an	1

TibbleGrouped: species (n=38)

In [4]:

starwars >> count(f.sex, f.gender, sort=True)

starwars >> count(f.sex, f.gender, sort=True)

Out[4]:

	sex	gender	n
	<object>	<object>	<int64>
0	male	masculine	60
1	female	feminine	16
2	none	masculine	5
3	NaN	NaN	4
4	hermaphroditic	masculine	1
5	none	feminine	1

TibbleGrouped: sex, gender (n=6)

In [5]:

starwars >> count(birth_decade=round(f.birth_year, -1))

starwars >> count(birth_decade=round(f.birth_year, -1))

Out[5]:

	birth_decade	n
	<float64>	<int64>
0	20.0	6
1	110.0	1
2	30.0	4
3	40.0	6
4	50.0	8
5	NaN	44
6	60.0	4
7	200.0	1
8	600.0	1
9	900.0	1
10	80.0	2
11	10.0	1
12	90.0	3
13	70.0	4
14	100.0	1

In [6]:

df = tribble(
  f.name,    f.gender,   f.runs,
  "Max",    "male",       10,
  "Sandra", "female",      1,
  "Susan",  "female",      4
)
# counts rows:
df >> count(f.gender)

df = tribble( f.name, f.gender, f.runs, "Max", "male", 10, "Sandra", "female", 1, "Susan", "female", 4 ) # counts rows: df >> count(f.gender)

Out[6]:

	gender	n
	<object>	<int64>
0	male	1
1	female	2

In [7]:

df >> count(f.gender, wt=f.runs)

df >> count(f.gender, wt=f.runs)

Out[7]:

	gender	n
	<object>	<int64>
0	male	10
1	female	5

In [8]:

starwars >> tally()

starwars >> tally()

Out[8]:

	n
	<int64>
0	87

In [9]:

starwars >> group_by(f.species) >> tally() 

starwars >> group_by(f.species) >> tally()

Out[9]:

	species	n
	<object>	<int64>
0	Human	35
1	Droid	6
2	Wookiee	2
3	Rodian	1
4	Hutt	1
5	Yoda's species	1
6	Trandoshan	1
7	Mon Calamari	1
8	Ewok	1
9	Sullustan	1
10	Neimodian	1
11	Gungan	3
12	NaN	4
13	Toydarian	1
14	Dug	1
15	Zabrak	2
16	Twi'lek	2
17	Vulptereen	1
18	Xexto	1
19	Toong	1
20	Cerean	1
21	Nautolan	1
22	Tholothian	1
23	Iktotchi	1
24	Quermian	1
25	Kel Dor	1
26	Chagrian	1
27	Geonosian	1
28	Mirialan	2
29	Clawdite	1
30	Besalisk	1
31	Kaminoan	2
32	Aleena	1
33	Skakoan	1
34	Muun	1
35	Togruta	1
36	Kaleesh	1
37	Pau'an	1

In [10]:

df >> add_count(f.gender, wt=f.runs)

df >> add_count(f.gender, wt=f.runs)

Out[10]:

	name	gender	runs	n
	<object>	<object>	<int64>	<int64>
0	Max	male	10	10
1	Sandra	female	1	5
2	Susan	female	4	5

TibbleGrouped: gender (n=2)

In [11]:

df

df

Out[11]:

	name	gender	runs
	<object>	<object>	<int64>
0	Max	male	10
1	Sandra	female	1
2	Susan	female	4

In [12]:

df >> add_tally(wt=f.runs)

df >> add_tally(wt=f.runs)

Out[12]:

	name	gender	runs	n
	<object>	<object>	<int64>	<int64>
0	Max	male	10	15
1	Sandra	female	1	15
2	Susan	female	4	15