uncount

In [1]:

# https://tidyr.tidyverse.org/reference/uncount.html
%run nb_helpers.py

from datar.all import *

nb_header(uncount)

# https://tidyr.tidyverse.org/reference/uncount.html %run nb_helpers.py from datar.all import * nb_header(uncount)

Try this notebook on binder.

★ uncount

¶

Duplicating rows according to a weighting variable¶

Args:¶

  data: A data frame
  weights: A vector of weights. Evaluated in the context of data
  _remove: If TRUE, and weights is the name of a column in data,
    then this column is removed.

  _id: Supply a string to create a new variable which gives a
    unique identifier for each created row (0-based).

Returns:¶

  dataframe with rows repeated.

In [2]:

df = tibble(x = c("a", "b"), n = c(1, 2))
df >> uncount(f.n)

df = tibble(x = c("a", "b"), n = c(1, 2)) df >> uncount(f.n)

Out[2]:

	x
	<object>
0	a
1	b
2	b

In [3]:

df >> uncount(f.n, _id="id")

df >> uncount(f.n, _id="id")

Out[3]:

	id	x
	<int64>	<object>
0	0	a
1	1	b
2	1	b

In [4]:

uncount(df, 2)

uncount(df, 2)

Out[4]:

	x	n
	<object>	<int64>
0	a	1
1	a	1
2	b	2
3	b	2

In [5]:

df >> uncount(2//f.n)

df >> uncount(2//f.n)

Out[5]:

	x
	<object>
0	a
1	a
2	b

In [ ]: