extract

In [1]:

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

from datar.all import *

nb_header(extract)

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

Try this notebook on binder.

★ extract

¶

Given a regular expression with capturing groups, extract() turns each¶

group into a new column. If the groups don't match, or the input is NA,
the output will be NA.

See https://tidyr.tidyverse.org/reference/extract.html

Args:¶

  data: The dataframe
  col: Column name or position.
  into: Names of new variables to create as character vector.
    Use None to omit the variable in the output.

  regex: a regular expression used to extract the desired values.
    There should be one group (defined by ()) for each element of into.

  remove: If TRUE, remove input column from output data frame.
  convert: The universal type for the extracted columns or a dict for
    individual ones

Returns:¶

  Dataframe with extracted columns.

In [2]:

df = tibble(x = c(NA, "a-b", "a-d", "b-c", "d-e"))
df >> extract(f.x, "A")

df = tibble(x = c(NA, "a-b", "a-d", "b-c", "d-e")) df >> extract(f.x, "A")

Out[2]:

	A
	<object>
0	NaN
1	a
2	a
3	b
4	d

In [3]:

df >> extract(f.x, c("A", "B"), r"(\w+)-(\w+)")

df >> extract(f.x, c("A", "B"), r"(\w+)-(\w+)")

Out[3]:

	A	B
	<object>	<object>
0	NaN	NaN
1	a	b
2	a	d
3	b	c
4	d	e

In [4]:

df >> extract(f.x, c("A", "B"), r"([a-d]+)-([a-d]+)")

df >> extract(f.x, c("A", "B"), r"([a-d]+)-([a-d]+)")

Out[4]:

	A	B
	<object>	<object>
0	NaN	NaN
1	a	b
2	a	d
3	b	c
4	NaN	NaN

In [5]:

# combine multiple columns
df = tibble(x='abcd')
df >> extract(f.x, ['a', 'b', 'a', 'b'], r'(.)(.)(.)(.)')

# combine multiple columns df = tibble(x='abcd') df >> extract(f.x, ['a', 'b', 'a', 'b'], r'(.)(.)(.)(.)')

Out[5]:

	a	b
	<object>	<object>
0	ac	bd