fill

In [1]:

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

from datar.all import *

nb_header(fill)

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

Try this notebook on binder.

★ fill

¶

Fills missing values in selected columns using the next or¶

previous entry.

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

Args:¶

  _data: A dataframe
  *columns: Columns to fill
  _direction: Direction in which to fill missing values.
    Currently either "down" (the default), "up",
    "downup" (i.e. first down and then up) or
    "updown" (first up and then down).

Returns:¶

  The dataframe with NAs being replaced.

In [2]:

sales = tribble(
  f.quarter, f.year, f.sales,
  "Q1",      2000,   66013,
  "Q2",        NA,   69182,
  "Q3",        NA,   53175,
  "Q4",        NA,   21001,
  "Q1",      2001,   46036,
  "Q2",        NA,   58842,
  "Q3",        NA,   44568,
  "Q4",        NA,   50197,
  "Q1",      2002,   39113,
  "Q2",        NA,   41668,
  "Q3",        NA,   30144,
  "Q4",        NA,   52897,
  "Q1",      2004,   32129,
  "Q2",        NA,   67686,
  "Q3",        NA,   31768,
  "Q4",        NA,   49094
)
sales

sales = tribble( f.quarter, f.year, f.sales, "Q1", 2000, 66013, "Q2", NA, 69182, "Q3", NA, 53175, "Q4", NA, 21001, "Q1", 2001, 46036, "Q2", NA, 58842, "Q3", NA, 44568, "Q4", NA, 50197, "Q1", 2002, 39113, "Q2", NA, 41668, "Q3", NA, 30144, "Q4", NA, 52897, "Q1", 2004, 32129, "Q2", NA, 67686, "Q3", NA, 31768, "Q4", NA, 49094 ) sales

Out[2]:

	quarter	year	sales
	<object>	<float64>	<int64>
0	Q1	2000.0	66013
1	Q2	NaN	69182
2	Q3	NaN	53175
3	Q4	NaN	21001
4	Q1	2001.0	46036
5	Q2	NaN	58842
6	Q3	NaN	44568
7	Q4	NaN	50197
8	Q1	2002.0	39113
9	Q2	NaN	41668
10	Q3	NaN	30144
11	Q4	NaN	52897
12	Q1	2004.0	32129
13	Q2	NaN	67686
14	Q3	NaN	31768
15	Q4	NaN	49094

In [3]:

sales >> fill(f.year)

sales >> fill(f.year)

Out[3]:

	quarter	year	sales
	<object>	<float64>	<int64>
0	Q1	2000.0	66013
1	Q2	2000.0	69182
2	Q3	2000.0	53175
3	Q4	2000.0	21001
4	Q1	2001.0	46036
5	Q2	2001.0	58842
6	Q3	2001.0	44568
7	Q4	2001.0	50197
8	Q1	2002.0	39113
9	Q2	2002.0	41668
10	Q3	2002.0	30144
11	Q4	2002.0	52897
12	Q1	2004.0	32129
13	Q2	2004.0	67686
14	Q3	2004.0	31768
15	Q4	2004.0	49094

In [4]:

tidy_pets = tribble(
  f.rank,  f.pet_type, f.breed,
  1,          NA,      "Boston Terrier",
  2,          NA,      "Retrievers (Labrador)",
  3,          NA,      "Retrievers (Golden)",
  4,          NA,      "French Bulldogs",
  5,          NA,      "Bulldogs",
  6,       "Dog",      "Beagles",
  1,          NA,      "Persian",
  2,          NA,      "Maine Coon",
  3,          NA,      "Ragdoll",
  4,          NA,      "Exotic",
  5,          NA,      "Siamese",
  6,       "Cat",      "American Short"
)
tidy_pets >> fill(f.pet_type, _direction = "up")

tidy_pets = tribble( f.rank, f.pet_type, f.breed, 1, NA, "Boston Terrier", 2, NA, "Retrievers (Labrador)", 3, NA, "Retrievers (Golden)", 4, NA, "French Bulldogs", 5, NA, "Bulldogs", 6, "Dog", "Beagles", 1, NA, "Persian", 2, NA, "Maine Coon", 3, NA, "Ragdoll", 4, NA, "Exotic", 5, NA, "Siamese", 6, "Cat", "American Short" ) tidy_pets >> fill(f.pet_type, _direction = "up")

Out[4]:

	rank	pet_type	breed
	<int64>	<object>	<object>
0	1	Dog	Boston Terrier
1	2	Dog	Retrievers (Labrador)
2	3	Dog	Retrievers (Golden)
3	4	Dog	French Bulldogs
4	5	Dog	Bulldogs
5	6	Dog	Beagles
6	1	Cat	Persian
7	2	Cat	Maine Coon
8	3	Cat	Ragdoll
9	4	Cat	Exotic
10	5	Cat	Siamese
11	6	Cat	American Short

In [5]:

squirrels = tribble(
  f.group,    f.name,        f.role, f.n_squirrels,
  1,           "Sam",    "Observer",            NA,
  1,          "Mara", "Scorekeeper",             8,
  1,         "Jesse",    "Observer",            NA,
  1,           "Tom",    "Observer",            NA,
  2,          "Mike",    "Observer",            NA,
  2,       "Rachael",    "Observer",            NA,
  2,       "Sydekea", "Scorekeeper",            14,
  2,      "Gabriela",    "Observer",            NA,
  3,       "Derrick",    "Observer",            NA,
  3,          "Kara", "Scorekeeper",             9,
  3,         "Emily",    "Observer",            NA,
  3,      "Danielle",    "Observer",            NA
)
        
squirrels >> \
  group_by(f.group) >> \
  fill(f.n_squirrels, _direction = "downup")

squirrels = tribble( f.group, f.name, f.role, f.n_squirrels, 1, "Sam", "Observer", NA, 1, "Mara", "Scorekeeper", 8, 1, "Jesse", "Observer", NA, 1, "Tom", "Observer", NA, 2, "Mike", "Observer", NA, 2, "Rachael", "Observer", NA, 2, "Sydekea", "Scorekeeper", 14, 2, "Gabriela", "Observer", NA, 3, "Derrick", "Observer", NA, 3, "Kara", "Scorekeeper", 9, 3, "Emily", "Observer", NA, 3, "Danielle", "Observer", NA ) squirrels >> \ group_by(f.group) >> \ fill(f.n_squirrels, _direction = "downup")

Out[5]:

	group	name	role	n_squirrels
	<int64>	<object>	<object>	<float64>
0	1	Sam	Observer	8.0
1	1	Mara	Scorekeeper	8.0
2	1	Jesse	Observer	8.0
3	1	Tom	Observer	8.0
4	2	Mike	Observer	14.0
5	2	Rachael	Observer	14.0
6	2	Sydekea	Scorekeeper	14.0
7	2	Gabriela	Observer	14.0
8	3	Derrick	Observer	9.0
9	3	Kara	Scorekeeper	9.0
10	3	Emily	Observer	9.0
11	3	Danielle	Observer	9.0

TibbleGrouped: group (n=3)

In [ ]: