Data Manipulation in the tidyverse

Load library

library(tidyverse)

Registered S3 methods overwritten by 'ggplot2':
  method         from
  [.quosures     rlang
  c.quosures     rlang
  print.quosures rlang
── Attaching packages ─────────────────────────────────────── tidyverse 1.2.1 ──
✔ ggplot2 3.1.1     ✔ purrr   0.3.2
✔ tibble  2.1.2     ✔ dplyr   0.8.1
✔ tidyr   0.8.3     ✔ stringr 1.4.0
✔ readr   1.3.1     ✔ forcats 0.4.0
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

What data sets are available?

data()

help(starwars)

Bssic information

class(starwars)

1. 'tbl_df'
2. 'tbl'
3. 'data.frame'

dim(starwars)

1. 87
2. 13

nrow(starwars)

87

ncol(starwars)

13

head(starwars, 3)

A tibble: 3 × 13

name	height	mass	hair_color	skin_color	eye_color	birth_year	gender	homeworld	species	films	vehicles	starships
<chr>	<int>	<dbl>	<chr>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	<list>	<list>	<list>
Luke Skywalker	172	77	blond	fair	blue	19	male	Tatooine	Human	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens	Snowspeeder , Imperial Speeder Bike	X-wing , Imperial shuttle
C-3PO	167	75	NA	gold	yellow	112	NA	Tatooine	Droid	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope
R2-D2	96	32	NA	white, blue	red	33	NA	Naboo	Droid	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens

tail(starwars, 3)

A tibble: 3 × 13

name	height	mass	hair_color	skin_color	eye_color	birth_year	gender	homeworld	species	films	vehicles	starships
<chr>	<int>	<dbl>	<chr>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	<list>	<list>	<list>
BB8	NA	NA	none	none	black	NA	none	NA	Droid	The Force Awakens
Captain Phasma	NA	NA	unknown	unknown	unknown	NA	female	NA	NA	The Force Awakens
Padmé Amidala	165	45	brown	light	brown	46	female	Naboo	Human	Attack of the Clones, The Phantom Menace , Revenge of the Sith		H-type Nubian yacht, Naboo star skiff , Naboo fighter

sample_n(starwars, 3)

A tibble: 3 × 13

name	height	mass	hair_color	skin_color	eye_color	birth_year	gender	homeworld	species	films	vehicles	starships
<chr>	<int>	<dbl>	<chr>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	<list>	<list>	<list>
Sly Moore	178	48	none	pale	white	NA	female	Umbara	NA	Attack of the Clones, Revenge of the Sith
Bail Prestor Organa	191	NA	black	tan	brown	67	male	Alderaan	Human	Attack of the Clones, Revenge of the Sith
Ben Quadinaros	163	65	none	grey, green, yellow	orange	NA	male	Tund	Toong	The Phantom Menace

Piping

starwars %>% head(5) %>% tail(3)

A tibble: 3 × 13

name	height	mass	hair_color	skin_color	eye_color	birth_year	gender	homeworld	species	films	vehicles	starships
<chr>	<int>	<dbl>	<chr>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	<list>	<list>	<list>
R2-D2	96	32	NA	white, blue	red	33.0	NA	Naboo	Droid	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens
Darth Vader	202	136	none	white	yellow	41.9	male	Tatooine	Human	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope		TIE Advanced x1
Leia Organa	150	49	brown	light	brown	19.0	female	Alderaan	Human	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens	Imperial Speeder Bike

starwars %>%
head(5) %>%
tail(3)

A tibble: 3 × 13

name	height	mass	hair_color	skin_color	eye_color	birth_year	gender	homeworld	species	films	vehicles	starships
<chr>	<int>	<dbl>	<chr>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	<list>	<list>	<list>
R2-D2	96	32	NA	white, blue	red	33.0	NA	Naboo	Droid	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens
Darth Vader	202	136	none	white	yellow	41.9	male	Tatooine	Human	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope		TIE Advanced x1
Leia Organa	150	49	brown	light	brown	19.0	female	Alderaan	Human	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens	Imperial Speeder Bike

Select

starwars %>%
select(name, birth_year, species) %>%
head(3)

A tibble: 3 × 3

name	birth_year	species
<chr>	<dbl>	<chr>
Luke Skywalker	19	Human
C-3PO	112	Droid
R2-D2	33	Droid

starwars %>%
select(name, age=birth_year, species) %>%
head(3)

A tibble: 3 × 3

name	age	species
<chr>	<dbl>	<chr>
Luke Skywalker	19	Human
C-3PO	112	Droid
R2-D2	33	Droid

starwars %>%
select(-name, -birth_year, -species) %>%
head(3)

A tibble: 3 × 10

height	mass	hair_color	skin_color	eye_color	gender	homeworld	films	vehicles	starships
<int>	<dbl>	<chr>	<chr>	<chr>	<chr>	<chr>	<list>	<list>	<list>
172	77	blond	fair	blue	male	Tatooine	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens	Snowspeeder , Imperial Speeder Bike	X-wing , Imperial shuttle
167	75	NA	gold	yellow	NA	Tatooine	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope
96	32	NA	white, blue	red	NA	Naboo	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens

starwars%>%
select(starts_with('s')) %>%
head(3)

A tibble: 3 × 3

skin_color	species	starships
<chr>	<chr>	<list>
fair	Human	X-wing , Imperial shuttle
gold	Droid
white, blue	Droid

starwars%>%
select(matches("[aeiou]{2,}")) %>%
head(3)

A tibble: 3 × 4

height	hair_color	birth_year	species
<int>	<chr>	<dbl>	<chr>
172	blond	19	Human
167	NA	112	Droid
96	NA	33	Droid

Arrange

starwars%>%
select(name, age=birth_year, mass) %>%
arrange(age) %>%
head(3)

A tibble: 3 × 3

name	age	mass
<chr>	<dbl>	<dbl>
Wicket Systri Warrick	8	20
IG-88	15	140
Luke Skywalker	19	77

starwars%>%
select(name, age=birth_year, mass) %>%
arrange(desc(age)) %>%
head(3)

A tibble: 3 × 3

name	age	mass
<chr>	<dbl>	<dbl>
Yoda	896	17
Jabba Desilijic Tiure	600	1358
Chewbacca	200	112

starwars%>%
select(name, age=birth_year, mass) %>%
arrange(age) %>%
head(5)

A tibble: 5 × 3

name	age	mass
<chr>	<dbl>	<dbl>
Wicket Systri Warrick	8	20
IG-88	15	140
Luke Skywalker	19	77
Leia Organa	19	49
Wedge Antilles	21	77

starwars%>%
select(name, age=birth_year, mass) %>%
arrange(age, mass) %>%
head(5)

A tibble: 5 × 3

name	age	mass
<chr>	<dbl>	<dbl>
Wicket Systri Warrick	8	20
IG-88	15	140
Leia Organa	19	49
Luke Skywalker	19	77
Wedge Antilles	21	77

starwars%>%
select(name, age=birth_year, mass) %>%
top_n(age, n=3)

A tibble: 3 × 3

name	age	mass
<chr>	<dbl>	<dbl>
Chewbacca	200	112
Jabba Desilijic Tiure	600	1358
Yoda	896	17

Filter

starwars %>%
filter(birth_year > 100)

A tibble: 5 × 13

name	height	mass	hair_color	skin_color	eye_color	birth_year	gender	homeworld	species	films	vehicles	starships
<chr>	<int>	<dbl>	<chr>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	<list>	<list>	<list>
C-3PO	167	75	NA	gold	yellow	112	NA	Tatooine	Droid	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope
Chewbacca	228	112	brown	unknown	blue	200	male	Kashyyyk	Wookiee	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens	AT-ST	Millennium Falcon, Imperial shuttle
Jabba Desilijic Tiure	175	1358	NA	green-tan, brown	orange	600	hermaphrodite	Nal Hutta	Hutt	The Phantom Menace, Return of the Jedi, A New Hope
Yoda	66	17	white	green	brown	896	male	NA	Yoda's species	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back
Dooku	193	80	white	fair	brown	102	male	Serenno	Human	Attack of the Clones, Revenge of the Sith	Flitknot speeder

starwars %>%
filter((birth_year >= 600) | (name == 'Dooku'))

A tibble: 3 × 13

name	height	mass	hair_color	skin_color	eye_color	birth_year	gender	homeworld	species	films	vehicles	starships
<chr>	<int>	<dbl>	<chr>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	<list>	<list>	<list>
Jabba Desilijic Tiure	175	1358	NA	green-tan, brown	orange	600	hermaphrodite	Nal Hutta	Hutt	The Phantom Menace, Return of the Jedi, A New Hope
Yoda	66	17	white	green	brown	896	male	NA	Yoda's species	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back
Dooku	193	80	white	fair	brown	102	male	Serenno	Human	Attack of the Clones, Revenge of the Sith	Flitknot speeder

starwars %>%
filter((birth_year >= 600) | (name == 'Dooku')) %>%
select(name, age=birth_year, homeworld)

A tibble: 3 × 3

name	age	homeworld
<chr>	<dbl>	<chr>
Jabba Desilijic Tiure	600	Nal Hutta
Yoda	896	NA
Dooku	102	Serenno

starwars %>%
filter(birth_year > 100, gender=='male')

A tibble: 3 × 13

name	height	mass	hair_color	skin_color	eye_color	birth_year	gender	homeworld	species	films	vehicles	starships
<chr>	<int>	<dbl>	<chr>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	<list>	<list>	<list>
Chewbacca	228	112	brown	unknown	blue	200	male	Kashyyyk	Wookiee	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens	AT-ST	Millennium Falcon, Imperial shuttle
Yoda	66	17	white	green	brown	896	male	NA	Yoda's species	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back
Dooku	193	80	white	fair	brown	102	male	Serenno	Human	Attack of the Clones, Revenge of the Sith	Flitknot speeder

starwars %>%
filter(str_detect(homeworld, "in")) %>%
head(3)

A tibble: 3 × 13

name	height	mass	hair_color	skin_color	eye_color	birth_year	gender	homeworld	species	films	vehicles	starships
<chr>	<int>	<dbl>	<chr>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	<list>	<list>	<list>
Luke Skywalker	172	77	blond	fair	blue	19.0	male	Tatooine	Human	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope , The Force Awakens	Snowspeeder , Imperial Speeder Bike	X-wing , Imperial shuttle
C-3PO	167	75	NA	gold	yellow	112.0	NA	Tatooine	Droid	Attack of the Clones , The Phantom Menace , Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope
Darth Vader	202	136	none	white	yellow	41.9	male	Tatooine	Human	Revenge of the Sith , Return of the Jedi , The Empire Strikes Back, A New Hope		TIE Advanced x1

Mutate

starwars%>%
select(name, age=birth_year, height, mass) %>%
head(3)

A tibble: 3 × 4

name	age	height	mass
<chr>	<dbl>	<int>	<dbl>
Luke Skywalker	19	172	77
C-3PO	112	167	75
R2-D2	33	96	32

starwars%>%
select(name, age=birth_year, height, mass) %>%
mutate(bmi=mass/(height/100)^2, obese=bmi>30) %>%
head(3)

A tibble: 3 × 6

name	age	height	mass	bmi	obese
<chr>	<dbl>	<int>	<dbl>	<dbl>	<lgl>
Luke Skywalker	19	172	77	26.02758	FALSE
C-3PO	112	167	75	26.89232	FALSE
R2-D2	33	96	32	34.72222	TRUE

starwars%>%
select(name, age=birth_year, height, mass) %>%
transmute(bmi=mass/(height/100)^2, obese=bmi>30) %>%
head(3)

A tibble: 3 × 2

bmi	obese
<dbl>	<lgl>
26.02758	FALSE
26.89232	FALSE
34.72222	TRUE

starwars %>%
transmute_if(is_character, str_to_upper) %>%
head(3)

A tibble: 3 × 7

name	hair_color	skin_color	eye_color	gender	homeworld	species
<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>
LUKE SKYWALKER	BLOND	FAIR	BLUE	MALE	TATOOINE	HUMAN
C-3PO	NA	GOLD	YELLOW	NA	TATOOINE	DROID
R2-D2	NA	WHITE, BLUE	RED	NA	NABOO	DROID

starwars %>%
select_at(c("birth_year", "height", "mass")) %>%
head(3)

A tibble: 3 × 3

birth_year	height	mass
<dbl>	<int>	<dbl>
19	172	77
112	167	75
33	96	32

starwars %>%
transmute_at(c("birth_year", "height", "mass"), ~ . + 1) %>%
head(3)

A tibble: 3 × 3

birth_year	height	mass
<dbl>	<dbl>	<dbl>
20	173	78
113	168	76
34	97	33

Summarize

starwars %>%
summarize(avg_mass = mean(mass, na.rm=TRUE),
          median_age=median(birth_year, na.rm=TRUE))

A tibble: 1 × 2

avg_mass	median_age
<dbl>	<dbl>
97.31186	52

starwars %>%
summarize_if(is.numeric, mean, na.rm=TRUE)

A tibble: 1 × 3

height	mass	birth_year
<dbl>	<dbl>	<dbl>
174.358	97.31186	87.56512

starwars %>%
summarize_if(is.numeric, list(mean, median), na.rm=TRUE)

A tibble: 1 × 6

height_fn1	mass_fn1	birth_year_fn1	height_fn2	mass_fn2	birth_year_fn2
<dbl>	<dbl>	<dbl>	<int>	<dbl>	<dbl>
174.358	97.31186	87.56512	180	79	52

Group by

starwars %>%
group_by(homeworld) %>%
summarize(avg_mass=mean(mass, na.rm=T)) %>%
head(3)

A tibble: 3 × 2

homeworld	avg_mass
<chr>	<dbl>
NA	82
Alderaan	64
Aleen Minor	15

starwars %>%
group_by(homeworld) %>%
summarize(avg_mass=mean(mass, na.rm=T)) %>%
filter(!is.na(homeworld)) %>%
head(3)

A tibble: 3 × 2

homeworld	avg_mass
<chr>	<dbl>
Alderaan	64
Aleen Minor	15
Bespin	79

starwars %>%
group_by(homeworld, species, gender) %>%
summarize(avg_mass=mean(mass, na.rm=T), n=n()) %>%
filter(!is.na(homeworld)) %>%
head(5)

A grouped_df: 5 × 5

homeworld	species	gender	avg_mass	n
<chr>	<chr>	<chr>	<dbl>	<int>
Alderaan	Human	female	49	1
Alderaan	Human	male	79	2
Aleen Minor	Aleena	male	15	1
Bespin	Human	male	79	1
Bestine IV	Human	male	110	1

Exercises

1. Show the name, height and mass of all Droids sorted by height from tallest to shortest.

starwars %>%
filter(species == 'Droid') %>%
arrange(desc(height)) %>%
select(name, height, mass)

A tibble: 5 × 3

name	height	mass
<chr>	<int>	<dbl>
IG-88	200	140
C-3PO	167	75
R5-D4	97	32
R2-D2	96	32
BB8	NA	NA

2. List the name and hoemworld of all non-humans who appeared in The Empire Strikes Back.

starwars %>%
filter(str_detect(films, 'The Empire Strikes Back'), species!='Human') %>%
select(name, homeworld)

Warning message in stri_detect_regex(string, pattern, negate = negate, opts_regex = opts(pattern)):
“argument is not an atomic vector; coercing”

A tibble: 6 × 2

name	homeworld
<chr>	<chr>
C-3PO	Tatooine
R2-D2	Naboo
Chewbacca	Kashyyyk
Yoda	NA
IG-88	NA
Bossk	Trandosha

3. Which homeworld has the most humans?

starwars %>%
filter(species == "Human") %>%
group_by(homeworld) %>%
summarize(n=n()) %>%
top_n(1)

Selecting by n

A tibble: 1 × 2

homeworld	n
<chr>	<int>
Tatooine	8

4. What species has the highest average BMI? Exclude Species with only 1 member, and ignore NAs in the calculation of the average.

starwars %>%
mutate(bmi = mass/(height/100)^2) %>%
group_by(species) %>%
summarize(avg_bmi=mean(bmi, na.rm=T), n=n()) %>%
filter(n>1) %>%
top_n(avg_bmi, n=1)

A tibble: 1 × 3

species	avg_bmi	n
<chr>	<dbl>	<int>
Droid	32.65613	5