1 + 1[1] 2Rbasics
Quarto
Quarto enables you to weave together content and executable code into a finished document. To learn more about Quarto see https://quarto.org.
Running Code
When you click the Render button a document will be generated that includes both content and the output of embedded code. You can embed code like this:
You can add options to executable code like this
[1] 4The echo: false option disables the printing of code (only output is displayed).
R basics
6+9[1] 15Import Packages
library(ggplot2)Warning: package 'ggplot2' was built under R version 4.0.5library(dplyr)Warning: package 'dplyr' was built under R version 4.0.5
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionlibrary(tidyr)Warning: package 'tidyr' was built under R version 4.0.5?starwarsstarting httpd help server ... doneUsing the Pipe %>% Operator
names(starwars) [1] "name" "height" "mass" "hair_color" "skin_color"
[6] "eye_color" "birth_year" "sex" "gender" "homeworld"
[11] "species" "films" "vehicles" "starships" Pipe operator
starwars %>%
filter(height >150 & mass <200 ) %>%
mutate(height_in_meters=height/100) %>%
select(height_in_meters,mass) %>%
arrange(mass) %>%
plot()
head(msleep)# A tibble: 6 x 11
name genus vore order conservation sleep_total sleep_rem sleep_cycle awake
<chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 Cheetah Acin~ carni Carn~ lc 12.1 NA NA 11.9
2 Owl mo~ Aotus omni Prim~ <NA> 17 1.8 NA 7
3 Mounta~ Aplo~ herbi Rode~ nt 14.4 2.4 NA 9.6
4 Greate~ Blar~ omni Sori~ lc 14.9 2.3 0.133 9.1
5 Cow Bos herbi Arti~ domesticated 4 0.7 0.667 20
6 Three-~ Brad~ herbi Pilo~ <NA> 14.4 2.2 0.767 9.6
# ... with 2 more variables: brainwt <dbl>, bodywt <dbl>head(starwars)# A tibble: 6 x 14
name height mass hair_color skin_color eye_color birth_year sex gender
<chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr>
1 Luke Sky~ 172 77 blond fair blue 19 male mascu~
2 C-3PO 167 75 <NA> gold yellow 112 none mascu~
3 R2-D2 96 32 <NA> white, bl~ red 33 none mascu~
4 Darth Va~ 202 136 none white yellow 41.9 male mascu~
5 Leia Org~ 150 49 brown light brown 19 fema~ femin~
6 Owen Lars 178 120 brown, gr~ light blue 52 male mascu~
# ... with 5 more variables: homeworld <chr>, species <chr>, films <list>,
# vehicles <list>, starships <list>length(starwars$height)[1] 87unique(starwars$hair_color) [1] "blond" NA "none" "brown"
[5] "brown, grey" "black" "auburn, white" "auburn, grey"
[9] "white" "grey" "auburn" "blonde"
[13] "unknown" unique(starwars$names)Warning: Unknown or uninitialised column: `names`.NULLmissing <- !complete.cases(msleep)
missing [1] TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE FALSE TRUE TRUE FALSE
[13] TRUE FALSE TRUE TRUE FALSE FALSE TRUE FALSE TRUE FALSE FALSE TRUE
[25] FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[37] TRUE TRUE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE TRUE FALSE
[49] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[61] TRUE TRUE TRUE FALSE TRUE TRUE FALSE TRUE TRUE TRUE FALSE TRUE
[73] TRUE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE#Shows all the rows with missing data
msleep[missing,]# A tibble: 63 x 11
name genus vore order conservation sleep_total sleep_rem sleep_cycle awake
<chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 Cheet~ Acin~ carni Carn~ lc 12.1 NA NA 11.9
2 Owl m~ Aotus omni Prim~ <NA> 17 1.8 NA 7
3 Mount~ Aplo~ herbi Rode~ nt 14.4 2.4 NA 9.6
4 Three~ Brad~ herbi Pilo~ <NA> 14.4 2.2 0.767 9.6
5 North~ Call~ carni Carn~ vu 8.7 1.4 0.383 15.3
6 Vespe~ Calo~ <NA> Rode~ <NA> 7 NA NA 17
7 Roe d~ Capr~ herbi Arti~ lc 3 NA NA 21
8 Goat Capri herbi Arti~ lc 5.3 0.6 NA 18.7
9 Grivet Cerc~ omni Prim~ lc 10 0.7 NA 14
10 Star-~ Cond~ omni Sori~ lc 10.3 2.2 NA 13.7
# ... with 53 more rows, and 2 more variables: brainwt <dbl>, bodywt <dbl>Select variables
starwars %>%
select(name,height,mass)# A tibble: 87 x 3
name height mass
<chr> <int> <dbl>
1 Luke Skywalker 172 77
2 C-3PO 167 75
3 R2-D2 96 32
4 Darth Vader 202 136
5 Leia Organa 150 49
6 Owen Lars 178 120
7 Beru Whitesun lars 165 75
8 R5-D4 97 32
9 Biggs Darklighter 183 84
10 Obi-Wan Kenobi 182 77
# ... with 77 more rowsstarwars %>%
select(1:3)# A tibble: 87 x 3
name height mass
<chr> <int> <dbl>
1 Luke Skywalker 172 77
2 C-3PO 167 75
3 R2-D2 96 32
4 Darth Vader 202 136
5 Leia Organa 150 49
6 Owen Lars 178 120
7 Beru Whitesun lars 165 75
8 R5-D4 97 32
9 Biggs Darklighter 183 84
10 Obi-Wan Kenobi 182 77
# ... with 77 more rowsstarwars %>%
select(ends_with("color")) # A tibble: 87 x 3
hair_color skin_color eye_color
<chr> <chr> <chr>
1 blond fair blue
2 <NA> gold yellow
3 <NA> white, blue red
4 none white yellow
5 brown light brown
6 brown, grey light blue
7 brown light blue
8 <NA> white, red red
9 black light brown
10 auburn, white fair blue-gray
# ... with 77 more rowsstarwars %>%
rename("characters"="name") %>%
head()# A tibble: 6 x 14
characters height mass hair_color skin_color eye_color birth_year sex
<chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr>
1 Luke Skywalker 172 77 blond fair blue 19 male
2 C-3PO 167 75 <NA> gold yellow 112 none
3 R2-D2 96 32 <NA> white, blue red 33 none
4 Darth Vader 202 136 none white yellow 41.9 male
5 Leia Organa 150 49 brown light brown 19 fema~
6 Owen Lars 178 120 brown, grey light blue 52 male
# ... with 6 more variables: gender <chr>, homeworld <chr>, species <chr>,
# films <list>, vehicles <list>, starships <list>class(starwars$hair_color)[1] "character"starwars$hair_color <-as.factor(starwars$hair_color)
starwars$hair_color [1] blond <NA> <NA> none brown
[6] brown, grey brown <NA> black auburn, white
[11] blond auburn, grey brown brown <NA>
[16] <NA> brown brown white grey
[21] black none none black none
[26] none auburn brown brown none
[31] brown none blond none none
[36] none brown black none black
[41] black none none none none
[46] none none none white none
[51] black none none none none
[56] none black brown brown none
[61] black black brown white black
[66] black blonde none none none
[71] white none none none none
[76] none none brown brown none
[81] none black brown brown none
[86] unknown brown
12 Levels: auburn auburn, grey auburn, white black blond blonde ... whitestarwars$hair_color <-as.character(starwars$hair_color)
starwars%>%
glimpse()Rows: 87
Columns: 14
$ name <chr> "Luke Skywalker", "C-3PO", "R2-D2", "Darth Vader", "Leia Or~
$ height <int> 172, 167, 96, 202, 150, 178, 165, 97, 183, 182, 188, 180, 2~
$ mass <dbl> 77.0, 75.0, 32.0, 136.0, 49.0, 120.0, 75.0, 32.0, 84.0, 77.~
$ hair_color <chr> "blond", NA, NA, "none", "brown", "brown, grey", "brown", N~
$ skin_color <chr> "fair", "gold", "white, blue", "white", "light", "light", "~
$ eye_color <chr> "blue", "yellow", "red", "yellow", "brown", "blue", "blue",~
$ birth_year <dbl> 19.0, 112.0, 33.0, 41.9, 19.0, 52.0, 47.0, NA, 24.0, 57.0, ~
$ sex <chr> "male", "none", "none", "male", "female", "male", "female",~
$ gender <chr> "masculine", "masculine", "masculine", "masculine", "femini~
$ homeworld <chr> "Tatooine", "Tatooine", "Naboo", "Tatooine", "Alderaan", "T~
$ species <chr> "Human", "Droid", "Droid", "Human", "Human", "Human", "Huma~
$ films <list> <"The Empire Strikes Back", "Revenge of the Sith", "Return~
$ vehicles <list> <"Snowspeeder", "Imperial Speeder Bike">, <>, <>, <>, "Imp~
$ starships <list> <"X-wing", "Imperial shuttle">, <>, <>, "TIE Advanced x1",~levels(starwars$sex)NULLstarwars$sex<-as.factor(starwars$sex)
levels(starwars$sex)[1] "female" "hermaphroditic" "male" "none" #Filter rows
starwars %>%
select(mass,sex) %>%
filter(mass<55 & sex=='male')# A tibble: 6 x 2
mass sex
<dbl> <fct>
1 17 male
2 20 male
3 40 male
4 45 male
5 15 male
6 48 male #Recode data
starwars %>%
select(sex) %>%
mutate(sex=recode(sex,"male"="man","female"="woman"))# A tibble: 87 x 1
sex
<fct>
1 man
2 none
3 none
4 man
5 woman
6 man
7 woman
8 none
9 man
10 man
# ... with 77 more rows#Mean
mean(starwars$height,na.rm=TRUE)[1] 174.358#Remove duplicates
starwars %>%
distinct()# A tibble: 87 x 14
name height mass hair_color skin_color eye_color birth_year sex gender
<chr> <int> <dbl> <chr> <chr> <chr> <dbl> <fct> <chr>
1 Luke Sk~ 172 77 blond fair blue 19 male mascu~
2 C-3PO 167 75 <NA> gold yellow 112 none mascu~
3 R2-D2 96 32 <NA> white, bl~ red 33 none mascu~
4 Darth V~ 202 136 none white yellow 41.9 male mascu~
5 Leia Or~ 150 49 brown light brown 19 fema~ femin~
6 Owen La~ 178 120 brown, gr~ light blue 52 male mascu~
7 Beru Wh~ 165 75 brown light blue 47 fema~ femin~
8 R5-D4 97 32 <NA> white, red red NA none mascu~
9 Biggs D~ 183 84 black light brown 24 male mascu~
10 Obi-Wan~ 182 77 auburn, w~ fair blue-gray 57 male mascu~
# ... with 77 more rows, and 5 more variables: homeworld <chr>, species <chr>,
# films <list>, vehicles <list>, starships <list>#Manipulate data
starwars %>%
mutate(height_m=height/100) %>%
select(name,height,height_m)# A tibble: 87 x 3
name height height_m
<chr> <int> <dbl>
1 Luke Skywalker 172 1.72
2 C-3PO 167 1.67
3 R2-D2 96 0.96
4 Darth Vader 202 2.02
5 Leia Organa 150 1.5
6 Owen Lars 178 1.78
7 Beru Whitesun lars 165 1.65
8 R5-D4 97 0.97
9 Biggs Darklighter 183 1.83
10 Obi-Wan Kenobi 182 1.82
# ... with 77 more rows#Conditional changes
starwars %>%
mutate(height_m=height/100) %>%
select(name,height,height_m) %>%
mutate(tallness=
if_else(height_m<1,"short","tall"))# A tibble: 87 x 4
name height height_m tallness
<chr> <int> <dbl> <chr>
1 Luke Skywalker 172 1.72 tall
2 C-3PO 167 1.67 tall
3 R2-D2 96 0.96 short
4 Darth Vader 202 2.02 tall
5 Leia Organa 150 1.5 tall
6 Owen Lars 178 1.78 tall
7 Beru Whitesun lars 165 1.65 tall
8 R5-D4 97 0.97 short
9 Biggs Darklighter 183 1.83 tall
10 Obi-Wan Kenobi 182 1.82 tall
# ... with 77 more rowsReshape Data
library(gapminder)
names(gapminder)[1] "country" "continent" "year" "lifeExp" "pop" "gdpPercap"data<-select(gapminder,country,year,lifeExp)
data# A tibble: 1,704 x 3
country year lifeExp
<fct> <int> <dbl>
1 Afghanistan 1952 28.8
2 Afghanistan 1957 30.3
3 Afghanistan 1962 32.0
4 Afghanistan 1967 34.0
5 Afghanistan 1972 36.1
6 Afghanistan 1977 38.4
7 Afghanistan 1982 39.9
8 Afghanistan 1987 40.8
9 Afghanistan 1992 41.7
10 Afghanistan 1997 41.8
# ... with 1,694 more rowsgapminder# A tibble: 1,704 x 6
country continent year lifeExp pop gdpPercap
<fct> <fct> <int> <dbl> <int> <dbl>
1 Afghanistan Asia 1952 28.8 8425333 779.
2 Afghanistan Asia 1957 30.3 9240934 821.
3 Afghanistan Asia 1962 32.0 10267083 853.
4 Afghanistan Asia 1967 34.0 11537966 836.
5 Afghanistan Asia 1972 36.1 13079460 740.
6 Afghanistan Asia 1977 38.4 14880372 786.
7 Afghanistan Asia 1982 39.9 12881816 978.
8 Afghanistan Asia 1987 40.8 13867957 852.
9 Afghanistan Asia 1992 41.7 16317921 649.
10 Afghanistan Asia 1997 41.8 22227415 635.
# ... with 1,694 more rowswide_data <-data %>%
pivot_wider(names_from=year,values_from=lifeExp)
wide_data# A tibble: 142 x 13
country `1952` `1957` `1962` `1967` `1972` `1977` `1982` `1987` `1992` `1997`
<fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 Afghan~ 28.8 30.3 32.0 34.0 36.1 38.4 39.9 40.8 41.7 41.8
2 Albania 55.2 59.3 64.8 66.2 67.7 68.9 70.4 72 71.6 73.0
3 Algeria 43.1 45.7 48.3 51.4 54.5 58.0 61.4 65.8 67.7 69.2
4 Angola 30.0 32.0 34 36.0 37.9 39.5 39.9 39.9 40.6 41.0
5 Argent~ 62.5 64.4 65.1 65.6 67.1 68.5 69.9 70.8 71.9 73.3
6 Austra~ 69.1 70.3 70.9 71.1 71.9 73.5 74.7 76.3 77.6 78.8
7 Austria 66.8 67.5 69.5 70.1 70.6 72.2 73.2 74.9 76.0 77.5
8 Bahrain 50.9 53.8 56.9 59.9 63.3 65.6 69.1 70.8 72.6 73.9
9 Bangla~ 37.5 39.3 41.2 43.5 45.3 46.9 50.0 52.8 56.0 59.4
10 Belgium 68 69.2 70.2 70.9 71.4 72.8 73.9 75.4 76.5 77.5
# ... with 132 more rows, and 2 more variables: `2002` <dbl>, `2007` <dbl>long_data <- wide_data %>%
pivot_longer(2:13,
names_to="year",
values_to="lifeExp")
long_data# A tibble: 1,704 x 3
country year lifeExp
<fct> <chr> <dbl>
1 Afghanistan 1952 28.8
2 Afghanistan 1957 30.3
3 Afghanistan 1962 32.0
4 Afghanistan 1967 34.0
5 Afghanistan 1972 36.1
6 Afghanistan 1977 38.4
7 Afghanistan 1982 39.9
8 Afghanistan 1987 40.8
9 Afghanistan 1992 41.7
10 Afghanistan 1997 41.8
# ... with 1,694 more rows