library(tidyverse)Solution to dplyr tasks
1 Get started
2 Data transformation with dplyr
Find all penguins that …
- … have a bill length between 40 and 45 mm.
filter(penguins, between(bill_len, 40, 45))# A tibble: 77 × 8
species island bill_len bill_dep flipper_len body_mass sex year
<fct> <fct> <dbl> <dbl> <int> <int> <fct> <int>
1 Adelie Torgersen 40.3 18 195 3250 female 2007
2 Adelie Torgersen 42 20.2 190 4250 <NA> 2007
3 Adelie Torgersen 41.1 17.6 182 3200 female 2007
4 Adelie Torgersen 42.5 20.7 197 4500 male 2007
5 Adelie Biscoe 40.6 18.6 183 3550 male 2007
6 Adelie Biscoe 40.5 17.9 187 3200 female 2007
7 Adelie Biscoe 40.5 18.9 180 3950 male 2007
8 Adelie Dream 40.9 18.9 184 3900 male 2007
9 Adelie Dream 42.2 18.5 180 3550 female 2007
10 Adelie Dream 40.8 18.4 195 3900 male 2007
# ℹ 67 more rows# same as
# filter(penguins, bill_len < 45 & bill_len > 40)- … for which we know the sex.
filter(penguins, !is.na(sex))# A tibble: 333 × 8
species island bill_len bill_dep flipper_len body_mass sex year
<fct> <fct> <dbl> <dbl> <int> <int> <fct> <int>
1 Adelie Torgersen 39.1 18.7 181 3750 male 2007
2 Adelie Torgersen 39.5 17.4 186 3800 female 2007
3 Adelie Torgersen 40.3 18 195 3250 female 2007
4 Adelie Torgersen 36.7 19.3 193 3450 female 2007
5 Adelie Torgersen 39.3 20.6 190 3650 male 2007
6 Adelie Torgersen 38.9 17.8 181 3625 female 2007
7 Adelie Torgersen 39.2 19.6 195 4675 male 2007
8 Adelie Torgersen 41.1 17.6 182 3200 female 2007
9 Adelie Torgersen 38.6 21.2 191 3800 male 2007
10 Adelie Torgersen 34.6 21.1 198 4400 male 2007
# ℹ 323 more rows- … which are of the species Adelie or Gentoo
filter(penguins, species %in% c("Adelie", "Gentoo"))# A tibble: 276 × 8
species island bill_len bill_dep flipper_len body_mass sex year
<fct> <fct> <dbl> <dbl> <int> <int> <fct> <int>
1 Adelie Torgersen 39.1 18.7 181 3750 male 2007
2 Adelie Torgersen 39.5 17.4 186 3800 female 2007
3 Adelie Torgersen 40.3 18 195 3250 female 2007
4 Adelie Torgersen NA NA NA NA <NA> 2007
5 Adelie Torgersen 36.7 19.3 193 3450 female 2007
6 Adelie Torgersen 39.3 20.6 190 3650 male 2007
7 Adelie Torgersen 38.9 17.8 181 3625 female 2007
8 Adelie Torgersen 39.2 19.6 195 4675 male 2007
9 Adelie Torgersen 34.1 18.1 193 3475 <NA> 2007
10 Adelie Torgersen 42 20.2 190 4250 <NA> 2007
# ℹ 266 more rows# or
# filter(penguins, (species == "Adelie" | species == "Gentoo"))- … lived on the island Dream in the year 2007. How many of them were from each of the 3 species?
filter(penguins, island == "Dream" & year == 2007) |>
count(species)# A tibble: 2 × 2
species n
<fct> <int>
1 Adelie 20
2 Chinstrap 26Count …
- … the number of penguins on each island.
count(penguins, island)# A tibble: 3 × 2
island n
<fct> <int>
1 Biscoe 168
2 Dream 124
3 Torgersen 52- … the number of penguins of each species on each island.
count(penguins, island, species)# A tibble: 5 × 3
island species n
<fct> <fct> <int>
1 Biscoe Adelie 44
2 Biscoe Gentoo 124
3 Dream Adelie 56
4 Dream Chinstrap 68
5 Torgersen Adelie 52Select …
- … only the variables species, sex and year
select(penguins, species, sex, year)# A tibble: 344 × 3
species sex year
<fct> <fct> <int>
1 Adelie male 2007
2 Adelie female 2007
3 Adelie female 2007
4 Adelie <NA> 2007
5 Adelie female 2007
6 Adelie male 2007
7 Adelie female 2007
8 Adelie male 2007
9 Adelie <NA> 2007
10 Adelie <NA> 2007
# ℹ 334 more rows- … only columns that contain measurements in mm
select(penguins, ends_with("mm"))# A tibble: 344 × 0# or
#select(penguins, contains("_mm"))Add a column …
- … with the ratio of bill length to bill depth
mutate(penguins,
ratio = bill_len / bill_dep)# A tibble: 344 × 9
species island bill_len bill_dep flipper_len body_mass sex year ratio
<fct> <fct> <dbl> <dbl> <int> <int> <fct> <int> <dbl>
1 Adelie Torgersen 39.1 18.7 181 3750 male 2007 2.09
2 Adelie Torgersen 39.5 17.4 186 3800 female 2007 2.27
3 Adelie Torgersen 40.3 18 195 3250 female 2007 2.24
4 Adelie Torgersen NA NA NA NA <NA> 2007 NA
5 Adelie Torgersen 36.7 19.3 193 3450 female 2007 1.90
6 Adelie Torgersen 39.3 20.6 190 3650 male 2007 1.91
7 Adelie Torgersen 38.9 17.8 181 3625 female 2007 2.19
8 Adelie Torgersen 39.2 19.6 195 4675 male 2007 2
9 Adelie Torgersen 34.1 18.1 193 3475 <NA> 2007 1.88
10 Adelie Torgersen 42 20.2 190 4250 <NA> 2007 2.08
# ℹ 334 more rows- … with abbreviations for the species (Adelie = A, Gentoo = G, Chinstrap = C).
mutate(penguins,
species_short = case_when(
species == "Adelie" ~ "A",
species == "Gentoo" ~ "G",
species == "Chinstrap" ~ "C"
))# A tibble: 344 × 9
species island bill_len bill_dep flipper_len body_mass sex year
<fct> <fct> <dbl> <dbl> <int> <int> <fct> <int>
1 Adelie Torgersen 39.1 18.7 181 3750 male 2007
2 Adelie Torgersen 39.5 17.4 186 3800 female 2007
3 Adelie Torgersen 40.3 18 195 3250 female 2007
4 Adelie Torgersen NA NA NA NA <NA> 2007
5 Adelie Torgersen 36.7 19.3 193 3450 female 2007
6 Adelie Torgersen 39.3 20.6 190 3650 male 2007
7 Adelie Torgersen 38.9 17.8 181 3625 female 2007
8 Adelie Torgersen 39.2 19.6 195 4675 male 2007
9 Adelie Torgersen 34.1 18.1 193 3475 <NA> 2007
10 Adelie Torgersen 42 20.2 190 4250 <NA> 2007
# ℹ 334 more rows
# ℹ 1 more variable: species_short <chr>Calculate …
- … mean flipper length and body mass for the 3 species and male and female penguins separately
penguins |>
summarize(
mean_flipper = mean(flipper_len, na.rm = TRUE),
mean_body = mean(body_mass, na.rm = TRUE),
.by = c(species, sex)
) # A tibble: 8 × 4
species sex mean_flipper mean_body
<fct> <fct> <dbl> <dbl>
1 Adelie male 192. 4043.
2 Adelie female 188. 3369.
3 Adelie <NA> 186. 3540
4 Gentoo female 213. 4680.
5 Gentoo male 222. 5485.
6 Gentoo <NA> 216. 4588.
7 Chinstrap female 192. 3527.
8 Chinstrap male 200. 3939.- Can you do the same but remove the penguins for which we don’t know the sex first?
penguins |>
filter(!is.na(sex)) |>
summarize(
mean_flipper = mean(flipper_len, na.rm = TRUE),
mean_body = mean(body_mass, na.rm = TRUE),
.by = c(species, sex)
)# A tibble: 6 × 4
species sex mean_flipper mean_body
<fct> <fct> <dbl> <dbl>
1 Adelie male 192. 4043.
2 Adelie female 188. 3369.
3 Gentoo female 213. 4680.
4 Gentoo male 222. 5485.
5 Chinstrap female 192. 3527.
6 Chinstrap male 200. 3939.3 For the fast ones
- Make a boxplot of penguin body mass with sex on the y-axis and facets for the different species. Can you remove the penguins with missing values for sex first?
penguins |>
filter(!is.na(sex)) |>
ggplot(aes(x = sex, y = body_mass)) +
geom_boxplot() +
facet_wrap(~species)
- Make a scatterplot with the ratio of bill length to bill depth on the y axis and flipper length on the x axis? Can you distinguish the point between male and female penguins and remove penguins with unknown sex before making the plot?
penguins |>
mutate(ratio = bill_len / bill_dep) |>
filter(!is.na(sex)) |>
ggplot(aes(x = flipper_len, y = ratio, color = sex)) +
geom_point() +
scale_color_manual(values = c("cyan4", "darkorange")) +
labs(
x = "Flipper lenght (mm)",
y = "Ratio bill length / bill depth (-)"
) +
theme_minimal()