class: middle, right, title-slide .title[ # Tidy data wrangling ] .subtitle[ ## demonstration ] .author[ ### Athanasia Monika Mowinckel ] --- layout: true <div class="my-sidebar"></div> --- name: ggplot2 class: dark, middle, center # ggplot2 --- .pull-left[ ```r ggplot(penguins, aes(x = bill_length_mm, fill = species)) + * geom_histogram(alpha = .9, * colour = "white") ``` ] .pull-right[ <!-- --> ] --- .pull-left[ ```r ggplot(penguins, aes(x = bill_length_mm, fill = species)) + * geom_histogram(alpha = .8, colour = "white") + * scale_fill_viridis_d() ``` ] .pull-right[ <!-- --> ] --- .pull-left[ ```r ggplot(penguins, aes(x = bill_length_mm, fill = species)) + geom_histogram(alpha = .8, colour = "white", * position = "dodge") + scale_fill_viridis_d() ``` ] .pull-right[ <!-- --> ] --- .pull-left[ ```r ggplot(penguins, aes(x = bill_length_mm, fill = species)) + geom_density( * alpha = .8, colour = "white", position = "dodge") + scale_fill_viridis_d() ``` ] .pull-right[ <!-- --> ] --- .pull-left[ ```r ggplot(penguins, * aes(y = bill_length_mm, fill = species)) + geom_density( alpha = .8, colour = "white", position = "dodge") + scale_fill_viridis_d() ``` ] .pull-right[ <!-- --> ] --- .pull-left[ ```r ggplot(penguins, aes(y = bill_length_mm, x = bill_depth_mm, * colour = species)) + * geom_point() + * scale_colour_viridis_d() ``` ] .pull-right[ <!-- --> ] --- .pull-left[ ```r ggplot(penguins, aes(y = bill_length_mm, x = bill_depth_mm, colour = species)) + geom_point() + * geom_line() + scale_colour_viridis_d() ``` ] .pull-right[ <!-- --> ] --- .pull-left[ ```r ggplot(penguins, aes(y = bill_length_mm, x = bill_depth_mm, colour = species)) + geom_point() + * geom_smooth(method = "lm") + scale_colour_viridis_d() ``` ] .pull-right[ <!-- --> ] --- .pull-left[ ```r ggplot(penguins, aes(y = bill_length_mm, x = bill_depth_mm)) + geom_point(aes(colour = species)) + geom_smooth(aes(colour = species), * method = "lm") + * geom_smooth(method = "lm") + scale_colour_viridis_d() ``` ] .pull-right[ <!-- --> ] --- class: dark, middle, center name: filter # filter --- ```r filter(penguins, species == "Chinstrap") ``` ``` ## # A tibble: 68 × 8 ## species island bill_lengt…¹ bill_…² flipp…³ ## <fct> <fct> <dbl> <dbl> <int> ## 1 Chinstrap Dream 46.5 17.9 192 ## 2 Chinstrap Dream 50 19.5 196 ## 3 Chinstrap Dream 51.3 19.2 193 ## 4 Chinstrap Dream 45.4 18.7 188 ## 5 Chinstrap Dream 52.7 19.8 197 ## 6 Chinstrap Dream 45.2 17.8 198 ## 7 Chinstrap Dream 46.1 18.2 178 ## 8 Chinstrap Dream 51.3 18.2 197 ## 9 Chinstrap Dream 46 18.9 195 ## 10 Chinstrap Dream 51.3 19.9 198 ## # … with 58 more rows, 3 more variables: ## # body_mass_g <int>, sex <fct>, year <int>, ## # and abbreviated variable names ## # ¹​bill_length_mm, ²​bill_depth_mm, ## # ³​flipper_length_mm ``` --- ```r filter(penguins, island == "Dream") ``` ``` ## # A tibble: 124 × 8 ## species island bill_length_mm bill_…¹ flipp…² ## <fct> <fct> <dbl> <dbl> <int> ## 1 Adelie Dream 39.5 16.7 178 ## 2 Adelie Dream 37.2 18.1 178 ## 3 Adelie Dream 39.5 17.8 188 ## 4 Adelie Dream 40.9 18.9 184 ## 5 Adelie Dream 36.4 17 195 ## 6 Adelie Dream 39.2 21.1 196 ## 7 Adelie Dream 38.8 20 190 ## 8 Adelie Dream 42.2 18.5 180 ## 9 Adelie Dream 37.6 19.3 181 ## 10 Adelie Dream 39.8 19.1 184 ## # … with 114 more rows, 3 more variables: ## # body_mass_g <int>, sex <fct>, year <int>, ## # and abbreviated variable names ## # ¹​bill_depth_mm, ²​flipper_length_mm ``` --- ```r filter(penguins, bill_length_mm > 40) ``` ``` ## # A tibble: 242 × 8 ## species island bill_leng…¹ bill_…² flipp…³ ## <fct> <fct> <dbl> <dbl> <int> ## 1 Adelie Torgersen 40.3 18 195 ## 2 Adelie Torgersen 42 20.2 190 ## 3 Adelie Torgersen 41.1 17.6 182 ## 4 Adelie Torgersen 42.5 20.7 197 ## 5 Adelie Torgersen 46 21.5 194 ## 6 Adelie Biscoe 40.6 18.6 183 ## 7 Adelie Biscoe 40.5 17.9 187 ## 8 Adelie Biscoe 40.5 18.9 180 ## 9 Adelie Dream 40.9 18.9 184 ## 10 Adelie Dream 42.2 18.5 180 ## # … with 232 more rows, 3 more variables: ## # body_mass_g <int>, sex <fct>, year <int>, ## # and abbreviated variable names ## # ¹​bill_length_mm, ²​bill_depth_mm, ## # ³​flipper_length_mm ``` --- ```r filter(penguins, bill_length_mm > 40, species == "Chinstrap") ``` ``` ## # A tibble: 68 × 8 ## species island bill_lengt…¹ bill_…² flipp…³ ## <fct> <fct> <dbl> <dbl> <int> ## 1 Chinstrap Dream 46.5 17.9 192 ## 2 Chinstrap Dream 50 19.5 196 ## 3 Chinstrap Dream 51.3 19.2 193 ## 4 Chinstrap Dream 45.4 18.7 188 ## 5 Chinstrap Dream 52.7 19.8 197 ## 6 Chinstrap Dream 45.2 17.8 198 ## 7 Chinstrap Dream 46.1 18.2 178 ## 8 Chinstrap Dream 51.3 18.2 197 ## 9 Chinstrap Dream 46 18.9 195 ## 10 Chinstrap Dream 51.3 19.9 198 ## # … with 58 more rows, 3 more variables: ## # body_mass_g <int>, sex <fct>, year <int>, ## # and abbreviated variable names ## # ¹​bill_length_mm, ²​bill_depth_mm, ## # ³​flipper_length_mm ``` --- class: dark, middle, center name: select # select --- ```r select(penguins, 1, 4, 6) ``` ``` ## # A tibble: 344 × 3 ## species bill_depth_mm body_mass_g ## <fct> <dbl> <int> ## 1 Adelie 18.7 3750 ## 2 Adelie 17.4 3800 ## 3 Adelie 18 3250 ## 4 Adelie NA NA ## 5 Adelie 19.3 3450 ## 6 Adelie 20.6 3650 ## 7 Adelie 17.8 3625 ## 8 Adelie 19.6 4675 ## 9 Adelie 18.1 3475 ## 10 Adelie 20.2 4250 ## # … with 334 more rows ``` --- ```r select(penguins, species, island, year, bill_length_mm) ``` ``` ## # A tibble: 344 × 4 ## species island year bill_length_mm ## <fct> <fct> <int> <dbl> ## 1 Adelie Torgersen 2007 39.1 ## 2 Adelie Torgersen 2007 39.5 ## 3 Adelie Torgersen 2007 40.3 ## 4 Adelie Torgersen 2007 NA ## 5 Adelie Torgersen 2007 36.7 ## 6 Adelie Torgersen 2007 39.3 ## 7 Adelie Torgersen 2007 38.9 ## 8 Adelie Torgersen 2007 39.2 ## 9 Adelie Torgersen 2007 34.1 ## 10 Adelie Torgersen 2007 42 ## # … with 334 more rows ``` --- ```r select(penguins, species, island, year, starts_with("bill")) ``` ``` ## # A tibble: 344 × 5 ## species island year bill_length…¹ bill_…² ## <fct> <fct> <int> <dbl> <dbl> ## 1 Adelie Torgersen 2007 39.1 18.7 ## 2 Adelie Torgersen 2007 39.5 17.4 ## 3 Adelie Torgersen 2007 40.3 18 ## 4 Adelie Torgersen 2007 NA NA ## 5 Adelie Torgersen 2007 36.7 19.3 ## 6 Adelie Torgersen 2007 39.3 20.6 ## 7 Adelie Torgersen 2007 38.9 17.8 ## 8 Adelie Torgersen 2007 39.2 19.6 ## 9 Adelie Torgersen 2007 34.1 18.1 ## 10 Adelie Torgersen 2007 42 20.2 ## # … with 334 more rows, and abbreviated ## # variable names ¹​bill_length_mm, ## # ²​bill_depth_mm ``` --- ```r select(penguins, species, island, body_mass_g:year, ends_with("mm")) ``` ``` ## # A tibble: 344 × 8 ## species island body_…¹ sex year bill_…² ## <fct> <fct> <int> <fct> <int> <dbl> ## 1 Adelie Torgersen 3750 male 2007 39.1 ## 2 Adelie Torgersen 3800 fema… 2007 39.5 ## 3 Adelie Torgersen 3250 fema… 2007 40.3 ## 4 Adelie Torgersen NA <NA> 2007 NA ## 5 Adelie Torgersen 3450 fema… 2007 36.7 ## 6 Adelie Torgersen 3650 male 2007 39.3 ## 7 Adelie Torgersen 3625 fema… 2007 38.9 ## 8 Adelie Torgersen 4675 male 2007 39.2 ## 9 Adelie Torgersen 3475 <NA> 2007 34.1 ## 10 Adelie Torgersen 4250 <NA> 2007 42 ## # … with 334 more rows, 2 more variables: ## # bill_depth_mm <dbl>, ## # flipper_length_mm <int>, and abbreviated ## # variable names ¹​body_mass_g, ## # ²​bill_length_mm ``` --- ```r select(penguins, species, ends_with("mm")) ``` ``` ## # A tibble: 344 × 4 ## species bill_length_mm bill_depth_mm flippe…¹ ## <fct> <dbl> <dbl> <int> ## 1 Adelie 39.1 18.7 181 ## 2 Adelie 39.5 17.4 186 ## 3 Adelie 40.3 18 195 ## 4 Adelie NA NA NA ## 5 Adelie 36.7 19.3 193 ## 6 Adelie 39.3 20.6 190 ## 7 Adelie 38.9 17.8 181 ## 8 Adelie 39.2 19.6 195 ## 9 Adelie 34.1 18.1 193 ## 10 Adelie 42 20.2 190 ## # … with 334 more rows, and abbreviated ## # variable name ¹​flipper_length_mm ``` --- ```r select(penguins, is.numeric) ``` ``` ## # A tibble: 344 × 5 ## bill_length_mm bill_d…¹ flipp…² body_…³ year ## <dbl> <dbl> <int> <int> <int> ## 1 39.1 18.7 181 3750 2007 ## 2 39.5 17.4 186 3800 2007 ## 3 40.3 18 195 3250 2007 ## 4 NA NA NA NA 2007 ## 5 36.7 19.3 193 3450 2007 ## 6 39.3 20.6 190 3650 2007 ## 7 38.9 17.8 181 3625 2007 ## 8 39.2 19.6 195 4675 2007 ## 9 34.1 18.1 193 3475 2007 ## 10 42 20.2 190 4250 2007 ## # … with 334 more rows, and abbreviated ## # variable names ¹​bill_depth_mm, ## # ²​flipper_length_mm, ³​body_mass_g ``` --- ```r select(penguins, !is.numeric) ``` ``` ## # A tibble: 344 × 3 ## species island sex ## <fct> <fct> <fct> ## 1 Adelie Torgersen male ## 2 Adelie Torgersen female ## 3 Adelie Torgersen female ## 4 Adelie Torgersen <NA> ## 5 Adelie Torgersen female ## 6 Adelie Torgersen male ## 7 Adelie Torgersen female ## 8 Adelie Torgersen male ## 9 Adelie Torgersen <NA> ## 10 Adelie Torgersen <NA> ## # … with 334 more rows ``` --- class: inverse, middle, center name: pipe # pipe --- ```r penguins ``` ``` ## # A tibble: 344 × 8 ## species island bill_leng…¹ bill_…² flipp…³ ## <fct> <fct> <dbl> <dbl> <int> ## 1 Adelie Torgersen 39.1 18.7 181 ## 2 Adelie Torgersen 39.5 17.4 186 ## 3 Adelie Torgersen 40.3 18 195 ## 4 Adelie Torgersen NA NA NA ## 5 Adelie Torgersen 36.7 19.3 193 ## 6 Adelie Torgersen 39.3 20.6 190 ## 7 Adelie Torgersen 38.9 17.8 181 ## 8 Adelie Torgersen 39.2 19.6 195 ## 9 Adelie Torgersen 34.1 18.1 193 ## 10 Adelie Torgersen 42 20.2 190 ## # … with 334 more rows, 3 more variables: ## # body_mass_g <int>, sex <fct>, year <int>, ## # and abbreviated variable names ## # ¹​bill_length_mm, ²​bill_depth_mm, ## # ³​flipper_length_mm ``` --- ```r mutate(penguins, extra_col = 1) ``` same as: ```r penguins |> mutate(extra_col = 1) ``` ``` ## # A tibble: 344 × 9 ## species island bill_leng…¹ bill_…² flipp…³ ## <fct> <fct> <dbl> <dbl> <int> ## 1 Adelie Torgersen 39.1 18.7 181 ## 2 Adelie Torgersen 39.5 17.4 186 ## 3 Adelie Torgersen 40.3 18 195 ## 4 Adelie Torgersen NA NA NA ## 5 Adelie Torgersen 36.7 19.3 193 ## 6 Adelie Torgersen 39.3 20.6 190 ## 7 Adelie Torgersen 38.9 17.8 181 ## 8 Adelie Torgersen 39.2 19.6 195 ## 9 Adelie Torgersen 34.1 18.1 193 ## 10 Adelie Torgersen 42 20.2 190 ## # … with 334 more rows, 4 more variables: ## # body_mass_g <int>, sex <fct>, year <int>, ## # extra_col <dbl>, and abbreviated variable ## # names ¹​bill_length_mm, ²​bill_depth_mm, ## # ³​flipper_length_mm ``` --- ```r penguins |> select(1:2, contains("bill")) |> mutate(extra_col = 1) ``` ``` ## # A tibble: 344 × 5 ## species island bill_leng…¹ bill_…² extra…³ ## <fct> <fct> <dbl> <dbl> <dbl> ## 1 Adelie Torgersen 39.1 18.7 1 ## 2 Adelie Torgersen 39.5 17.4 1 ## 3 Adelie Torgersen 40.3 18 1 ## 4 Adelie Torgersen NA NA 1 ## 5 Adelie Torgersen 36.7 19.3 1 ## 6 Adelie Torgersen 39.3 20.6 1 ## 7 Adelie Torgersen 38.9 17.8 1 ## 8 Adelie Torgersen 39.2 19.6 1 ## 9 Adelie Torgersen 34.1 18.1 1 ## 10 Adelie Torgersen 42 20.2 1 ## # … with 334 more rows, and abbreviated ## # variable names ¹​bill_length_mm, ## # ²​bill_depth_mm, ³​extra_col ``` --- ```r penguins |> select(1:2, contains("bill")) |> mutate(extra_col = 1) |> filter(sex == "female") ``` --- class: inverse, middle, center name: mutate # mutate --- ```r penguins |> mutate( new_column = 1, bill_ld_ratio = bill_length_mm/bill_depth_mm ) ``` ``` ## # A tibble: 344 × 10 ## species island bill_leng…¹ bill_…² flipp…³ ## <fct> <fct> <dbl> <dbl> <int> ## 1 Adelie Torgersen 39.1 18.7 181 ## 2 Adelie Torgersen 39.5 17.4 186 ## 3 Adelie Torgersen 40.3 18 195 ## 4 Adelie Torgersen NA NA NA ## 5 Adelie Torgersen 36.7 19.3 193 ## 6 Adelie Torgersen 39.3 20.6 190 ## 7 Adelie Torgersen 38.9 17.8 181 ## 8 Adelie Torgersen 39.2 19.6 195 ## 9 Adelie Torgersen 34.1 18.1 193 ## 10 Adelie Torgersen 42 20.2 190 ## # … with 334 more rows, 5 more variables: ## # body_mass_g <int>, sex <fct>, year <int>, ## # new_column <dbl>, bill_ld_ratio <dbl>, and ## # abbreviated variable names ¹​bill_length_mm, ## # ²​bill_depth_mm, ³​flipper_length_mm ``` --- ```r penguins |> group_by(species) |> mutate( bill_length_sp_max = max(bill_length_mm, na.rm = TRUE), bill_length_pc = (bill_length_mm/bill_length_sp_max)*100 ) ``` ``` ## # A tibble: 344 × 10 ## # Groups: species [3] ## species island bill_leng…¹ bill_…² flipp…³ ## <fct> <fct> <dbl> <dbl> <int> ## 1 Adelie Torgersen 39.1 18.7 181 ## 2 Adelie Torgersen 39.5 17.4 186 ## 3 Adelie Torgersen 40.3 18 195 ## 4 Adelie Torgersen NA NA NA ## 5 Adelie Torgersen 36.7 19.3 193 ## 6 Adelie Torgersen 39.3 20.6 190 ## 7 Adelie Torgersen 38.9 17.8 181 ## 8 Adelie Torgersen 39.2 19.6 195 ## 9 Adelie Torgersen 34.1 18.1 193 ## 10 Adelie Torgersen 42 20.2 190 ## # … with 334 more rows, 5 more variables: ## # body_mass_g <int>, sex <fct>, year <int>, ## # bill_length_sp_max <dbl>, ## # bill_length_pc <dbl>, and abbreviated ## # variable names ¹​bill_length_mm, ## # ²​bill_depth_mm, ³​flipper_length_mm ``` --- ```r penguins |> mutate(across(ends_with("mm"), ~ .x/10)) ``` ``` ## # A tibble: 344 × 8 ## species island bill_leng…¹ bill_…² flipp…³ ## <fct> <fct> <dbl> <dbl> <dbl> ## 1 Adelie Torgersen 3.91 1.87 18.1 ## 2 Adelie Torgersen 3.95 1.74 18.6 ## 3 Adelie Torgersen 4.03 1.8 19.5 ## 4 Adelie Torgersen NA NA NA ## 5 Adelie Torgersen 3.67 1.93 19.3 ## 6 Adelie Torgersen 3.93 2.06 19 ## 7 Adelie Torgersen 3.89 1.78 18.1 ## 8 Adelie Torgersen 3.92 1.96 19.5 ## 9 Adelie Torgersen 3.41 1.81 19.3 ## 10 Adelie Torgersen 4.2 2.02 19 ## # … with 334 more rows, 3 more variables: ## # body_mass_g <int>, sex <fct>, year <int>, ## # and abbreviated variable names ## # ¹​bill_length_mm, ²​bill_depth_mm, ## # ³​flipper_length_mm ```