HealthyR demo Plot Improvements
A.Carolina Ledezma-Carrizalez
2023-12-06
Plot Improvements - demo
From Ewen Harrison - Riinu Pius - The University of Edinburgh
{https://media.ed.ac.uk/media/HealthyR+demoA+Plot+Improvements/1_obw1zgc0}
Day 06 of HealthyR demo
Plot Improvements
Take A Sad Plot and Make it Better
Load libraries
library(tidyverse)
library(scales)
library(palmerpenguins)
library(ggbeeswarm)
library(colorspace)Dataset
Meet the penguins
The ‘Palmerpenguins’ contain size measurements of three species of penguins observed on three islands in the Palmer Archipelago, Antarctica.
This data was collected between 2007 and 2009 by Dr. Kristen Gorman with the Palmer Station Long-Term Ecological Research Program, part of the US Long-Term Ecological Research Network. The data was imported directly from the Portal from the Environmental Data Initiative (EDI) and are available for use under a CC0 (“No Rights Reserved”) license in accordance with the Palmer Station Data Policy.
Conoce a los pingüinos
Los palmerpenguins contienen medidas de tamaño de tres
especies de pingüinos observadas en tres islas del archipiélago Palmer,
en la Antártida.
Estos datos fueron recolectados entre 2007 y 2009 por la Dra. Kristen Gorman con el Programa de Investigación Ecológica a Largo Plazo de la Estación Palmer , parte de la Red de Investigación Ecológica a Largo Plazo de EE.UU. Los datos se importaron directamente del Portal de datos de la Iniciativa de datos ambientales (EDI) y están disponibles para su uso con licencia CC0 (“Sin derechos reservados”) de acuerdo con la Política de datos de Palmer Station .
finalfit::missing_glimpse(penguins)## label var_type n missing_n missing_percent
## species species <fct> 344 0 0.0
## island island <fct> 344 0 0.0
## bill_length_mm bill_length_mm <dbl> 342 2 0.6
## bill_depth_mm bill_depth_mm <dbl> 342 2 0.6
## flipper_length_mm flipper_length_mm <int> 342 2 0.6
## body_mass_g body_mass_g <int> 342 2 0.6
## sex sex <fct> 333 11 3.2
## year year <int> 344 0 0.0 penguins = penguins %>%
drop_na(species, sex, body_mass_g)Sad Plot
penguins %>%
ggplot(aes(x = species, y = body_mass_g)) +
geom_boxplot() +
facet_grid(.~island)
Sad Plot + raw data
penguins %>%
ggplot(aes(x = species, y = body_mass_g)) +
geom_boxplot(outlier.shape = NA) +
geom_jitter(alpha = 0.2) +
facet_grid(.~island)
# Checkout geom_boxplot2
## https://stackoverflow.com/questions/5677885/ignore-outliers-in-ggplot2-boxplotSad Plot + raw data + remove grey background
penguins %>%
ggplot(aes(x = species, y = body_mass_g)) +
geom_boxplot(outlier.shape = NA) +
geom_jitter(alpha = 0.2) +
facet_grid(.~island) +
theme_bw()
Sad Plot + raw data + remove grey background + axis labels
library(ggtext)
penguins %>%
ggplot(aes(x = species, y = body_mass_g)) +
geom_boxplot(outlier.shape = NA) +
geom_jitter(alpha = 0.2) +
labs(x = "Species", y = "Body mass (g^(2))") +
facet_grid(. ~ island) +
theme_bw() +
theme(axis.title.y = element_markdown())
Sad Plot + raw data + remove grey background + axis labels + remove empty factor levels
forcats::fct_drop## function (f, only = NULL)
## {
## f <- check_factor(f)
## check_character(only, allow_null = TRUE)
## levels <- levels(f)
## count <- table(f)
## to_drop <- levels[count == 0]
## if (!is.null(only)) {
## to_drop <- intersect(to_drop, only)
## }
## refactor(f, new_levels = setdiff(levels, to_drop))
## }
## <bytecode: 0x000001d938639f00>
## <environment: namespace:forcats>penguins %>%
ggplot(aes(x = species, y = body_mass_g)) +
geom_boxplot(outlier.shape = NA) +
geom_jitter(alpha = 0.2) +
labs(x = "Species", y = "Body mass (g^(2))") +
facet_grid(. ~ island, scales = "free_x") +
theme_bw() +
theme(axis.title.y = element_markdown())
Sad plot + change whisker length
penguins %>%
ggplot(aes(x = species, y = body_mass_g)) +
geom_boxplot(coef = 2) +
facet_grid(.~island)
Hints
- Add the raw data - colour per species - change colour palatte
- Remove the outliers
- Remove the grey background
- Fix the axes lables - remove legend
- Add the mean
penguins %>%
ggplot(aes(x = species, y = body_mass_g)) +
geom_boxplot(fill = NA, outlier.shape = NA, alpha = 0.2) + # remove outliers
facet_grid(.~island, scales = "free_x", space = "free_x") + # free x axis
geom_jitter(aes(colour = species), alpha = 0.5, width = 0.1, size = 3) + # jitter
labs(y = "Body Mass (g)", x = "Penguin Species", caption = "Source: Palmerpenguins") + # Axis captions
stat_summary(fun = mean,
geom = "point", shape = 20, size = 5, color = "black", fill = "black") + # Add mean
scale_colour_viridis_d() + # Change colour scheme
theme_bw() + # Remove grey background
theme(legend.position = "none") # Remove legend - note: setting the theme should be done after removing background theme
My version with the help of Cedric Scherer
# Scatterplot example 1: penguin flipper length versus body mass
ggplot(data = penguins, aes(x = flipper_length_mm, y = body_mass_g)) +
geom_point(aes(color = species,
shape = species),
size = 2) +
theme_minimal()+
scale_color_manual(values = c("darkorange","darkorchid","cyan4"))
# Scatterplot example 2: penguin bill length versus bill depth
ggplot(data = penguins, aes(x = bill_length_mm, y = bill_depth_mm)) +
geom_point(aes(color = species,
shape = species),
size = 2) +
theme_minimal()+
scale_color_manual(values = c("darkorange","darkorchid","cyan4"))
#Traigo mis imagenes
url <- "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/master/man/figures/lter_penguins.png"
img <- magick::image_read((url))
pic <- grid::rasterGrob(img, interpolate = TRUE)
pal <- c("#FF8C00", "#A034F0", "#159090")
add_sample <- function(x){
return(c(y = max(x) + .025,
label = length(x)))
}
penguins %>%
group_by(species) %>%
mutate(bill_ratio = bill_length_mm / bill_depth_mm) %>%
filter(!is.na(bill_ratio)) %>%
ggplot(aes(x = fct_rev(species), y = bill_ratio)) +
ggdist::stat_halfeye(
aes(color = species,
fill = after_scale(lighten(color, .5))),
adjust = .5,
width = .75,
.width = 0,
justification = -.4,
point_color = NA) +
geom_boxplot(
aes(color = species,
color = after_scale(darken(color, .1, space = "HLS")),
fill = after_scale(desaturate(lighten(color, .8), .4))),
width = .42,
outlier.shape = NA
) +
geom_point(
aes(color = species,
color = after_scale(darken(color, .1, space = "HLS"))),
fill = "white",
shape = 21,
stroke = .4,
size = 2,
position = position_jitter(seed = 1, width = .12)
) +
geom_point(
aes(fill = species),
color = "transparent",
shape = 21,
stroke = .4,
size = 2,
alpha = .3,
position = position_jitter(seed = 1, width = .12)
) +
stat_summary(
geom = "text",
fun = "median",
aes(label = round(..y.., 2),
color = species,
color = after_scale(darken(color, .1, space = "HLS"))),
family = "Roboto Mono",
fontface = "bold",
size = 4.5,
vjust = -3.5
) +
stat_summary(
geom = "text",
fun.data = add_sample,
aes(label = paste("n =", ..label..),
color = species,
color = after_scale(darken(color, .1, space = "HLS"))),
family = "Roboto Condensed",
size = 4,
hjust = 0
) +
coord_flip(xlim = c(1.2, NA), clip = "off") +
annotation_custom(pic, ymin = 2.9, ymax = 3.85, xmin = 2.7, xmax = 4.7) +
scale_y_continuous(
limits = c(1.57, 3.8),
breaks = seq(1.6, 3.8, by = .2),
expand = c(.001, .001)
) +
scale_color_manual(values = pal, guide = "none") +
scale_fill_manual(values = pal, guide = "none") +
labs(
x = NULL,
y = "Bill ratio",
title = "Bill Ratios of Brush–Tailed Penguins (*Pygoscelis* spec.)",
subtitle = "Distribution of bill ratios, estimated as bill length divided by bill depth.",
caption = "Gorman, Williams & Fraser (2014) *PLoS ONE* DOI: 10.1371/journal.pone.0090081<br>Visualization: Cédric Scherer • llustration: Allison Horst"
) +
theme_minimal(base_family = "Zilla Slab", base_size = 15) +
theme(
panel.grid.minor = element_blank(),
panel.grid.major.y = element_blank(),
axis.ticks = element_blank(),
axis.text.x = element_text(family = "Roboto Mono"),
axis.text.y = element_text(
color = rev(darken(pal, .1, space = "HLS")),
size = 12
),
axis.title.x = element_text(margin = margin(t = 10),
size = 16),
plot.title = element_markdown(face = "bold", size = 16),
plot.subtitle = element_text(
color = "grey40", hjust = 0,
margin = margin(0, 0, 20, 0)
),
plot.title.position = "plot",
plot.caption = element_markdown(
color = "grey40", lineheight = 1.2,
margin = margin(20, 0, 0, 0)),
plot.margin = margin(15, 15, 10, 15)
)