R for Marine Science Workshop 1

Author

Ryan Waln

Published

June 11, 2026

Introduction

This file is paired with a base R file to allow easy plotting of penguin data.

Material covered on base R script includes:

  • importing data
  • formatting data for R
  • Tidyverse tibbles vs base R data frames
  • piping
  • mutating data
  • basic NA value handling

Material covered on this qmd file includes:

  • piping data to create plots
  • plotting graphs with error bars
  • saving tables and figures

Load packages

library(tidyverse)

Source script

source("Workshop1.R")

Pipe data to summarize mean body mass for each species and island and create a box plot of body mass by species, with the island variable mapped to fill

mass_metrics = penguins %>%
  group_by(species, island) %>%
  summarise(
    sample_size = n(),                                     # Count total individuals per category
    mean_mass_g = mean(body_mass_g, na.rm = TRUE),         # Calculate mean ignoring missing cells
    sd_mass_g   = sd(body_mass_g, na.rm = TRUE)            # Standard deviation calculation
  )

print(mass_metrics) 
# A tibble: 5 × 5
# Groups:   species [3]
  species   island    sample_size mean_mass_g sd_mass_g
  <fct>     <fct>           <int>       <dbl>     <dbl>
1 Adelie    Biscoe             44       3710.      488.
2 Adelie    Dream              56       3688.      455.
3 Adelie    Torgersen          52       3706.      445.
4 Chinstrap Dream              68       3733.      384.
5 Gentoo    Biscoe            124       5076.      504.
penguins |>
  ggplot(aes(x = species, y = body_mass_g, fill = island)) +  #Plots with assigned x and y axis with islands as fill
  geom_boxplot(na.rm = TRUE) + # Stops missing value trap
  
  #Add labels and theme
  labs(
    title = "Penguin Body Mass by Species and Island",
    x = "Species",
    y = "Body Mass (g)",
    fill = "Island"
  )  +
  theme_minimal()

Instead of creating a summary table object first, you can pipe your grouped data straight into a plot and use geom_errorbar() to represent the spread of your data

# Pipe directly from aggregation to plotting with error bars
mass_compare_plot = penguins |>
  group_by(species, island) |>
  summarise(
    mean_mass = mean(body_mass_g, na.rm = TRUE),
    sd_mass = sd(body_mass_g, na.rm = TRUE),
    n = n(),
    .groups = "drop"
  ) |>
  ggplot(aes(x = species, y = mean_mass, colour = island)) +
  geom_point(size = 3) +
  geom_errorbar(aes(ymin = mean_mass - sd_mass, 
                    ymax = mean_mass + sd_mass), 
                width = 0.2) +
  labs(title = "Mean Body Mass by Species and Island",
       subtitle = "Error bars represent standard deviation",
       y = "Mean Body Mass (g)",
       x = "Species") +
  theme_minimal()

mass_compare_plot

Plot with standard error instead (always include table when presenting to others)

mass_compare_plot2 = penguins |>
  group_by(species, island) |>
  summarise(
    mean_mass = mean(body_mass_g, na.rm = TRUE),
    sd_mass = sd(body_mass_g, na.rm = TRUE),
    n = n(),
    se_mass = (sd_mass/ sqrt(n)), #calculate SE
    .groups = "drop"
  ) |>
  ggplot(aes(x = species, y = mean_mass, colour = island)) +
  geom_point(size = 3) +
  geom_errorbar(aes(ymin = mean_mass - se_mass, 
                    ymax = mean_mass + se_mass), 
                width = 0.2) +
  labs(title = "Mean Body Mass by Species and Island",
       subtitle = "Error bars represent standard error",
       y = "Mean Body Mass (g)",
       x = "Species") +
  theme_minimal()

mass_compare_plot2

#Display summary table to help determine patterns
mass_metrics = penguins %>%
  group_by(species, island) %>%
  summarise(
    sample_size = n(),                                     # Count total individuals per category
    mean_mass_g = mean(body_mass_g, na.rm = TRUE),         # Calculate mean ignoring missing cells
    sd_mass_g   = sd(body_mass_g, na.rm = TRUE)            # Standard deviation calculation
  )

print(mass_metrics)  
# A tibble: 5 × 5
# Groups:   species [3]
  species   island    sample_size mean_mass_g sd_mass_g
  <fct>     <fct>           <int>       <dbl>     <dbl>
1 Adelie    Biscoe             44       3710.      488.
2 Adelie    Dream              56       3688.      455.
3 Adelie    Torgersen          52       3706.      445.
4 Chinstrap Dream              68       3733.      384.
5 Gentoo    Biscoe            124       5076.      504.

Data suggests Gentoo Penguins are much bigger than other species and Adelie penguins do not vary much by mass across the islands

Saving Work

Can save Tables as:

Universal CSV text file: Ideal for sharing data tables with collaborators who do not use R.

Native R Binary RDS object: Saving as an RDS file preserves your exact vector configurations (such as custom categorical factor levels and numeric type definitions), meaning you never have to re-format column types when you reload the data next time you work on it.

Save Tables

# add ../ to go up one level since .Rmd & .qmd will always default to saving in exact loaction

# 1. Exporting our collapsed summary table as a universal flat text file
write_csv(biological_signal, "../outputs/penguin_species_mass_summary.csv")

# 2. Saving our cleaned morphological cohort table as a native R binary file
saveRDS(clean_scientific_fields, "../outputs/clean_penguin_morphology_cohort.rds")

Save Plot

ggsave("../outputs/figures/mass_compare_plot2.png", 
       plot = mass_compare_plot2, 
       width = 120, height = 120, 
       units = "mm", dpi = 300)