formative

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.6
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.1     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.2.0     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

peng <- read_csv("penguins_raw.csv")

## Rows: 344 Columns: 17
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (9): studyName, Species, Region, Island, Stage, Individual ID, Clutch C...
## dbl  (7): Sample Number, Culmen Length (mm), Culmen Depth (mm), Flipper Leng...
## date (1): Date Egg
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

head(peng)

## # A tibble: 6 × 17
##   studyName `Sample Number` Species          Region Island Stage `Individual ID`
##   <chr>               <dbl> <chr>            <chr>  <chr>  <chr> <chr>          
## 1 PAL0708                 1 Adelie Penguin … Anvers Torge… Adul… N1A1           
## 2 PAL0708                 2 Adelie Penguin … Anvers Torge… Adul… N1A2           
## 3 PAL0708                 3 Adelie Penguin … Anvers Torge… Adul… N2A1           
## 4 PAL0708                 4 Adelie Penguin … Anvers Torge… Adul… N2A2           
## 5 PAL0708                 5 Adelie Penguin … Anvers Torge… Adul… N3A1           
## 6 PAL0708                 6 Adelie Penguin … Anvers Torge… Adul… N3A2           
## # ℹ 10 more variables: `Clutch Completion` <chr>, `Date Egg` <date>,
## #   `Culmen Length (mm)` <dbl>, `Culmen Depth (mm)` <dbl>,
## #   `Flipper Length (mm)` <dbl>, `Body Mass (g)` <dbl>, Sex <chr>,
## #   `Delta 15 N (o/oo)` <dbl>, `Delta 13 C (o/oo)` <dbl>, Comments <chr>

library(tidyverse)     
library(plotly)       

peng_public <- peng %>%
  mutate(Species_simple = case_when(
    Species == "Adelie Penguin (Pygoscelis adeliae)"        ~ "Adelie",
    Species == "Chinstrap penguin (Pygoscelis antarctica)" ~ "Chinstrap",
    Species == "Gentoo penguin (Pygoscelis papua)"         ~ "Gentoo",
    TRUE ~ Species
  )) %>%
  group_by(Species_simple) %>%
  summarise(
    mean_mass = mean(`Body Mass (g)`, na.rm = TRUE)
  )


library(plotly)

p_public_interactive <- ggplot(
  peng_public,
  aes(x = Species_simple,
      y = mean_mass,
      fill = Species_simple,
      text = paste0(
        "Species: ", Species_simple,
        "<br>Average mass: ", round(mean_mass), " g"
      ))
) +
  geom_col(width = 0.55) +
  labs(
    title = "Gentoo penguins are much heavier\n than Adelie and Chinstrap",
    x = "",
    y = "Average body mass (g)"
  ) +
  scale_fill_brewer(palette = "Set2") +
  scale_y_continuous(expand = expansion(mult = c(0, 0.05))) +
  theme_minimal(base_size = 16) +
  theme(
    legend.position = "none",
    plot.title = element_text(hjust = 0.5, face = "bold"),
    axis.text.x = element_text(angle = 0, vjust = 1)
  )

ggplotly(p_public_interactive, tooltip = "text")