Day 8: End-of-day practice

Refining reef data with factors and dates

Today you’ll revisit the coral/fish reef question from Day 7, this time refining two things from the first time around: parsing Date as a real date instead of pulling the year out with str_sub(), and taking control of how Site and Habitat are ordered in your plots instead of leaving R to sort them alphabetically.

Read data

Download the data moorea_coral.csv, moorea_fish.csv.

Inside your day 8 folder, create a subfolder called data, and put both CSVs in it.

Create an R script in your day 8 folder called reef-factors-dates.R.

Add a code chunk containing the following code:

library(tidyverse)
library(lubridate)

moorea_coral <- read_csv(
  "data/moorea_coral.csv",
  na = c("", "NA", "ND") # This vector tells read_csv() which values to interpret as missing data
)

moorea_fish <- read_csv(
  "data/moorea_fish.csv",
  na = c("", "NA", "ND")
)

Use glimpse() on each to see what you’re working with.

Part 1: Dates

Exercise 1: Parse real dates

  1. Create a vector called non_coral containing the five non-coral category labels: "Sand", "CTB", "Macroalgae", "Non-coralline Crustose Algae", and "Unknown or Other". Filter moorea_coral to exclude any row whose Taxonomy_Substrate_or_Functional_Group is in non_coral, and to keep only rows where Depth is less than 17.
  2. Date is stored as text formatted "YYYY-MM". Use mutate() to turn it into an actual date column. Then use year() on that date column to create a Year column.
Tip

Compare the two approaches at the console:

str_sub("2017-04", 1, 4) |> as.numeric()

ym("2017-04") |> year()

Both get you a year — but only the second one gives you back something that’s still a date, so you can keep asking it date questions.

Exercise 2: Summarize coral cover

Each quadrat (identified by Quad40) can contain several coral genera, so summarizing in one step would average across genera within a quadrat instead of adding them up. Summarize in two steps instead:

  1. First, sum Percent_Cover by year, site, habitat, depth, and Quad40 to get the total coral cover in each quadrat. Call the new column quadrat_cover.
  2. Then, summarize the mean of quadrat_cover by year, site, and habitat. Call the new column mean_coral_cover.
  3. Arrange the result by year, site, and habitat. Store it as coral_summary.

Exercise 3: Wrangle and join the fish data

  1. Filter moorea_fish to rows where Coarse_Trophic is "Primary Consumer" — the herbivorous, algae-grazing fish.
  2. Summarize the total biomass (sum of Biomass) by site, habitat, and year. Call the new column total_biomass. Store it as fish_summary.
  3. Use inner_join() to combine coral_summary and fish_summary, matching on site, habitat, and year. Store the result as reef_joined.

Part 2: Factors

Exercise 4: Order habitats ecologically

The coral surveys only cover two habitats, Forereef and Fringing. Backreef shows up in the fish data, but never in moorea_coral, so it always drops out of reef_joined during the inner_join() (the same reason your row counts didn’t match in Exercise 3). By default, those two remaining habitats sort alphabetically: Forereef, Fringing — putting the deeper habitat first. Use fct_relevel() to put them in shallow-to-deep order instead: "Fringing", "Forereef".

  1. mutate() reef_joined$Habitat into a factor with that level order.
  2. Remake last week’s habitat comparison: select() Site, Habitat, Year, and mean_coral_cover, then pivot_wider() to spread Habitat into its own columns.
  3. Add a column calculating the difference in coral cover between the two habitats, and plot its distribution as a histogram — same as Day 7, but now the column order in your wide data (and any faceting you do downstream) follows reef structure instead of the alphabet.

Exercise 5: Order sites by coral cover

Right now Site sorts as LTER_1, LTER_2, …, LTER_6 — an arbitrary label order that says nothing about the reef. Use fct_reorder() to reorder Site’s levels by mean_coral_cover instead.

  1. Using reef_joined, create a scatterplot with mean coral cover on the x-axis and herbivorous fish biomass on the y-axis, facet_wrap()-ed by Site.
  2. Reorder Site with fct_reorder(Site, mean_coral_cover) before faceting, and compare the two versions. With sites ordered by coral cover, does a pattern with fish biomass become easier to see?
Tip

fct_reorder() needs a summary value per level, so it works best right before a plot — reorder inside the mutate() that feeds your ggplot() call, rather than saving the reordered factor back into reef_joined for later use.