This is the Lab Week 8 document for R-DAVIS. Complete the tasks below in this file (or in your own `.qmd` or `.Rmd` file, if you prefer) and save it.

**This week you'll submit a PDF, not the code file.** When you're done, render your document so the PDF shows both your code and your figures, then upload that PDF to Gradescope. The most reliable way to get there:

1. Click **Render** in RStudio (or press `Ctrl/Cmd+Shift+K`). This makes an `.html` file in the same folder as your lab.
2. Open the `.html` file in your web browser.
3. Print the page (`Ctrl/Cmd+P`) and choose **Save as PDF** as the printer.
4. Upload that PDF to Gradescope.

You can also change `html` to `pdf` in the `format:` line at the top of this file and render straight to PDF, but that needs some extra software (run `quarto install tinytex` in the Terminal first) and doesn't always cooperate. If it gives you trouble, use the HTML route above.


For our week eight lab, we are going to practice making plots that you could show to someone else. First we'll fix up a messy plot of the environmental impact statement (EIS) data from lecture, and then you'll make a plot of your own with some new data. The codebook at https://ucd-rdavis.github.io/R-DAVIS/data/eis_codebook.md describes every column. The data are from the U.S. EPA's Environmental Impact Statement database (https://cdxapps.epa.gov/cdx-enepa-II/public/action/eis/search), cleaned up for this course.

Load the data and remake the `stage` and `agency` columns from lecture using the code below.

```{r}
library(tidyverse)

eis <- read_csv("https://ucd-rdavis.github.io/R-DAVIS/data/eis_clean.csv") %>%
  filter(filed_year <= 2025)

eis <- eis %>%
  mutate(stage = case_when(
    str_detect(document_type, "Draft") ~ "Draft",
    str_detect(document_type, "Final") ~ "Final",
    TRUE ~ "Other"
  ))

top_agencies <- eis %>%
  count(lead_agency, sort = TRUE) %>%
  slice_head(n = 6) %>%
  pull(lead_agency)

eis <- eis %>%
  mutate(agency = if_else(lead_agency %in% top_agencies, lead_agency, "Other agencies"))
```

**Part A: Fix this plot**

Here's a plot of the number of filings each year for each agency and stage:

```{r}
ggplot(data = eis %>% count(filed_year, agency, stage),
       mapping = aes(x = filed_year, y = n, color = agency, linetype = stage)) +
  geom_line()
```

It's a mess.

1. Write a few sentences about what makes this plot hard to read.

2. Use anything you learned this week (faceting, themes, color, labels, annotation) to make a new version of this plot that you could show to someone else. Give it a title that tells the reader what to take away from it.

3. Write one or two sentences about what your new plot shows, and why you made the choices you did.

**Part B: Make your own plot**

For the second part of this lab, you'll find a new dataset and make a plot with it. We'd really encourage you to bring your own data, whether it's from your research, a class, or anything else you're interested in. If you're stuck, the Resources page on the course website (https://ucd-rdavis.github.io/R-DAVIS/resources.html) lists other datasets you can use.

4. Read your data into R, and write a sentence or two about where it came from and what one row represents.

5. Do a little exploring with tables and quick plots, like we did at the start of week 7. Then come up with a question you could answer with a plot.

6. Make a plot that answers your question. Choose a plot type and a color palette that fit your data, and add a title and labels. Save it with `ggsave()`.

7. Write a few sentences about what your plot shows, and why you chose the plot type and colors that you did.