This is the Lab Week 4 document for R-DAVIS. Complete the tasks below in this file (or in your own `.Rmd` or `.R` file, if you prefer), save it, and upload that file to Canvas. No need to render it to HTML.


This week the lab will review data manipulation in the tidyverse, using the international environmental agreements data from lecture. The codebook at https://ucd-rdavis.github.io/R-DAVIS/data/iea_codebook.md describes every column. The data are a simplified subset of the International Environmental Agreements Database Project (https://www.iea.ulaval.ca; Mitchell et al. 2020, *Global Environmental Politics* 20(1): 103–121), prepared for this course.

1. Create a tibble named `agreements` from the iea_agreements.csv file, found at https://ucd-rdavis.github.io/R-DAVIS/data/iea_agreements.csv.

2. Subset `agreements` using Tidyverse methods to keep agreements signed between 1972 and 1992 (the years of the Stockholm and Rio environmental summits), and print out the first 6 rows.

3. Create a new tibble showing the largest number of members (`n_members`) for each subject + scope combination and name it `biggest_agreements`. Sort the tibble to take a look at the largest and smallest subject + scope combinations. HINT: it's easier to calculate max if there are no NAs in the dataframe...

4. Try to figure out where the NA values of `n_members` are concentrated in the data- is there a particular scope, subject, instrument, time period, or whatever, where there are lots of NA values? There isn't necessarily a right or wrong answer here, but manipulate `agreements` a few different ways to explore this. Maybe use `count` and `arrange` here. Does `year_in_force` have its NAs in the same places? Why might that be?

5. Take `agreements`, remove the rows where `n_members` is NA and add a column that contains the average number of members of each subject + scope combination to the **full** `agreements` dataframe. Then get rid of all the columns except for agreement_name, subject, scope, n_members, and your new average members column. Save this tibble as `agreements_avg_members`.

6. Take `agreements_avg_members` and add a new column called `above_average` that contains logical values stating whether or not a row's `n_members` is above average for its subject + scope combination (recall the new column we made for this tibble).