02_extra_exercises.qmd

---
title: "Learn R Part I - Extended Exercises"
format: html
editor: visual
---

#### 1. Load {tidyverse}

Use the `library()` command (the package name does not need to be in quotes)

```{r}

```

#### 2. Load colleges data using `read_csv()`

The data set for these exercises includes admissions information for 4-year colleges and universities in the U.S. southeast (<https://nces.ed.gov/ipeds/use-the-data>). The data file is called `admissions_data.csv` and is saved in the `data` subfolder. You can name your data frame object `se_colleges` .

```{r}

```

#### 3. How many colleges are in the U.S. southeast?

*Hint:* There is one college per row.

*Note:* You can find this information in the `read_csv()` loading message, or the Environment pane.

#### 4. What are the unique values of the `control` variable?

```{r}

```

#### 5. What are the minimum and maximum number of applicants in the data?

```{r}

```

#### 6. Subset rows

Filter the rows to only include HBCUs (Historically Black Colleges and Universities) in the states of NC and VA that enrolled fewer than 500 students

*Note:* `hbcu` is a binary variable (1 or 0), where 1 indicates a college is an HBCU.

```{r}

```

#### 7. Subset columns

Subset the columns to only include `institution_name` and the three variables that start with "`n_`"

```{r}

```

#### 8. Sort rows

What are the top 3 colleges in the state of Alabama (AL) by number of applicants?

```{r}

```

#### 9. Create new variables

Add two new variables (you come up with their names):

1.  Acceptance rate (`n_admitted` divided by `n_applied`)
2.  Yield rate (`n_enrolled` divided by `n_admitted`)

Then, add a pipe and filter only to colleges with an acceptance rate below .15 and a yield rate above .5. Which colleges meet these criteria?

```{r}

```