Setup
library(tidyverse)
library(openintro)
loans <- loans_full_schema %>%
mutate(
homeownership = str_to_title(homeownership),
bankruptcy = if_else(public_record_bankrupt >= 1, "Yes", "No")
) %>%
filter(annual_income >= 10) %>%
select(
loan_amount, homeownership, bankruptcy,
application_type, annual_income, interest_rate
)
loans
# A tibble: 9,976 × 6
loan_amount homeownership bankruptcy application_type annual_income interes…¹
<int> <chr> <chr> <fct> <dbl> <dbl>
1 28000 Mortgage No individual 90000 14.1
2 5000 Rent Yes individual 40000 12.6
3 2000 Rent No individual 40000 17.1
4 21600 Rent No individual 30000 6.72
5 23000 Rent No joint 35000 14.1
6 5000 Own No individual 34000 6.72
7 24000 Mortgage No joint 35000 13.6
8 20000 Mortgage No individual 110000 12.0
9 20000 Mortgage No individual 65000 13.6
10 6400 Rent No individual 30000 6.71
# … with 9,966 more rows, and abbreviated variable name ¹interest_rate
# ℹ Use `print(n = ...)` to see more rows
Exercise
Using the loans
data, create side-by-side box plots that shows the relationship between loan amount and application type, faceted by homeownership.