Cycle 1:

library(openintro)
## Loading required package: airports
## Loading required package: cherryblossom
## Loading required package: usdata
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.4.3
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
ggplot(loans_full_schema, aes(x = homeownership, y = interest_rate, fill = homeownership)) +
  geom_boxplot(alpha = 0.7) +
  labs(
    title = "Interest Rate vs Home Ownership",
    x = "Home Ownership Status",
    y = "Interest Rate (%)"
  ) +
  theme(legend.position = "none")


Cycle 2:

common_purposes <- loans_full_schema %>%
  group_by(loan_purpose) %>%
  tally(sort = TRUE) %>%
  top_n(8) %>%
  pull(loan_purpose)
## Selecting by n
loans_filtered <- loans_full_schema %>% 
  filter(loan_purpose %in% common_purposes)

ggplot(loans_filtered, aes(x = reorder(loan_purpose, interest_rate, median), y = interest_rate)) +
  geom_violin(fill = "steelblue", alpha = 0.5) +
  geom_boxplot(width = 0.1, outlier.shape = NA) +
  coord_flip() +
  labs(
    title = "Interest Rates by Loan Purpose",
    x = "Loan Purpose",
    y = "Interest Rate (%)"
  )


Cycle 3:

ggplot(loans_full_schema, aes(x = debt_to_income, y = interest_rate)) +
  geom_point(alpha = 0.1, color = "darkgreen") +
  geom_smooth(method = "lm", color = "coral") +
  labs(
    title = "Interest Rate vs Debt-to-Income Ratio",
    x = "Debt to Income",
    y = "Interest Rate (%)"
  ) 
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 24 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 24 rows containing missing values or values outside the scale range
## (`geom_point()`).


Cycle 4:

ggplot(loans_full_schema, aes(x = debt_to_income, y = interest_rate, color = verified_income)) +
  geom_smooth(method = "lm", se = FALSE) +
  labs(
    title = "Impact of Income Verification on Interest Rates",
    x = "Debt to Income Ratio",
    y = "Interest Rate (%)",
    color = "Income Verified"
  )
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 24 rows containing non-finite outside the scale range
## (`stat_smooth()`).