Working with the Data
Once you’ve retrieved the data, you can use standard data manipulation tools to analyze it. Here are some common analysis patterns:
Analyze Local vs. Total Revenue Per-Pupil
# download 2022 data for connecticut
ct_sy22 <- get_finance_data(yr = "2022", geo = "CT")
# plot local revenue vs. total revenue w/ urbanicity + enrollment
ggplot(ct_sy22) +
geom_point(aes(
x = rev_local_pp,
y = rev_total_pp,
color = urbanicity,
size = enroll),
alpha = .6) +
scale_size_area(
max_size = 10,
labels = scales::label_comma()
) +
scale_x_continuous(labels = scales::label_dollar()) +
scale_y_continuous(labels = scales::label_dollar()) +
labs(
title = "Connecticut Districts' Local vs. Total Revenue Per-Pupil, SY2021-22",
x = "Local Revenue Per-Pupil",
y = "Total Revenue Per-Pupil",
size = "Enrollment",
color = "Urbanicity") +
theme_bw()
Analyzing Revenue Sources by Urbanicity
# compare revenue sources across districts
revenue_analysis <- ct_sy22 |>
mutate(
pct_local = rev_local / rev_total,
pct_state = rev_state / rev_total,
pct_federal = rev_fed / rev_total
) |>
select(dist_name, urbanicity, enroll, pct_local, pct_state, pct_federal) |>
group_by(urbanicity) |>
summarize(
avg_pct_local = mean(pct_local, na.rm = TRUE),
avg_pct_state = mean(pct_state, na.rm = TRUE),
avg_pct_federal = mean(pct_federal, na.rm = TRUE),
n_districts = n(),
enrollment = sum(enroll, na.rm = TRUE)
)
print(revenue_analysis)## # A tibble: 4 × 6
## urbanicity avg_pct_local avg_pct_state avg_pct_federal n_districts enrollment
## <fct> <dbl> <dbl> <dbl> <int> <dbl>
## 1 City 0.250 0.608 0.143 29 126751
## 2 Suburb 0.649 0.289 0.0623 85 285922
## 3 Town 0.584 0.351 0.0649 8 14823
## 4 Rural 0.649 0.303 0.0490 65 52477