## ----include = FALSE----------------------------------------------------------
# chunks that download hosted data are skipped on CRAN machines; set
# NOT_CRAN=true (as the pkgdown workflow does) to evaluate everything
NOT_CRAN <- identical(Sys.getenv("NOT_CRAN"), "true")
knitr::opts_chunk$set(
  message = FALSE,
  warning = FALSE,
  eval = NOT_CRAN
)

## ----setup, include = FALSE, eval = TRUE--------------------------------------
library(edfinr)
library(dplyr)
library(ggplot2)

## ----eval = FALSE-------------------------------------------------------------
# library(edfinr)
# library(dplyr)
# library(ggplot2)

## ----example-1----------------------------------------------------------------
# ky_sy23 <- get_finance_data(yr = "2023", geo = "KY")
# glimpse(ky_sy23)

## ----example-2----------------------------------------------------------------
# ky_full_sy23 <- get_finance_data(yr = "2023", geo = "KY", dataset_type = "full")
# setdiff(names(ky_full_sy23), names(ky_sy23))

## ----finding-variables, eval = TRUE-------------------------------------------
vars <- list_variables("full")
vars

# filter by category
list_variables("full", category = "debt")

## ----example-3----------------------------------------------------------------
# sec_data <- get_finance_data(
#   yr = "2019:2023",  # years 2019 through 2023
#   geo = "AL,AR,FL,GA,KY,LA,MS,MO,OK,SC,TN,TX"  # comma-separated state codes
# )
# 
# us_sy23 <- get_finance_data(yr = "2023", geo = "all")

## ----caching, eval = FALSE----------------------------------------------------
# # re-download even if a cached copy exists, without progress messages
# ky_fresh <- get_finance_data(yr = "2023", geo = "KY", refresh = TRUE, quiet = TRUE)

## ----analysis-1, fig.width = 7, fig.height = 5, fig.alt = "Scatterplot of Connecticut districts' local share of revenue versus total revenue per-pupil for SY2022-23, with point size showing enrollment and color showing urbanicity; the most locally-reliant districts tend to have higher total revenue per-pupil."----
# ct_sy23 <- get_finance_data(yr = "2023", geo = "CT")
# 
# ggplot(ct_sy23) +
#   geom_point(aes(
#     x = rev_local / rev_total,
#     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_percent()) +
#   scale_y_continuous(labels = scales::label_dollar()) +
#   labs(
#     title = "Connecticut Districts' Local Revenue Share vs. Total Revenue Per-Pupil, SY2022-23",
#     x = "Local Share of Total Revenue",
#     y = "Total Revenue Per-Pupil",
#     size = "Enrollment",
#     color = "Urbanicity") +
#   theme_bw()

## ----analysis-2---------------------------------------------------------------
# # compare revenue mix across urbanicity groups (dollar-weighted)
# revenue_analysis <- ct_sy23 |>
#   group_by(urbanicity) |>
#   summarize(
#     pct_local = sum(rev_local, na.rm = TRUE) / sum(rev_total, na.rm = TRUE),
#     pct_state = sum(rev_state, na.rm = TRUE) / sum(rev_total, na.rm = TRUE),
#     pct_federal = sum(rev_fed, na.rm = TRUE) / sum(rev_total, na.rm = TRUE),
#     n_districts = n(),
#     enrollment = sum(enroll, na.rm = TRUE)
#   )
# 
# revenue_analysis