scorecard

Load the information

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6      ✔ purrr   0.3.5 
## ✔ tibble  3.1.8      ✔ dplyr   1.0.10
## ✔ tidyr   1.2.1      ✔ stringr 1.4.1 
## ✔ readr   2.1.3      ✔ forcats 0.5.2 
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

scorecard = read.csv("https://asayanalytics.com/scorecard_csv")

A hypothesis

What state costs the most?

scorecard %>%
  group_by(STABBR) %>%
  summarize(`Average Cost` = mean(COSTT4_A, NA.rm=TRUE)) %>%
  ggplot(aes(x=STABBR, y=`Average Cost`)) +
  geom_col()