library(readxl)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
district<-read_excel("district.xls")
special_education_proportion <- district |> select("DISTNAME", "DPETSPEP", "DPFPASPEP")
summary(special_education_proportion$DPETSPEP)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.00    9.90   12.10   12.27   14.20   51.70
summary(special_education_proportion$DPFPASPEP)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   5.800   8.900   9.711  12.500  49.000       5
cleaned_special_education_proportation <- special_education_proportion |> filter(DPFPASPEP>0)
ggplot(cleaned_special_education_proportation, aes(DPFPASPEP,DPETSPEP)) + 
 geom_point()

 cor(cleaned_special_education_proportation$DPFPASPEP, cleaned_special_education_proportation$DPETSPEP)
## [1] 0.371033

#negative correlation