library(readxl) library(tidyverse)

district<-read_excel(“district.xls”)

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   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── 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")

new_frame=district%>%select(DISTNAME,DPETSPEP,DPFPASPEP)


summary(new_frame$DPETSPEP)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.00    9.90   12.10   12.27   14.20   51.70
summary(new_frame$DPFPASPEP)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   5.800   8.900   9.711  12.500  49.000       5
#"Money spent on special education" has the missing value

new_frame_cleaned=new_frame%>%filter(!is.na(DPFPASPEP))

#1202 remaining variables
ggplot(new_frame_cleaned,aes(DPETSPEP,DPFPASPEP))+geom_point()

#There appears to be a weak correlation considering that the majority of points congregate near the bottom left
cor(new_frame_cleaned$DPETSPEP,new_frame_cleaned$DPFPASPEP)
## [1] 0.3700234