Juan C Gonzalez PAD 6833 - Homework 3

R Markdown - A tall white fountain played

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

library(readxl)
district <- read_xls("district.xls")
districtDataSet <- district[c("DISTNAME", "DPETSPEP", "DPFPASPEP")]
summary(districtDataSet)

##    DISTNAME            DPETSPEP       DPFPASPEP     
##  Length:1207        Min.   : 0.00   Min.   : 0.000  
##  Class :character   1st Qu.: 9.90   1st Qu.: 5.800  
##  Mode  :character   Median :12.10   Median : 8.900  
##                     Mean   :12.27   Mean   : 9.711  
##                     3rd Qu.:14.20   3rd Qu.:12.500  
##                     Max.   :51.70   Max.   :49.000  
##                                     NA's   :5

colSums(is.na(districtDataSet))

##  DISTNAME  DPETSPEP DPFPASPEP 
##         0         0         5

 districtCleanData <- districtDataSet |> 
  drop_na(DPFPASPEP)
summary(districtCleanData)

##    DISTNAME            DPETSPEP      DPFPASPEP     
##  Length:1202        Min.   : 0.0   Min.   : 0.000  
##  Class :character   1st Qu.: 9.9   1st Qu.: 5.800  
##  Mode  :character   Median :12.2   Median : 8.900  
##                     Mean   :12.3   Mean   : 9.711  
##                     3rd Qu.:14.2   3rd Qu.:12.500  
##                     Max.   :51.7   Max.   :49.000

library(ggplot2)
ggplot(districtCleanData, aes(x = DPETSPEP, y = DPFPASPEP)) +
  geom_point() +
  labs (x = "% of students in special ed", y = "% of expenditures in special ed")

cor(districtCleanData$DPETSPEP,districtCleanData$DPFPASPEP)

## [1] 0.3700234

#This data gives me the impression that there is not a strong corrolation between special needs student and the amount a campus is willing to spend on special education.