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")

#1. Below I am creating a new date frame using the district dataset to pull “DISTNAME”, “DPETSPEP” (percent special education) and “DPFPASPEP” (money spent on special education). The new data frame will be called special_ed.

# Creating a new data frame 
special_ed <- district[, c("DISTNAME", "DPETSPEP", "DPFPASPEP")]

# View new data frame
head(special_ed)
## # A tibble: 6 × 3
##   DISTNAME      DPETSPEP DPFPASPEP
##   <chr>            <dbl>     <dbl>
## 1 CAYUGA ISD        14.6      28.9
## 2 ELKHART ISD       12.1       8.8
## 3 FRANKSTON ISD     13.1       8.4
## 4 NECHES ISD        10.5      10.1
## 5 PALESTINE ISD     13.5       6.1
## 6 WESTWOOD ISD      14.5       9.4

#2 Below is a summary of the statistics for both DPETSPEP and DFPASPEP.

#Summarizing percentage of special education 
summary(special_ed$DPETSPEP)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.00    9.90   12.10   12.27   14.20   51.70
#Summarizing money spent on special education
summary(special_ed$DPFPASPEP)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   5.800   8.900   9.711  12.500  49.000       5

#4 The variable with missing values is DPFPASPEP (money spent on special education). This is shown in the summary as 5 NA’s.

#5 Below I have removed the missing observations. There are now 1201 remaining observations.

special_ed_cleaned<-special_ed %>% filter(DPFPASPEP>0)

remaining_observations <- nrow(special_ed_cleaned)

#6 Below is a point graph to compare DPFPASPEP and DPETSPEP.

#Below is my point graph comparing DPFPASPEP and DPETSPEP
compare_two<-special_ed_cleaned %>% select(DISTNAME,DPFPASPEP,DPETSPEP)

ggplot(compare_two,aes(DPFPASPEP,DPETSPEP)) + geom_point()

#7 Numerical correlation between both DPFPASPEP and DPETSPEP

# Correlation between DPFPASPEP and DPETSPEP
correlation <- cor(compare_two$DPFPASPEP, compare_two$DPETSPEP, use = "complete.obs")

# Print the correlation
correlation
## [1] 0.371033

#8 I see a weak to moderate correlation. Point graphs slightly shows that higher spending is generally associated with a higher percentage of special education students, but the connection isn’t very tight.