Homework 3

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

library(readxl)

library(readxl)
district<-read_excel("district.xls")

new_district<-district %>% select(DISTNAME,DPETSPEP,DPFPASPEP)

head(new_district)

## # 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

summary(new_district$DPETSPEP)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.00    9.90   12.10   12.27   14.20   51.70

summary(new_district$DPFPASPEP)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   5.800   8.900   9.711  12.500  49.000       5

# DPFPASPEP has missing values

new_district_cleaned<-new_district %>% filter(DPFPASPEP>0)
# there are now 1201 observations left 

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

# there is positive correlation between these variables

cor(new_district_cleaned$DPFPASPEP,new_district_cleaned$DPETSPEP)

## [1] 0.371033

# my takeaway of this result is the varibales having about 37% correlation wiht each other, and it is a positive relationship because it is above 0.