Research Paper Data Selection NK

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.1     ✔ readr     2.2.0
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.3     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.2     
## ── 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)

district<-read_excel("district.xls")

NKData<-district%>%select(DISTRICT,REGION,DZCAMPUS,DPETSPEP)

summary(NKData)

##       DISTRICT          REGION        DZCAMPUS          DPETSPEP    
##  Length   :1207   Length   :1207   Min.   :  1.000   Min.   : 0.00  
##  N.unique :1207   N.unique :  20   1st Qu.:  2.000   1st Qu.: 9.90  
##  N.blank  :   0   N.blank  :   0   Median :  3.000   Median :12.10  
##  Min.nchar:   6   Min.nchar:   2   Mean   :  7.428   Mean   :12.27  
##  Max.nchar:   6   Max.nchar:   2   3rd Qu.:  5.000   3rd Qu.:14.20  
##                                    Max.   :273.000   Max.   :51.70

hist(NKData$DZCAMPUS)

plot(NKData$DISTRICT,NKData$DPETSPEP)

cor(NKData$DZCAMPUS,NKData$DPETSPEP)

## [1] -0.04096039