knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.2.1 ✔ readr 2.2.0
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.3 ✔ tibble 3.3.1
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(readxl)
district<-read_excel("district.xls")
sped <- district %>% select(DISTNAME, DPETSPEP, DPFPASPEP)
summary(sped)
## DISTNAME DPETSPEP DPFPASPEP
## Length :1207 Min. : 0.00 Min. : 0.000
## N.unique :1196 1st Qu.: 9.90 1st Qu.: 5.800
## N.blank : 0 Median :12.10 Median : 8.900
## Min.nchar: 7 Mean :12.27 Mean : 9.711
## Max.nchar: 50 3rd Qu.:14.20 3rd Qu.:12.500
## Max. :51.70 Max. :49.000
## NAs :5
# DPFPASPEP has 5 NAs
sped_cleaned<-sped %>% filter(DPFPASPEP>0)
count(sped_cleaned) # 1201 are remaining as DPFPASPEP reflected a 0 for minimum. This means there was an obs that reported a 0. With filter(DPFPASPEP>0) any value 0 or below would be filtered out.
## # A tibble: 1 × 1
## n
## <int>
## 1 1201
ggplot(sped_cleaned, aes(x=DPFPASPEP, y=DPETSPEP)) + geom_point()
# positive correlation
cor(sped_cleaned$DPFPASPEP, sped_cleaned$DPETSPEP)
## [1] 0.371033
# [1] 0.371033 affirms positive correlation from Q6
# A weak positive relationship exists between DPETSPEP and DPFPASPEP. Generally, the lower the percentage of students, the less the district spends.