library(readxl)
district <- read_excel("district.xls")
View(district)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.2.0 ✔ readr 2.1.6
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.1 ✔ tibble 3.3.1
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.1
## ── 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
hwdata <- district %>%
select(DISTNAME, DPETSPEP, DPFPASPEP)
summary(hwdata$DPETSPEP)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 9.90 12.10 12.27 14.20 51.70
summary(hwdata$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 5 missing values
drop_na(hwdata)
## # A tibble: 1,202 × 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
## 7 SLOCUM ISD 14.7 9.9
## 8 ANDREWS ISD 10.4 10.9
## 9 PINEYWOODS COMMUNITY ACADEMY 11.6 9.2
## 10 HUDSON ISD 11.9 10.3
## # ℹ 1,192 more rows
#1202 observations remain
ggplot(data = hwdata, aes(x = DPETSPEP, y = DPFPASPEP)) +
geom_point()
## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_point()`).
cor(hwdata$DPETSPEP,hwdata$DPFPASPEP)
## [1] NA
#the math data didnt produce a result, but it looks to me a positive correlation