Data Selection_PAD 6833

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 1.9.4     ✔ 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

enrollment_23 <- read_excel("enrollment_23.xlsx")

enrollment_24 <-read_excel("enrollment_24.xlsx")

library(dplyr)
library(lubridate)

North <- data.frame (zipcode = c(78247, 78258, 78259, 78260, 78261, 78266), category = c("District 1", "District 1", "District 1", "District 1", "District 1", "District 1"))

Liveoak_Universal_Windcrest <- data.frame (zipcode = c(78148, 78154, 78233, 78239), category = c("District 2", "District 2", "District 2", "District 2"))

Castlehills_Ridgeview <- data.frame(zipcode= c(78213, 78216, 78229, 78230, 78231, 78232, 78248), category = c("District 3", "District 3", "District 3", "District 3", "District 3", "District 3", "District 3"))

Converse_Kirby <- data.frame (zipcode =c(78108, 78109, 78244, 78227, 78242, 78245, 78252), category = c("District 4", "District 4", "District 4", "District 4", "District 4", "District 4", "District 4"))

Southsan <- data.frame(zipcode= c(78211, 78224, 78242), category = c("District 5", "District 5", "District 5"))

Southwest <- data.frame (zipcode =c(78002, 78052, 78054, 78073, 78224, 78227, 78242, 78245, 78252), category = c("District 6", "District 6", "District 6", "District 6", "District 6", "District 6", "District 6", "District 6", "District 6"))

Northernhills_Austinhwy <- data.frame(zipcode= c(78209, 78212, 78217, 78218), category = c("District 7", "District 7", "District 7", "District 7"))

race_eth_23 <- enrollment_23 %>% mutate(hispanic=ifelse(grepl("Hispanic",ethnicity),1,0))

race_eth_24 <- enrollment_24 %>% mutate(hispanic=ifelse(grepl("Hispanic",ethnicity),1,0))