HW3

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   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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(tidyr)
library(readxl)

district<-read_excel("district.xls")
head(district)

## # A tibble: 6 × 137
##   DISTNAME DISTRICT DZCNTYNM REGION DZRATING DZCAMPUS DPETALLC DPETBLAP DPETHISP
##   <chr>    <chr>    <chr>    <chr>  <chr>       <dbl>    <dbl>    <dbl>    <dbl>
## 1 CAYUGA … 001902   001 AND… 07     A               3      574      4.4     11.5
## 2 ELKHART… 001903   001 AND… 07     A               4     1150      4       11.8
## 3 FRANKST… 001904   001 AND… 07     A               3      808      8.5     11.3
## 4 NECHES … 001906   001 AND… 07     A               2      342      8.2     13.5
## 5 PALESTI… 001907   001 AND… 07     B               6     3360     25.1     42.9
## 6 WESTWOO… 001908   001 AND… 07     B               4     1332     19.7     26.2
## # ℹ 128 more variables: DPETWHIP <dbl>, DPETINDP <dbl>, DPETASIP <dbl>,
## #   DPETPCIP <dbl>, DPETTWOP <dbl>, DPETECOP <dbl>, DPETLEPP <dbl>,
## #   DPETSPEP <dbl>, DPETBILP <dbl>, DPETVOCP <dbl>, DPETGIFP <dbl>,
## #   DA0AT21R <dbl>, DA0912DR21R <dbl>, DAGC4X21R <dbl>, DAGC5X20R <dbl>,
## #   DAGC6X19R <dbl>, DA0GR21N <dbl>, DA0GS21N <dbl>, DDA00A001S22R <dbl>,
## #   DDA00A001222R <dbl>, DDA00A001322R <dbl>, DDA00AR01S22R <dbl>,
## #   DDA00AR01222R <dbl>, DDA00AR01322R <dbl>, DDA00AM01S22R <dbl>, …

special_ed_data<-district |> select(DISTNAME, DPETSPEP,DPFPASPEP)

summary("DPETSPEP")

##    Length     Class      Mode 
##         1 character character

summary("DPFPASPEP")

##    Length     Class      Mode 
##         1 character character

#both variables have missing values

special_ed_data |> drop_na()

## # 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

clean_special_ed_data <- special_ed_data |> drop_na()
print(clean_special_ed_data)

## # 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

summary("DPETSPEP")

##    Length     Class      Mode 
##         1 character character

summary("DPFPASPEP")

##    Length     Class      Mode 
##         1 character character

#IDK why it keeps doing this…I thought I removed all the missing values, so why does it still say ‘character’ ?? #There are now 1202 obs. of 3 variables instead of 1207 out of 3 variables

ggplot(clean_special_ed_data,aes(x=DPETSPEP, y=DPFPASPEP)) + geom_point()

cor(clean_special_ed_data$DPETSPEP,clean_special_ed_data$DPFPASPEP)

## [1] 0.3700234

#This coefficient shows that there is a weak and positive correlation between percent of special education and money spent on special education