Sarah Rodriguez Homework Week Three

#create an Rmarkdown document with "district" data 
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 1.9.3     ✔ 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

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

#create a new data frame with "DISTNAME", "DPETSPEP" (percent special education) and "DPFPASPEP" (money spent on special education). call the data frame whatever you want

school_data <-district %>% select(DISTNAME, DPETSPEP, DPFPASPEP)

head(school_data)

## # A tibble: 6 × 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

# give me "summary()" statistics for both DPETSPEP and DFPASPEP. You can summarize them separately if you want.

summary(school_data$DPETSPEP)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.00    9.90   12.10   12.27   14.20   51.70

summary(school_data$DPFPASPEP)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   5.800   8.900   9.711  12.500  49.000       5

 # Which variable has missing values? 
#DPFPASPEP has the missing values

# remove the missing observations. How many are left overall?
school_data2 <-school_data %>% filter(!is.na(DPFPASPEP))
#1202 observations

# Create a point graph (hint: ggplot + geom_point()) to compare DPFPASPEP and DPETSPEP. Are they correlated?

ggplot(school_data2,aes(x=DPFPASPEP, y=DPETSPEP)) + geom_point()  

#  Do a mathematical check (cor()) of DPFPASPEP and DPETSPEP. What is the result?

cor(school_data2$DPFPASPEP, school_data2$DPETSPEP)

## [1] 0.3700234