Hmwk 4

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   4.0.2     ✔ tibble    3.3.1
## ✔ lubridate 1.9.4     ✔ 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

library(readxl)

TEA_Data<-read_excel("district.xls")

pastecs::stat.desc(TEA_Data$DZRVLOCP)

##       nbr.val      nbr.null        nbr.na           min           max 
##  1202.0000000     8.0000000     5.0000000    -6.2000000    97.6000000 
##         range           sum        median          mean       SE.mean 
##   103.8000000 45584.3000000    35.3000000    37.9237105     0.6928507 
##  CI.mean.0.95           var       std.dev      coef.var 
##     1.3593323   577.0105864    24.0210447     0.6334044

pastecs::stat.desc(TEA_Data$DPETALLC)

##      nbr.val     nbr.null       nbr.na          min          max        range 
## 1.207000e+03 0.000000e+00 0.000000e+00 4.000000e+00 1.937270e+05 1.937230e+05 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 5.402928e+06 8.840000e+02 4.476328e+03 3.594000e+02 7.051187e+02 1.559062e+08 
##      std.dev     coef.var 
## 1.248624e+04 2.789393e+00

hist(TEA_Data$DZRVLOCP)

TEA_Data<-TEA_Data %>% drop_na(DZRVLOCP)

TEA_Data%>% filter(DZRVLOCP<0)

## # A tibble: 2 × 137
##   DISTNAME DISTRICT DZCNTYNM REGION DZRATING DZCAMPUS DPETALLC DPETBLAP DPETHISP
##   <chr>    <chr>    <chr>    <chr>  <chr>       <dbl>    <dbl>    <dbl>    <dbl>
## 1 TRIUMPH… 071803   071 EL … 19     A               2      198      2.5     95.5
## 2 FORT EL… 242906   242 WHE… 16     A               1      159      0        7.5
## # 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>, …

TEA_Data<-TEA_Data %>% mutate(DZRVLOCP_transformed=sqrt(DZRVLOCP))

## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `DZRVLOCP_transformed = sqrt(DZRVLOCP)`.
## Caused by warning in `sqrt()`:
## ! NaNs produced