Homework 4

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(readxl)
library(pastecs)

## 
## Attaching package: 'pastecs'
## 
## The following objects are masked from 'package:dplyr':
## 
##     first, last
## 
## The following object is masked from 'package:tidyr':
## 
##     extract

setwd("C:/Users/David/Desktop/My Class Stuff/Wednesday Class")
data_florida <- read_excel("Data_Florida.xlsx", sheet = "Award Year Summary")

## New names:
## • `Recipients` -> `Recipients...6`
## • `# of Loans Originated` -> `# of Loans Originated...7`
## • `$ of Loans Originated` -> `$ of Loans Originated...8`
## • `# of Disbursements` -> `# of Disbursements...9`
## • `$ of Disbursements` -> `$ of Disbursements...10`
## • `Recipients` -> `Recipients...11`
## • `# of Loans Originated` -> `# of Loans Originated...12`
## • `$ of Loans Originated` -> `$ of Loans Originated...13`
## • `# of Disbursements` -> `# of Disbursements...14`
## • `$ of Disbursements` -> `$ of Disbursements...15`
## • `Recipients` -> `Recipients...16`
## • `# of Loans Originated` -> `# of Loans Originated...17`
## • `$ of Loans Originated` -> `$ of Loans Originated...18`
## • `# of Disbursements` -> `# of Disbursements...19`
## • `$ of Disbursements` -> `$ of Disbursements...20`
## • `Recipients` -> `Recipients...21`
## • `# of Loans Originated` -> `# of Loans Originated...22`
## • `$ of Loans Originated` -> `$ of Loans Originated...23`
## • `# of Disbursements` -> `# of Disbursements...24`
## • `$ of Disbursements` -> `$ of Disbursements...25`

names(data_florida)

##  [1] "OPE ID"                     "School"                    
##  [3] "State"                      "Zip Code"                  
##  [5] "School Type"                "Recipients...6"            
##  [7] "# of Loans Originated...7"  "$ of Loans Originated...8" 
##  [9] "# of Disbursements...9"     "$ of Disbursements...10"   
## [11] "Recipients...11"            "# of Loans Originated...12"
## [13] "$ of Loans Originated...13" "# of Disbursements...14"   
## [15] "$ of Disbursements...15"    "Recipients...16"           
## [17] "# of Loans Originated...17" "$ of Loans Originated...18"
## [19] "# of Disbursements...19"    "$ of Disbursements...20"   
## [21] "Recipients...21"            "# of Loans Originated...22"
## [23] "$ of Loans Originated...23" "# of Disbursements...24"   
## [25] "$ of Disbursements...25"

#1 
fl_loans <- data_florida %>% select(school_type = `School Type`, total_loans = `$ of Loans Originated...8`)

#2: Total loans is the dollar amount of loans distributed to students under the FEEL subsidized loan program during the 2009-2010 year.
stat.desc(fl_loans$total_loans)

##      nbr.val     nbr.null       nbr.na          min          max        range 
## 3.820000e+03 1.140000e+02 0.000000e+00 0.000000e+00 2.833224e+08 2.833224e+08 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 1.300420e+10 6.665555e+05 3.404240e+06 1.515814e+05 2.971883e+05 8.777184e+13 
##      std.dev     coef.var 
## 9.368663e+06 2.752057e+00

#3 Remove NAs
fl_loans_clean <- fl_loans |> dplyr::filter(!is.na(total_loans))

#4 Histogram
hist(fl_loans_clean$total_loans)

#5 Log Transformation
fl_loans_clean <- fl_loans_clean %>% mutate(log_loans= log1p(total_loans))
summary(fl_loans_clean$log_loans)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.00   11.19   13.41   12.76   14.93   19.46

#6 histogram of log transformation
hist(fl_loans_clean$log_loans)