part 3 question 1)

part3-q1.R

library(tidyverse)
library(readxl)

#load the training data
training_data <- read_excel("training_participation_survey.xlsx")

#question 1: Error rates in variables
cat("\nPART 3 - Question 1: Error Rates\n")

#check program status errors (should only be specific values)

valid_program_status <- c("Completed and Passed","Completed but Failed","Dropped Out")

program_status_errors <- sum(!training_data$program_status %in% valid_program_status) / nrow(training_data) * 100

cat("Program Status Error Rate: ", round(program_status_errors, 1),"%\n")