code

library(readr)
library(healthcareai)

#loading data
employee_data <- read_csv("C:/Users/mukul/OneDrive/Desktop/employee_data.csv")
View(employee_data)

#descriptive analysis
ed=employee_data
dim(ed)
colnames(ed)
mean(ed$n_projects)
cor(ed$n_projects, ed$avg_monthly_hrs)
cor.test(ed$n_projects, ed$avg_monthly_hrs)

#data cleaning
missingness(ed)  #reports missing data
#prep_data(ed)

ed1=prep_data(ed) # addresses missing data

write.csv(ed1, "ed1.csv")

# Machine Learning
machine_learn(ed,outcome=status)

#split test -train
models = machine_learn(ed,outcome=status) # assigning ML value to models
ed_train = split_train_test (ed, outcome=status, 0.8)
predicts(models, newdata = ed_train$test)

#alternatively
ed_train = split_train_test (ed, outcome=status, 0.8)
models = machine_learn(ed_train$train,outcome=status) 
predicts(models, newdata = ed_train$test)