Goal is to predict attrition, the employees who are likely to leave the company.

#Import Data

library(tidyverse)
## Warning: package 'purrr' was built under R version 4.4.3
## ── 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 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── 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(correlationfunnel)
## ══ Using correlationfunnel? ════════════════════════════════════════════════════
## You might also be interested in applied data science training for business.
## </> Learn more at - www.business-science.io </>
library(tidymodels)
## Warning: package 'tidymodels' was built under R version 4.4.3
## ── Attaching packages ────────────────────────────────────── tidymodels 1.3.0 ──
## ✔ broom        1.0.7     ✔ rsample      1.2.1
## ✔ dials        1.4.0     ✔ tune         1.3.0
## ✔ infer        1.0.7     ✔ workflows    1.2.0
## ✔ modeldata    1.4.0     ✔ workflowsets 1.1.0
## ✔ parsnip      1.3.0     ✔ yardstick    1.3.2
## ✔ recipes      1.1.1
## Warning: package 'dials' was built under R version 4.4.3
## Warning: package 'infer' was built under R version 4.4.3
## Warning: package 'modeldata' was built under R version 4.4.3
## Warning: package 'parsnip' was built under R version 4.4.3
## Warning: package 'recipes' was built under R version 4.4.3
## Warning: package 'rsample' was built under R version 4.4.3
## Warning: package 'tune' was built under R version 4.4.3
## Warning: package 'workflows' was built under R version 4.4.3
## Warning: package 'workflowsets' was built under R version 4.4.3
## Warning: package 'yardstick' was built under R version 4.4.3
## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter()   masks stats::filter()
## ✖ recipes::fixed()  masks stringr::fixed()
## ✖ dplyr::lag()      masks stats::lag()
## ✖ yardstick::spec() masks readr::spec()
## ✖ recipes::step()   masks stats::step()
library(rsample)
library(purrr)
library(recipes)
library(themis)
## Warning: package 'themis' was built under R version 4.4.3
library(usemodels)
## Warning: package 'usemodels' was built under R version 4.4.3
library(doParallel)
## Warning: package 'doParallel' was built under R version 4.4.3
## Loading required package: foreach
## Warning: package 'foreach' was built under R version 4.4.3
## 
## Attaching package: 'foreach'
## 
## The following objects are masked from 'package:purrr':
## 
##     accumulate, when
## 
## Loading required package: iterators
## Warning: package 'iterators' was built under R version 4.4.3
## Loading required package: parallel
library(workflows)

data <- read_csv("00_data/WA_Fn-UseC_-HR-Employee-Attrition.csv")
## Rows: 1470 Columns: 35
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (9): Attrition, BusinessTravel, Department, EducationField, Gender, Job...
## dbl (26): Age, DailyRate, DistanceFromHome, Education, EmployeeCount, Employ...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

#Clean Data

skimr::skim(data)
Data summary
Name data
Number of rows 1470
Number of columns 35
_______________________
Column type frequency:
character 9
numeric 26
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
Attrition 0 1 2 3 0 2 0
BusinessTravel 0 1 10 17 0 3 0
Department 0 1 5 22 0 3 0
EducationField 0 1 5 16 0 6 0
Gender 0 1 4 6 0 2 0
JobRole 0 1 7 25 0 9 0
MaritalStatus 0 1 6 8 0 3 0
Over18 0 1 1 1 0 1 0
OverTime 0 1 2 3 0 2 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
Age 0 1 36.92 9.14 18 30.00 36.0 43.00 60 ▂▇▇▃▂
DailyRate 0 1 802.49 403.51 102 465.00 802.0 1157.00 1499 ▇▇▇▇▇
DistanceFromHome 0 1 9.19 8.11 1 2.00 7.0 14.00 29 ▇▅▂▂▂
Education 0 1 2.91 1.02 1 2.00 3.0 4.00 5 ▂▃▇▆▁
EmployeeCount 0 1 1.00 0.00 1 1.00 1.0 1.00 1 ▁▁▇▁▁
EmployeeNumber 0 1 1024.87 602.02 1 491.25 1020.5 1555.75 2068 ▇▇▇▇▇
EnvironmentSatisfaction 0 1 2.72 1.09 1 2.00 3.0 4.00 4 ▅▅▁▇▇
HourlyRate 0 1 65.89 20.33 30 48.00 66.0 83.75 100 ▇▇▇▇▇
JobInvolvement 0 1 2.73 0.71 1 2.00 3.0 3.00 4 ▁▃▁▇▁
JobLevel 0 1 2.06 1.11 1 1.00 2.0 3.00 5 ▇▇▃▂▁
JobSatisfaction 0 1 2.73 1.10 1 2.00 3.0 4.00 4 ▅▅▁▇▇
MonthlyIncome 0 1 6502.93 4707.96 1009 2911.00 4919.0 8379.00 19999 ▇▅▂▁▂
MonthlyRate 0 1 14313.10 7117.79 2094 8047.00 14235.5 20461.50 26999 ▇▇▇▇▇
NumCompaniesWorked 0 1 2.69 2.50 0 1.00 2.0 4.00 9 ▇▃▂▂▁
PercentSalaryHike 0 1 15.21 3.66 11 12.00 14.0 18.00 25 ▇▅▃▂▁
PerformanceRating 0 1 3.15 0.36 3 3.00 3.0 3.00 4 ▇▁▁▁▂
RelationshipSatisfaction 0 1 2.71 1.08 1 2.00 3.0 4.00 4 ▅▅▁▇▇
StandardHours 0 1 80.00 0.00 80 80.00 80.0 80.00 80 ▁▁▇▁▁
StockOptionLevel 0 1 0.79 0.85 0 0.00 1.0 1.00 3 ▇▇▁▂▁
TotalWorkingYears 0 1 11.28 7.78 0 6.00 10.0 15.00 40 ▇▇▂▁▁
TrainingTimesLastYear 0 1 2.80 1.29 0 2.00 3.0 3.00 6 ▂▇▇▂▃
WorkLifeBalance 0 1 2.76 0.71 1 2.00 3.0 3.00 4 ▁▃▁▇▂
YearsAtCompany 0 1 7.01 6.13 0 3.00 5.0 9.00 40 ▇▂▁▁▁
YearsInCurrentRole 0 1 4.23 3.62 0 2.00 3.0 7.00 18 ▇▃▂▁▁
YearsSinceLastPromotion 0 1 2.19 3.22 0 0.00 1.0 3.00 15 ▇▁▁▁▁
YearsWithCurrManager 0 1 4.12 3.57 0 2.00 3.0 7.00 17 ▇▂▅▁▁ 
factors_vec <- data %>% select(Education,EnvironmentSatisfaction, JobInvolvement, JobSatisfaction, PerformanceRating, RelationshipSatisfaction, WorkLifeBalance) %>% names()

data_clean <- data %>%
  
  # Address factors imported as numeric
  mutate(across(all_of(factors_vec), as.factor)) %>%
  
  # Drop zero-variance variables
  select(-c(Over18,EmployeeCount, StandardHours)) %>%
  
  # Recode Attrition
  mutate(Attrition = if_else(Attrition == "Yes", "Left", Attrition))

#Explore Data

data_clean %>% count(Attrition)
## # A tibble: 2 × 2
##   Attrition     n
##   <chr>     <int>
## 1 Left        237
## 2 No         1233
data_clean %>%
  ggplot(aes(Attrition))+
  geom_bar()

Attrition vs. Monthly Income

data_clean %>%
  ggplot(aes(Attrition, MonthlyIncome)) +
  geom_boxplot()

Correlation Plot

# Step 1: Binarize the data
data_binarized <- data_clean %>%
  select(-EmployeeNumber) %>%
  binarize()

data_binarized %>% glimpse()
## Rows: 1,470
## Columns: 120
## $ `Age__-Inf_30`                       <dbl> 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, …
## $ Age__30_36                           <dbl> 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, …
## $ Age__36_43                           <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ Age__43_Inf                          <dbl> 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ Attrition__Left                      <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ Attrition__No                        <dbl> 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ `BusinessTravel__Non-Travel`         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ BusinessTravel__Travel_Frequently    <dbl> 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, …
## $ BusinessTravel__Travel_Rarely        <dbl> 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, …
## $ `DailyRate__-Inf_465`                <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ DailyRate__465_802                   <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, …
## $ DailyRate__802_1157                  <dbl> 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, …
## $ DailyRate__1157_Inf                  <dbl> 0, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, …
## $ Department__Human_Resources          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `Department__Research_&_Development` <dbl> 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ Department__Sales                    <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `DistanceFromHome__-Inf_2`           <dbl> 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, …
## $ DistanceFromHome__2_7                <dbl> 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, …
## $ DistanceFromHome__7_14               <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ DistanceFromHome__14_Inf             <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, …
## $ Education__1                         <dbl> 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, …
## $ Education__2                         <dbl> 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, …
## $ Education__3                         <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, …
## $ Education__4                         <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ Education__5                         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField__Human_Resources      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField__Life_Sciences        <dbl> 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, …
## $ EducationField__Marketing            <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField__Medical              <dbl> 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 1, …
## $ EducationField__Other                <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField__Technical_Degree     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EnvironmentSatisfaction__1           <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, …
## $ EnvironmentSatisfaction__2           <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EnvironmentSatisfaction__3           <dbl> 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, …
## $ EnvironmentSatisfaction__4           <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, …
## $ Gender__Female                       <dbl> 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, …
## $ Gender__Male                         <dbl> 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, …
## $ `HourlyRate__-Inf_48`                <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, …
## $ HourlyRate__48_66                    <dbl> 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ HourlyRate__66_83.75                 <dbl> 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, …
## $ HourlyRate__83.75_Inf                <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, …
## $ JobInvolvement__1                    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobInvolvement__2                    <dbl> 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ JobInvolvement__3                    <dbl> 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, …
## $ JobInvolvement__4                    <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, …
## $ JobLevel__1                          <dbl> 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, …
## $ JobLevel__2                          <dbl> 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ JobLevel__3                          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ JobLevel__4                          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobLevel__5                          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Healthcare_Representative   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ JobRole__Human_Resources             <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Laboratory_Technician       <dbl> 0, 0, 1, 0, 1, 1, 1, 1, 0, 0, 1, …
## $ JobRole__Manager                     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Manufacturing_Director      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ JobRole__Research_Director           <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Research_Scientist          <dbl> 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Sales_Executive             <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Sales_Representative        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobSatisfaction__1                   <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ JobSatisfaction__2                   <dbl> 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, …
## $ JobSatisfaction__3                   <dbl> 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 0, …
## $ JobSatisfaction__4                   <dbl> 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, …
## $ MaritalStatus__Divorced              <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, …
## $ MaritalStatus__Married               <dbl> 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, …
## $ MaritalStatus__Single                <dbl> 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, …
## $ `MonthlyIncome__-Inf_2911`           <dbl> 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, …
## $ MonthlyIncome__2911_4919             <dbl> 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, …
## $ MonthlyIncome__4919_8379             <dbl> 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ MonthlyIncome__8379_Inf              <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ `MonthlyRate__-Inf_8047`             <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ MonthlyRate__8047_14235.5            <dbl> 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, …
## $ MonthlyRate__14235.5_20461.5         <dbl> 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, …
## $ MonthlyRate__20461.5_Inf             <dbl> 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ `NumCompaniesWorked__-Inf_1`         <dbl> 0, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, …
## $ NumCompaniesWorked__1_2              <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ NumCompaniesWorked__2_4              <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ NumCompaniesWorked__4_Inf            <dbl> 1, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, …
## $ OverTime__No                         <dbl> 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, …
## $ OverTime__Yes                        <dbl> 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, …
## $ `PercentSalaryHike__-Inf_12`         <dbl> 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, …
## $ PercentSalaryHike__12_14             <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, …
## $ PercentSalaryHike__14_18             <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ PercentSalaryHike__18_Inf            <dbl> 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, …
## $ PerformanceRating__3                 <dbl> 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, …
## $ PerformanceRating__4                 <dbl> 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, …
## $ RelationshipSatisfaction__1          <dbl> 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ RelationshipSatisfaction__2          <dbl> 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, …
## $ RelationshipSatisfaction__3          <dbl> 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, …
## $ RelationshipSatisfaction__4          <dbl> 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, …
## $ StockOptionLevel__0                  <dbl> 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0, …
## $ StockOptionLevel__1                  <dbl> 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, …
## $ StockOptionLevel__2                  <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ StockOptionLevel__3                  <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ `TotalWorkingYears__-Inf_6`          <dbl> 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, …
## $ TotalWorkingYears__6_10              <dbl> 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 0, …
## $ TotalWorkingYears__10_15             <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ TotalWorkingYears__15_Inf            <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ `TrainingTimesLastYear__-Inf_2`      <dbl> 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, …
## $ TrainingTimesLastYear__2_3           <dbl> 0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, …
## $ TrainingTimesLastYear__3_Inf         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, …
## $ WorkLifeBalance__1                   <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ WorkLifeBalance__2                   <dbl> 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, …
## $ WorkLifeBalance__3                   <dbl> 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, …
## $ WorkLifeBalance__4                   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `YearsAtCompany__-Inf_3`             <dbl> 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, …
## $ YearsAtCompany__3_5                  <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, …
## $ YearsAtCompany__5_9                  <dbl> 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, …
## $ YearsAtCompany__9_Inf                <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `YearsInCurrentRole__-Inf_2`         <dbl> 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, …
## $ YearsInCurrentRole__2_3              <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ YearsInCurrentRole__3_7              <dbl> 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, …
## $ YearsInCurrentRole__7_Inf            <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `YearsSinceLastPromotion__-Inf_1`    <dbl> 1, 1, 1, 0, 0, 0, 1, 1, 1, 0, 1, …
## $ YearsSinceLastPromotion__1_3         <dbl> 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, …
## $ YearsSinceLastPromotion__3_Inf       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ `YearsWithCurrManager__-Inf_2`       <dbl> 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, …
## $ YearsWithCurrManager__2_3            <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, …
## $ YearsWithCurrManager__3_7            <dbl> 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, …
## $ YearsWithCurrManager__7_Inf          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
# Step 2: Correlation
data_correlation <- data_binarized %>%
  correlate(Attrition__Left)

#Step #3: Plot
data_correlation %>%
  correlationfunnel::plot_correlation_funnel()
## Warning: ggrepel: 73 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

#Model Building

##Split data

set.seed(1234)

#data_clean <- data_clean %>% sample_n(100)
data_clean <- data_clean %>% group_by(Attrition) %>% sample_n(237)


data_split <- initial_split(data_clean, strata = Attrition)
data_train<- training(data_split)
data_test <- testing(data_split)

data_cv <- rsample::vfold_cv(data_train, strata = Attrition)

##Preprocess Data

xgboost_recipe <- recipes::recipe(Attrition ~ ., data = data_train) %>%
  update_role(EmployeeNumber, new_role = "ID") %>%
  step_dummy(all_nominal_predictors()) %>%
  step_smote(Attrition)
  

xgboost_recipe %>% prep() %>% juice() %>% glimpse()
## Rows: 354
## Columns: 59
## $ Age                               <dbl> 19, 20, 19, 58, 25, 31, 33, 35, 21, …
## $ DailyRate                         <dbl> 303, 1362, 504, 781, 1219, 330, 827,…
## $ DistanceFromHome                  <dbl> 2, 10, 10, 2, 4, 22, 29, 25, 18, 10,…
## $ EmployeeNumber                    <dbl> 243, 701, 1248, 918, 1106, 1389, 110…
## $ HourlyRate                        <dbl> 47, 32, 96, 57, 32, 98, 54, 96, 65, …
## $ JobLevel                          <dbl> 1, 1, 1, 1, 1, 2, 2, 1, 1, 2, 1, 1, …
## $ MonthlyIncome                     <dbl> 1102, 1009, 1859, 2380, 3691, 6179, …
## $ MonthlyRate                       <dbl> 9241, 26999, 6148, 13384, 4605, 2105…
## $ NumCompaniesWorked                <dbl> 1, 1, 1, 9, 1, 1, 1, 1, 1, 1, 1, 5, …
## $ PercentSalaryHike                 <dbl> 22, 11, 25, 14, 15, 15, 22, 19, 19, …
## $ StockOptionLevel                  <dbl> 0, 0, 0, 1, 1, 2, 0, 1, 0, 0, 2, 0, …
## $ TotalWorkingYears                 <dbl> 1, 1, 1, 3, 7, 10, 14, 10, 1, 10, 1,…
## $ TrainingTimesLastYear             <dbl> 3, 5, 2, 3, 3, 3, 4, 3, 3, 4, 2, 3, …
## $ YearsAtCompany                    <dbl> 1, 1, 1, 1, 7, 10, 13, 10, 1, 10, 0,…
## $ YearsInCurrentRole                <dbl> 0, 0, 1, 0, 7, 2, 7, 2, 0, 3, 0, 2, …
## $ YearsSinceLastPromotion           <dbl> 1, 1, 0, 0, 5, 6, 3, 7, 0, 0, 0, 1, …
## $ YearsWithCurrManager              <dbl> 0, 1, 0, 0, 6, 7, 8, 8, 0, 8, 0, 2, …
## $ Attrition                         <fct> Left, Left, Left, Left, Left, Left, …
## $ BusinessTravel_Travel_Frequently  <dbl> 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 1, …
## $ BusinessTravel_Travel_Rarely      <dbl> 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, …
## $ Department_Research...Development <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ Department_Sales                  <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ Education_X2                      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ Education_X3                      <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ Education_X4                      <dbl> 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, …
## $ Education_X5                      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField_Life.Sciences      <dbl> 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, …
## $ EducationField_Marketing          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField_Medical            <dbl> 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0, …
## $ EducationField_Other              <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, …
## $ EducationField_Technical.Degree   <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, …
## $ EnvironmentSatisfaction_X2        <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EnvironmentSatisfaction_X3        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, …
## $ EnvironmentSatisfaction_X4        <dbl> 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 0, …
## $ Gender_Male                       <dbl> 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, …
## $ JobInvolvement_X2                 <dbl> 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1, …
## $ JobInvolvement_X3                 <dbl> 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, …
## $ JobInvolvement_X4                 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ JobRole_Human.Resources           <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole_Laboratory.Technician     <dbl> 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, …
## $ JobRole_Manager                   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole_Manufacturing.Director    <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, …
## $ JobRole_Research.Director         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole_Research.Scientist        <dbl> 0, 1, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, …
## $ JobRole_Sales.Executive           <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole_Sales.Representative      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobSatisfaction_X2                <dbl> 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ JobSatisfaction_X3                <dbl> 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, …
## $ JobSatisfaction_X4                <dbl> 1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, …
## $ MaritalStatus_Married             <dbl> 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, …
## $ MaritalStatus_Single              <dbl> 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, …
## $ OverTime_Yes                      <dbl> 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, …
## $ PerformanceRating_X4              <dbl> 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, …
## $ RelationshipSatisfaction_X2       <dbl> 0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, …
## $ RelationshipSatisfaction_X3       <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, …
## $ RelationshipSatisfaction_X4       <dbl> 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, …
## $ WorkLifeBalance_X2                <dbl> 1, 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, …
## $ WorkLifeBalance_X3                <dbl> 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, …
## $ WorkLifeBalance_X4                <dbl> 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, …

##Specify Model

usemodels::use_xgboost(Attrition ~., data = data_train)
## Adding missing grouping variables: `Attrition`
## xgboost_recipe <- 
##   recipe(formula = Attrition ~ ., data = data_train) %>% 
##   step_string2factor(one_of(NA_character_)) %>% 
##   step_zv(all_predictors()) 
## 
## xgboost_spec <- 
##   boost_tree(trees = tune(), min_n = tune(), tree_depth = tune(), learn_rate = tune(), 
##     loss_reduction = tune(), sample_size = tune()) %>% 
##   set_mode("classification") %>% 
##   set_engine("xgboost") 
## 
## xgboost_workflow <- 
##   workflow() %>% 
##   add_recipe(xgboost_recipe) %>% 
##   add_model(xgboost_spec) 
## 
## set.seed(19609)
## xgboost_tune <-
##   tune_grid(xgboost_workflow, resamples = stop("add your rsample object"), grid = stop("add number of candidate points"))
xgboost_spec <- 
  boost_tree(trees = tune()) %>% 
  set_mode("classification") %>% 
  set_engine("xgboost") 

xgboost_workflow <- 
  workflow() %>% 
  add_recipe(xgboost_recipe) %>% 
  add_model(xgboost_spec)

##Tune Hyperparameters

doParallel::registerDoParallel()

set.seed(47927)
xgboost_tune <-
  tune_grid(xgboost_workflow,
            resamples = data_cv, grid = 5,
              control = control_grid(save_pred = TRUE ))
## Warning: ! tune detected a parallel backend registered with foreach but no backend
##   registered with future.
## ℹ Support for parallel processing with foreach was soft-deprecated in tune
##   1.2.1.
## ℹ See ?parallelism (`?tune::parallelism()`) to learn more.

#Model Evaluation

Identify Optimal values for hyperparameters

collect_metrics(xgboost_tune)
## # A tibble: 15 × 7
##    trees .metric     .estimator  mean     n std_err .config             
##    <int> <chr>       <chr>      <dbl> <int>   <dbl> <chr>               
##  1    23 accuracy    binary     0.670    10  0.0262 Preprocessor1_Model1
##  2    23 brier_class binary     0.212    10  0.0182 Preprocessor1_Model1
##  3    23 roc_auc     binary     0.757    10  0.0327 Preprocessor1_Model1
##  4   498 accuracy    binary     0.678    10  0.0338 Preprocessor1_Model2
##  5   498 brier_class binary     0.247    10  0.0261 Preprocessor1_Model2
##  6   498 roc_auc     binary     0.754    10  0.0379 Preprocessor1_Model2
##  7   983 accuracy    binary     0.675    10  0.0360 Preprocessor1_Model3
##  8   983 brier_class binary     0.248    10  0.0266 Preprocessor1_Model3
##  9   983 roc_auc     binary     0.751    10  0.0392 Preprocessor1_Model3
## 10  1490 accuracy    binary     0.678    10  0.0327 Preprocessor1_Model4
## 11  1490 brier_class binary     0.249    10  0.0265 Preprocessor1_Model4
## 12  1490 roc_auc     binary     0.749    10  0.0388 Preprocessor1_Model4
## 13  1985 accuracy    binary     0.687    10  0.0338 Preprocessor1_Model5
## 14  1985 brier_class binary     0.250    10  0.0265 Preprocessor1_Model5
## 15  1985 roc_auc     binary     0.749    10  0.0385 Preprocessor1_Model5
collect_predictions(xgboost_tune) %>%
  group_by(id)%>%
  roc_curve(Attrition, .pred_Left) %>%
  autoplot()

Fit the model for the lat time

xgboost_last <- xgboost_workflow %>%
  finalize_workflow(select_best(xgboost_tune, metric = "accuracy")) %>%
  last_fit(data_split)
## Warning: package 'xgboost' was built under R version 4.4.3
collect_metrics(xgboost_last)
## # A tibble: 3 × 4
##   .metric     .estimator .estimate .config             
##   <chr>       <chr>          <dbl> <chr>               
## 1 accuracy    binary         0.692 Preprocessor1_Model1
## 2 roc_auc     binary         0.748 Preprocessor1_Model1
## 3 brier_class binary         0.256 Preprocessor1_Model1
collect_predictions(xgboost_last) %>% yardstick::conf_mat(Attrition, .pred_class) %>%
  autoplot()

Variable importance

library(vip)
## Warning: package 'vip' was built under R version 4.4.3
## 
## Attaching package: 'vip'
## The following object is masked from 'package:utils':
## 
##     vi
xgboost_last %>%
  workflows::extract_fit_engine() %>%
  vip()