Goal: Predict attrition; employees who are likely to leave the company

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   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── 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)
## ══ correlationfunnel Tip #1 ════════════════════════════════════════════════════
## Make sure your data is not overly imbalanced prior to using `correlate()`.
## If less than 5% imbalance, consider sampling. :)
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.

Explore 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 ▇▂▅▁▁

Issues with data:

factors_vec <- data %>% select(Education, EnvironmentSatisfaction, JobInvolvement, JobSatisfaction, PerformanceRating, RelationshipSatisfaction, WorkLifeBalance, JobLevel, StockOptionLevel) %>% 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
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)

data_correlation
## # A tibble: 120 × 3
##    feature           bin       correlation
##    <fct>             <chr>           <dbl>
##  1 Attrition         Left            1    
##  2 Attrition         No             -1    
##  3 OverTime          Yes             0.246
##  4 OverTime          No             -0.246
##  5 JobLevel          1               0.213
##  6 MonthlyIncome     -Inf_2911       0.207
##  7 StockOptionLevel  0               0.195
##  8 YearsAtCompany    -Inf_3          0.183
##  9 MaritalStatus     Single          0.175
## 10 TotalWorkingYears -Inf_6          0.169
## # ℹ 110 more rows
# Step 3: Plot
data_correlation %>% 
    correlationfunnel::plot_correlation_funnel()
## Warning: ggrepel: 72 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

Model Building

Splitting Data

library(tidymodels)
## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom        1.0.5      ✔ rsample      1.2.1 
## ✔ dials        1.2.1      ✔ tune         1.2.1 
## ✔ infer        1.0.7      ✔ workflows    1.1.4 
## ✔ modeldata    1.4.0      ✔ workflowsets 1.1.0 
## ✔ parsnip      1.2.1      ✔ yardstick    1.3.1 
## ✔ recipes      1.0.10
## Warning: package 'modeldata' was built under R version 4.3.3
## ── 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()
## • Search for functions across packages at https://www.tidymodels.org/find/
data_clean <- data_clean %>% sample_n(100)

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)
data_cv
## #  10-fold cross-validation using stratification 
## # A tibble: 10 × 2
##    splits         id    
##    <list>         <chr> 
##  1 <split [66/9]> Fold01
##  2 <split [66/9]> Fold02
##  3 <split [67/8]> Fold03
##  4 <split [68/7]> Fold04
##  5 <split [68/7]> Fold05
##  6 <split [68/7]> Fold06
##  7 <split [68/7]> Fold07
##  8 <split [68/7]> Fold08
##  9 <split [68/7]> Fold09
## 10 <split [68/7]> Fold10

Preprocessing Data

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

xgboost_rec %>% prep() %>% juice() %>% glimpse()
## Warning: !  The following column has zero variance so scaling cannot be used:
##   StockOptionLevel_X3.
## ℹ Consider using ?step_zv (`?recipes::step_zv()`) to remove those columns
##   before normalizing.
## Rows: 126
## Columns: 63
## $ Age                               <dbl> -1.30177339, 0.12593083, -1.08212658…
## $ DailyRate                         <dbl> 1.2786856, 0.1195438, -0.2448833, -1…
## $ DistanceFromHome                  <dbl> -0.4734215, -0.4734215, -0.9421556, …
## $ EmployeeNumber                    <dbl> 65, 1210, 1562, 1797, 1038, 142, 291…
## $ HourlyRate                        <dbl> -0.81131755, 1.53102354, -0.08258921…
## $ MonthlyIncome                     <dbl> -0.82234888, -1.08685772, 0.42147720…
## $ MonthlyRate                       <dbl> -0.46984119, 0.69262355, -1.21675731…
## $ NumCompaniesWorked                <dbl> -0.6531973, 1.3880442, -0.6531973, -…
## $ PercentSalaryHike                 <dbl> -0.6395776, 0.4263851, -1.1725589, 0…
## $ TotalWorkingYears                 <dbl> -1.3705887, -0.9963382, -0.3725872, …
## $ TrainingTimesLastYear             <dbl> 0.3234838, -0.6096426, 1.2566102, -0…
## $ YearsAtCompany                    <dbl> -0.96431189, -1.12051792, 0.28533635…
## $ YearsInCurrentRole                <dbl> -0.7738435, -1.2476253, 0.6475017, 0…
## $ YearsSinceLastPromotion           <dbl> -0.2009070, -0.8705971, 1.1384732, 1…
## $ YearsWithCurrManager              <dbl> -0.75482152, -1.29655945, 0.59952331…
## $ Attrition                         <fct> Left, Left, Left, Left, Left, Left, …
## $ BusinessTravel_Travel_Frequently  <dbl> -0.411805, -0.411805, -0.411805, -0.…
## $ BusinessTravel_Travel_Rarely      <dbl> 0.5785861, -1.7053065, 0.5785861, 0.…
## $ Department_Research...Development <dbl> 0.7449832, 0.7449832, -1.3244146, -1…
## $ Department_Sales                  <dbl> -0.7023769, -0.7023769, 1.4047538, 1…
## $ Education_X2                      <dbl> -0.3668044, 2.6898988, -0.3668044, -…
## $ Education_X3                      <dbl> -0.8804761, -0.8804761, 1.1206059, 1…
## $ Education_X4                      <dbl> 1.4479871, -0.6814057, -0.6814057, -…
## $ Education_X5                      <dbl> -0.164414, -0.164414, -0.164414, -0.…
## $ EducationField_Life.Sciences      <dbl> -0.6399686, 1.5417424, 1.5417424, 1.…
## $ EducationField_Marketing          <dbl> -0.3896086, -0.3896086, -0.3896086, …
## $ EducationField_Medical            <dbl> -0.6194382, -0.6194382, -0.6194382, …
## $ EducationField_Other              <dbl> -0.2929114, -0.2929114, -0.2929114, …
## $ EducationField_Technical.Degree   <dbl> 1.9866219, -0.4966555, -0.4966555, -…
## $ EnvironmentSatisfaction_X2        <dbl> -0.5172723, -0.5172723, 1.9074416, -…
## $ EnvironmentSatisfaction_X3        <dbl> 1.4935611, -0.6606135, -0.6606135, 1…
## $ EnvironmentSatisfaction_X4        <dbl> -0.6606135, -0.6606135, -0.6606135, …
## $ Gender_Male                       <dbl> 0.7886881, 0.7886881, 0.7886881, 0.7…
## $ JobInvolvement_X2                 <dbl> -0.6606135, 1.4935611, 1.4935611, -0…
## $ JobInvolvement_X3                 <dbl> 0.9045504, -1.0907813, -1.0907813, 0…
## $ JobInvolvement_X4                 <dbl> -0.3186983, -0.3186983, -0.3186983, …
## $ JobLevel_X2                       <dbl> -0.7235589, -0.7235589, 1.3636301, 1…
## $ JobLevel_X3                       <dbl> -0.4758656, -0.4758656, -0.4758656, …
## $ JobLevel_X4                       <dbl> -0.343236, -0.343236, -0.343236, -0.…
## $ JobLevel_X5                       <dbl> -0.2357686, -0.2357686, -0.2357686, …
## $ JobRole_Human.Resources           <dbl> -0.1154701, -0.1154701, -0.1154701, …
## $ JobRole_Laboratory.Technician     <dbl> 2.395956, -0.411805, -0.411805, -0.4…
## $ JobRole_Manager                   <dbl> -0.3896086, -0.3896086, -0.3896086, …
## $ JobRole_Manufacturing.Director    <dbl> -0.2654735, -0.2654735, -0.2654735, …
## $ JobRole_Research.Director         <dbl> -0.2654735, -0.2654735, -0.2654735, …
## $ JobRole_Research.Scientist        <dbl> -0.5377689, 1.8347410, -0.5377689, -…
## $ JobRole_Sales.Executive           <dbl> -0.598989, -0.598989, 1.647220, 1.64…
## $ JobSatisfaction_X2                <dbl> -0.4758656, -0.4758656, -0.4758656, …
## $ JobSatisfaction_X3                <dbl> 1.7053065, -0.5785861, -0.5785861, -…
## $ JobSatisfaction_X4                <dbl> -0.6814057, -0.6814057, -0.6814057, …
## $ MaritalStatus_Married             <dbl> -1.0066446, -1.0066446, 0.9801539, -…
## $ MaritalStatus_Single              <dbl> 1.4479871, -0.6814057, -0.6814057, 1…
## $ OverTime_Yes                      <dbl> 1.9074416, -0.5172723, -0.5172723, 1…
## $ PerformanceRating_X4              <dbl> -0.3668044, -0.3668044, -0.3668044, …
## $ RelationshipSatisfaction_X2       <dbl> -0.4758656, -0.4758656, -0.4758656, …
## $ RelationshipSatisfaction_X3       <dbl> 1.3244146, -0.7449832, -0.7449832, -…
## $ RelationshipSatisfaction_X4       <dbl> -0.598989, -0.598989, 1.647220, 1.64…
## $ StockOptionLevel_X1               <dbl> -1.0338708, 0.9543423, 0.9543423, -1…
## $ StockOptionLevel_X2               <dbl> -0.2654735, -0.2654735, -0.2654735, …
## $ StockOptionLevel_X3               <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ WorkLifeBalance_X2                <dbl> 1.9866219, -0.4966555, -0.4966555, -…
## $ WorkLifeBalance_X3                <dbl> -1.216553, -1.216553, 0.811035, 0.81…
## $ WorkLifeBalance_X4                <dbl> -0.3186983, -0.3186983, -0.3186983, …

Specify Model

xgboost_spec <- 
  boost_tree(trees = tune(), tree_depth = tune()) %>% 
  set_mode("classification") %>% 
  set_engine("xgboost") 

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

Tune Hyperparameters

doParallel::registerDoParallel()

set.seed(11448)
xgboost_tune <-
  tune_grid(xgboost_workflow,
            resamples = data_cv,
            grid = 5,
            control = control_grid(save_pred = TRUE))
## Warning: package 'xgboost' was built under R version 4.3.3

Model Evaluation

Identify optimal hyperparameters

collect_metrics(xgboost_tune)
## # A tibble: 15 × 8
##    trees tree_depth .metric     .estimator  mean     n std_err .config          
##    <int>      <int> <chr>       <chr>      <dbl> <int>   <dbl> <chr>            
##  1  1947          3 accuracy    binary     0.718    10  0.0534 Preprocessor1_Mo…
##  2  1947          3 brier_class binary     0.221    10  0.0372 Preprocessor1_Mo…
##  3  1947          3 roc_auc     binary     0.493    10  0.0979 Preprocessor1_Mo…
##  4  1086          5 accuracy    binary     0.746    10  0.0428 Preprocessor1_Mo…
##  5  1086          5 brier_class binary     0.209    10  0.0345 Preprocessor1_Mo…
##  6  1086          5 roc_auc     binary     0.540    10  0.102  Preprocessor1_Mo…
##  7   118          9 accuracy    binary     0.746    10  0.0428 Preprocessor1_Mo…
##  8   118          9 brier_class binary     0.204    10  0.0367 Preprocessor1_Mo…
##  9   118          9 roc_auc     binary     0.540    10  0.105  Preprocessor1_Mo…
## 10   624         10 accuracy    binary     0.746    10  0.0428 Preprocessor1_Mo…
## 11   624         10 brier_class binary     0.209    10  0.0346 Preprocessor1_Mo…
## 12   624         10 roc_auc     binary     0.540    10  0.102  Preprocessor1_Mo…
## 13  1363         13 accuracy    binary     0.746    10  0.0428 Preprocessor1_Mo…
## 14  1363         13 brier_class binary     0.209    10  0.0344 Preprocessor1_Mo…
## 15  1363         13 roc_auc     binary     0.540    10  0.102  Preprocessor1_Mo…
collect_predictions(xgboost_tune) %>%
    group_by(id) %>%
    roc_curve(Attrition, .pred_Left) %>% 
    autoplot()

Fit the model for the last time

xgboost_last <- xgboost_workflow %>%
    finalize_workflow(select_best(xgboost_tune, metric = "accuracy")) %>%
    last_fit(data_split)
## → A | warning: !  The following column has zero variance so scaling cannot be used:
##                  StockOptionLevel_X3.
##                ℹ Consider using ?step_zv (`?recipes::step_zv()`) to remove those columns
##                  before normalizing.
## 
There were issues with some computations   A: x1

There were issues with some computations   A: x1
collect_metrics(xgboost_last)
## # A tibble: 3 × 4
##   .metric     .estimator .estimate .config             
##   <chr>       <chr>          <dbl> <chr>               
## 1 accuracy    binary         0.76  Preprocessor1_Model1
## 2 roc_auc     binary         0.595 Preprocessor1_Model1
## 3 brier_class binary         0.174 Preprocessor1_Model1
collect_predictions(xgboost_last) %>%
    yardstick::conf_mat(Attrition, .pred_class) %>%
    autoplot()

Variable importance

library(vip)
## 
## Attaching package: 'vip'
## The following object is masked from 'package:utils':
## 
##     vi
xgboost_last %>%
    workflows::extract_fit_engine() %>%
    vip()

Conclusion

The previous model had an accuracy of 0.851 and an AUC of 0.753.