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

Import data

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)
## Warning: package 'correlationfunnel' was built under R version 4.4.2
## ══ correlationfunnel Tip #2 ════════════════════════════════════════════════════
## Clean your NA's prior to using `binarize()`.
## Missing values and cleaning data are critical to getting great correlations. :)
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

Missing values Factors or numeric variables Education, EnviornmentSatisfaction, JobInvolvement, PerformanceRating, RelationshipSatisfaction, Worklifebalance Zero variance variables Over 18, EmployeeCount, StandardHours Character variables: Convert them to numbers Unbalanced target variables: Attrition ID variable: EmployeeNumber

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

data_clean <- data %>%
    #Address factors imported as numeric 
    mutate(across(all_of(factors_vec), as.factor)) %>%

    # Drop zero-variable 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          No             -0.246
##  4 OverTime          Yes             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: 73 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

Model Building

Split Data

library(tidymodels)
## Warning: package 'tidymodels' was built under R version 4.4.2
## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom        1.0.6     ✔ rsample      1.2.1
## ✔ dials        1.3.0     ✔ 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    1.3.2
## ✔ recipes      1.1.0
## Warning: package 'dials' was built under R version 4.4.2
## Warning: package 'infer' was built under R version 4.4.2
## Warning: package 'modeldata' was built under R version 4.4.2
## Warning: package 'parsnip' was built under R version 4.4.2
## Warning: package 'tune' was built under R version 4.4.2
## Warning: package 'workflows' was built under R version 4.4.2
## Warning: package 'workflowsets' was built under R version 4.4.3
## Warning: package 'yardstick' was built under R version 4.4.2
## ── 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()
## • Use suppressPackageStartupMessages() to eliminate package startup messages
set.seed(1234)
data <- 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 [990/111]> Fold01
##  2 <split [990/111]> Fold02
##  3 <split [990/111]> Fold03
##  4 <split [990/111]> Fold04
##  5 <split [991/110]> Fold05
##  6 <split [991/110]> Fold06
##  7 <split [991/110]> Fold07
##  8 <split [992/109]> Fold08
##  9 <split [992/109]> Fold09
## 10 <split [992/109]> Fold10

Preprocess data

library(themis)
## Warning: package 'themis' was built under R version 4.4.3
data_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)

    
    data_rec %>% prep() %>% juice() %>% glimpse()
## Rows: 1,848
## Columns: 62
## $ Age                               <dbl> -0.9841381, -0.1045553, -0.3244510, …
## $ DailyRate                         <dbl> -1.7333405, 1.0374489, -0.2522728, 0…
## $ DistanceFromHome                  <dbl> 1.77013307, -0.04281252, -0.40540164…
## $ EmployeeNumber                    <dbl> 19, 27, 31, 33, 42, 47, 55, 58, 64, …
## $ HourlyRate                        <dbl> -0.7955162930, 0.7943430317, 0.84402…
## $ MonthlyIncome                     <dbl> -0.94942556, -0.65500781, -0.7504427…
## $ MonthlyRate                       <dbl> -0.17861854, -1.01597110, 0.40504190…
## $ NumCompaniesWorked                <dbl> 0.9389874, 1.7450889, -0.2701648, -0…
## $ PercentSalaryHike                 <dbl> -0.32630180, 2.13812237, -1.14777652…
## $ RelationshipSatisfaction          <dbl> -0.6544526, -0.6544526, 0.2789053, -…
## $ TotalWorkingYears                 <dbl> -0.67952021, -0.16488444, -0.4222023…
## $ TrainingTimesLastYear             <dbl> 0.9318008, 0.9318008, -0.6368730, 1.…
## $ YearsAtCompany                    <dbl> -0.4870091001, -0.3248690882, -0.487…
## $ YearsInCurrentRole                <dbl> -0.61452407, -0.33948708, -0.6145240…
## $ YearsSinceLastPromotion           <dbl> -0.67919910, -0.67919910, -0.3622011…
## $ YearsWithCurrManager              <dbl> -0.30817101, -0.30817101, -0.3081710…
## $ Attrition                         <fct> Left, Left, Left, Left, Left, Left, …
## $ BusinessTravel_Travel_Frequently  <dbl> -0.4781076, -0.4781076, -0.4781076, …
## $ BusinessTravel_Travel_Rarely      <dbl> 0.6285524, 0.6285524, 0.6285524, -1.…
## $ Department_Research...Development <dbl> 0.716921, -1.393587, 0.716921, 0.716…
## $ Department_Sales                  <dbl> -0.6525172, 1.5311346, -0.6525172, -…
## $ Education_X2                      <dbl> -0.4824015, -0.4824015, -0.4824015, …
## $ Education_X3                      <dbl> 1.2533961, -0.7971078, -0.7971078, -…
## $ Education_X4                      <dbl> -0.6159175, 1.6221194, -0.6159175, -…
## $ Education_X5                      <dbl> -0.1701342, -0.1701342, -0.1701342, …
## $ EducationField_Life.Sciences      <dbl> 1.2090320, 1.2090320, -0.8263567, 1.…
## $ EducationField_Marketing          <dbl> -0.3512225, -0.3512225, -0.3512225, …
## $ EducationField_Medical            <dbl> -0.6938248, -0.6938248, 1.4399771, -…
## $ EducationField_Other              <dbl> -0.2462489, -0.2462489, -0.2462489, …
## $ EducationField_Technical.Degree   <dbl> -0.3071606, -0.3071606, -0.3071606, …
## $ EnvironmentSatisfaction_X2        <dbl> -0.5037416, -0.5037416, 1.9833415, 1…
## $ EnvironmentSatisfaction_X3        <dbl> 1.5179630, 1.5179630, -0.6581793, -0…
## $ EnvironmentSatisfaction_X4        <dbl> -0.6638515, -0.6638515, -0.6638515, …
## $ Gender_Male                       <dbl> 0.8216966, 0.8216966, 0.8216966, -1.…
## $ JobInvolvement_X2                 <dbl> 1.7074832, 1.7074832, -0.5851254, -0…
## $ JobInvolvement_X3                 <dbl> -1.1977214, -1.1977214, 0.8341604, -…
## $ JobInvolvement_X4                 <dbl> -0.3245396, -0.3245396, -0.3245396, …
## $ JobLevel_X2                       <dbl> -0.7565295, -0.7565295, -0.7565295, …
## $ JobLevel_X3                       <dbl> -0.4136678, -0.4136678, -0.4136678, …
## $ JobLevel_X4                       <dbl> -0.2854091, -0.2854091, -0.2854091, …
## $ JobLevel_X5                       <dbl> -0.2110723, -0.2110723, -0.2110723, …
## $ JobRole_Human.Resources           <dbl> -0.1915458, -0.1915458, -0.1915458, …
## $ JobRole_Laboratory.Technician     <dbl> 2.1022910, -0.4752395, -0.4752395, -…
## $ JobRole_Manager                   <dbl> -0.2643999, -0.2643999, -0.2643999, …
## $ JobRole_Manufacturing.Director    <dbl> -0.3380364, -0.3380364, -0.3380364, …
## $ JobRole_Research.Director         <dbl> -0.2462489, -0.2462489, -0.2462489, …
## $ JobRole_Research.Scientist        <dbl> -0.4909619, -0.4909619, 2.0349681, 2…
## $ JobRole_Sales.Executive           <dbl> -0.5277239, -0.5277239, -0.5277239, …
## $ JobRole_Sales.Representative      <dbl> -0.2441691, 4.0918020, -0.2441691, -…
## $ JobSatisfaction_X2                <dbl> -0.4781076, -0.4781076, -0.4781076, …
## $ JobSatisfaction_X3                <dbl> 1.5017810, -0.6652713, -0.6652713, -…
## $ JobSatisfaction_X4                <dbl> -0.6581793, -0.6581793, -0.6581793, …
## $ MaritalStatus_Married             <dbl> -0.9116968, -0.9116968, -0.9116968, …
## $ MaritalStatus_Single              <dbl> 1.4459585, 1.4459585, 1.4459585, 1.4…
## $ OverTime_Yes                      <dbl> 1.618434, -0.617320, -0.617320, 1.61…
## $ PerformanceRating_X4              <dbl> -0.4345264, 2.2992657, -0.4345264, 2…
## $ StockOptionLevel_X1               <dbl> -0.8435871, -0.8435871, -0.8435871, …
## $ StockOptionLevel_X2               <dbl> -0.3463115, -0.3463115, -0.3463115, …
## $ StockOptionLevel_X3               <dbl> -0.2335554, -0.2335554, -0.2335554, …
## $ WorkLifeBalance_X2                <dbl> -0.5501667, -0.5501667, -0.5501667, …
## $ WorkLifeBalance_X3                <dbl> 0.7955852, 0.7955852, 0.7955852, 0.7…
## $ WorkLifeBalance_X4                <dbl> -0.3330138, -0.3330138, -0.3330138, …

Specify Model

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

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

Tune hyperpararmeters

tree_grid <- grid_regular(trees(),
                          tree_depth(),
                          levels = 5)

doParallel::registerDoParallel()

set.seed(27809)
xgboost_tune <-
  tune_grid(xgboost_workflow, 
            resamples = data_cv,
            grid = 5,
            control = control_grid(save_pred = TRUE))

Model evaluation

Identify optimal value for 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  1003         12 accuracy    binary     0.869    10 0.00934 Preprocessor1_Mo…
##  2  1003         12 brier_class binary     0.109    10 0.00773 Preprocessor1_Mo…
##  3  1003         12 roc_auc     binary     0.793    10 0.0237  Preprocessor1_Mo…
##  4  1889         12 accuracy    binary     0.872    10 0.00908 Preprocessor1_Mo…
##  5  1889         12 brier_class binary     0.111    10 0.00760 Preprocessor1_Mo…
##  6  1889         12 roc_auc     binary     0.791    10 0.0232  Preprocessor1_Mo…
##  7  1206          4 accuracy    binary     0.869    10 0.0106  Preprocessor1_Mo…
##  8  1206          4 brier_class binary     0.114    10 0.00797 Preprocessor1_Mo…
##  9  1206          4 roc_auc     binary     0.776    10 0.0249  Preprocessor1_Mo…
## 10   388          7 accuracy    binary     0.865    10 0.00920 Preprocessor1_Mo…
## 11   388          7 brier_class binary     0.111    10 0.00821 Preprocessor1_Mo…
## 12   388          7 roc_auc     binary     0.788    10 0.0223  Preprocessor1_Mo…
## 13   622          9 accuracy    binary     0.868    10 0.0111  Preprocessor1_Mo…
## 14   622          9 brier_class binary     0.112    10 0.00868 Preprocessor1_Mo…
## 15   622          9 roc_auc     binary     0.777    10 0.0239  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)
## Warning: package 'xgboost' was built under R version 4.4.2
collect_metrics(xgboost_last)
## # A tibble: 3 × 4
##   .metric     .estimator .estimate .config             
##   <chr>       <chr>          <dbl> <chr>               
## 1 accuracy    binary         0.859 Preprocessor1_Model1
## 2 roc_auc     binary         0.800 Preprocessor1_Model1
## 3 brier_class binary         0.121 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()

Conclusion

The previous model, accuracy of 0.851 and AUC of 0.753