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

Import Data

library(tidyverse)
## Warning: package 'ggplot2' was built under R version 4.3.3
## ── 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 1.9.3     ✔ 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 4.3.3
## ══ correlationfunnel Tip #3 ════════════════════════════════════════════════════
## Using `binarize()` with data containing many columns or many rows can increase dimensionality substantially.
## Try subsetting your data column-wise or row-wise to avoid creating too many columns.
## You can always make a big problem smaller by 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 ▇▂▅▁▁ 
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

# 1
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, …
# 2
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
# 3
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 4.3.3
## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom        1.0.5     ✔ 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    1.3.1
## ✔ recipes      1.1.0
## Warning: package 'dials' was built under R version 4.3.3
## Warning: package 'infer' was built under R version 4.3.3
## Warning: package 'modeldata' was built under R version 4.3.3
## Warning: package 'parsnip' was built under R version 4.3.3
## Warning: package 'recipes' was built under R version 4.3.3
## Warning: package 'rsample' was built under R version 4.3.3
## Warning: package 'tune' was built under R version 4.3.3
## Warning: package 'workflows' was built under R version 4.3.3
## Warning: package 'workflowsets' was built under R version 4.3.3
## Warning: package 'yardstick' 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()
## • Dig deeper into tidy modeling with R at https://www.tmwr.org
set.seed(1111)
#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)

preprocess data

library(themis)
## Warning: package 'themis' was built under R version 4.3.3
xgboost_recipe <- 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) %>%
    step_pca(all_numeric_predictors(), threshold = .99)
    
    

xgboost_recipe %>% prep() %>% juice() %>% glimpse()
## Rows: 1,848
## Columns: 55
## $ EmployeeNumber <dbl> 1, 4, 27, 31, 42, 47, 55, 58, 64, 65, 90, 118, 133, 137…
## $ Attrition      <fct> Left, Left, Left, Left, Left, Left, Left, Left, Left, L…
## $ PC01           <dbl> -0.09115459, -3.01091545, -1.82718781, -1.95296906, -1.…
## $ PC02           <dbl> 2.6659129, -1.1732025, 2.1530702, -0.7958233, 2.6809205…
## $ PC03           <dbl> 1.9476825, 1.0667566, -2.3563917, 0.8033933, -0.9176034…
## $ PC04           <dbl> -1.43614444, -2.37589326, -1.04110509, -1.48355643, 3.7…
## $ PC05           <dbl> 0.14994005, 0.23903150, 1.19154731, -1.49899465, -2.420…
## $ PC06           <dbl> -0.5876572, -0.2885035, 1.4344067, -0.2761409, 0.527482…
## $ PC07           <dbl> 2.1191094, -0.2382491, -0.5327742, -0.6104317, -0.52569…
## $ PC08           <dbl> 0.2972151, 2.0564369, -2.5133998, -0.2647634, -2.273079…
## $ PC09           <dbl> 1.01418646, 2.95970286, 2.26103957, -1.87570930, 0.1032…
## $ PC10           <dbl> -0.50628212, -0.34407431, 1.00852500, -1.72722756, 0.30…
## $ PC11           <dbl> 0.466037111, 1.918849239, 2.107858575, 0.965202931, 1.8…
## $ PC12           <dbl> 0.99197058, 1.04991095, 1.79449662, 0.06331999, 1.40379…
## $ PC13           <dbl> -0.796088351, 0.670280577, 0.133483664, -1.386307832, 1…
## $ PC14           <dbl> 1.50935001, -1.45374279, -0.25176925, -0.07542391, 0.84…
## $ PC15           <dbl> 0.827910524, -1.400079062, -1.432869432, -0.041753976, …
## $ PC16           <dbl> -0.3909822, -1.3644214, -0.4770805, 1.2075698, -1.41154…
## $ PC17           <dbl> 0.8561303, -1.7582332, 1.3829126, 0.4213961, -2.7607880…
## $ PC18           <dbl> 0.508198848, -0.429485588, 1.848269729, 0.528529777, 0.…
## $ PC19           <dbl> 2.63061289, -1.01260554, -1.65894366, 0.87105480, 1.342…
## $ PC20           <dbl> -1.56772065, -1.55295301, 0.45018402, 0.13123341, -1.25…
## $ PC21           <dbl> 0.03836413, -1.83700438, -0.42343239, 0.38426570, -0.11…
## $ PC22           <dbl> 1.2630452, 0.3740535, 0.1383354, 1.4181666, -0.1925572,…
## $ PC23           <dbl> -2.3692806, -1.0340295, 1.5080427, -0.4068049, 1.025358…
## $ PC24           <dbl> -0.04784872, -0.58342554, 0.52085509, -0.27322593, -0.9…
## $ PC25           <dbl> -1.0622283, 2.1180206, 1.1471271, -0.7837534, 0.3366203…
## $ PC26           <dbl> 0.06948810, -1.12506638, 0.09552582, 1.55946571, 0.3842…
## $ PC27           <dbl> 0.74498129, -1.02062933, -0.75095773, -0.97271887, 1.03…
## $ PC28           <dbl> -0.29052891, -0.94573663, 0.90584713, -0.64439361, 0.15…
## $ PC29           <dbl> -1.49918805, 0.19753865, -1.51976893, 0.02620179, 0.013…
## $ PC30           <dbl> -0.49588904, -0.93257863, -1.28975722, -0.19147691, -0.…
## $ PC31           <dbl> -0.33325495, -1.48480890, 0.14950181, 0.49081834, 0.378…
## $ PC32           <dbl> -0.53544117, 0.10418746, -0.06478864, -0.10714866, 0.80…
## $ PC33           <dbl> 0.26207096, -0.60694345, 0.38067684, -0.58403105, 0.750…
## $ PC34           <dbl> 1.38387205, 0.99713471, 0.39919202, 0.08437083, -1.7855…
## $ PC35           <dbl> -0.57286318, -0.60730794, -0.41836842, -0.56317034, -0.…
## $ PC36           <dbl> 0.25072493, 1.16519683, 0.96620615, -0.00501983, 0.1997…
## $ PC37           <dbl> -0.63275390, -1.04269181, -1.74701299, -0.11244980, 1.1…
## $ PC38           <dbl> -0.154600597, -0.664239402, 0.667130224, -0.443361823, …
## $ PC39           <dbl> -0.11474170, 0.49069572, -0.37110718, 0.65373994, 0.145…
## $ PC40           <dbl> 0.96554350, 0.21894349, 0.12091525, -0.21531972, -0.332…
## $ PC41           <dbl> 0.05366607, 0.30248853, 0.61517741, -0.06392551, -0.994…
## $ PC42           <dbl> 0.07834455, 0.15474731, -0.36343843, -0.08343644, 0.193…
## $ PC43           <dbl> 0.912349194, -0.372936692, 0.768035924, 0.110763843, -0…
## $ PC44           <dbl> 0.04394786, -0.37153708, 0.13464689, 0.09693996, 0.6770…
## $ PC45           <dbl> -0.126143754, 0.186336729, -0.869482750, -0.529449051, …
## $ PC46           <dbl> -0.03128264, 0.37099287, 0.40621157, 0.52944619, -0.432…
## $ PC47           <dbl> 1.14048319, 0.30138229, -0.27803733, -0.26482913, 0.180…
## $ PC48           <dbl> 0.43537018, -0.24391924, -0.05612994, -0.03872075, 0.39…
## $ PC49           <dbl> -0.38645877, -0.09469250, 0.19339710, 0.25598934, 0.925…
## $ PC50           <dbl> 0.24942760, 0.31734958, -0.17042574, -0.30596634, -0.78…
## $ PC51           <dbl> 0.52000439, -0.14347906, 0.40178435, 0.35787268, -0.638…
## $ PC52           <dbl> 0.10878771, 0.03607990, 0.42173657, -0.93567679, 0.3829…
## $ PC53           <dbl> -0.909627840, 0.016538936, -0.020945448, 0.219749017, 0…

specify model

library(usemodels)
## Warning: package 'usemodels' was built under R version 4.3.3
usemodels::use_xgboost(Attrition ~., data = data_train)
## xgboost_recipe <- 
##   recipe(formula = Attrition ~ ., data = data_train) %>% 
##   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(39460)
## 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(), tree_depth = tune()) %>% 
  set_mode("classification") %>% 
  set_engine("xgboost") 

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

tune hyperparameters

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

doParallel::registerDoParallel()

set.seed(43658)
xgboost_tune <-
  tune_grid(xgboost_workflow, 
            resamples = data_cv,
            grid = 5,
            control = control_grid(save_pred = TRUE))

Model Evaluation

Identify optimal values 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  1394          1 accuracy    binary     0.839    10 0.00672 Preprocessor1_Mo…
##  2  1394          1 brier_class binary     0.132    10 0.00594 Preprocessor1_Mo…
##  3  1394          1 roc_auc     binary     0.762    10 0.0287  Preprocessor1_Mo…
##  4   429          5 accuracy    binary     0.857    10 0.00892 Preprocessor1_Mo…
##  5   429          5 brier_class binary     0.125    10 0.00719 Preprocessor1_Mo…
##  6   429          5 roc_auc     binary     0.773    10 0.0268  Preprocessor1_Mo…
##  7   916          8 accuracy    binary     0.853    10 0.00547 Preprocessor1_Mo…
##  8   916          8 brier_class binary     0.125    10 0.00731 Preprocessor1_Mo…
##  9   916          8 roc_auc     binary     0.772    10 0.0257  Preprocessor1_Mo…
## 10   139         10 accuracy    binary     0.854    10 0.00770 Preprocessor1_Mo…
## 11   139         10 brier_class binary     0.121    10 0.00565 Preprocessor1_Mo…
## 12   139         10 roc_auc     binary     0.763    10 0.0290  Preprocessor1_Mo…
## 13  1942         15 accuracy    binary     0.846    10 0.00876 Preprocessor1_Mo…
## 14  1942         15 brier_class binary     0.129    10 0.00667 Preprocessor1_Mo…
## 15  1942         15 roc_auc     binary     0.776    10 0.0237  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 4.3.3
collect_metrics(xgboost_last)
## # A tibble: 3 × 4
##   .metric     .estimator .estimate .config             
##   <chr>       <chr>          <dbl> <chr>               
## 1 accuracy    binary         0.851 Preprocessor1_Model1
## 2 roc_auc     binary         0.800 Preprocessor1_Model1
## 3 brier_class binary         0.120 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 4.3.3
## 
## Attaching package: 'vip'
## The following object is masked from 'package:utils':
## 
##     vi
xgboost_last %>%
    workflows::extract_fit_engine() %>%
    vip()

Conclusion

The previous model, accuracy was 0.851 and AUC of 0.753.