Goal: to 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   3.5.0     ✔ 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. :)
library(tidymodels)
## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom        1.0.5      ✔ rsample      1.2.1 
## ✔ dials        1.2.1      ✔ tune         1.2.0 
## ✔ infer        1.0.7      ✔ workflows    1.1.4 
## ✔ modeldata    1.3.0      ✔ workflowsets 1.1.0 
## ✔ parsnip      1.2.1      ✔ yardstick    1.3.1 
## ✔ recipes      1.0.10     
## ── 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 tidymodels_prefer() to resolve common conflicts.
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 ▇▂▅▁▁

Issues with data * Missing values * Factors or numeric values * Education, EnvironmentSatisfaction, JobInvolvement, JobSatisfaction, PerformanceRating, RelationshipSatisfaction, WorkLifeBalance * Zero variance variables * Over18, EmployCount, StandardHours * Character variables: Convert them to numbers in the recipe step * Unbalanced target variable: Attrition * Id variable: EmployeeNumber

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

data_clean <- data %>%
  
  # Address factors imported as numeric 
  mutate(across(factors_vec, as.factor)) %>%
  
  # Drop zero-variance variables
  select(-c(Over18, EmployeeCount, StandardHours))
## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `across(factors_vec, as.factor)`.
## Caused by warning:
## ! Using an external vector in selections was deprecated in tidyselect 1.1.0.
## ℹ Please use `all_of()` or `any_of()` instead.
##   # Was:
##   data %>% select(factors_vec)
## 
##   # Now:
##   data %>% select(all_of(factors_vec))
## 
## See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.

Explore data

data_clean %>% count(Attrition)
## # A tibble: 2 × 2
##   Attrition     n
##   <chr>     <int>
## 1 No         1233
## 2 Yes         237
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()

# Step 2: Correlation
data_correlation <- data_binarized %>%
  correlate(Attrition__Yes)

data_correlation
## # A tibble: 120 × 3
##    feature           bin       correlation
##    <fct>             <chr>           <dbl>
##  1 Attrition         No             -1    
##  2 Attrition         Yes             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: 72 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_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 [66/8]> Fold01
##  2 <split [66/8]> Fold02
##  3 <split [66/8]> Fold03
##  4 <split [66/8]> Fold04
##  5 <split [67/7]> Fold05
##  6 <split [67/7]> Fold06
##  7 <split [67/7]> Fold07
##  8 <split [67/7]> Fold08
##  9 <split [67/7]> Fold09
## 10 <split [67/7]> Fold10

Preprocess Data

library(themis)

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

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

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

Tune Hyperparameters

doParallel::registerDoParallel()

set.seed(45034)
xgboost_tune <-
  tune_grid(xgboost_workflow,
            resamples = data_cv,
            grid = 5)