# Load libraries
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(tidymodels)
## ── 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      1.1.1     
## ── 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
library(janitor)
## 
## Attaching package: 'janitor'
## 
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test
library(readr)
# Load dataset
attrition_raw_tbl <- 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.
# Set seed for reproducibility
set.seed(123)

attrition_tbl <- attrition_raw_tbl %>%
  mutate(Attrition = as.factor(Attrition))

glimpse(attrition_tbl)
## Rows: 1,470
## Columns: 35
## $ Age                      <dbl> 41, 49, 37, 33, 27, 32, 59, 30, 38, 36, 35, 2…
## $ Attrition                <fct> Yes, No, Yes, No, No, No, No, No, No, No, No,…
## $ BusinessTravel           <chr> "Travel_Rarely", "Travel_Frequently", "Travel…
## $ DailyRate                <dbl> 1102, 279, 1373, 1392, 591, 1005, 1324, 1358,…
## $ Department               <chr> "Sales", "Research & Development", "Research …
## $ DistanceFromHome         <dbl> 1, 8, 2, 3, 2, 2, 3, 24, 23, 27, 16, 15, 26, …
## $ Education                <dbl> 2, 1, 2, 4, 1, 2, 3, 1, 3, 3, 3, 2, 1, 2, 3, …
## $ EducationField           <chr> "Life Sciences", "Life Sciences", "Other", "L…
## $ EmployeeCount            <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ EmployeeNumber           <dbl> 1, 2, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16,…
## $ EnvironmentSatisfaction  <dbl> 2, 3, 4, 4, 1, 4, 3, 4, 4, 3, 1, 4, 1, 2, 3, …
## $ Gender                   <chr> "Female", "Male", "Male", "Female", "Male", "…
## $ HourlyRate               <dbl> 94, 61, 92, 56, 40, 79, 81, 67, 44, 94, 84, 4…
## $ JobInvolvement           <dbl> 3, 2, 2, 3, 3, 3, 4, 3, 2, 3, 4, 2, 3, 3, 2, …
## $ JobLevel                 <dbl> 2, 2, 1, 1, 1, 1, 1, 1, 3, 2, 1, 2, 1, 1, 1, …
## $ JobRole                  <chr> "Sales Executive", "Research Scientist", "Lab…
## $ JobSatisfaction          <dbl> 4, 2, 3, 3, 2, 4, 1, 3, 3, 3, 2, 3, 3, 4, 3, …
## $ MaritalStatus            <chr> "Single", "Married", "Single", "Married", "Ma…
## $ MonthlyIncome            <dbl> 5993, 5130, 2090, 2909, 3468, 3068, 2670, 269…
## $ MonthlyRate              <dbl> 19479, 24907, 2396, 23159, 16632, 11864, 9964…
## $ NumCompaniesWorked       <dbl> 8, 1, 6, 1, 9, 0, 4, 1, 0, 6, 0, 0, 1, 0, 5, …
## $ Over18                   <chr> "Y", "Y", "Y", "Y", "Y", "Y", "Y", "Y", "Y", …
## $ OverTime                 <chr> "Yes", "No", "Yes", "Yes", "No", "No", "Yes",…
## $ PercentSalaryHike        <dbl> 11, 23, 15, 11, 12, 13, 20, 22, 21, 13, 13, 1…
## $ PerformanceRating        <dbl> 3, 4, 3, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 3, 3, …
## $ RelationshipSatisfaction <dbl> 1, 4, 2, 3, 4, 3, 1, 2, 2, 2, 3, 4, 4, 3, 2, …
## $ StandardHours            <dbl> 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 8…
## $ StockOptionLevel         <dbl> 0, 1, 0, 0, 1, 0, 3, 1, 0, 2, 1, 0, 1, 1, 0, …
## $ TotalWorkingYears        <dbl> 8, 10, 7, 8, 6, 8, 12, 1, 10, 17, 6, 10, 5, 3…
## $ TrainingTimesLastYear    <dbl> 0, 3, 3, 3, 3, 2, 3, 2, 2, 3, 5, 3, 1, 2, 4, …
## $ WorkLifeBalance          <dbl> 1, 3, 3, 3, 3, 2, 2, 3, 3, 2, 3, 3, 2, 3, 3, …
## $ YearsAtCompany           <dbl> 6, 10, 0, 8, 2, 7, 1, 1, 9, 7, 5, 9, 5, 2, 4,…
## $ YearsInCurrentRole       <dbl> 4, 7, 0, 7, 2, 7, 0, 0, 7, 7, 4, 5, 2, 2, 2, …
## $ YearsSinceLastPromotion  <dbl> 0, 1, 0, 3, 2, 3, 0, 0, 1, 7, 0, 0, 4, 1, 0, …
## $ YearsWithCurrManager     <dbl> 5, 7, 0, 0, 2, 6, 0, 0, 8, 7, 3, 8, 3, 2, 3, …
# Split the data into training and testing sets
data_split <- initial_split(attrition_tbl, prop = 0.8, strata = Attrition)
train_data <- training(data_split)
test_data  <- testing(data_split)
# Create a recipe for preprocessing
attrition_recipe <- recipe(Attrition ~ ., data = train_data) %>%
  # Remove columns with no predictive value
  update_role(EmployeeCount, StandardHours, Over18, EmployeeNumber, new_role = "ID") %>%
  step_rm(has_role("ID")) %>%
  # Impute missing values (if any)
  step_impute_median(all_numeric(), -all_outcomes()) %>%
  step_impute_mode(all_nominal(), -all_outcomes()) %>%
  # Convert categorical variables to dummy variables
  step_dummy(all_nominal(), -all_outcomes()) %>%
  # Normalize numeric predictors
  step_normalize(all_numeric(), -all_outcomes())
# Define a logistic regression model
log_reg_model <- logistic_reg(mode = "classification") %>%
  set_engine("glm")

# Create a workflow
attrition_workflow <- workflow() %>%
  add_model(log_reg_model) %>%
  add_recipe(attrition_recipe)

# Train the model
log_reg_fit <- fit(attrition_workflow, data = train_data)

# Predict on test set with probabilities
predictions <- predict(log_reg_fit, test_data, type = "prob") %>%
  bind_cols(test_data %>% select(Attrition))

# View first few predictions
head(predictions)
## # A tibble: 6 × 3
##   .pred_No .pred_Yes Attrition
##      <dbl>     <dbl> <fct>    
## 1    0.974  0.0256   No       
## 2    0.929  0.0707   No       
## 3    0.932  0.0684   No       
## 4    0.956  0.0440   No       
## 5    0.924  0.0756   No       
## 6    0.999  0.000592 No
# Generate class predictions for confusion matrix
class_preds <- predict(log_reg_fit, test_data) %>%
  bind_cols(test_data %>% select(Attrition))

# Confusion matrix
conf_mat(class_preds, truth = Attrition, estimate = .pred_class)
##           Truth
## Prediction  No Yes
##        No  235  26
##        Yes  12  22
# ROC AUC
roc_auc(predictions, truth = Attrition, .pred_Yes)
## # A tibble: 1 × 3
##   .metric .estimator .estimate
##   <chr>   <chr>          <dbl>
## 1 roc_auc binary         0.112