library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.4.1
## Warning: package 'dplyr' was built under R version 4.4.1
## Warning: package 'lubridate' was built under R version 4.4.1
## ── 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)
## Warning: package 'tidymodels' was built under R version 4.4.1
## ── 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    1.3.1 
## ✔ recipes      1.0.10
## Warning: package 'dials' was built under R version 4.4.1
## Warning: package 'infer' was built under R version 4.4.1
## Warning: package 'modeldata' was built under R version 4.4.1
## Warning: package 'parsnip' was built under R version 4.4.1
## Warning: package 'tune' was built under R version 4.4.1
## Warning: package 'workflows' was built under R version 4.4.1
## Warning: package 'workflowsets' was built under R version 4.4.1
## Warning: package 'yardstick' was built under R version 4.4.1
## ── 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(h2o)
## Warning: package 'h2o' was built under R version 4.4.2
## 
## ----------------------------------------------------------------------
## 
## Your next step is to start H2O:
##     > h2o.init()
## 
## For H2O package documentation, ask for help:
##     > ??h2o
## 
## After starting H2O, you can use the Web UI at http://localhost:54321
## For more information visit https://docs.h2o.ai
## 
## ----------------------------------------------------------------------
## 
## 
## Attaching package: 'h2o'
## 
## The following objects are masked from 'package:lubridate':
## 
##     day, hour, month, week, year
## 
## The following objects are masked from 'package:stats':
## 
##     cor, sd, var
## 
## The following objects are masked from 'package:base':
## 
##     %*%, %in%, &&, ||, apply, as.factor, as.numeric, colnames,
##     colnames<-, ifelse, is.character, is.factor, is.numeric, log,
##     log10, log1p, log2, round, signif, trunc
attrition_raw_tbl <- read_csv("WA_Fn-UseC_-HR-Employee-Attrition.csv") %>%
  
  # h2o requires all variables to be either numeric or factors
    mutate(across(where(is.character), factor))
## 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.
attrition_raw_tbl %>% glimpse()
## 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           <fct> Travel_Rarely, Travel_Frequently, Travel_Rare…
## $ DailyRate                <dbl> 1102, 279, 1373, 1392, 591, 1005, 1324, 1358,…
## $ Department               <fct> Sales, Research & Development, Research & Dev…
## $ 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           <fct> Life Sciences, Life Sciences, Other, Life Sci…
## $ 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                   <fct> Female, Male, Male, Female, Male, Male, Femal…
## $ 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                  <fct> Sales Executive, Research Scientist, Laborato…
## $ JobSatisfaction          <dbl> 4, 2, 3, 3, 2, 4, 1, 3, 3, 3, 2, 3, 3, 4, 3, …
## $ MaritalStatus            <fct> Single, Married, Single, Married, Married, Si…
## $ 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                   <fct> Y, Y, Y, Y, Y, Y, Y, Y, Y, Y, Y, Y, Y, Y, Y, …
## $ OverTime                 <fct> Yes, No, Yes, Yes, No, No, Yes, No, No, No, N…
## $ 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, …
# Clean the dataset
attrition_clean_tbl <- attrition_raw_tbl %>%
  # Remove duplicates
  distinct() %>%
  
  # Remove irrelevant or constant columns
  select(-EmployeeCount, -StandardHours, -Over18) %>%
  
  # Handle missing values (example: replacing NA with median for numeric columns)
  mutate(across(where(is.numeric), ~ ifelse(is.na(.), median(., na.rm = TRUE), .))) %>%
  
  # Convert character columns to factors
  mutate(across(where(is.character), as.factor)) %>%
  
  # Ensure all numeric columns are properly formatted
  mutate(across(where(is.numeric), as.numeric))

# View cleaned dataset
glimpse(attrition_clean_tbl)
## Rows: 1,470
## Columns: 32
## $ 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           <fct> Travel_Rarely, Travel_Frequently, Travel_Rare…
## $ DailyRate                <dbl> 1102, 279, 1373, 1392, 591, 1005, 1324, 1358,…
## $ Department               <fct> Sales, Research & Development, Research & Dev…
## $ 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           <fct> Life Sciences, Life Sciences, Other, Life Sci…
## $ 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                   <fct> Female, Male, Male, Female, Male, Male, Femal…
## $ 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                  <fct> Sales Executive, Research Scientist, Laborato…
## $ JobSatisfaction          <dbl> 4, 2, 3, 3, 2, 4, 1, 3, 3, 3, 2, 3, 3, 4, 3, …
## $ MaritalStatus            <fct> Single, Married, Single, Married, Married, Si…
## $ 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, …
## $ OverTime                 <fct> Yes, No, Yes, Yes, No, No, Yes, No, No, No, N…
## $ 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, …
## $ 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 Data into Training and Testing Sets
set.seed(123)
data_split <- initial_split(attrition_clean_tbl, prop = 0.8)
train_data <- training(data_split)
test_data <- testing(data_split)
# Initialize H2O
h2o.init(nthreads = -1, max_mem_size = "4G")
##  Connection successful!
## 
## R is connected to the H2O cluster: 
##     H2O cluster uptime:         7 minutes 15 seconds 
##     H2O cluster timezone:       America/New_York 
##     H2O data parsing timezone:  UTC 
##     H2O cluster version:        3.44.0.3 
##     H2O cluster version age:    11 months and 27 days 
##     H2O cluster name:           H2O_started_from_R_Surplus_cva614 
##     H2O cluster total nodes:    1 
##     H2O cluster total memory:   3.33 GB 
##     H2O cluster total cores:    4 
##     H2O cluster allowed cores:  4 
##     H2O cluster healthy:        TRUE 
##     H2O Connection ip:          localhost 
##     H2O Connection port:        54321 
##     H2O Connection proxy:       NA 
##     H2O Internal Security:      FALSE 
##     R Version:                  R version 4.4.0 (2024-04-24 ucrt)
## Warning in h2o.clusterInfo(): 
## Your H2O cluster version is (11 months and 27 days) old. There may be a newer version available.
## Please download and install the latest version from: https://h2o-release.s3.amazonaws.com/h2o/latest_stable.html
# Convert training and testing datasets to H2O frames
train_h2o <- as.h2o(train_data)
##   |                                                                              |                                                                      |   0%  |                                                                              |======================================================================| 100%
test_h2o <- as.h2o(test_data)
##   |                                                                              |                                                                      |   0%  |                                                                              |======================================================================| 100%
# Train H2O AutoML Model
aml <- h2o.automl(
  y = "Attrition", 
  training_frame = train_h2o,
  max_models = 10,
  seed = 123,
  exclude_algos = c("DeepLearning")  # Example of excluding certain models
)
##   |                                                                              |                                                                      |   0%  |                                                                              |======                                                                |   8%
## 10:32:06.45: AutoML: XGBoost is not available; skipping it.  |                                                                              |==================                                                    |  25%  |                                                                              |============================================                          |  62%  |                                                                              |======================================================================| 100%
# View AutoML leaderboard
lb <- h2o.get_leaderboard(aml, extra_columns = "ALL")
print(lb)
##                                                  model_id       auc   logloss
## 1 StackedEnsemble_BestOfFamily_1_AutoML_2_20241218_103206 0.8101188 0.3390033
## 2                          GLM_1_AutoML_2_20241218_103206 0.8096257 0.3432421
## 3    StackedEnsemble_AllModels_1_AutoML_2_20241218_103206 0.8080389 0.3375175
## 4             GBM_grid_1_AutoML_2_20241218_103206_model_2 0.7947015 0.3536282
## 5             GBM_grid_1_AutoML_2_20241218_103206_model_1 0.7917719 0.3520702
## 6                          GBM_1_AutoML_2_20241218_103206 0.7802303 0.3591342
##       aucpr mean_per_class_error      rmse        mse training_time_ms
## 1 0.5953457            0.2464820 0.3120193 0.09735603             1233
## 2 0.5870282            0.2507599 0.3133935 0.09821551               50
## 3 0.5852746            0.2459192 0.3126998 0.09778120             1267
## 4 0.5358702            0.2774401 0.3259225 0.10622550              117
## 5 0.5196405            0.2810424 0.3234366 0.10461121              153
## 6 0.5129623            0.2965214 0.3272991 0.10712467              124
##   predict_time_per_row_ms            algo
## 1                0.025693 StackedEnsemble
## 2                0.006333             GLM
## 3                0.024791 StackedEnsemble
## 4                0.013750             GBM
## 5                0.013382             GBM
## 6                0.011681             GBM
## 
## [12 rows x 10 columns]
# Extract the best model
best_model <- h2o.get_best_model(aml)
# Make Predictions on Test Data
predictions <- h2o.predict(best_model, test_h2o) %>% as.data.frame()
##   |                                                                              |                                                                      |   0%  |                                                                              |======================================================================| 100%
# Combine predictions with the test data
test_results <- test_data %>%
  mutate(
    .pred_class = predictions$predict,    # Predicted class
    .pred_Yes = predictions$Yes,         # Probability of "Yes"
    .pred_No = predictions$No            # Probability of "No"
  )
# Define metric set
metrics <- metric_set(accuracy, roc_auc)

# Evaluate metrics
results <- test_results %>%
  metrics(
    truth = Attrition,
    estimate = .pred_class,              # For accuracy
    .pred_Yes                            # For roc_auc
  )

# Print evaluation results
print(results)
## # A tibble: 2 × 3
##   .metric  .estimator .estimate
##   <chr>    <chr>          <dbl>
## 1 accuracy binary         0.871
## 2 roc_auc  binary         0.110
# Shutdown h2o when done
h2o.shutdown(prompt = FALSE)