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 errorslibrary(tidymodels)## Warning: package 'tidymodels' was built under R version 4.4.2## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom 1.0.8 ✔ 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 'broom' was built under R version 4.4.3## 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 4.4.2## 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 tidymodels_prefer() to resolve common conflicts.library(h2o)## Warning: package 'h2o' was built under R version 4.4.3##
## ----------------------------------------------------------------------
##
## 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, truncattrition_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.# Use glimpse to examine the data
glimpse(attrition_raw_tbl)## Rows: 1,470
## Columns: 35
## $ Age <dbl> 41, 49, 37, 33, 27, 32, 59, 30, 38, 36, 35, 2…
## $ Attrition <chr> "Yes", "No", "Yes", "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, …set.seed(123)
split <- initial_split(attrition_raw_tbl, prop = 0.8, strata = "Attrition")
train_data <- training(split)
test_data <- testing(split)
# Optional: Reduce training size for faster prototyping
train_data <- train_data %>% sample_frac(0.5)attrition_recipe <- recipe(Attrition ~ ., data = train_data) %>%
step_rm(Over18, EmployeeCount, StandardHours) %>%
step_dummy(all_nominal(), one_hot = TRUE) %>%
step_center(all_numeric(), -all_outcomes()) %>%
step_scale(all_numeric(), -all_outcomes())
# Fit the recipe
attrition_recipe_prep <- prep(attrition_recipe, training = train_data)
# Apply preprocessing
train_data_processed <- bake(attrition_recipe_prep, new_data = train_data)
test_data_processed <- bake(attrition_recipe_prep, new_data = test_data)h2o.init()## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 2 minutes 48 seconds
## H2O cluster timezone: America/New_York
## H2O data parsing timezone: UTC
## H2O cluster version: 3.44.0.3
## H2O cluster version age: 1 year, 4 months and 10 days
## H2O cluster name: H2O_started_from_R_adamc_pcs264
## H2O cluster total nodes: 1
## H2O cluster total memory: 2.89 GB
## H2O cluster total cores: 12
## H2O cluster allowed cores: 12
## H2O cluster healthy: TRUE
## H2O Connection ip: localhost
## H2O Connection port: 54321
## H2O Connection proxy: NA
## H2O Internal Security: FALSE
## R Version: R version 4.4.1 (2024-06-14 ucrt)## Warning in h2o.clusterInfo():
## Your H2O cluster version is (1 year, 4 months and 10 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 to H2OFrame
train_h2o <- as.h2o(train_data_processed)## | | | 0% | |======================================================================| 100%test_h2o <- as.h2o(test_data_processed)## | | | 0% | |======================================================================| 100%# Define predictors and response
predictors <- setdiff(names(train_data_processed), "Attrition_Yes")
response <- "Attrition_Yes"
# Train AutoML
automl <- h2o.automl(
x = predictors,
y = response,
training_frame = train_h2o,
max_runtime_secs = 30,
max_models = 5,
exclude_algos = c("StackedEnsemble"),
seed = 123
)## | | | 0% | |======= | 10%
## 19:10:43.797: AutoML: XGBoost is not available; skipping it. | |=========== | 15% | |======================================================================| 100%predictions <- h2o.predict(automl@leader, newdata = test_h2o)$predict## | | | 0% | |======================================================================| 100%performance <- h2o.performance(automl@leader, newdata = test_h2o)
print(performance)## H2ORegressionMetrics: glm
##
## MSE: 0.0001298281
## RMSE: 0.01139421
## MAE: 0.00864985
## RMSLE: 0.01229906
## Mean Residual Deviance : 0.0001298281
## R^2 : 0.9998729
## Null Deviance :301.3765
## Null D.o.F. :294
## Residual Deviance :0.03829928
## Residual D.o.F. :241
## AIC :-1692.87summary(automl@leader)## Model Details:
## ==============
##
## H2ORegressionModel: glm
## Model Key: GLM_1_AutoML_2_20250430_191043
## GLM Model: summary
## family link regularization
## 1 gaussian identity Ridge ( lambda = 0.009983 )
## lambda_search
## 1 nlambda = 30, lambda.max = 99.83, lambda.min = 0.009983, lambda.1se = 0.009983
## number_of_predictors_total number_of_active_predictors number_of_iterations
## 1 53 53 30
## training_frame
## 1 AutoML_2_20250430_191043_training_train_data_processed_sid_95dd_1
##
## H2ORegressionMetrics: glm
## ** Reported on training data. **
##
## MSE: 0.0001286205
## RMSE: 0.0113411
## MAE: 0.008406775
## RMSLE: 0.01152495
## Mean Residual Deviance : 0.0001286205
## R^2 : 0.9998712
## Null Deviance :587
## Null D.o.F. :587
## Residual Deviance :0.07562884
## Residual D.o.F. :534
## AIC :-3489.011
##
##
##
## H2ORegressionMetrics: glm
## ** Reported on cross-validation data. **
## ** 5-fold cross-validation on training data (Metrics computed for combined holdout predictions) **
##
## MSE: 0.0002617287
## RMSE: 0.01617803
## MAE: 0.011901
## RMSLE: 0.01652345
## Mean Residual Deviance : 0.0002617287
## R^2 : 0.9997378
## Null Deviance :590.8731
## Null D.o.F. :587
## Residual Deviance :0.1538964
## Residual D.o.F. :534
## AIC :-3071.271
##
##
## Cross-Validation Metrics Summary:
## mean sd cv_1_valid cv_2_valid cv_3_valid
## mae 0.011903 0.000737 0.011863 0.011444 0.011489
## mean_residual_deviance 0.000262 0.000032 0.000247 0.000267 0.000232
## mse 0.000262 0.000032 0.000247 0.000267 0.000232
## null_deviance 118.174614 26.120630 99.503430 124.715546 85.238010
## r2 0.999727 0.000045 0.999703 0.999747 0.999661
## residual_deviance 0.030779 0.003714 0.029177 0.031482 0.027371
## rmse 0.016157 0.000976 0.015725 0.016334 0.015230
## rmsle 0.016395 0.002266 0.018804 0.013793 0.018740
## cv_4_valid cv_5_valid
## mae 0.011529 0.013187
## mean_residual_deviance 0.000248 0.000315
## mse 0.000248 0.000315
## null_deviance 129.812580 151.603490
## r2 0.999776 0.999750
## residual_deviance 0.028983 0.036884
## rmse 0.015739 0.017755
## rmsle 0.015052 0.015584
##
## Scoring History:
## timestamp duration iteration lambda predictors deviance_train
## 1 2025-04-30 19:10:44 0.000 sec 1 .1E3 54 0.970
## 2 2025-04-30 19:10:44 0.000 sec 2 .73E2 54 0.960
## 3 2025-04-30 19:10:44 0.000 sec 3 .53E2 54 0.947
## 4 2025-04-30 19:10:44 0.000 sec 4 .39E2 54 0.929
## 5 2025-04-30 19:10:44 0.000 sec 5 .28E2 54 0.906
## deviance_xval deviance_se alpha iterations training_rmse training_deviance
## 1 0.985 0.099 0.000000 NA NA NA
## 2 0.977 0.098 0.000000 NA NA NA
## 3 0.967 0.097 0.000000 NA NA NA
## 4 0.953 0.096 0.000000 NA NA NA
## 5 0.935 0.094 0.000000 NA NA NA
## training_mae training_r2
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
##
## ---
## timestamp duration iteration lambda predictors deviance_train
## 26 2025-04-30 19:10:44 0.014 sec 26 .36E-1 54 0.002
## 27 2025-04-30 19:10:44 0.014 sec 27 .26E-1 54 0.001
## 28 2025-04-30 19:10:44 0.014 sec 28 .19E-1 54 0.000
## 29 2025-04-30 19:10:44 0.014 sec 29 .14E-1 54 0.000
## 30 2025-04-30 19:10:44 0.018 sec 30 .1E-1 54 0.000
## 31 2025-04-30 19:10:44 0.018 sec 31 .0E0 54 0.000
## deviance_xval deviance_se alpha iterations training_rmse
## 26 0.003 0.000 0.000000 NA NA
## 27 0.002 0.000 0.000000 NA NA
## 28 0.001 0.000 0.000000 NA NA
## 29 0.000 0.000 0.000000 NA NA
## 30 0.000 0.000 0.000000 NA NA
## 31 0.000 0.000 0.000000 31 0.01134
## training_deviance training_mae training_r2
## 26 NA NA NA
## 27 NA NA NA
## 28 NA NA NA
## 29 NA NA NA
## 30 NA NA NA
## 31 0.00013 0.00841 0.99987
##
## Variable Importances: (Extract with `h2o.varimp`)
## =================================================
##
## Variable Importances:
## variable relative_importance scaled_importance percentage
## 1 Attrition_No 0.986911 1.000000 0.958840
## 2 OverTime_Yes 0.005037 0.005104 0.004894
## 3 EnvironmentSatisfaction 0.002244 0.002274 0.002180
## 4 MaritalStatus_Single 0.002067 0.002094 0.002008
## 5 YearsInCurrentRole 0.002063 0.002091 0.002004
##
## ---
## variable relative_importance scaled_importance
## 48 EducationField_Life.Sciences 0.000176 0.000178
## 49 EducationField_Medical 0.000075 0.000076
## 50 StockOptionLevel 0.000043 0.000044
## 51 Department_Sales 0.000039 0.000040
## 52 JobRole_Research.Scientist 0.000010 0.000010
## 53 MonthlyIncome 0.000001 0.000001
## percentage
## 48 0.000171
## 49 0.000073
## 50 0.000042
## 51 0.000038
## 52 0.000010
## 53 0.000001