Automate the process of building and tuning a classification model to
predict employee attrition using h2o::h2o.automl, with
adjustments to explore alternative results.
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: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, trunclibrary(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() ──
## ✖ lubridate::day() masks h2o::day()
## ✖ dplyr::filter() masks stats::filter()
## ✖ lubridate::hour() masks h2o::hour()
## ✖ dplyr::lag() masks stats::lag()
## ✖ lubridate::month() masks h2o::month()
## ✖ lubridate::week() masks h2o::week()
## ✖ lubridate::year() masks h2o::year()
## 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()
## • Search for functions across packages at https://www.tidymodels.org/find/library(tidyquant)## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
## ── Attaching core tidyquant packages ──────────────────────── tidyquant 1.0.9 ──
## ✔ PerformanceAnalytics 2.0.4 ✔ TTR 0.24.4
## ✔ quantmod 0.4.26 ✔ xts 0.14.0── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
## ✖ zoo::as.Date() masks base::as.Date()
## ✖ zoo::as.Date.numeric() masks base::as.Date.numeric()
## ✖ scales::col_factor() masks readr::col_factor()
## ✖ lubridate::day() masks h2o::day()
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ xts::first() masks dplyr::first()
## ✖ recipes::fixed() masks stringr::fixed()
## ✖ lubridate::hour() masks h2o::hour()
## ✖ dplyr::lag() masks stats::lag()
## ✖ xts::last() masks dplyr::last()
## ✖ PerformanceAnalytics::legend() masks graphics::legend()
## ✖ TTR::momentum() masks dials::momentum()
## ✖ lubridate::month() masks h2o::month()
## ✖ yardstick::spec() masks readr::spec()
## ✖ quantmod::summary() masks h2o::summary(), base::summary()
## ✖ lubridate::week() masks h2o::week()
## ✖ lubridate::year() masks h2o::year()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsdata <- read_csv("../00_data/data_wrangled/data_clean.csv") %>%
mutate(across(where(is.character), factor))## Rows: 1470 Columns: 32
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (8): Attrition, BusinessTravel, Department, EducationField, Gender, Job...
## dbl (24): Age, DailyRate, DistanceFromHome, Education, EmployeeNumber, Envir...
##
## 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(5678)
data_split <- initial_split(data, strata = "Attrition")
train_tbl <- training(data_split)
test_tbl <- testing(data_split)recipe_obj <- recipe(Attrition ~ ., data = train_tbl) %>%
step_zv(all_predictors()) %>%
step_normalize(all_numeric_predictors())h2o.init()##
## H2O is not running yet, starting it now...
##
## Note: In case of errors look at the following log files:
## C:\Users\adamc\AppData\Local\Temp\RtmpKiHoKC\file32a835c7c84/h2o_adamc_started_from_r.out
## C:\Users\adamc\AppData\Local\Temp\RtmpKiHoKC\file32a8796363f4/h2o_adamc_started_from_r.err
##
##
## Starting H2O JVM and connecting: Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 4 seconds 45 milliseconds
## 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 3 days
## H2O cluster name: H2O_started_from_R_adamc_dxc201
## H2O cluster total nodes: 1
## H2O cluster total memory: 3.47 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 3 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.htmlsplit_h2o <- h2o.splitFrame(as.h2o(train_tbl), ratios = c(0.80), seed = 4321)## | | | 0% | |======================================================================| 100%train_h2o <- split_h2o[[1]]
valid_h2o <- split_h2o[[2]]
test_h2o <- as.h2o(test_tbl)## | | | 0% | |======================================================================| 100%y <- "Attrition"
x <- setdiff(names(train_tbl), y)
start_time <- Sys.time()
models_h2o <- h2o.automl(
x = x,
y = y,
training_frame = train_h2o,
validation_frame = valid_h2o,
leaderboard_frame = test_h2o,
max_models = 12,
exclude_algos = c("StackedEnsemble"),
nfolds = 3,
seed = 6543
)## | | | 0% | |== | 3%
## 20:57:32.643: User specified a validation frame with cross-validation still enabled. Please note that the models will still be validated using cross-validation only, the validation frame will be used to provide purely informative validation metrics on the trained models.
## 20:57:32.662: AutoML: XGBoost is not available; skipping it. | |=== | 4% | |========= | 13% | |================== | 26% | |================================== | 48% | |======================================================================| 100%end_time <- Sys.time()
build_time <- end_time - start_timemodels_h2o@leaderboard## model_id auc logloss aucpr
## 1 GLM_1_AutoML_1_20250423_205732 0.8084142 0.3449359 0.5606262
## 2 GBM_1_AutoML_1_20250423_205732 0.7852751 0.3586866 0.5420927
## 3 GBM_grid_1_AutoML_1_20250423_205732_model_1 0.7808522 0.3576500 0.5603714
## 4 GBM_3_AutoML_1_20250423_205732 0.7710895 0.3647481 0.5226752
## 5 GBM_4_AutoML_1_20250423_205732 0.7638619 0.3624771 0.5382197
## 6 GBM_grid_1_AutoML_1_20250423_205732_model_2 0.7607875 0.3722016 0.4772664
## mean_per_class_error rmse mse
## 1 0.2721683 0.3184301 0.1013977
## 2 0.2716828 0.3272289 0.1070787
## 3 0.2902104 0.3234541 0.1046225
## 4 0.2816343 0.3281420 0.1076772
## 5 0.2816343 0.3246604 0.1054044
## 6 0.2758091 0.3322451 0.1103868
##
## [12 rows x 7 columns]best_model <- models_h2o@leaderdir.create("h2o_models", showWarnings = FALSE)
best_model_path <- h2o.saveModel(best_model, path = "h2o_models/", force = TRUE)
best_model <- h2o.loadModel(best_model_path)predictions <- h2o.predict(best_model, newdata = test_h2o) %>%
as_tibble() %>%
bind_cols(test_tbl)## | | | 0% | |======================================================================| 100%performance_h2o <- h2o.performance(best_model, newdata = test_h2o)
h2o_auc <- h2o.auc(performance_h2o)
conf_mat <- h2o.confusionMatrix(performance_h2o)
h2o_auc## [1] 0.8084142conf_mat## Confusion Matrix (vertical: actual; across: predicted) for max f1 @ threshold = 0.372540744000785:
## No Yes Error Rate
## No 285 24 0.077670 =24/309
## Yes 28 32 0.466667 =28/60
## Totals 313 56 0.140921 =52/369previous_auc <- 0.81 # Adjusted placeholder value
cat("Previous Model AUC:", previous_auc, "\n")## Previous Model AUC: 0.81cat("New H2O Model AUC:", h2o_auc, "\n")## New H2O Model AUC: 0.8084142if (h2o_auc > previous_auc) {
cat("The h2o model shows improvement with an AUC of", h2o_auc,
"over the previous model's AUC of", previous_auc, "\n")
} else {
cat("The previous model outperformed the current model with an AUC of", previous_auc,
"compared to the h2o model's", h2o_auc, "\n")
}## The previous model outperformed the current model with an AUC of 0.81 compared to the h2o model's 0.8084142cat("Model training and selection using h2o.automl took", round(as.numeric(build_time), 2), "seconds.\n")## Model training and selection using h2o.automl took 2.72 seconds.