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()
## • Search for functions across packages at https://www.tidymodels.org/find/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, truncdata_raw <- 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.# Peek at the structure
glimpse(data_raw)## 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(456)
split <- initial_split(data_raw, prop = 0.7, strata = Attrition)
train_set <- training(split)
test_set <- testing(split)recipe_obj <- recipe(Attrition ~ ., data = train_set) %>%
step_rm(EmployeeCount, StandardHours, Over18) %>%
step_mutate(Attrition = ifelse(Attrition == "Yes", 1, 0)) %>%
step_dummy(all_nominal(), -all_outcomes()) %>%
step_zv(all_predictors()) %>%
step_normalize(all_numeric(), -all_outcomes())
recipe_prep <- prep(recipe_obj)
train_ready <- bake(recipe_prep, new_data = train_set)
test_ready <- bake(recipe_prep, new_data = test_set)h2o.init(max_mem_size = "2G")## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 12 minutes 14 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: 2.88 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.htmltrain_h2o <- as.h2o(train_ready)## | | | 0% | |======================================================================| 100%test_h2o <- as.h2o(test_ready)## | | | 0% | |======================================================================| 100%x_vars <- setdiff(names(train_ready), "Attrition")
y_var <- "Attrition"
automl_model <- h2o.automl(
x = x_vars,
y = y_var,
training_frame = train_h2o,
max_models = 10,
max_runtime_secs = 60,
seed = 456
)## | | | 0% | |==== | 6%
## 19:20:09.857: AutoML: XGBoost is not available; skipping it.
## 19:20:09.867: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training.
## 19:20:10.2: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training.
## 19:20:10.652: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training.
## 19:20:11.355: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training.
## 19:20:12.8: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training. | |============ | 18%
## 19:20:12.843: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training.
## 19:20:13.642: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training.
## 19:20:14.618: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training.
## 19:20:15.269: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training. | |=================== | 26%
## 19:20:16.602: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training.
## 19:20:16.843: _response param, We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training. | |======================================================================| 100%preds <- h2o.predict(automl_model@leader, newdata = test_h2o)## | | | 0% | |======================================================================| 100%head(preds)## predict
## 1 0.4744130
## 2 0.5120544
## 3 0.3174994
## 4 0.2358872
## 5 0.1199458
## 6 0.0471622perf <- h2o.performance(automl_model@leader, newdata = test_h2o)
perf## H2ORegressionMetrics: stackedensemble
##
## MSE: 0.1058096
## RMSE: 0.3252839
## MAE: 0.2339051
## RMSLE: 0.2385398
## Mean Residual Deviance : 0.1058096summary(automl_model@leader)## Model Details:
## ==============
##
## H2ORegressionModel: stackedensemble
## Model Key: StackedEnsemble_AllModels_1_AutoML_4_20250430_192009
## Model Summary for Stacked Ensemble:
## key value
## 1 Stacking strategy cross_validation
## 2 Number of base models (used / total) 6/10
## 3 # GBM base models (used / total) 4/6
## 4 # DRF base models (used / total) 0/2
## 5 # GLM base models (used / total) 1/1
## 6 # DeepLearning base models (used / total) 1/1
## 7 Metalearner algorithm GLM
## 8 Metalearner fold assignment scheme Random
## 9 Metalearner nfolds 5
## 10 Metalearner fold_column NA
## 11 Custom metalearner hyperparameters None
##
## H2ORegressionMetrics: stackedensemble
## ** Reported on training data. **
##
## MSE: 0.04034839
## RMSE: 0.2008691
## MAE: 0.145336
## RMSLE: 0.154217
## Mean Residual Deviance : 0.04034839
##
##
##
## H2ORegressionMetrics: stackedensemble
## ** Reported on cross-validation data. **
## ** 5-fold cross-validation on training data (Metrics computed for combined holdout predictions) **
##
## MSE: 0.09779512
## RMSE: 0.3127221
## MAE: 0.2081963
## RMSLE: 0.2220462
## Mean Residual Deviance : 0.09779512
##
##
## Cross-Validation Metrics Summary:
## mean sd cv_1_valid cv_2_valid cv_3_valid
## mae 0.208473 0.009696 0.194384 0.219414 0.203878
## mean_residual_deviance 0.097824 0.010011 0.084090 0.109386 0.091613
## mse 0.097824 0.010011 0.084090 0.109386 0.091613
## null_deviance 27.722963 2.398876 24.358622 27.437992 29.329515
## r2 0.273565 0.038777 0.286946 0.221959 0.325286
## residual_deviance 20.081257 1.819958 17.238503 21.330301 19.788477
## rmse 0.312435 0.016147 0.289983 0.330736 0.302677
## rmsle 0.221404 0.010616 0.208810 0.235261 0.212922
## cv_4_valid cv_5_valid
## mae 0.214182 0.210508
## mean_residual_deviance 0.103575 0.100455
## mse 0.103575 0.100455
## null_deviance 30.608612 26.880080
## r2 0.281069 0.252563
## residual_deviance 21.957907 20.091093
## rmse 0.321831 0.316947
## rmsle 0.226058 0.223970
##
## NULL