Lrnr_h2o_grid: Grid Search Models with h2o
In tlverse/sl3: Pipelines for Machine Learning and Super Learning

Lrnr_h2o_grid

R Documentation

Grid Search Models with h2o

Description

Lrnr_h2o_grid - This learner provides facilities for fitting various types of models with support for grid search over the hyperparameter space of such models, using an interface to the H2O platform. For details on the procedures available and any limitations, consult the documentation of the h2o package.

Format

R6Class object.

Value

Learner object with methods for training and prediction. See Lrnr_base for documentation on learners.

Parameters

algorithm: An h2o ML algorithm. For a list, please see http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science.html#.
seed=1: RNG see to use when fitting.
distribution=NULL: Specifies the loss function for GBM, Deep Learning, and XGBoost.
intercept=TRUE: If TRUE, and intercept term is included.
standardize=TRUE: Standardize covariates to have mean = 0 and SD = 1.
lambda=0: Lasso Parameter.
max_iterations=100: Maximum number of iterations.
ignore_const_columns=FALSE: If TRUE, drop constant covariate columns
missing_values_handling="Skip": How to handle missing values.
...: Other arguments passed to the h2o algorithm of choice. See http://docs.h2o.ai/h2o/latest-stable/h2o-docs/parameters.html for a list.

Common Parameters

Individual learners have their own sets of parameters. Below is a list of shared parameters, implemented by Lrnr_base, and shared by all learners.

covariates: A character vector of covariates. The learner will use this to subset the covariates for any specified task
outcome_type: A variable_type object used to control the outcome_type used by the learner. Overrides the task outcome_type if specified
...: All other parameters should be handled by the invidual learner classes. See the documentation for the learner class you're instantiating

Other Learners: Custom_chain, Lrnr_HarmonicReg, Lrnr_arima, Lrnr_bartMachine, Lrnr_base, Lrnr_bayesglm, Lrnr_caret, Lrnr_cv_selector, Lrnr_cv, Lrnr_dbarts, Lrnr_define_interactions, Lrnr_density_discretize, Lrnr_density_hse, Lrnr_density_semiparametric, Lrnr_earth, Lrnr_expSmooth, Lrnr_gam, Lrnr_ga, Lrnr_gbm, Lrnr_glm_fast, Lrnr_glm_semiparametric, Lrnr_glmnet, Lrnr_glmtree, Lrnr_glm, Lrnr_grfcate, Lrnr_grf, Lrnr_gru_keras, Lrnr_gts, Lrnr_hal9001, Lrnr_haldensify, Lrnr_hts, Lrnr_independent_binomial, Lrnr_lightgbm, Lrnr_lstm_keras, Lrnr_mean, Lrnr_multiple_ts, Lrnr_multivariate, Lrnr_nnet, Lrnr_nnls, Lrnr_optim, Lrnr_pca, Lrnr_pkg_SuperLearner, Lrnr_polspline, Lrnr_pooled_hazards, Lrnr_randomForest, Lrnr_ranger, Lrnr_revere_task, Lrnr_rpart, Lrnr_rugarch, Lrnr_screener_augment, Lrnr_screener_coefs, Lrnr_screener_correlation, Lrnr_screener_importance, Lrnr_sl, Lrnr_solnp_density, Lrnr_solnp, Lrnr_stratified, Lrnr_subset_covariates, Lrnr_svm, Lrnr_tsDyn, Lrnr_ts_weights, Lrnr_xgboost, Pipeline, Stack, define_h2o_X(), undocumented_learner

Examples

library(h2o)
suppressWarnings(h2o.init())
set.seed(1)

# load example data
data(cpp_imputed)
covars <- c(
  "apgar1", "apgar5", "parity", "gagebrth", "mage", "meducyrs",
  "sexn"
)
outcome <- "haz"
cpp_imputed <- cpp_imputed[1:150, ]

# create sl3 task
task <- sl3_Task$new(cpp_imputed, covariates = covars, outcome = outcome)

# h2o grid search hyperparameter alpha
h2o_glm_grid <- Lrnr_h2o_grid$new(
  algorithm = "glm",
  hyper_params = list(alpha = c(0, 0.5))
)
h2o_glm_grid_fit <- h2o_glm_grid$train(task)
pred <- h2o_glm_grid_fit$predict()

tlverse/sl3 documentation built on Nov. 18, 2024, 12:46 a.m.