Package ai.h2o.automl

Interface Summary

Interface	Description
H2ORunnable	The H2ORunnable interface should be implemented by any class whose instances are intended to be submitted to the H2O forkjoin pool via H2O.submitTask.
IAlgo
ModelingStepsProvider<T extends ModelingSteps>	A simple class used by service discovery to register new ModelingSteps implementations.
ModelParametersProvider<P extends hex.Model.Parameters>
ModelSelectionStrategies.LeaderboardHolder
ModelSelectionStrategy<M extends hex.Model>
TimedH2ORunnable

Class Summary

Class	Description
AutoML	H2O AutoML AutoML is used for automating the machine learning workflow, which includes automatic training and tuning of many models within a user-specified time-limit.
AutoMLBuildSpec	Parameters which specify the build (or extension) of an AutoML build job.
AutoMLBuildSpec.AutoMLBuildControl	The specification of overall build parameters for the AutoML process.
AutoMLBuildSpec.AutoMLBuildModels	The specification of the parameters for building models for a single algo (e.g., GBM), including base model parameters and hyperparameter search.
AutoMLBuildSpec.AutoMLCustomParameters
AutoMLBuildSpec.AutoMLCustomParameters.AutoMLCustomParameter<V>
AutoMLBuildSpec.AutoMLCustomParameters.Builder
AutoMLBuildSpec.AutoMLInput	The specification of the datasets to be used for the AutoML process.
AutoMLBuildSpec.AutoMLStoppingCriteria
AutoMLSession
H2OJob<T extends water.Keyed & H2ORunnable>
ModelingStep<M extends hex.Model>	Parent class defining common properties and common logic for actual AutoML training steps.
ModelingStep.DynamicStep<M extends hex.Model>	Step designed to dynamically choose to train a model or another, a grid or anything else, based on the current automl workflow history.
ModelingStep.DynamicStep.VirtualAlgo
ModelingStep.GridStep<M extends hex.Model>	Step designed to build multiple models using a (random) grid search.
ModelingStep.ModelStep<M extends hex.Model>	Step designed to build a single/default model.
ModelingStep.SelectionStep<M extends hex.Model>	Step designed to train some models (or not) and then deciding to make a selection and add and/or remove models to/from the current leaderboard.
ModelingSteps
ModelingStepsRegistry	The registry responsible for loading all ModelingStepsProvider using service discovery, and providing the list of ModelingStep to execute.
Models<M extends hex.Model>
ModelSelectionStrategies
ModelSelectionStrategies.KeepBestConstantSize<M extends hex.Model>
ModelSelectionStrategies.KeepBestN<M extends hex.Model>
ModelSelectionStrategies.KeepBestNFromSubgroup<M extends hex.Model>
ModelSelectionStrategies.LeaderboardBasedSelectionStrategy<M extends hex.Model>
ModelSelectionStrategy.Selection<M extends hex.Model>
StepDefinition	Defines a step or a list of steps to be executed.
StepDefinition.Step
WorkAllocations
WorkAllocations.Work

Enum Summary

Enum	Description
Algo
AutoML.Constraint
ModelingStep.SeedPolicy
StepDefinition.Alias
WorkAllocations.JobType