hex.grid

Interface HyperSpaceWalker<MP extends Model.Parameters,C extends HyperSpaceSearchCriteria>

All Known Implementing Classes:

HyperSpaceWalker.BaseWalker, HyperSpaceWalker.CartesianWalker, HyperSpaceWalker.RandomDiscreteValueWalker, SequentialWalker

public interface HyperSpaceWalker<MP extends Model.Parameters,C extends HyperSpaceSearchCriteria>

Nested Class Summary

Nested Classes

Modifier and Type	Interface and Description
static class	HyperSpaceWalker.BaseWalker<MP extends Model.Parameters,C extends HyperSpaceSearchCriteria> Superclass for for all hyperparameter space walkers.
static class	HyperSpaceWalker.CartesianWalker<MP extends Model.Parameters> Hyperparameter space walker which visits each combination of hyperparameters in order.
static interface	HyperSpaceWalker.HyperSpaceIterator<MP extends Model.Parameters>
static class	HyperSpaceWalker.RandomDiscreteValueWalker<MP extends Model.Parameters> Hyperparameter space walker which visits random combinations of hyperparameters whose possible values are given in explicit lists as they are with CartesianWalker.

Method Summary

Modifier and Type	Method and Description
default long	estimateGridWork(long maxModels) Return estimated grid work.
default java.lang.String[]	getAllHyperParamNames()
java.lang.String[]	getAllHyperParamNamesInSubspaces()
java.lang.String[]	getHyperParamNames() Returns hyper parameters names which are used for walking the hyper parameters space.
java.util.Map<java.lang.String,java.lang.Object[]>	getHyperParams()
long	getMaxHyperSpaceSize() Return estimated maximum size of hyperspace, not subject to any early stopping criteria.
ModelParametersBuilderFactory<MP>	getParametersBuilderFactory()
MP	getParams() Return initial model parameters for search.
HyperSpaceWalker.HyperSpaceIterator<MP>	iterator() Returns an iterator to traverse this hyper-space.
C	search_criteria() Search criteria for the hyperparameter search including directives for how to search and when to stop the search.
boolean	stopEarly(Model model, ScoringInfo[] sk) Based on the last model, the given array of ScoringInfo, and our stopping criteria should we stop early?

Method Detail

search_criteria

C search_criteria()

Search criteria for the hyperparameter search including directives for how to search and when to stop the search.

stopEarly

boolean stopEarly(Model model,
                  ScoringInfo[] sk)

Based on the last model, the given array of ScoringInfo, and our stopping criteria should we stop early?

iterator

HyperSpaceWalker.HyperSpaceIterator<MP> iterator()

Returns an iterator to traverse this hyper-space.

Returns:

an iterator

getHyperParamNames

java.lang.String[] getHyperParamNames()

Returns hyper parameters names which are used for walking the hyper parameters space. The names have to match the names of attributes in model parameters MP.

Returns:

names of used hyper parameters

getAllHyperParamNamesInSubspaces

java.lang.String[] getAllHyperParamNamesInSubspaces()

getAllHyperParamNames

default java.lang.String[] getAllHyperParamNames()

getHyperParams

java.util.Map<java.lang.String,java.lang.Object[]> getHyperParams()

getMaxHyperSpaceSize

long getMaxHyperSpaceSize()

Return estimated maximum size of hyperspace, not subject to any early stopping criteria. Can return -1 if estimate is not available.

Returns:

size of hyper space to explore

getParams

MP getParams()

Return initial model parameters for search.

Returns:

return model parameters

estimateGridWork

default long estimateGridWork(long maxModels)

Return estimated grid work. Can return Long.MAX_VALUE if no estimate is available.

Parameters:

maxModels -

Returns:

estimate of grid work

getParametersBuilderFactory

ModelParametersBuilderFactory<MP> getParametersBuilderFactory()