org.apache.spark.ml.tuning

Class TrainValidationSplit

Object

org.apache.spark.ml.PipelineStage

org.apache.spark.ml.Estimator<TrainValidationSplitModel>

org.apache.spark.ml.tuning.TrainValidationSplit

All Implemented Interfaces:

java.io.Serializable, Logging, Params, HasCollectSubModels, HasParallelism, HasSeed, TrainValidationSplitParams, ValidatorParams, Identifiable, MLWritable

public class TrainValidationSplit
extends Estimator<TrainValidationSplitModel>
implements TrainValidationSplitParams, HasParallelism, HasCollectSubModels, MLWritable, Logging

Validation for hyper-parameter tuning. Randomly splits the input dataset into train and validation sets, and uses evaluation metric on the validation set to select the best model. Similar to CrossValidator, but only splits the set once.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
TrainValidationSplit()
TrainValidationSplit(String uid)

Method Summary

Modifier and Type	Method and Description
BooleanParam	collectSubModels() Param for whether to collect a list of sub-models trained during tuning.
TrainValidationSplit	copy(ParamMap extra) Creates a copy of this instance with the same UID and some extra params.
Param<Estimator<?>>	estimator() param for the estimator to be validated
Param<ParamMap[]>	estimatorParamMaps() param for estimator param maps
Param<Evaluator>	evaluator() param for the evaluator used to select hyper-parameters that maximize the validated metric
TrainValidationSplitModel	fit(Dataset<?> dataset) Fits a model to the input data.
static TrainValidationSplit	load(String path)
IntParam	parallelism() The number of threads to use when running parallel algorithms.
static MLReader<TrainValidationSplit>	read()
LongParam	seed() Param for random seed.
TrainValidationSplit	setCollectSubModels(boolean value) Whether to collect submodels when fitting.
TrainValidationSplit	setEstimator(Estimator<?> value)
TrainValidationSplit	setEstimatorParamMaps(ParamMap[] value)
TrainValidationSplit	setEvaluator(Evaluator value)
TrainValidationSplit	setParallelism(int value) Set the maximum level of parallelism to evaluate models in parallel.
TrainValidationSplit	setSeed(long value)
TrainValidationSplit	setTrainRatio(double value)
DoubleParam	trainRatio() Param for ratio between train and validation data.
StructType	transformSchema(StructType schema) :: DeveloperApi ::
String	uid() An immutable unique ID for the object and its derivatives.
MLWriter	write() Returns an MLWriter instance for this ML instance.

Methods inherited from class org.apache.spark.ml.Estimator

fit, fit, fit, fit

Methods inherited from class org.apache.spark.ml.PipelineStage

params

Methods inherited from class Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.apache.spark.ml.tuning.TrainValidationSplitParams

getTrainRatio

Methods inherited from interface org.apache.spark.ml.tuning.ValidatorParams

getEstimator, getEstimatorParamMaps, getEvaluator, logTuningParams, transformSchemaImpl

Methods inherited from interface org.apache.spark.ml.param.shared.HasSeed

getSeed

Methods inherited from interface org.apache.spark.ml.param.Params

clear, copyValues, defaultCopy, defaultParamMap, explainParam, explainParams, extractParamMap, extractParamMap, get, getDefault, getOrDefault, getParam, hasDefault, hasParam, isDefined, isSet, paramMap, params, set, set, set, setDefault, setDefault, shouldOwn

Methods inherited from interface org.apache.spark.ml.util.Identifiable

toString

Methods inherited from interface org.apache.spark.ml.param.shared.HasParallelism

getExecutionContext, getParallelism

Methods inherited from interface org.apache.spark.ml.param.shared.HasCollectSubModels

getCollectSubModels

Methods inherited from interface org.apache.spark.ml.util.MLWritable

save

Methods inherited from interface org.apache.spark.internal.Logging

initializeForcefully, initializeLogging, initializeLogIfNecessary, initializeLogIfNecessary, isTraceEnabled, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarning

Constructor Detail

TrainValidationSplit

public TrainValidationSplit(String uid)

TrainValidationSplit

public TrainValidationSplit()

Method Detail

read

public static MLReader<TrainValidationSplit> read()

load

public static TrainValidationSplit load(String path)

collectSubModels

public final BooleanParam collectSubModels()

Description copied from interface: HasCollectSubModels

Param for whether to collect a list of sub-models trained during tuning. If set to false, then only the single best sub-model will be available after fitting. If set to true, then all sub-models will be available. Warning: For large models, collecting all sub-models can cause OOMs on the Spark driver.

Specified by:

collectSubModels in interface HasCollectSubModels

Returns:

(undocumented)

parallelism

public IntParam parallelism()

Description copied from interface: HasParallelism

The number of threads to use when running parallel algorithms. Default is 1 for serial execution

Specified by:

parallelism in interface HasParallelism

Returns:

(undocumented)

trainRatio

public DoubleParam trainRatio()

Description copied from interface: TrainValidationSplitParams

Param for ratio between train and validation data. Must be between 0 and 1. Default: 0.75

Specified by:

trainRatio in interface TrainValidationSplitParams

Returns:

(undocumented)

estimator

public Param<Estimator<?>> estimator()

Description copied from interface: ValidatorParams

param for the estimator to be validated

Specified by:

estimator in interface ValidatorParams

Returns:

(undocumented)

estimatorParamMaps

public Param<ParamMap[]> estimatorParamMaps()

Description copied from interface: ValidatorParams

param for estimator param maps

Specified by:

estimatorParamMaps in interface ValidatorParams

Returns:

(undocumented)

evaluator

public Param<Evaluator> evaluator()

Description copied from interface: ValidatorParams

param for the evaluator used to select hyper-parameters that maximize the validated metric

Specified by:

evaluator in interface ValidatorParams

Returns:

(undocumented)

seed

public final LongParam seed()

Description copied from interface: HasSeed

Param for random seed.

Specified by:

seed in interface HasSeed

Returns:

(undocumented)

uid

public String uid()

Description copied from interface: Identifiable

An immutable unique ID for the object and its derivatives.

Specified by:

uid in interface Identifiable

Returns:

(undocumented)

setEstimator

public TrainValidationSplit setEstimator(Estimator<?> value)

setEstimatorParamMaps

public TrainValidationSplit setEstimatorParamMaps(ParamMap[] value)

setEvaluator

public TrainValidationSplit setEvaluator(Evaluator value)

setTrainRatio

public TrainValidationSplit setTrainRatio(double value)

setSeed

public TrainValidationSplit setSeed(long value)

setParallelism

public TrainValidationSplit setParallelism(int value)

Set the maximum level of parallelism to evaluate models in parallel. Default is 1 for serial evaluation

Parameters:

value - (undocumented)

Returns:

(undocumented)

setCollectSubModels

public TrainValidationSplit setCollectSubModels(boolean value)

Whether to collect submodels when fitting. If set, we can get submodels from the returned model.

Note: If set this param, when you save the returned model, you can set an option "persistSubModels" to be "true" before saving, in order to save these submodels. You can check documents of TrainValidationSplitModel.TrainValidationSplitModelWriter for more information.

Parameters:

value - (undocumented)

Returns:

(undocumented)

fit

public TrainValidationSplitModel fit(Dataset<?> dataset)

Description copied from class: Estimator

Fits a model to the input data.

Specified by:

fit in class Estimator<TrainValidationSplitModel>

Parameters:

dataset - (undocumented)

Returns:

(undocumented)

transformSchema

public StructType transformSchema(StructType schema)

Description copied from class: PipelineStage

:: DeveloperApi ::

Check transform validity and derive the output schema from the input schema.

We check validity for interactions between parameters during transformSchema and raise an exception if any parameter value is invalid. Parameter value checks which do not depend on other parameters are handled by Param.validate().

Typical implementation should first conduct verification on schema change and parameter validity, including complex parameter interaction checks.

Specified by:

transformSchema in class PipelineStage

Parameters:

schema - (undocumented)

Returns:

(undocumented)

copy

public TrainValidationSplit copy(ParamMap extra)

Description copied from interface: Params

Creates a copy of this instance with the same UID and some extra params. Subclasses should implement this method and set the return type properly. See defaultCopy().

Specified by:

copy in interface Params

Specified by:

copy in class Estimator<TrainValidationSplitModel>

Parameters:

extra - (undocumented)

Returns:

(undocumented)

write

public MLWriter write()

Description copied from interface: MLWritable

Returns an MLWriter instance for this ML instance.

Specified by:

write in interface MLWritable

Returns:

(undocumented)