org.apache.spark.ml.param

Interface Params

All Superinterfaces:

Identifiable, java.io.Serializable

All Known Subinterfaces:

AFTSurvivalRegressionParams, ALSModelParams, ALSParams, BisectingKMeansParams, BucketedRandomProjectionLSHParams, ChiSqSelectorParams, ClassifierParams, CountVectorizerParams, CrossValidatorParams, DecisionTreeClassifierParams, DecisionTreeParams, DecisionTreeRegressorParams, FPGrowthParams, GaussianMixtureParams, GBTClassifierParams, GBTParams, GBTRegressorParams, GeneralizedLinearRegressionBase, HasAggregationDepth, HasCheckpointInterval, HasCollectSubModels, HasDistanceMeasure, HasElasticNetParam, HasFeaturesCol, HasFitIntercept, HasHandleInvalid, HasInputCol, HasInputCols, HasLabelCol, HasLoss, HasMaxIter, HasNumFeatures, HasOutputCol, HasOutputCols, HasParallelism, HasPredictionCol, HasProbabilityCol, HasRawPredictionCol, HasRegParam, HasSeed, HasSolver, HasStandardization, HasStepSize, HasThreshold, HasThresholds, HasTol, HasValidationIndicatorCol, HasVarianceCol, HasVarianceImpurity, HasWeightCol, IDFBase, ImputerParams, IsotonicRegressionBase, KMeansParams, LDAParams, LinearRegressionParams, LinearSVCParams, LogisticRegressionParams, LSHParams, MaxAbsScalerParams, MinMaxScalerParams, MultilayerPerceptronParams, NaiveBayesParams, OneHotEncoderBase, OneVsRestParams, PCAParams, PowerIterationClusteringParams, PredictorParams, ProbabilisticClassifierParams, QuantileDiscretizerBase, RandomForestClassifierParams, RandomForestParams, RandomForestRegressorParams, RFormulaBase, RobustScalerParams, StandardScalerParams, StringIndexerBase, TrainValidationSplitParams, TreeClassifierParams, TreeEnsembleClassifierParams, TreeEnsembleParams, TreeEnsembleRegressorParams, TreeRegressorParams, ValidatorParams, VectorIndexerParams, Word2VecBase

All Known Implementing Classes:

AFTSurvivalRegression, AFTSurvivalRegressionModel, ALS, ALSModel, Binarizer, BinaryClassificationEvaluator, BisectingKMeans, BisectingKMeansModel, BucketedRandomProjectionLSH, BucketedRandomProjectionLSHModel, Bucketizer, ChiSqSelector, ChiSqSelectorModel, ClassificationModel, Classifier, ClusteringEvaluator, ColumnPruner, CountVectorizer, CountVectorizerModel, CrossValidator, CrossValidatorModel, DCT, DecisionTreeClassificationModel, DecisionTreeClassifier, DecisionTreeRegressionModel, DecisionTreeRegressor, DistributedLDAModel, ElementwiseProduct, Estimator, Evaluator, FeatureHasher, FPGrowth, FPGrowthModel, GaussianMixture, GaussianMixtureModel, GBTClassificationModel, GBTClassifier, GBTRegressionModel, GBTRegressor, GeneralizedLinearRegression, GeneralizedLinearRegressionModel, HashingTF, IDF, IDFModel, Imputer, ImputerModel, IndexToString, Interaction, IsotonicRegression, IsotonicRegressionModel, JavaParams, KMeans, KMeansModel, LDA, LDAModel, LinearRegression, LinearRegressionModel, LinearSVC, LinearSVCModel, LocalLDAModel, LogisticRegression, LogisticRegressionModel, MaxAbsScaler, MaxAbsScalerModel, MinHashLSH, MinHashLSHModel, MinMaxScaler, MinMaxScalerModel, Model, MulticlassClassificationEvaluator, MultilabelClassificationEvaluator, MultilayerPerceptronClassificationModel, MultilayerPerceptronClassifier, NaiveBayes, NaiveBayesModel, NGram, Normalizer, OneHotEncoder, OneHotEncoderModel, OneVsRest, OneVsRestModel, PCA, PCAModel, Pipeline, PipelineModel, PipelineStage, PolynomialExpansion, PowerIterationClustering, PredictionModel, Predictor, PrefixSpan, ProbabilisticClassificationModel, ProbabilisticClassifier, QuantileDiscretizer, RandomForestClassificationModel, RandomForestClassifier, RandomForestRegressionModel, RandomForestRegressor, RankingEvaluator, RegexTokenizer, RegressionEvaluator, RegressionModel, Regressor, RFormula, RFormulaModel, RobustScaler, RobustScalerModel, SQLTransformer, StandardScaler, StandardScalerModel, StopWordsRemover, StringIndexer, StringIndexerModel, Tokenizer, TrainValidationSplit, TrainValidationSplitModel, Transformer, UnaryTransformer, VectorAssembler, VectorAttributeRewriter, VectorIndexer, VectorIndexerModel, VectorSizeHint, VectorSlicer, Word2Vec, Word2VecModel

public interface Params
extends Identifiable, scala.Serializable

:: DeveloperApi :: Trait for components that take parameters. This also provides an internal param map to store parameter values attached to the instance.

Method Summary

Modifier and Type	Method and Description
Params	clear(Param<?> param) Clears the user-supplied value for the input param.
Params	copy(ParamMap extra) Creates a copy of this instance with the same UID and some extra params.
<T extends Params> T	copyValues(T to, ParamMap extra) Copies param values from this instance to another instance for params shared by them.
<T extends Params> T	defaultCopy(ParamMap extra) Default implementation of copy with extra params.
ParamMap	defaultParamMap() Internal param map for default values.
String	explainParam(Param<?> param) Explains a param.
String	explainParams() Explains all params of this instance.
ParamMap	extractParamMap() extractParamMap with no extra values.
ParamMap	extractParamMap(ParamMap extra) Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values less than user-supplied values less than extra.
<T> scala.Option<T>	get(Param<T> param) Optionally returns the user-supplied value of a param.
<T> scala.Option<T>	getDefault(Param<T> param) Gets the default value of a parameter.
<T> T	getOrDefault(Param<T> param) Gets the value of a param in the embedded param map or its default value.
Param<Object>	getParam(String paramName) Gets a param by its name.
<T> boolean	hasDefault(Param<T> param) Tests whether the input param has a default value set.
boolean	hasParam(String paramName) Tests whether this instance contains a param with a given name.
boolean	isDefined(Param<?> param) Checks whether a param is explicitly set or has a default value.
boolean	isSet(Param<?> param) Checks whether a param is explicitly set.
ParamMap	paramMap() Internal param map for user-supplied values.
Param<?>[]	params() Returns all params sorted by their names.
<T> Params	set(Param<T> param, T value) Sets a parameter in the embedded param map.
Params	set(ParamPair<?> paramPair) Sets a parameter in the embedded param map.
Params	set(String param, Object value) Sets a parameter (by name) in the embedded param map.
<T> Params	setDefault(Param<T> param, T value) Sets a default value for a param.
Params	setDefault(scala.collection.Seq<ParamPair<?>> paramPairs) Sets default values for a list of params.
void	shouldOwn(Param<?> param) Validates that the input param belongs to this instance.

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

toString, uid

Method Detail

params

Param<?>[] params()

Returns all params sorted by their names. The default implementation uses Java reflection to list all public methods that have no arguments and return Param.

Returns:

(undocumented)

Note:

Developer should not use this method in constructor because we cannot guarantee that this variable gets initialized before other params.

explainParam

String explainParam(Param<?> param)

Explains a param.

Parameters:

param - input param, must belong to this instance.

Returns:

a string that contains the input param name, doc, and optionally its default value and the user-supplied value

explainParams

String explainParams()

Explains all params of this instance. See explainParam().

Returns:

(undocumented)

isSet

boolean isSet(Param<?> param)

Checks whether a param is explicitly set.

isDefined

boolean isDefined(Param<?> param)

Checks whether a param is explicitly set or has a default value.

hasParam

boolean hasParam(String paramName)

Tests whether this instance contains a param with a given name.

getParam

Param<Object> getParam(String paramName)

Gets a param by its name.

set

<T> Params set(Param<T> param,
               T value)

Sets a parameter in the embedded param map.

Parameters:

param - (undocumented)

value - (undocumented)

Returns:

(undocumented)

set

Params set(String param,
           Object value)

Sets a parameter (by name) in the embedded param map.

Parameters:

param - (undocumented)

value - (undocumented)

Returns:

(undocumented)

set

Params set(ParamPair<?> paramPair)

Sets a parameter in the embedded param map.

Parameters:

paramPair - (undocumented)

Returns:

(undocumented)

get

<T> scala.Option<T> get(Param<T> param)

Optionally returns the user-supplied value of a param.

Parameters:

param - (undocumented)

Returns:

(undocumented)

clear

Params clear(Param<?> param)

Clears the user-supplied value for the input param.

Parameters:

param - (undocumented)

Returns:

(undocumented)

getOrDefault

<T> T getOrDefault(Param<T> param)

Gets the value of a param in the embedded param map or its default value. Throws an exception if neither is set.

Parameters:

param - (undocumented)

Returns:

(undocumented)

setDefault

<T> Params setDefault(Param<T> param,
                      T value)

Sets a default value for a param.

Parameters:

param - param to set the default value. Make sure that this param is initialized before this method gets called.

value - the default value

Returns:

(undocumented)

setDefault

Params setDefault(scala.collection.Seq<ParamPair<?>> paramPairs)

Sets default values for a list of params.

Note: Java developers should use the single-parameter setDefault. Annotating this with varargs can cause compilation failures due to a Scala compiler bug. See SPARK-9268.

Parameters:

paramPairs - a list of param pairs that specify params and their default values to set respectively. Make sure that the params are initialized before this method gets called.

Returns:

(undocumented)

getDefault

<T> scala.Option<T> getDefault(Param<T> param)

Gets the default value of a parameter.

Parameters:

param - (undocumented)

Returns:

(undocumented)

hasDefault

<T> boolean hasDefault(Param<T> param)

Tests whether the input param has a default value set.

Parameters:

param - (undocumented)

Returns:

(undocumented)

copy

Params copy(ParamMap extra)

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().

Parameters:

extra - (undocumented)

Returns:

(undocumented)

defaultCopy

<T extends Params> T defaultCopy(ParamMap extra)

Default implementation of copy with extra params. It tries to create a new instance with the same UID. Then it copies the embedded and extra parameters over and returns the new instance.

Parameters:

extra - (undocumented)

Returns:

(undocumented)

extractParamMap

ParamMap extractParamMap(ParamMap extra)

Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values less than user-supplied values less than extra.

Parameters:

extra - (undocumented)

Returns:

(undocumented)

extractParamMap

ParamMap extractParamMap()

extractParamMap with no extra values.

Returns:

(undocumented)

paramMap

ParamMap paramMap()

Internal param map for user-supplied values.

defaultParamMap

ParamMap defaultParamMap()

Internal param map for default values.

shouldOwn

void shouldOwn(Param<?> param)

Validates that the input param belongs to this instance.

copyValues

<T extends Params> T copyValues(T to,
                                ParamMap extra)

Copies param values from this instance to another instance for params shared by them.

This handles default Params and explicitly set Params separately. Default Params are copied from and to defaultParamMap, and explicitly set Params are copied from and to paramMap. Warning: This implicitly assumes that this Params instance and the target instance share the same set of default Params.

Parameters:

to - the target instance, which should work with the same set of default Params as this source instance

extra - extra params to be copied to the target's paramMap

Returns:

the target instance with param values copied