org.apache.spark.ml

Class Estimator<M extends Model<M>>

Object

org.apache.spark.ml.PipelineStage

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

All Implemented Interfaces:

java.io.Serializable, Logging, Identifiable, Params

Direct Known Subclasses:

CrossValidator, LogisticRegression, Pipeline, StandardScaler

public abstract class Estimator<M extends Model<M>>
extends PipelineStage
implements Params

:: AlphaComponent :: Abstract class for estimators that fit models to data.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
Estimator()

Method Summary

Methods

Modifier and Type	Method and Description
M	fit(JavaSchemaRDD dataset, ParamMap paramMap) Fits a single model to the input data with provided parameter map.
java.util.List<M>	fit(JavaSchemaRDD dataset, ParamMap[] paramMaps) Fits multiple models to the input data with multiple sets of parameters.
M	fit(JavaSchemaRDD dataset, ParamPair<?>... paramPairs) Fits a single model to the input data with optional parameters.
M	fit(JavaSchemaRDD dataset, scala.collection.Seq<ParamPair<?>> paramPairs) Fits a single model to the input data with optional parameters.
abstract M	fit(SchemaRDD dataset, ParamMap paramMap) Fits a single model to the input data with provided parameter map.
scala.collection.Seq<M>	fit(SchemaRDD dataset, ParamMap[] paramMaps) Fits multiple models to the input data with multiple sets of parameters.
M	fit(SchemaRDD dataset, ParamPair<?>... paramPairs) Fits a single model to the input data with optional parameters.
M	fit(SchemaRDD dataset, scala.collection.Seq<ParamPair<?>> paramPairs) Fits a single model to the input data with optional parameters.

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

transformSchema

Methods inherited from class Object

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

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

explainParams, get, getParam, isSet, paramMap, params, set, validate, validate

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

uid

Methods inherited from interface org.apache.spark.Logging

initializeIfNecessary, initializeLogging, isTraceEnabled, log_, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarning

Constructor Detail

Estimator

public Estimator()

Method Detail

fit

public M fit(SchemaRDD dataset,
    ParamPair<?>... paramPairs)

Fits a single model to the input data with optional parameters.

Parameters:

dataset - input dataset

paramPairs - optional list of param pairs (overwrite embedded params)

Returns:

fitted model

fit

public M fit(JavaSchemaRDD dataset,
    ParamPair<?>... paramPairs)

Fits a single model to the input data with optional parameters.

Parameters:

dataset - input dataset

paramPairs - optional list of param pairs (overwrite embedded params)

Returns:

fitted model

fit

public M fit(SchemaRDD dataset,
    scala.collection.Seq<ParamPair<?>> paramPairs)

Fits a single model to the input data with optional parameters.

Parameters:

dataset - input dataset

paramPairs - optional list of param pairs (overwrite embedded params)

Returns:

fitted model

fit

public abstract M fit(SchemaRDD dataset,
    ParamMap paramMap)

Fits a single model to the input data with provided parameter map.

Parameters:

dataset - input dataset

paramMap - parameter map

Returns:

fitted model

fit

public scala.collection.Seq<M> fit(SchemaRDD dataset,
                          ParamMap[] paramMaps)

Fits multiple models to the input data with multiple sets of parameters. The default implementation uses a for loop on each parameter map. Subclasses could overwrite this to optimize multi-model training.

Parameters:

dataset - input dataset

paramMaps - an array of parameter maps

Returns:

fitted models, matching the input parameter maps

fit

public M fit(JavaSchemaRDD dataset,
    scala.collection.Seq<ParamPair<?>> paramPairs)

Fits a single model to the input data with optional parameters.

Parameters:

dataset - input dataset

paramPairs - optional list of param pairs (overwrite embedded params)

Returns:

fitted model

fit

public M fit(JavaSchemaRDD dataset,
    ParamMap paramMap)

Fits a single model to the input data with provided parameter map.

Parameters:

dataset - input dataset

paramMap - parameter map

Returns:

fitted model

fit

public java.util.List<M> fit(JavaSchemaRDD dataset,
                    ParamMap[] paramMaps)

Fits multiple models to the input data with multiple sets of parameters.

Parameters:

dataset - input dataset

paramMaps - an array of parameter maps

Returns:

fitted models, matching the input parameter maps