org.apache.spark.ml.regression

Class LinearRegression

Object

org.apache.spark.ml.PipelineStage

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

org.apache.spark.ml.Predictor<FeaturesType,Learner,M>

org.apache.spark.ml.regression.LinearRegression

All Implemented Interfaces:

java.io.Serializable, Params, DefaultParamsWritable, Identifiable, MLWritable

public class LinearRegression
extends Predictor<FeaturesType,Learner,M>
implements DefaultParamsWritable

Linear regression.

The learning objective is to minimize the squared error, with regularization. The specific squared error loss function used is: L = 1/2n ||A coefficients - y||^2^

This supports multiple types of regularization: - none (a.k.a. ordinary least squares) - L2 (ridge regression) - L1 (Lasso) - L2 + L1 (elastic net)

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
LinearRegression()
LinearRegression(String uid)

Method Summary

Methods

Modifier and Type	Method and Description
static Params	clear(Param<?> param)
LinearRegression	copy(ParamMap extra) Creates a copy of this instance with the same UID and some extra params.
static DoubleParam	elasticNetParam()
static String	explainParam(Param<?> param)
static String	explainParams()
static ParamMap	extractParamMap()
static ParamMap	extractParamMap(ParamMap extra)
static Param<String>	featuresCol()
Param<String>	featuresCol() Param for features column name.
static M	fit(Dataset<?> dataset)
static M	fit(Dataset<?> dataset, ParamMap paramMap)
static scala.collection.Seq<M>	fit(Dataset<?> dataset, ParamMap[] paramMaps)
static M	fit(Dataset<?> dataset, ParamPair<?> firstParamPair, ParamPair<?>... otherParamPairs)
static M	fit(Dataset<?> dataset, ParamPair<?> firstParamPair, scala.collection.Seq<ParamPair<?>> otherParamPairs)
static BooleanParam	fitIntercept()
static <T> scala.Option<T>	get(Param<T> param)
static <T> scala.Option<T>	getDefault(Param<T> param)
static double	getElasticNetParam()
static String	getFeaturesCol()
String	getFeaturesCol()
static boolean	getFitIntercept()
static String	getLabelCol()
String	getLabelCol()
static int	getMaxIter()
static <T> T	getOrDefault(Param<T> param)
static Param<Object>	getParam(String paramName)
static String	getPredictionCol()
String	getPredictionCol()
static double	getRegParam()
static String	getSolver()
static boolean	getStandardization()
static double	getTol()
static String	getWeightCol()
static <T> boolean	hasDefault(Param<T> param)
static boolean	hasParam(String paramName)
static boolean	isDefined(Param<?> param)
static boolean	isSet(Param<?> param)
static Param<String>	labelCol()
Param<String>	labelCol() Param for label column name.
static LinearRegression	load(String path)
static IntParam	maxIter()
static Param<?>[]	params()
static Param<String>	predictionCol()
Param<String>	predictionCol() Param for prediction column name.
static DoubleParam	regParam()
static void	save(String path)
static <T> Params	set(Param<T> param, T value)
LinearRegression	setElasticNetParam(double value) Set the ElasticNet mixing parameter.
static Learner	setFeaturesCol(String value)
LinearRegression	setFitIntercept(boolean value) Set if we should fit the intercept Default is true.
static Learner	setLabelCol(String value)
LinearRegression	setMaxIter(int value) Set the maximum number of iterations.
static Learner	setPredictionCol(String value)
LinearRegression	setRegParam(double value) Set the regularization parameter.
LinearRegression	setSolver(String value) Set the solver algorithm used for optimization.
LinearRegression	setStandardization(boolean value) Whether to standardize the training features before fitting the model.
LinearRegression	setTol(double value) Set the convergence tolerance of iterations.
LinearRegression	setWeightCol(String value) Whether to over-/under-sample training instances according to the given weights in weightCol.
static Param<String>	solver()
static BooleanParam	standardization()
static DoubleParam	tol()
static String	toString()
static StructType	transformSchema(StructType schema)
String	uid() An immutable unique ID for the object and its derivatives.
StructType	validateAndTransformSchema(StructType schema, boolean fitting, DataType featuresDataType) Validates and transforms the input schema with the provided param map.
static void	validateParams()
static Param<String>	weightCol()
static MLWriter	write()

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

fit, setFeaturesCol, setLabelCol, setPredictionCol, transformSchema

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

fit, fit, fit, fit

Methods inherited from class Object

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

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

write

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

save

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, validateParams

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

toString

Constructor Detail

LinearRegression

public LinearRegression(String uid)

LinearRegression

public LinearRegression()

Method Detail

load

public static LinearRegression load(String path)

toString

public static String toString()

params

public static Param<?>[] params()

validateParams

public static void validateParams()

explainParam

public static String explainParam(Param<?> param)

explainParams

public static String explainParams()

isSet

public static final boolean isSet(Param<?> param)

isDefined

public static final boolean isDefined(Param<?> param)

hasParam

public static boolean hasParam(String paramName)

getParam

public static Param<Object> getParam(String paramName)

set

public static final <T> Params set(Param<T> param,
             T value)

get

public static final <T> scala.Option<T> get(Param<T> param)

clear

public static final Params clear(Param<?> param)

getOrDefault

public static final <T> T getOrDefault(Param<T> param)

getDefault

public static final <T> scala.Option<T> getDefault(Param<T> param)

hasDefault

public static final <T> boolean hasDefault(Param<T> param)

extractParamMap

public static final ParamMap extractParamMap(ParamMap extra)

extractParamMap

public static final ParamMap extractParamMap()

fit

public static M fit(Dataset<?> dataset,
    ParamPair<?> firstParamPair,
    scala.collection.Seq<ParamPair<?>> otherParamPairs)

fit

public static M fit(Dataset<?> dataset,
    ParamMap paramMap)

fit

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

fit

public static M fit(Dataset<?> dataset,
    ParamPair<?> firstParamPair,
    ParamPair<?>... otherParamPairs)

labelCol

public static final Param<String> labelCol()

getLabelCol

public static final String getLabelCol()

featuresCol

public static final Param<String> featuresCol()

getFeaturesCol

public static final String getFeaturesCol()

predictionCol

public static final Param<String> predictionCol()

getPredictionCol

public static final String getPredictionCol()

setLabelCol

public static Learner setLabelCol(String value)

setFeaturesCol

public static Learner setFeaturesCol(String value)

setPredictionCol

public static Learner setPredictionCol(String value)

fit

public static M fit(Dataset<?> dataset)

transformSchema

public static StructType transformSchema(StructType schema)

regParam

public static final DoubleParam regParam()

getRegParam

public static final double getRegParam()

elasticNetParam

public static final DoubleParam elasticNetParam()

getElasticNetParam

public static final double getElasticNetParam()

maxIter

public static final IntParam maxIter()

getMaxIter

public static final int getMaxIter()

tol

public static final DoubleParam tol()

getTol

public static final double getTol()

fitIntercept

public static final BooleanParam fitIntercept()

getFitIntercept

public static final boolean getFitIntercept()

standardization

public static final BooleanParam standardization()

getStandardization

public static final boolean getStandardization()

weightCol

public static final Param<String> weightCol()

getWeightCol

public static final String getWeightCol()

solver

public static final Param<String> solver()

getSolver

public static final String getSolver()

save

public static void save(String path)
                 throws java.io.IOException

Throws:

java.io.IOException

write

public static MLWriter write()

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)

setRegParam

public LinearRegression setRegParam(double value)

Set the regularization parameter. Default is 0.0.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setFitIntercept

public LinearRegression setFitIntercept(boolean value)

Set if we should fit the intercept Default is true.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setStandardization

public LinearRegression setStandardization(boolean value)

Whether to standardize the training features before fitting the model. The coefficients of models will be always returned on the original scale, so it will be transparent for users. Note that with/without standardization, the models should be always converged to the same solution when no regularization is applied. In R's GLMNET package, the default behavior is true as well. Default is true.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setElasticNetParam

public LinearRegression setElasticNetParam(double value)

Set the ElasticNet mixing parameter. For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty. For 0 < alpha < 1, the penalty is a combination of L1 and L2. Default is 0.0 which is an L2 penalty.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setMaxIter

public LinearRegression setMaxIter(int value)

Set the maximum number of iterations. Default is 100.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setTol

public LinearRegression setTol(double value)

Set the convergence tolerance of iterations. Smaller value will lead to higher accuracy with the cost of more iterations. Default is 1E-6.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setWeightCol

public LinearRegression setWeightCol(String value)

Whether to over-/under-sample training instances according to the given weights in weightCol. If not set or empty, all instances are treated equally (weight 1.0). Default is not set, so all instances have weight one.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setSolver

public LinearRegression setSolver(String value)

Set the solver algorithm used for optimization. In case of linear regression, this can be "l-bfgs", "normal" and "auto". "l-bfgs" denotes Limited-memory BFGS which is a limited-memory quasi-Newton optimization method. "normal" denotes using Normal Equation as an analytical solution to the linear regression problem. The default value is "auto" which means that the solver algorithm is selected automatically.

Parameters:

value - (undocumented)

Returns:

(undocumented)

copy

public LinearRegression 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 Predictor<Vector,LinearRegression,LinearRegressionModel>

Parameters:

extra - (undocumented)

Returns:

(undocumented)

validateAndTransformSchema

public StructType validateAndTransformSchema(StructType schema,
                                    boolean fitting,
                                    DataType featuresDataType)

Validates and transforms the input schema with the provided param map.

Parameters:

schema - input schema

fitting - whether this is in fitting

featuresDataType - SQL DataType for FeaturesType. E.g., VectorUDT for vector features.

Returns:

output schema

labelCol

public Param<String> labelCol()

Param for label column name.

Returns:

(undocumented)

getLabelCol

public String getLabelCol()

featuresCol

public Param<String> featuresCol()

Param for features column name.

Returns:

(undocumented)

getFeaturesCol

public String getFeaturesCol()

predictionCol

public Param<String> predictionCol()

Param for prediction column name.

Returns:

(undocumented)

getPredictionCol

public String getPredictionCol()