org.apache.spark.ml.classification

Class LogisticRegression

java.lang.Object

org.apache.spark.ml.PipelineStage

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

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

org.apache.spark.ml.classification.Classifier<FeaturesType,E,M>

org.apache.spark.ml.classification.ProbabilisticClassifier<Vector,LogisticRegression,LogisticRegressionModel>

org.apache.spark.ml.classification.LogisticRegression

All Implemented Interfaces:

java.io.Serializable, Params, Identifiable

public class LogisticRegression
extends ProbabilisticClassifier<Vector,LogisticRegression,LogisticRegressionModel>

:: Experimental :: Logistic regression. Currently, this class only supports binary classification. It will support multiclass in the future.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
LogisticRegression()
LogisticRegression(java.lang.String uid)

Method Summary

Methods

Modifier and Type	Method and Description
protected static <T> T	$(Param<T> param)
protected static void	checkThresholdConsistency()
void	checkThresholdConsistency() If threshold and thresholds are both set, ensures they are consistent.
static Params	clear(Param<?> param)
LogisticRegression	copy(ParamMap extra) Creates a copy of this instance with the same UID and some extra params.
protected static <T extends Params> T	copyValues(T to, ParamMap extra)
protected static <T extends Params> ParamMap	copyValues$default$2()
protected static <T extends Params> T	defaultCopy(ParamMap extra)
static DoubleParam	elasticNetParam()
static java.lang.String	explainParam(Param<?> param)
static java.lang.String	explainParams()
protected static RDD<LabeledPoint>	extractLabeledPoints(Dataset<?> dataset)
protected static RDD<LabeledPoint>	extractLabeledPoints(Dataset<?> dataset, int numClasses)
static ParamMap	extractParamMap()
static ParamMap	extractParamMap(ParamMap extra)
static Param<java.lang.String>	featuresCol()
Param<java.lang.String>	featuresCol() Param for features column name.
static M	fit(Dataset<?> dataset)
static M	fit(Dataset<?> dataset, ParamMap paramMap)
static scala.collection.Seq<M>	fit(Dataset<?> dataset, ParamMap[] paramMaps)
static M	fit(Dataset<?> dataset, ParamPair<?> firstParamPair, ParamPair<?>... otherParamPairs)
static M	fit(Dataset<?> dataset, ParamPair<?> firstParamPair, scala.collection.Seq<ParamPair<?>> otherParamPairs)
static BooleanParam	fitIntercept()
static <T> scala.Option<T>	get(Param<T> param)
static <T> scala.Option<T>	getDefault(Param<T> param)
static double	getElasticNetParam()
static java.lang.String	getFeaturesCol()
java.lang.String	getFeaturesCol()
static boolean	getFitIntercept()
static java.lang.String	getLabelCol()
java.lang.String	getLabelCol()
static int	getMaxIter()
protected static int	getNumClasses(Dataset<?> dataset, int maxNumClasses)
protected static int	getNumClasses$default$2()
static <T> T	getOrDefault(Param<T> param)
static Param<java.lang.Object>	getParam(java.lang.String paramName)
static java.lang.String	getPredictionCol()
java.lang.String	getPredictionCol()
static java.lang.String	getProbabilityCol()
static java.lang.String	getRawPredictionCol()
java.lang.String	getRawPredictionCol()
static double	getRegParam()
static boolean	getStandardization()
double	getThreshold() Get threshold for binary classification.
double[]	getThresholds() Get thresholds for binary or multiclass classification.
static double	getTol()
static java.lang.String	getWeightCol()
static <T> boolean	hasDefault(Param<T> param)
static boolean	hasParam(java.lang.String paramName)
protected static void	initializeLogIfNecessary(boolean isInterpreter)
static boolean	isDefined(Param<?> param)
static boolean	isSet(Param<?> param)
protected static boolean	isTraceEnabled()
static Param<java.lang.String>	labelCol()
Param<java.lang.String>	labelCol() Param for label column name.
static LogisticRegression	load(java.lang.String path)
protected static org.slf4j.Logger	log()
protected static void	logDebug(scala.Function0<java.lang.String> msg)
protected static void	logDebug(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void	logError(scala.Function0<java.lang.String> msg)
protected static void	logError(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void	logInfo(scala.Function0<java.lang.String> msg)
protected static void	logInfo(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static java.lang.String	logName()
protected static void	logTrace(scala.Function0<java.lang.String> msg)
protected static void	logTrace(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void	logWarning(scala.Function0<java.lang.String> msg)
protected static void	logWarning(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
static IntParam	maxIter()
static Param<?>[]	params()
static Param<java.lang.String>	predictionCol()
Param<java.lang.String>	predictionCol() Param for prediction column name.
static Param<java.lang.String>	probabilityCol()
static Param<java.lang.String>	rawPredictionCol()
Param<java.lang.String>	rawPredictionCol() Param for raw prediction (a.k.a.
static DoubleParam	regParam()
static void	save(java.lang.String path)
static <T> Params	set(Param<T> param, T value)
protected static Params	set(ParamPair<?> paramPair)
protected static Params	set(java.lang.String param, java.lang.Object value)
protected static <T> Params	setDefault(Param<T> param, T value)
protected static Params	setDefault(scala.collection.Seq<ParamPair<?>> paramPairs)
LogisticRegression	setElasticNetParam(double value) Set the ElasticNet mixing parameter.
static Learner	setFeaturesCol(java.lang.String value)
LogisticRegression	setFitIntercept(boolean value) Whether to fit an intercept term.
static Learner	setLabelCol(java.lang.String value)
LogisticRegression	setMaxIter(int value) Set the maximum number of iterations.
static Learner	setPredictionCol(java.lang.String value)
static E	setProbabilityCol(java.lang.String value)
static E	setRawPredictionCol(java.lang.String value)
LogisticRegression	setRegParam(double value) Set the regularization parameter.
LogisticRegression	setStandardization(boolean value) Whether to standardize the training features before fitting the model.
LogisticRegression	setThreshold(double value) Set threshold in binary classification, in range [0, 1].
LogisticRegression	setThresholds(double[] value) Set thresholds in multiclass (or binary) classification to adjust the probability of predicting each class.
LogisticRegression	setTol(double value) Set the convergence tolerance of iterations.
LogisticRegression	setWeightCol(java.lang.String value) Whether to over-/under-sample training instances according to the given weights in weightCol.
static BooleanParam	standardization()
static DoubleParam	threshold()
static DoubleArrayParam	thresholds()
static DoubleParam	tol()
static java.lang.String	toString()
protected LogisticRegressionModel	train(Dataset<?> dataset) Train a model using the given dataset and parameters.
protected LogisticRegressionModel	train(Dataset<?> dataset, boolean handlePersistence)
static StructType	transformSchema(StructType schema)
protected static StructType	transformSchema(StructType schema, boolean logging)
java.lang.String	uid() An immutable unique ID for the object and its derivatives.
protected static StructType	validateAndTransformSchema(StructType schema, boolean fitting, DataType featuresDataType)
StructType	validateAndTransformSchema(StructType schema, boolean fitting, DataType featuresDataType)
StructType	validateAndTransformSchema(StructType schema, boolean fitting, DataType featuresDataType) Validates and transforms the input schema with the provided param map.
static void	validateParams()
void	validateParams() Validates parameter values stored internally.
static Param<java.lang.String>	weightCol()
static MLWriter	write()

Methods inherited from class org.apache.spark.ml.classification.ProbabilisticClassifier

setProbabilityCol

Methods inherited from class org.apache.spark.ml.classification.Classifier

extractLabeledPoints, getNumClasses, setRawPredictionCol

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

extractLabeledPoints, fit, setFeaturesCol, setLabelCol, setPredictionCol, transformSchema

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

fit, fit, fit, fit

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

transformSchema

Methods inherited from class java.lang.Object

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

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

Constructor Detail

LogisticRegression

public LogisticRegression(java.lang.String uid)

LogisticRegression

public LogisticRegression()

Method Detail

load

public static LogisticRegression load(java.lang.String path)

toString

public static java.lang.String toString()

params

public static Param<?>[] params()

explainParam

public static java.lang.String explainParam(Param<?> param)

explainParams

public static java.lang.String explainParams()

isSet

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

isDefined

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

hasParam

public static boolean hasParam(java.lang.String paramName)

getParam

public static Param<java.lang.Object> getParam(java.lang.String paramName)

set

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

set

protected static final Params set(java.lang.String param,
         java.lang.Object value)

set

protected static final Params set(ParamPair<?> paramPair)

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)

$

protected static final <T> T $(Param<T> param)

setDefault

protected static final <T> Params setDefault(Param<T> param,
                    T value)

setDefault

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

getDefault

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

hasDefault

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

defaultCopy

protected static final <T extends Params> T defaultCopy(ParamMap extra)

extractParamMap

public static final ParamMap extractParamMap(ParamMap extra)

extractParamMap

public static final ParamMap extractParamMap()

copyValues

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

copyValues$default$2

protected static <T extends Params> ParamMap copyValues$default$2()

logName

protected static java.lang.String logName()

log

protected static org.slf4j.Logger log()

logInfo

protected static void logInfo(scala.Function0<java.lang.String> msg)

logDebug

protected static void logDebug(scala.Function0<java.lang.String> msg)

logTrace

protected static void logTrace(scala.Function0<java.lang.String> msg)

logWarning

protected static void logWarning(scala.Function0<java.lang.String> msg)

logError

protected static void logError(scala.Function0<java.lang.String> msg)

logInfo

protected static void logInfo(scala.Function0<java.lang.String> msg,
           java.lang.Throwable throwable)

logDebug

protected static void logDebug(scala.Function0<java.lang.String> msg,
            java.lang.Throwable throwable)

logTrace

protected static void logTrace(scala.Function0<java.lang.String> msg,
            java.lang.Throwable throwable)

logWarning

protected static void logWarning(scala.Function0<java.lang.String> msg,
              java.lang.Throwable throwable)

logError

protected static void logError(scala.Function0<java.lang.String> msg,
            java.lang.Throwable throwable)

isTraceEnabled

protected static boolean isTraceEnabled()

initializeLogIfNecessary

protected static void initializeLogIfNecessary(boolean isInterpreter)

transformSchema

protected static StructType transformSchema(StructType schema,
                         boolean logging)

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<java.lang.String> labelCol()

getLabelCol

public static final java.lang.String getLabelCol()

featuresCol

public static final Param<java.lang.String> featuresCol()

getFeaturesCol

public static final java.lang.String getFeaturesCol()

predictionCol

public static final Param<java.lang.String> predictionCol()

getPredictionCol

public static final java.lang.String getPredictionCol()

setLabelCol

public static Learner setLabelCol(java.lang.String value)

setFeaturesCol

public static Learner setFeaturesCol(java.lang.String value)

setPredictionCol

public static Learner setPredictionCol(java.lang.String value)

fit

public static M fit(Dataset<?> dataset)

transformSchema

public static StructType transformSchema(StructType schema)

extractLabeledPoints

protected static RDD<LabeledPoint> extractLabeledPoints(Dataset<?> dataset)

rawPredictionCol

public static final Param<java.lang.String> rawPredictionCol()

getRawPredictionCol

public static final java.lang.String getRawPredictionCol()

setRawPredictionCol

public static E setRawPredictionCol(java.lang.String value)

extractLabeledPoints

protected static RDD<LabeledPoint> extractLabeledPoints(Dataset<?> dataset,
                                     int numClasses)

getNumClasses

protected static int getNumClasses(Dataset<?> dataset,
                int maxNumClasses)

getNumClasses$default$2

protected static int getNumClasses$default$2()

probabilityCol

public static final Param<java.lang.String> probabilityCol()

getProbabilityCol

public static final java.lang.String getProbabilityCol()

thresholds

public static final DoubleArrayParam thresholds()

validateAndTransformSchema

protected static StructType validateAndTransformSchema(StructType schema,
                                    boolean fitting,
                                    DataType featuresDataType)

setProbabilityCol

public static E setProbabilityCol(java.lang.String value)

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()

fitIntercept

public static final BooleanParam fitIntercept()

getFitIntercept

public static final boolean getFitIntercept()

tol

public static final DoubleParam tol()

getTol

public static final double getTol()

standardization

public static final BooleanParam standardization()

getStandardization

public static final boolean getStandardization()

weightCol

public static final Param<java.lang.String> weightCol()

getWeightCol

public static final java.lang.String getWeightCol()

threshold

public static final DoubleParam threshold()

checkThresholdConsistency

protected static void checkThresholdConsistency()

validateParams

public static void validateParams()

save

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

Throws:

java.io.IOException

write

public static MLWriter write()

uid

public java.lang.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 LogisticRegression setRegParam(double value)

Set the regularization parameter. Default is 0.0.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setElasticNetParam

public LogisticRegression 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 LogisticRegression setMaxIter(int value)

Set the maximum number of iterations. Default is 100.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setTol

public LogisticRegression 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)

setFitIntercept

public LogisticRegression setFitIntercept(boolean value)

Whether to fit an intercept term. Default is true.

Parameters:

value - (undocumented)

Returns:

(undocumented)

setStandardization

public LogisticRegression 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)

setThreshold

public LogisticRegression setThreshold(double value)

Set threshold in binary classification, in range [0, 1].

If the estimated probability of class label 1 is > threshold, then predict 1, else 0. A high threshold encourages the model to predict 0 more often; a low threshold encourages the model to predict 1 more often.

Note: Calling this with threshold p is equivalent to calling setThresholds(Array(1-p, p)). When setThreshold() is called, any user-set value for thresholds will be cleared. If both threshold and thresholds are set in a ParamMap, then they must be equivalent.

Default is 0.5.

Parameters:

value - (undocumented)

Returns:

(undocumented)

getThreshold

public double getThreshold()

Get threshold for binary classification.

If threshold is set, returns that value. Otherwise, if thresholds is set with length 2 (i.e., binary classification), this returns the equivalent threshold:

1 / (1 + thresholds(0) / thresholds(1))

. Otherwise, returns {@link threshold} default value. @group getParam @throws IllegalArgumentException if {@link thresholds} is set to an array of length other than 2.

Returns:

(undocumented)

setWeightCol

public LogisticRegression setWeightCol(java.lang.String value)

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

Parameters:

value - (undocumented)

Returns:

(undocumented)

setThresholds

public LogisticRegression setThresholds(double[] value)

Set thresholds in multiclass (or binary) classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values >= 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class' threshold.

Note: When setThresholds() is called, any user-set value for threshold will be cleared. If both threshold and thresholds are set in a ParamMap, then they must be equivalent.

Overrides:

setThresholds in class ProbabilisticClassifier<Vector,LogisticRegression,LogisticRegressionModel>

Parameters:

value - (undocumented)

Returns:

(undocumented)

getThresholds

public double[] getThresholds()

Get thresholds for binary or multiclass classification.

If thresholds is set, return its value. Otherwise, if threshold is set, return the equivalent thresholds for binary classification: (1-threshold, threshold). If neither are set, throw an exception.

Returns:

(undocumented)

train

protected LogisticRegressionModel train(Dataset<?> dataset)

Description copied from class: Predictor

Train a model using the given dataset and parameters. Developers can implement this instead of fit() to avoid dealing with schema validation and copying parameters into the model.

Specified by:

train in class Predictor<Vector,LogisticRegression,LogisticRegressionModel>

Parameters:

dataset - Training dataset

Returns:

Fitted model

train

protected LogisticRegressionModel train(Dataset<?> dataset,
                            boolean handlePersistence)

copy

public LogisticRegression 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.

Specified by:

copy in interface Params

Specified by:

copy in class Predictor<Vector,LogisticRegression,LogisticRegressionModel>

Parameters:

extra - (undocumented)

Returns:

(undocumented)

See Also:

defaultCopy()

checkThresholdConsistency

public void checkThresholdConsistency()

If threshold and thresholds are both set, ensures they are consistent.

Throws:

java.lang.IllegalArgumentException - if threshold and thresholds are not equivalent

validateParams

public void validateParams()

Description copied from interface: Params

Validates parameter values stored internally. Raise an exception if any parameter value is invalid.

This only needs to check for interactions between parameters. Parameter value checks which do not depend on other parameters are handled by Param.validate(). This method does not handle input/output column parameters; those are checked during schema validation.

validateAndTransformSchema

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

rawPredictionCol

public Param<java.lang.String> rawPredictionCol()

Param for raw prediction (a.k.a. confidence) column name.

Returns:

(undocumented)

getRawPredictionCol

public java.lang.String getRawPredictionCol()

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<java.lang.String> labelCol()

Param for label column name.

Returns:

(undocumented)

getLabelCol

public java.lang.String getLabelCol()

featuresCol

public Param<java.lang.String> featuresCol()

Param for features column name.

Returns:

(undocumented)

getFeaturesCol

public java.lang.String getFeaturesCol()

predictionCol

public Param<java.lang.String> predictionCol()

Param for prediction column name.

Returns:

(undocumented)

getPredictionCol

public java.lang.String getPredictionCol()