org.apache.spark.ml.classification

Class LogisticRegressionModel

java.lang.Object

org.apache.spark.ml.PipelineStage

org.apache.spark.ml.Transformer

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

org.apache.spark.ml.PredictionModel<FeaturesType,M>

org.apache.spark.ml.classification.ClassificationModel<FeaturesType,M>

org.apache.spark.ml.classification.ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

org.apache.spark.ml.classification.LogisticRegressionModel

All Implemented Interfaces:

java.io.Serializable, Params, Identifiable, MLWritable

public class LogisticRegressionModel
extends ProbabilisticClassificationModel<Vector,LogisticRegressionModel>
implements MLWritable

:: Experimental :: Model produced by LogisticRegression.

See Also:

Serialized Form

Method Summary

Methods

Modifier and Type	Method and Description
protected static <T> T	$(Param<T> param)
protected static void	checkThresholdConsistency()
void	checkThresholdConsistency() If threshold and thresholds are both set, ensures they are consistent.
static Params	clear(Param<?> param)
Vector	coefficients()
LogisticRegressionModel	copy(ParamMap extra) Creates a copy of this instance with the same UID and some extra params.
protected static <T extends Params> T	copyValues(T to, ParamMap extra)
protected static <T extends Params> ParamMap	copyValues$default$2()
protected static <T extends Params> T	defaultCopy(ParamMap extra)
static DoubleParam	elasticNetParam()
LogisticRegressionSummary	evaluate(Dataset<?> dataset) Evaluates the model on a test dataset.
static java.lang.String	explainParam(Param<?> param)
static java.lang.String	explainParams()
static ParamMap	extractParamMap()
static ParamMap	extractParamMap(ParamMap extra)
static Param<java.lang.String>	featuresCol()
Param<java.lang.String>	featuresCol() Param for features column name.
protected static DataType	featuresDataType()
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()
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)
static boolean	hasParent()
boolean	hasSummary() Indicates whether a training summary exists for this model instance.
protected static void	initializeLogIfNecessary(boolean isInterpreter)
double	intercept()
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 LogisticRegressionModel	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()
int	numClasses()
int	numFeatures()
static Param<?>[]	params()
static void	parent_$eq(Estimator<M> x$1)
static Estimator<M>	parent()
protected double	predict(Vector features) Predict label for the given feature vector.
static Param<java.lang.String>	predictionCol()
Param<java.lang.String>	predictionCol() Param for prediction column name.
protected static Vector	predictProbability(FeaturesType features)
protected Vector	predictRaw(Vector features)
protected double	probability2prediction(Vector probability) Given a vector of class conditional probabilities, select the predicted label.
static Param<java.lang.String>	probabilityCol()
protected double	raw2prediction(Vector rawPrediction) Given a vector of raw predictions, select the predicted label.
protected static Vector	raw2probability(Vector rawPrediction)
protected Vector	raw2probabilityInPlace(Vector rawPrediction) Estimate the probability of each class given the raw prediction, doing the computation in-place.
static Param<java.lang.String>	rawPredictionCol()
Param<java.lang.String>	rawPredictionCol() Param for raw prediction (a.k.a.
static MLReader<LogisticRegressionModel>	read()
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)
static M	setFeaturesCol(java.lang.String value)
static M	setParent(Estimator<M> parent)
static M	setPredictionCol(java.lang.String value)
static M	setProbabilityCol(java.lang.String value)
static M	setRawPredictionCol(java.lang.String value)
LogisticRegressionModel	setThreshold(double value) Set threshold in binary classification, in range [0, 1].
LogisticRegressionModel	setThresholds(double[] value) Set thresholds in multiclass (or binary) classification to adjust the probability of predicting each class.
static BooleanParam	standardization()
LogisticRegressionTrainingSummary	summary() Gets summary of model on training set.
static DoubleParam	threshold()
static DoubleArrayParam	thresholds()
static DoubleParam	tol()
static java.lang.String	toString()
static Dataset<Row>	transform(Dataset<?> dataset)
static Dataset<Row>	transform(Dataset<?> dataset, ParamMap paramMap)
static Dataset<Row>	transform(Dataset<?> dataset, ParamPair<?> firstParamPair, ParamPair<?>... otherParamPairs)
static Dataset<Row>	transform(Dataset<?> dataset, ParamPair<?> firstParamPair, scala.collection.Seq<ParamPair<?>> otherParamPairs)
protected static Dataset<Row>	transformImpl(Dataset<?> dataset)
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()
MLWriter	write() Returns a MLWriter instance for this ML instance.

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

normalizeToProbabilitiesInPlace, predictProbability, raw2probability, setProbabilityCol, transform

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

setRawPredictionCol

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

featuresDataType, setFeaturesCol, setPredictionCol, transformImpl, transformSchema

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

hasParent, parent, setParent

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

transform, transform, transform

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

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

save

Method Detail

read

public static MLReader<LogisticRegressionModel> read()

load

public static LogisticRegressionModel 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)

transform

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

transform

public static Dataset<Row> transform(Dataset<?> dataset,
                     ParamMap paramMap)

transform

public static Dataset<Row> transform(Dataset<?> dataset,
                     ParamPair<?> firstParamPair,
                     ParamPair<?>... otherParamPairs)

parent

public static Estimator<M> parent()

parent_$eq

public static void parent_$eq(Estimator<M> x$1)

setParent

public static M setParent(Estimator<M> parent)

hasParent

public static boolean hasParent()

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()

setFeaturesCol

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

setPredictionCol

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

featuresDataType

protected static DataType featuresDataType()

transformSchema

public static StructType transformSchema(StructType schema)

transformImpl

protected static Dataset<Row> transformImpl(Dataset<?> dataset)

rawPredictionCol

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

getRawPredictionCol

public static final java.lang.String getRawPredictionCol()

setRawPredictionCol

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

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 M setProbabilityCol(java.lang.String value)

transform

public static Dataset<Row> transform(Dataset<?> dataset)

raw2probability

protected static Vector raw2probability(Vector rawPrediction)

predictProbability

protected static Vector predictProbability(FeaturesType features)

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

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

Specified by:

uid in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

Returns:

(undocumented)

coefficients

public Vector coefficients()

intercept

public double intercept()

setThreshold

public LogisticRegressionModel 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)

setThresholds

public LogisticRegressionModel 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 ProbabilisticClassificationModel<Vector,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.

Overrides:

getThresholds in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

Returns:

(undocumented)

numFeatures

public int numFeatures()

Overrides:

numFeatures in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

numClasses

public int numClasses()

Specified by:

numClasses in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

summary

public LogisticRegressionTrainingSummary summary()

Gets summary of model on training set. An exception is thrown if trainingSummary == None.

Returns:

(undocumented)

hasSummary

public boolean hasSummary()

Indicates whether a training summary exists for this model instance.

evaluate

public LogisticRegressionSummary evaluate(Dataset<?> dataset)

Evaluates the model on a test dataset.

Parameters:

dataset - Test dataset to evaluate model on.

Returns:

(undocumented)

predict

protected double predict(Vector features)

Predict label for the given feature vector. The behavior of this can be adjusted using thresholds.

Overrides:

predict in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

Parameters:

features - (undocumented)

Returns:

(undocumented)

raw2probabilityInPlace

protected Vector raw2probabilityInPlace(Vector rawPrediction)

Description copied from class: ProbabilisticClassificationModel

Estimate the probability of each class given the raw prediction, doing the computation in-place. These predictions are also called class conditional probabilities.

This internal method is used to implement transform() and output probabilityCol.

Specified by:

raw2probabilityInPlace in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

Parameters:

rawPrediction - (undocumented)

Returns:

Estimated class conditional probabilities (modified input vector)

predictRaw

protected Vector predictRaw(Vector features)

Specified by:

predictRaw in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

copy

public LogisticRegressionModel 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 ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

Parameters:

extra - (undocumented)

Returns:

(undocumented)

See Also:

defaultCopy()

raw2prediction

protected double raw2prediction(Vector rawPrediction)

Description copied from class: ClassificationModel

Given a vector of raw predictions, select the predicted label. This may be overridden to support thresholds which favor particular labels.

Overrides:

raw2prediction in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

Parameters:

rawPrediction - (undocumented)

Returns:

predicted label

probability2prediction

protected double probability2prediction(Vector probability)

Description copied from class: ProbabilisticClassificationModel

Given a vector of class conditional probabilities, select the predicted label. This supports thresholds which favor particular labels.

Overrides:

probability2prediction in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>

Parameters:

probability - (undocumented)

Returns:

predicted label

write

public MLWriter write()

Returns a MLWriter instance for this ML instance.

For LogisticRegressionModel, this does NOT currently save the training summary. An option to save summary may be added in the future.

This also does not save the parent currently.

Specified by:

write in interface MLWritable

Returns:

(undocumented)

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()