org.apache.spark.mllib.classification

Class LogisticRegressionModel

Object

org.apache.spark.mllib.regression.GeneralizedLinearModel

org.apache.spark.mllib.classification.LogisticRegressionModel

All Implemented Interfaces:

java.io.Serializable, ClassificationModel, Saveable

public class LogisticRegressionModel
extends GeneralizedLinearModel
implements ClassificationModel, scala.Serializable, Saveable

Classification model trained using Multinomial/Binary Logistic Regression.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
LogisticRegressionModel(Vector weights, double intercept) Constructs a LogisticRegressionModel with weights and intercept for binary classification.
LogisticRegressionModel(Vector weights, double intercept, int numFeatures, int numClasses)

Method Summary

Methods

Modifier and Type	Method and Description
LogisticRegressionModel	clearThreshold() :: Experimental :: Clears the threshold so that predict will output raw prediction scores.
scala.Option<Object>	getThreshold() :: Experimental :: Returns the threshold (if any) used for converting raw prediction scores into 0/1 predictions.
double	intercept()
static LogisticRegressionModel	load(SparkContext sc, String path)
int	numClasses()
int	numFeatures()
void	save(SparkContext sc, String path) Save this model to the given path.
LogisticRegressionModel	setThreshold(double threshold) :: Experimental :: Sets the threshold that separates positive predictions from negative predictions in Binary Logistic Regression.
Vector	weights()

Methods inherited from class org.apache.spark.mllib.regression.GeneralizedLinearModel

predict, predict, toString

Methods inherited from class Object

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

Methods inherited from interface org.apache.spark.mllib.classification.ClassificationModel

predict, predict, predict

Constructor Detail

LogisticRegressionModel

public LogisticRegressionModel(Vector weights,
                       double intercept,
                       int numFeatures,
                       int numClasses)

LogisticRegressionModel

public LogisticRegressionModel(Vector weights,
                       double intercept)

Constructs a LogisticRegressionModel with weights and intercept for binary classification.

Method Detail

load

public static LogisticRegressionModel load(SparkContext sc,
                           String path)

weights

public Vector weights()

Overrides:

weights in class GeneralizedLinearModel

intercept

public double intercept()

Overrides:

intercept in class GeneralizedLinearModel

numFeatures

public int numFeatures()

numClasses

public int numClasses()

setThreshold

public LogisticRegressionModel setThreshold(double threshold)

:: Experimental :: Sets the threshold that separates positive predictions from negative predictions in Binary Logistic Regression. An example with prediction score greater than or equal to this threshold is identified as an positive, and negative otherwise. The default value is 0.5.

getThreshold

public scala.Option<Object> getThreshold()

:: Experimental :: Returns the threshold (if any) used for converting raw prediction scores into 0/1 predictions.

clearThreshold

public LogisticRegressionModel clearThreshold()

:: Experimental :: Clears the threshold so that predict will output raw prediction scores.

save

public void save(SparkContext sc,
        String path)

Description copied from interface: Saveable

Save this model to the given path.

This saves: - human-readable (JSON) model metadata to path/metadata/ - Parquet formatted data to path/data/

The model may be loaded using Loader.load.

Specified by:

save in interface Saveable

Parameters:

sc - Spark context used to save model data.

path - Path specifying the directory in which to save this model. If the directory already exists, this method throws an exception.