org.apache.spark.ml.classification

Class NaiveBayesModel

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,NaiveBayesModel>

org.apache.spark.ml.classification.NaiveBayesModel

All Implemented Interfaces:

java.io.Serializable, Params, Identifiable, MLWritable

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

:: Experimental :: Model produced by NaiveBayes param: pi log of class priors, whose dimension is C (number of classes) param: theta log of class conditional probabilities, whose dimension is C (number of classes) by D (number of features)

See Also:

Serialized Form

Method Summary

Methods

Modifier and Type	Method and Description
protected static <T> T	$(Param<T> param)
static Params	clear(Param<?> param)
NaiveBayesModel	copy(ParamMap extra) Creates a copy of this instance with the same UID and some extra params.
protected static <T extends Params> T	copyValues(T to, ParamMap extra)
protected static <T extends Params> ParamMap	copyValues$default$2()
protected static <T extends Params> T	defaultCopy(ParamMap extra)
static 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 <T> scala.Option<T>	get(Param<T> param)
static <T> scala.Option<T>	getDefault(Param<T> param)
static java.lang.String	getFeaturesCol()
java.lang.String	getFeaturesCol()
static java.lang.String	getLabelCol()
java.lang.String	getLabelCol()
static java.lang.String	getModelType()
java.lang.String	getModelType()
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	getSmoothing()
double	getSmoothing()
static double[]	getThresholds()
static <T> boolean	hasDefault(Param<T> param)
static boolean	hasParam(java.lang.String paramName)
static boolean	hasParent()
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 NaiveBayesModel	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 Param<java.lang.String>	modelType()
Param<java.lang.String>	modelType() The model type which is a string (case-sensitive).
int	numClasses()
int	numFeatures()
static Param<?>[]	params()
static void	parent_$eq(Estimator<M> x$1)
static Estimator<M>	parent()
Vector	pi()
protected static double	predict(FeaturesType features)
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 static double	probability2prediction(Vector probability)
static Param<java.lang.String>	probabilityCol()
protected static double	raw2prediction(Vector rawPrediction)
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<NaiveBayesModel>	read()
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)
static M	setThresholds(double[] value)
static DoubleParam	smoothing()
DoubleParam	smoothing() The smoothing parameter.
Matrix	theta()
static DoubleArrayParam	thresholds()
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()
MLWriter	write() Returns an MLWriter instance for this ML instance.

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

normalizeToProbabilitiesInPlace, predictProbability, probability2prediction, raw2prediction, raw2probability, setProbabilityCol, setThresholds, transform

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

predict, 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, wait, wait, wait

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

Method Detail

read

public static MLReader<NaiveBayesModel> read()

load

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

params

public static Param<?>[] params()

validateParams

public static void validateParams()

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)

predict

protected static double predict(FeaturesType features)

probabilityCol

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

getProbabilityCol

public static final java.lang.String getProbabilityCol()

thresholds

public static final DoubleArrayParam thresholds()

getThresholds

public static double[] getThresholds()

validateAndTransformSchema

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

setProbabilityCol

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

setThresholds

public static M setThresholds(double[] value)

transform

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

raw2probability

protected static Vector raw2probability(Vector rawPrediction)

raw2prediction

protected static double raw2prediction(Vector rawPrediction)

predictProbability

protected static Vector predictProbability(FeaturesType features)

probability2prediction

protected static double probability2prediction(Vector probability)

smoothing

public static final DoubleParam smoothing()

getSmoothing

public static final double getSmoothing()

modelType

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

getModelType

public static final java.lang.String getModelType()

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,NaiveBayesModel>

Returns:

(undocumented)

pi

public Vector pi()

theta

public Matrix theta()

numFeatures

public int numFeatures()

Overrides:

numFeatures in class ProbabilisticClassificationModel<Vector,NaiveBayesModel>

numClasses

public int numClasses()

Specified by:

numClasses in class ProbabilisticClassificationModel<Vector,NaiveBayesModel>

predictRaw

protected Vector predictRaw(Vector features)

Specified by:

predictRaw in class ProbabilisticClassificationModel<Vector,NaiveBayesModel>

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,NaiveBayesModel>

Parameters:

rawPrediction - (undocumented)

Returns:

Estimated class conditional probabilities (modified input vector)

copy

public NaiveBayesModel 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,NaiveBayesModel>

Parameters:

extra - (undocumented)

Returns:

(undocumented)

See Also:

defaultCopy()

toString

public java.lang.String toString()

Specified by:

toString in interface Identifiable

Overrides:

toString in class ProbabilisticClassificationModel<Vector,NaiveBayesModel>

write

public MLWriter write()

Description copied from interface: MLWritable

Returns an MLWriter instance for this ML instance.

Specified by:

write in interface MLWritable

Returns:

(undocumented)

smoothing

public DoubleParam smoothing()

The smoothing parameter. (default = 1.0).

Returns:

(undocumented)

getSmoothing

public double getSmoothing()

modelType

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

The model type which is a string (case-sensitive). Supported options: "multinomial" and "bernoulli". (default = multinomial)

Returns:

(undocumented)

getModelType

public java.lang.String getModelType()

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()