LogisticRegression

Instance Constructors

new LogisticRegression()

Value Members

final def !=(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def !=(arg0: Any): Boolean

Definition Classes
Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def ==(arg0: Any): Boolean

Definition Classes
Any
def addOutputColumn(schema: StructType, colName: String, dataType: DataType): StructType

Attributes
protected
Definition Classes
Params
final def asInstanceOf[T0]: T0

Definition Classes
Any
def checkInputColumn(schema: StructType, colName: String, dataType: DataType): Unit

Check whether the given schema contains an input column.
Check whether the given schema contains an input column.
colName
Parameter name for the input column.
dataType
SQL DataType of the input column.

Attributes
protected
Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def explainParams(): String

Returns the documentation of all params.
Returns the documentation of all params.

Definition Classes
Params
def extractLabeledPoints(dataset: DataFrame, paramMap: ParamMap): RDD[LabeledPoint]

Extract labelCol and featuresCol from the given dataset, and put it in an RDD with strong types.
Extract labelCol and featuresCol from the given dataset, and put it in an RDD with strong types.

Attributes
protected
Definition Classes
Predictor
val featuresCol: Param[String]

param for features column name
param for features column name

Definition Classes
HasFeaturesCol
def featuresDataType: DataType

:: DeveloperApi ::
:: DeveloperApi ::
Returns the SQL DataType corresponding to the FeaturesType type parameter.
This is used by validateAndTransformSchema(). This workaround is needed since SQL has different APIs for Scala and Java.
The default value is VectorUDT, but it may be overridden if FeaturesType is not Vector.

Attributes
protected
Definition Classes
Predictor
Annotations
@DeveloperApi()
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def fit(dataset: DataFrame, paramMap: ParamMap): LogisticRegressionModel

Fits a single model to the input data with provided parameter map.
Fits a single model to the input data with provided parameter map.
dataset
input dataset
paramMap
Parameter map. These values override any specified in this Estimator's embedded ParamMap.
returns
fitted model

Definition Classes
Predictor → Estimator
def fit(dataset: DataFrame, paramMaps: Array[ParamMap]): Seq[LogisticRegressionModel]

Fits multiple models to the input data with multiple sets of parameters.
Fits multiple models to the input data with multiple sets of parameters. The default implementation uses a for loop on each parameter map. Subclasses could overwrite this to optimize multi-model training.
dataset
input dataset
paramMaps
An array of parameter maps. These values override any specified in this Estimator's embedded ParamMap.
returns
fitted models, matching the input parameter maps

Definition Classes
Estimator
def fit(dataset: DataFrame, paramPairs: ParamPair[_]*): LogisticRegressionModel

Fits a single model to the input data with optional parameters.
Fits a single model to the input data with optional parameters.
dataset
input dataset
paramPairs
Optional list of param pairs. These values override any specified in this Estimator's embedded ParamMap.
returns
fitted model

Definition Classes
Estimator
Annotations
@varargs()
def get[T](param: Param[T]): T

Gets the value of a parameter in the embedded param map.
Gets the value of a parameter in the embedded param map.

Attributes
protected
Definition Classes
Params
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getFeaturesCol: String

Definition Classes
HasFeaturesCol
def getLabelCol: String

Definition Classes
HasLabelCol
def getMaxIter: Int

Definition Classes
HasMaxIter
def getPredictionCol: String

Definition Classes
HasPredictionCol
def getProbabilityCol: String

Definition Classes
HasProbabilityCol
def getRawPredictionCol: String

Definition Classes
HasRawPredictionCol
def getRegParam: Double

Definition Classes
HasRegParam
def getThreshold: Double

Definition Classes
HasThreshold
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def isSet(param: Param[_]): Boolean

Checks whether a param is explicitly set.
Checks whether a param is explicitly set.

Definition Classes
Params
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
val labelCol: Param[String]

param for label column name
param for label column name

Definition Classes
HasLabelCol
def log: Logger

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logName: String

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
val maxIter: IntParam

param for max number of iterations
param for max number of iterations

Definition Classes
HasMaxIter
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
val paramMap: ParamMap

Internal param map.
Internal param map.

Attributes
protected
Definition Classes
Params
def params: Array[Param[_]]

Returns all params.
Returns all params.

Definition Classes
Params
val predictionCol: Param[String]

param for prediction column name
param for prediction column name

Definition Classes
HasPredictionCol
val probabilityCol: Param[String]

param for predicted class conditional probabilities column name
param for predicted class conditional probabilities column name

Definition Classes
HasProbabilityCol
val rawPredictionCol: Param[String]

param for raw prediction column name
param for raw prediction column name

Definition Classes
HasRawPredictionCol
val regParam: DoubleParam

param for regularization parameter
param for regularization parameter

Definition Classes
HasRegParam
def set[T](param: Param[T], value: T): LogisticRegression.this.type

Sets a parameter in the embedded param map.
Sets a parameter in the embedded param map.

Attributes
protected
Definition Classes
Params
def setFeaturesCol(value: String): LogisticRegression

Definition Classes
Predictor
def setLabelCol(value: String): LogisticRegression

Definition Classes
Predictor
def setMaxIter(value: Int): LogisticRegression.this.type
def setPredictionCol(value: String): LogisticRegression

Definition Classes
Predictor
def setProbabilityCol(value: String): LogisticRegression

Definition Classes
ProbabilisticClassifier
def setRawPredictionCol(value: String): LogisticRegression

Definition Classes
Classifier
def setRegParam(value: Double): LogisticRegression.this.type
def setThreshold(value: Double): LogisticRegression.this.type
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
val threshold: DoubleParam

param for threshold in (binary) prediction
param for threshold in (binary) prediction

Definition Classes
HasThreshold
def toString(): String

Definition Classes
AnyRef → Any
def train(dataset: DataFrame, paramMap: ParamMap): LogisticRegressionModel

:: DeveloperApi ::
:: DeveloperApi ::
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.
dataset
Training dataset
paramMap
Parameter map. Unlike fit()'s paramMap, this paramMap has already been combined with the embedded ParamMap.
returns
Fitted model

Attributes
protected
Definition Classes
LogisticRegression → Predictor
def transformSchema(schema: StructType, paramMap: ParamMap): StructType

:: DeveloperApi ::
:: DeveloperApi ::
Derives the output schema from the input schema and parameters. The schema describes the columns and types of the data.
schema
Input schema to this stage
paramMap
Parameters passed to this stage
returns
Output schema from this stage

Definition Classes
Predictor → PipelineStage
def transformSchema(schema: StructType, paramMap: ParamMap, logging: Boolean): StructType

Derives the output schema from the input schema and parameters, optionally with logging.
Derives the output schema from the input schema and parameters, optionally with logging.

Attributes
protected
Definition Classes
PipelineStage
def validate(): Unit

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

Definition Classes
Params
def validate(paramMap: ParamMap): Unit

Validates parameter values stored internally plus the input parameter map.
Validates parameter values stored internally plus the input parameter map. Raises an exception if any parameter is invalid.

Definition Classes
Params
def validateAndTransformSchema(schema: StructType, paramMap: ParamMap, fitting: Boolean, featuresDataType: DataType): StructType

Validates and transforms the input schema with the provided param map.
Validates and transforms the input schema with the provided param map.
schema
input schema
paramMap
additional parameters
fitting
whether this is in fitting
featuresDataType
SQL DataType for FeaturesType. E.g., org.apache.spark.mllib.linalg.VectorUDT for vector features.
returns
output schema

Attributes
protected
Definition Classes
ProbabilisticClassifierParams → ClassifierParams → PredictorParams
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Inherited from LogisticRegressionParams

Inherited from HasThreshold

Inherited from HasMaxIter

Inherited from HasRegParam

Inherited from ProbabilisticClassifier[Vector, LogisticRegression, LogisticRegressionModel]

Inherited from ProbabilisticClassifierParams

Inherited from HasProbabilityCol

Inherited from Classifier[Vector, LogisticRegression, LogisticRegressionModel]

Inherited from ClassifierParams

Inherited from HasRawPredictionCol

Inherited from Predictor[Vector, LogisticRegression, LogisticRegressionModel]

Inherited from PredictorParams

Inherited from HasPredictionCol

Inherited from HasFeaturesCol

Inherited from HasLabelCol

Inherited from Estimator[LogisticRegressionModel]

Inherited from Params

Inherited from Identifiable

Inherited from PipelineStage

Inherited from Logging

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Parameters

A list of (hyper-)parameter keys this algorithm can take. Users can set and get the parameter values through setters and getters, respectively.

Members

Parameter setters

Parameter getters

class LogisticRegression extends ProbabilisticClassifier[Vector, LogisticRegression, LogisticRegressionModel] with LogisticRegressionParams

Instance Constructors

new LogisticRegression()

Value Members

final def !=(arg0: AnyRef): Boolean

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: AnyRef): Boolean

final def ==(arg0: Any): Boolean

def addOutputColumn(schema: StructType, colName: String, dataType: DataType): StructType

final def asInstanceOf[T0]: T0

def checkInputColumn(schema: StructType, colName: String, dataType: DataType): Unit

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def explainParams(): String

def extractLabeledPoints(dataset: DataFrame, paramMap: ParamMap): RDD[LabeledPoint]

val featuresCol: Param[String]

def featuresDataType: DataType

def finalize(): Unit

def fit(dataset: DataFrame, paramMap: ParamMap): LogisticRegressionModel

def fit(dataset: DataFrame, paramMaps: Array[ParamMap]): Seq[LogisticRegressionModel]

def fit(dataset: DataFrame, paramPairs: ParamPair[_]*): LogisticRegressionModel

def get[T](param: Param[T]): T

final def getClass(): Class[_]

def getFeaturesCol: String

def getLabelCol: String

def getMaxIter: Int

def getPredictionCol: String

def getProbabilityCol: String

def getRawPredictionCol: String

def getRegParam: Double

def getThreshold: Double

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

def isSet(param: Param[_]): Boolean

def isTraceEnabled(): Boolean

val labelCol: Param[String]

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String

def logTrace(msg: ⇒ String, throwable: Throwable): Unit

def logTrace(msg: ⇒ String): Unit

def logWarning(msg: ⇒ String, throwable: Throwable): Unit

def logWarning(msg: ⇒ String): Unit

val maxIter: IntParam

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

val paramMap: ParamMap

def params: Array[Param[_]]

val predictionCol: Param[String]

val probabilityCol: Param[String]

val rawPredictionCol: Param[String]

val regParam: DoubleParam

def set[T](param: Param[T], value: T): LogisticRegression.this.type

def setFeaturesCol(value: String): LogisticRegression

def setLabelCol(value: String): LogisticRegression

def setMaxIter(value: Int): LogisticRegression.this.type

def setPredictionCol(value: String): LogisticRegression

def setProbabilityCol(value: String): LogisticRegression

def setRawPredictionCol(value: String): LogisticRegression

def setRegParam(value: Double): LogisticRegression.this.type

def setThreshold(value: Double): LogisticRegression.this.type

final def synchronized[T0](arg0: ⇒ T0): T0

val threshold: DoubleParam

def toString(): String

def train(dataset: DataFrame, paramMap: ParamMap): LogisticRegressionModel

def transformSchema(schema: StructType, paramMap: ParamMap): StructType

def transformSchema(schema: StructType, paramMap: ParamMap, logging: Boolean): StructType

def validate(): Unit

def validate(paramMap: ParamMap): Unit

def validateAndTransformSchema(schema: StructType, paramMap: ParamMap, fitting: Boolean, featuresDataType: DataType): StructType

final def wait(): Unit