Splitter

abstract def copy(extra: ParamMap): Params

abstract def preValidationPrepare(data: Dataset[Row]): PrevalidationVal

Function to set parameters before passing into the validation step eg - do data balancing or dropping based on the labels

final def !=(arg0: Any): Boolean

final def ##(): Int

final def $[T](param: Param[T]): T

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def checkPreconditions(): Unit

final def clear(param: Param[_]): Splitter.this.type

def clone(): AnyRef

def copyValues[T <: Params](to: T, extra: ParamMap): T

final def defaultCopy[T <: Params](extra: ParamMap): T

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def explainParam(param: Param[_]): String

def explainParams(): String

final def extractParamMap(): ParamMap

final def extractParamMap(extra: ParamMap): ParamMap

def finalize(): Unit

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

final def getClass(): Class[_]

final def getDefault[T](param: Param[T]): Option[T]

def getMaxTrainingSample: Int

final def getOrDefault[T](param: Param[T]): T

def getParam(paramName: String): Param[Any]

def getReserveTestFraction: Double

def getSeed: Long

final def hasDefault[T](param: Param[T]): Boolean

def hasParam(paramName: String): Boolean

def hashCode(): Int

final def isDefined(param: Param[_]): Boolean

final def isInstanceOf[T0]: Boolean

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

final val labelColumnName: Param[String]

final val maxTrainingSample: IntParam

Maximum size of dataset want to train on.

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

lazy val params: Array[Param[_]]

final val reserveTestFraction: DoubleParam

Fraction of data to reserve for test Default is 0.1

final val seed: LongParam

Seed for data splitting

final def set(paramPair: ParamPair[_]): Splitter.this.type

final def set(param: String, value: Any): Splitter.this.type

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

final def setDefault(paramPairs: ParamPair[_]*): Splitter.this.type

final def setDefault[T](param: Param[T], value: T): Splitter.this.type

def setMaxTrainingSample(value: Int): Splitter.this.type

def setReserveTestFraction(value: Double): Splitter.this.type

def setSeed(value: Long): Splitter.this.type

def split[T](data: Dataset[T]): (Dataset[T], Dataset[T])

Function to use to create the training set and test set.

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

def toString(): String

val uid: String

def validationPrepare(data: Dataset[Row]): Dataset[Row]

Function to use to prepare the dataset for modeling within the validation step eg - do data balancing or dropping based on the labels

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

def withLabelColumnName(label: String): Splitter

Add a splitter parameter to name the label column