ForkedEstimator

abstract def copy(extra: ParamMap): SummarizableEstimator[ModelOut]

abstract def createForks(dataset: DataFrame): Seq[(ForeKeyType, DataFrame)]

Override this method and create forks to train from the data.

abstract def mergeModels(sqlContext: SQLContext, models: Seq[(ForeKeyType, ModelIn)]): ModelOut

Given models trained for each fork create a combined model.

final def !=(arg0: AnyRef): Boolean

final def !=(arg0: Any): Boolean

final def ##(): Int

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

final def ==(arg0: AnyRef): Boolean

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

final val cacheForks: Param[Boolean]

final def clear(param: Param[_]): ForkedEstimator.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

def fit(dataset: DataFrame): ModelOut

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

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

def fit(dataset: DataFrame, firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): ModelOut

def fitFork(estimator: SummarizableEstimator[ModelIn], wholeData: DataFrame, partialData: (ForeKeyType, DataFrame)): (ForeKeyType, ModelIn)

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

final def getClass(): Class[_]

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

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

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

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

def isTraceEnabled(): Boolean

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

def mayBePropagateKey(data: DataFrame, key: Any): DataFrame

final def ne(arg0: AnyRef): Boolean

val nested: SummarizableEstimator[ModelIn]

Nested estimator to call for each fork.

final def notify(): Unit

final def notifyAll(): Unit

lazy val params: Array[Param[_]]

final val pathForTempModels: Param[String]

final val propagatedKeyColumn: Param[String]

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

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

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

def setCacheForks(value: Boolean): ForkedEstimator.this.type

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

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

def setPathForTempModels(value: String): ForkedEstimator.this.type

def setPropagatedKeyColumn(value: String): ForkedEstimator.this.type

def setTrainParallel(value: Boolean): ForkedEstimator.this.type

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

def toString(): String

final val trainParallel: Param[Boolean]

def transformSchema(schema: StructType): StructType

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

val uid: String

def validateParams(): Unit

final def wait(): Unit

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

final def wait(arg0: Long): Unit