OpOneHotVectorizer

abstract def convertToSeqOfMaps(dataset: Dataset[Seq[T.Value]]): RDD[Seq[Map[String, Int]]]

abstract def makeModel(topValues: Seq[Seq[String]], shouldCleanText: Boolean, shouldTrackNulls: Boolean, operationName: String, uid: String): SequenceModel[T, OPVector]

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

final def checkInputLength(features: Array[_]): Boolean

Checks the input length

final def checkSerializable: Try[Unit]

Check if the stage is serializable

final val cleanText: BooleanParam

def cleanTextFn(s: String, shouldClean: Boolean): String

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

def clone(): AnyRef

final def copy(extra: ParamMap): OpOneHotVectorizer.this.type

This method is used to make a copy of the instance with new parameters in several methods in spark internals Default will find the constructor and make a copy for any class (AS LONG AS ALL CONSTRUCTOR PARAMS ARE VALS, this is why type tags are written as implicit vals in base classes).

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

def countMapUniques[V](dataset: Dataset[Seq[Map[String, V]]], size: Int, bits: Int)(implicit kryo: KryoSerializer, ct: ClassTag[V]): (Seq[Map[String, HLL]], Long)

Count unique values of each of the sequence & map key components in the dataset using HyperLogLog HLL

def countUniques[V](dataset: Dataset[Seq[V]], size: Int, bits: Int)(implicit kryo: KryoSerializer, ct: ClassTag[V]): (Seq[HLL], Long)

Count unique values of each of the sequence components in the dataset using HyperLogLog HLL

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: Dataset[_]): SequenceModel[T, OPVector]

Spark operation on dataset to produce Dataset for constructor fit function and then turn output function into a Model

def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[SequenceModel[T, OPVector]]

def fit(dataset: Dataset[_], paramMap: ParamMap): SequenceModel[T, OPVector]

def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): SequenceModel[T, OPVector]

def fitFn(dataset: Dataset[Seq[T.Value]]): SequenceModel[T, OPVector]

Function that fits the sequence model

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

final def getClass(): Class[_]

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

final def getHLLBits: Int

final def getInputFeature[T <: FeatureType](i: Int): Option[FeatureLike[T]]

Gets an input feature Note: this method IS NOT safe to use outside the driver, please use getTransientFeature method instead

final def getInputFeatures(): Array[OPFeature]

Gets the input features Note: this method IS NOT safe to use outside the driver, please use getTransientFeatures method instead

final def getInputSchema(): StructType

final def getMaxPctCardinality: Double

final def getMetadata(): Metadata

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

def getOutput(): FeatureLike[OPVector]

Output features that will be created by this stage

final def getOutputFeatureName: String

Name of output feature (i.e.

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

final def getTransientFeature(i: Int): Option[TransientFeature]

Gets an input feature at index i

final def getTransientFeatures(): Array[TransientFeature]

Gets the input Features

def getUnseenName: String

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

def hasParam(paramName: String): Boolean

def hashCode(): Int

final val hllBits: IntParam

final def inN: Array[TransientFeature]

def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

final def inputAsArray(in: InputFeatures): Array[OPFeature]

Function to convert InputFeatures to an Array of FeatureLike

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 makeVectorColumnMetadata(shouldTrackNulls: Boolean, unseen: Option[String], topValues: Seq[Seq[String]], features: Array[TransientFeature]): Array[OpVectorColumnMetadata]

def makeVectorMetadata(shouldTrackNulls: Boolean, unseen: Option[String], topValues: Seq[Seq[String]], outputName: String, features: Array[TransientFeature], stageName: String): OpVectorMetadata

final val maxPctCardinality: DoubleParam

final val minSupport: IntParam

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def onGetMetadata(): Unit

Function to be called on getMetadata

def onSetInput(): Unit

Function to be called on setInput

val operationName: String

unique name of the operation this stage performs

final def outputAsArray(out: OutputFeatures): Array[OPFeature]

Function to convert OutputFeatures to an Array of FeatureLike

def outputFeatureUid: String

def outputIsResponse: Boolean

Should output feature be a response? Yes, if any of the input features are.

lazy val params: Array[Param[_]]

def save(path: String): Unit

val seqIConvert: FeatureTypeSparkConverter[T]

implicit val seqIEncoder: Encoder[Seq[T.Value]]

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

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

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

def setCleanText(clean: Boolean): OpOneHotVectorizer.this.type

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

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

final def setHLLBits(value: Int): OpOneHotVectorizer.this.type

final def setInput(features: FeatureLike[T]*): OpOneHotVectorizer.this.type

final def setInput(features: InputFeatures): OpOneHotVectorizer.this.type

Input features that will be used by the stage

final def setInputFeatures[S <: OPFeature](features: Array[S]): OpOneHotVectorizer.this.type

Sets input features

final def setMaxPctCardinality(v: Double): OpOneHotVectorizer.this.type

final def setMetadata(m: Metadata): OpOneHotVectorizer.this.type

def setMinSupport(min: Int): OpOneHotVectorizer.this.type

def setOutputFeatureName(name: String): OpOneHotVectorizer.this.type

def setTopK(numberToKeep: Int): OpOneHotVectorizer.this.type

def setTrackNulls(v: Boolean): OpOneHotVectorizer.this.type

Option to keep track of values that were missing

def setUnseenName(unseenNameIn: String): OpOneHotVectorizer.this.type

final def stageName: String

Stage unique name consisting of the stage operation name and uid

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

def toString(): String

final val topK: IntParam

final val trackNulls: BooleanParam

final def transformSchema(schema: StructType): StructType

This function translates the input and output features into spark schema checks and changes that will occur on the underlying data frame

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

implicit val tti: scala.reflect.api.JavaUniverse.TypeTag[T]

type tag for input

implicit val ttiv: scala.reflect.api.JavaUniverse.TypeTag[T.Value]

type tag for input value

implicit val tto: scala.reflect.api.JavaUniverse.TypeTag[OPVector]

type tag for input

implicit val ttov: scala.reflect.api.JavaUniverse.TypeTag[Value]

type tag for output value

val uid: String

uid for instance

final val unseenName: Param[String]

final def wait(): Unit

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

final def wait(arg0: Long): Unit

final def write: MLWriter