AnnotatorModel

abstract def annotate(annotations: Seq[Annotation]): Seq[Annotation]

takes a document and annotations and produces new annotations of this annotator's annotation type

abstract val inputAnnotatorTypes: Array[String]

Annotator reference id.

abstract val outputAnnotatorType: AnnotatorType

abstract val uid: String

final def !=(arg0: Any): Boolean

final def ##(): Int

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

def $$[T](feature: StructFeature[T]): T

def $$[K, V](feature: MapFeature[K, V]): Map[K, V]

def $$[T](feature: SetFeature[T]): Set[T]

def $$[T](feature: ArrayFeature[T]): Array[T]

final def ==(arg0: Any): Boolean

def afterAnnotate(dataset: DataFrame): DataFrame

final def asInstanceOf[T0]: T0

def beforeAnnotate(dataset: Dataset[_]): Dataset[_]

final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

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

def clone(): AnyRef

def copy(extra: ParamMap): M

requirement for annotators copies

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

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

def dfAnnotate: UserDefinedFunction

Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

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

def explainParams(): String

def extraValidate(structType: StructType): Boolean

def extraValidateMsg: String

Override for additional custom schema checks

final def extractParamMap(): ParamMap

final def extractParamMap(extra: ParamMap): ParamMap

val features: ArrayBuffer[Feature[_, _, _]]

def finalize(): Unit

def get[T](feature: StructFeature[T]): Option[T]

def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]

def get[T](feature: SetFeature[T]): Option[Set[T]]

def get[T](feature: ArrayFeature[T]): Option[Array[T]]

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

final def getClass(): Class[_]

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

def getInputCols: Array[String]

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

final def getOutputCol: String

Gets annotation column name going to generate

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

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

def hasParam(paramName: String): Boolean

def hasParent: Boolean

def hashCode(): Int

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

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

final val inputCols: StringArrayParam

columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

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

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def onWrite(path: String, spark: SparkSession): Unit

final val outputCol: Param[String]

lazy val params: Array[Param[_]]

var parent: Estimator[M]

def save(path: String): Unit

def set[T](feature: StructFeature[T], value: T): AnnotatorModel.this.type

def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): AnnotatorModel.this.type

def set[T](feature: SetFeature[T], value: Set[T]): AnnotatorModel.this.type

def set[T](feature: ArrayFeature[T], value: Array[T]): AnnotatorModel.this.type

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

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

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

def setDefault[T](feature: StructFeature[T], value: () ⇒ T): AnnotatorModel.this.type

def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): AnnotatorModel.this.type

def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): AnnotatorModel.this.type

def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): AnnotatorModel.this.type

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

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

final def setInputCols(value: String*): AnnotatorModel.this.type

final def setInputCols(value: Array[String]): AnnotatorModel.this.type

Overrides required annotators column if different than default

final def setOutputCol(value: String): AnnotatorModel.this.type

Overrides annotation column name when transforming

def setParent(parent: Estimator[M]): M

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

def toString(): String

final def transform(dataset: Dataset[_]): DataFrame

Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content

def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame

def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame

final def transformSchema(schema: StructType): StructType

requirement for pipeline transformation validation.

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

def validate(schema: StructType): Boolean

takes a Dataset and checks to see if all the required annotation types are present.

final def wait(): Unit

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

final def wait(arg0: Long): Unit

def wrapColumnMetadata(col: Column): Column

def write: MLWriter