LemmatizerModel

Instance Constructors

new LemmatizerModel()
new LemmatizerModel(uid: String)

uid
required internal uid provided by constructor

Type Members

type AnnotationContent = Seq[Row]

internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI
internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

Attributes
protected
Definition Classes
AnnotatorModel
type AnnotatorType = String

Definition Classes
HasOutputAnnotatorType

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def $[T](param: Param[T]): T

Attributes
protected
Definition Classes
Params
def $$[T](feature: StructFeature[T]): T

Attributes
protected
Definition Classes
HasFeatures
def $$[K, V](feature: MapFeature[K, V]): Map[K, V]

Attributes
protected
Definition Classes
HasFeatures
def $$[T](feature: SetFeature[T]): Set[T]

Attributes
protected
Definition Classes
HasFeatures
def $$[T](feature: ArrayFeature[T]): Array[T]

Attributes
protected
Definition Classes
HasFeatures
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame

Attributes
protected
Definition Classes
AnnotatorModel
def afterAnnotate(dataset: DataFrame): DataFrame

Attributes
protected
Definition Classes
AnnotatorModel
def annotate(annotations: Seq[Annotation]): Seq[Annotation]

annotations
Annotations that correspond to inputAnnotationCols generated by previous annotators if any
returns
one to one annotation from token to a lemmatized word, if found on dictionary or leave the word as is

Definition Classes
LemmatizerModel → HasSimpleAnnotate
final def asInstanceOf[T0]: T0

Definition Classes
Any
def beforeAnnotate(dataset: Dataset[_]): Dataset[_]

Attributes
protected
Definition Classes
AnnotatorModel
final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

Attributes
protected
Definition Classes
HasInputAnnotationCols
final def clear(param: Param[_]): LemmatizerModel.this.type

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def copy(extra: ParamMap): LemmatizerModel

requirement for annotators copies
requirement for annotators copies

Definition Classes
RawAnnotator → Model → Transformer → PipelineStage → Params
def copyValues[T <: Params](to: T, extra: ParamMap): T

Attributes
protected
Definition Classes
Params
final def defaultCopy[T <: Params](extra: ParamMap): T

Attributes
protected
Definition Classes
Params
def dfAnnotate: UserDefinedFunction

Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column
Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column
returns
udf function to be applied to inputCols using this annotator's annotate function as part of ML transformation

Definition Classes
HasSimpleAnnotate
final def eq(arg0: AnyRef): Boolean

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

Definition Classes
AnyRef → Any
def explainParam(param: Param[_]): String

Definition Classes
Params
def explainParams(): String

Definition Classes
Params
def extraValidate(structType: StructType): Boolean

Attributes
protected
Definition Classes
RawAnnotator
def extraValidateMsg: String

Override for additional custom schema checks
Override for additional custom schema checks

Attributes
protected
Definition Classes
RawAnnotator
final def extractParamMap(): ParamMap

Definition Classes
Params
final def extractParamMap(extra: ParamMap): ParamMap

Definition Classes
Params
val features: ArrayBuffer[Feature[_, _, _]]

Definition Classes
HasFeatures
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def get[T](feature: StructFeature[T]): Option[T]

Attributes
protected
Definition Classes
HasFeatures
def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]

Attributes
protected
Definition Classes
HasFeatures
def get[T](feature: SetFeature[T]): Option[Set[T]]

Attributes
protected
Definition Classes
HasFeatures
def get[T](feature: ArrayFeature[T]): Option[Array[T]]

Attributes
protected
Definition Classes
HasFeatures
final def get[T](param: Param[T]): Option[T]

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

Definition Classes
AnyRef → Any
final def getDefault[T](param: Param[T]): Option[T]

Definition Classes
Params
def getInputCols: Array[String]

returns
input annotations columns currently used

Definition Classes
HasInputAnnotationCols
def getLazyAnnotator: Boolean

Definition Classes
CanBeLazy
final def getOrDefault[T](param: Param[T]): T

Definition Classes
Params
final def getOutputCol: String

Gets annotation column name going to generate
Gets annotation column name going to generate

Definition Classes
HasOutputAnnotationCol
def getParam(paramName: String): Param[Any]

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

Definition Classes
Params
def hasParam(paramName: String): Boolean

Definition Classes
Params
def hasParent: Boolean

Definition Classes
Model
def hashCode(): Int

Definition Classes
AnyRef → Any
def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

Attributes
protected
Definition Classes
Logging
def initializeLogIfNecessary(isInterpreter: Boolean): Unit

Attributes
protected
Definition Classes
Logging
val inputAnnotatorTypes: Array[AnnotatorType]

Input annotator type : TOKEN
Input annotator type : TOKEN

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

Attributes
protected
Definition Classes
HasInputAnnotationCols
final def isDefined(param: Param[_]): Boolean

Definition Classes
Params
final def isInstanceOf[T0]: Boolean

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

Definition Classes
Params
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
val lazyAnnotator: BooleanParam

Definition Classes
CanBeLazy
val lemmaDict: MapFeature[String, String]

lemmaDict
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
def msgHelper(schema: StructType): String

Attributes
protected
Definition Classes
HasInputAnnotationCols
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def onWrite(path: String, spark: SparkSession): Unit

Attributes
protected
Definition Classes
ParamsAndFeaturesWritable
val outputAnnotatorType: AnnotatorType

Output annotator type : TOKEN
Output annotator type : TOKEN

Definition Classes
LemmatizerModel → HasOutputAnnotatorType
final val outputCol: Param[String]

Attributes
protected
Definition Classes
HasOutputAnnotationCol
lazy val params: Array[Param[_]]

Definition Classes
Params
var parent: Estimator[LemmatizerModel]

Definition Classes
Model
def save(path: String): Unit

Definition Classes
MLWritable
Annotations
@Since( "1.6.0" ) @throws( ... )
def set[T](feature: StructFeature[T], value: T): LemmatizerModel.this.type

Attributes
protected
Definition Classes
HasFeatures
def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): LemmatizerModel.this.type

Attributes
protected
Definition Classes
HasFeatures
def set[T](feature: SetFeature[T], value: Set[T]): LemmatizerModel.this.type

Attributes
protected
Definition Classes
HasFeatures
def set[T](feature: ArrayFeature[T], value: Array[T]): LemmatizerModel.this.type

Attributes
protected
Definition Classes
HasFeatures
final def set(paramPair: ParamPair[_]): LemmatizerModel.this.type

Attributes
protected
Definition Classes
Params
final def set(param: String, value: Any): LemmatizerModel.this.type

Attributes
protected
Definition Classes
Params
final def set[T](param: Param[T], value: T): LemmatizerModel.this.type

Definition Classes
Params
def setDefault[T](feature: StructFeature[T], value: () ⇒ T): LemmatizerModel.this.type

Attributes
protected
Definition Classes
HasFeatures
def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): LemmatizerModel.this.type

Attributes
protected
Definition Classes
HasFeatures
def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): LemmatizerModel.this.type

Attributes
protected
Definition Classes
HasFeatures
def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): LemmatizerModel.this.type

Attributes
protected
Definition Classes
HasFeatures
final def setDefault(paramPairs: ParamPair[_]*): LemmatizerModel.this.type

Attributes
protected
Definition Classes
Params
final def setDefault[T](param: Param[T], value: T): LemmatizerModel.this.type

Attributes
protected
Definition Classes
Params
final def setInputCols(value: String*): LemmatizerModel.this.type

Definition Classes
HasInputAnnotationCols
final def setInputCols(value: Array[String]): LemmatizerModel.this.type

Overrides required annotators column if different than default
Overrides required annotators column if different than default

Definition Classes
HasInputAnnotationCols
def setLazyAnnotator(value: Boolean): LemmatizerModel.this.type

Definition Classes
CanBeLazy
def setLemmaDict(value: Map[String, String]): LemmatizerModel.this.type
final def setOutputCol(value: String): LemmatizerModel.this.type

Overrides annotation column name when transforming
Overrides annotation column name when transforming

Definition Classes
HasOutputAnnotationCol
def setParent(parent: Estimator[LemmatizerModel]): LemmatizerModel

Definition Classes
Model
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
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
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
dataset
Dataset[Row]

Definition Classes
AnnotatorModel → Transformer
def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame

Definition Classes
Transformer
Annotations
@Since( "2.0.0" )
def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame

Definition Classes
Transformer
Annotations
@Since( "2.0.0" ) @varargs()
final def transformSchema(schema: StructType): StructType

requirement for pipeline transformation validation.
requirement for pipeline transformation validation. It is called on fit()

Definition Classes
RawAnnotator → PipelineStage
def transformSchema(schema: StructType, logging: Boolean): StructType

Attributes
protected
Definition Classes
PipelineStage
Annotations
@DeveloperApi()
val uid: String

required internal uid provided by constructor
required internal uid provided by constructor

Definition Classes
LemmatizerModel → Identifiable
def validate(schema: StructType): Boolean

takes a Dataset and checks to see if all the required annotation types are present.
takes a Dataset and checks to see if all the required annotation types are present.
schema
to be validated
returns
True if all the required types are present, else false

Attributes
protected
Definition Classes
RawAnnotator
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( ... )
def wrapColumnMetadata(col: Column): Column

Attributes
protected
Definition Classes
RawAnnotator
def write: MLWriter

Definition Classes
ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Related Docs: object LemmatizerModel | package annotators

class LemmatizerModel extends AnnotatorModel[LemmatizerModel] with HasSimpleAnnotate[LemmatizerModel]

Instance Constructors

new LemmatizerModel()

new LemmatizerModel(uid: String)

Type Members

type AnnotationContent = Seq[Row]

type AnnotatorType = String

Value Members

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 _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame

def afterAnnotate(dataset: DataFrame): DataFrame

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

final def asInstanceOf[T0]: T0

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

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

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

def clone(): AnyRef

def copy(extra: ParamMap): LemmatizerModel

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

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

def dfAnnotate: UserDefinedFunction

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

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]

def getLazyAnnotator: Boolean

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

final def getOutputCol: String

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

val inputAnnotatorTypes: Array[AnnotatorType]

final val inputCols: StringArrayParam

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

final def isInstanceOf[T0]: Boolean

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

def isTraceEnabled(): Boolean

val lazyAnnotator: BooleanParam

val lemmaDict: MapFeature[String, 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

def msgHelper(schema: StructType): String

final def ne(arg0: AnyRef): Boolean