BertEmbeddings

Instance Constructors

new BertEmbeddings()
new BertEmbeddings(uid: String)

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
BertEmbeddings → AnnotatorModel
def annotate(annotations: Seq[Annotation]): Seq[Annotation]

takes a document and annotations and produces new annotations of this annotator's annotation type
takes a document and annotations and produces new annotations of this annotator's annotation type
annotations
Annotations that correspond to inputAnnotationCols generated by previous annotators if any
returns
any number of annotations processed for every input annotation. Not necessary one to one relationship

Definition Classes
BertEmbeddings → AnnotatorModel
final def asInstanceOf[T0]: T0

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

Attributes
protected
Definition Classes
AnnotatorModel
val caseSensitive: BooleanParam

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

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

Definition Classes
Params
def clone(): AnyRef

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

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
def createDatabaseConnection(database: Name): RocksDBConnection

Definition Classes
HasStorageRef
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

Attributes
protected
Definition Classes
AnnotatorModel
val dimension: IntParam

Definition Classes
HasEmbeddingsProperties
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
def getCaseSensitive: Boolean

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

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

Definition Classes
Params
def getDimension: Int

Definition Classes
HasEmbeddingsProperties
def getInputCols: Array[String]

returns
input annotations columns currently used

Definition Classes
HasInputAnnotationCols
def getLazyAnnotator: Boolean

Definition Classes
CanBeLazy
def getMaxSentenceLength: Int
def getModelIfNotSet: TensorflowBert
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
def getPoolingLayer: Int
def getStorageRef: String

Definition Classes
HasStorageRef
def getTFhubPath: String
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[String]

Annotator reference id.
Annotator reference id. Used to identify elements in metadata or to refer to this annotator type

Definition Classes
BertEmbeddings → 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
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
val maxSentenceLength: IntParam
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

Definition Classes
BertEmbeddings → ParamsAndFeaturesWritable
val outputAnnotatorType: AnnotatorType

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

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

Definition Classes
Params
var parent: Estimator[BertEmbeddings]

Definition Classes
Model
val poolingLayer: IntParam
def save(path: String): Unit

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

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

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

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

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

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

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

Definition Classes
Params
def setBatchSize(size: Int): BertEmbeddings.this.type
def setCaseSensitive(value: Boolean): BertEmbeddings.this.type

Definition Classes
BertEmbeddings → HasCaseSensitiveProperties
def setConfigProtoBytes(bytes: Array[Int]): BertEmbeddings.this.type
def setDefault[T](feature: StructFeature[T], value: () ⇒ T): BertEmbeddings.this.type

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

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

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

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

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

Attributes
protected
Definition Classes
Params
def setDimension(value: Int): BertEmbeddings.this.type

Definition Classes
BertEmbeddings → HasEmbeddingsProperties
final def setInputCols(value: String*): BertEmbeddings.this.type

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

Definition Classes
CanBeLazy
def setMaxSentenceLength(value: Int): BertEmbeddings.this.type
def setModelIfNotSet(spark: SparkSession, tensorflow: TensorflowWrapper): BertEmbeddings.this.type
final def setOutputCol(value: String): BertEmbeddings.this.type

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

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

Definition Classes
Model
def setPoolingLayer(layer: Int): BertEmbeddings.this.type
def setStorageRef(value: String): BertEmbeddings.this.type

Definition Classes
HasStorageRef
def setTFhubPath(value: String): Unit
def setVocabulary(value: Map[String, Int]): BertEmbeddings.this.type
val storageRef: Param[String]

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

Definition Classes
AnyRef
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
def tokenize(sentences: Seq[Sentence]): Seq[WordpieceTokenizedSentence]
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

Definition Classes
BertEmbeddings → 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
def validateStorageRef(dataset: Dataset[_], inputCols: Array[String], annotatorType: String): Unit

Definition Classes
HasStorageRef
val vocabulary: MapFeature[String, Int]
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 wrapEmbeddingsMetadata(col: Column, embeddingsDim: Int, embeddingsRef: Option[String] = None): Column

Attributes
protected
Definition Classes
HasEmbeddingsProperties
def write: MLWriter

Definition Classes
ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
def writeTensorflowHub(path: String, tfPath: String, spark: SparkSession, suffix: String = "_use"): Unit

Definition Classes
WriteTensorflowModel
def writeTensorflowModel(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]] = None): Unit

Definition Classes
WriteTensorflowModel

Related Docs: object BertEmbeddings | package embeddings

class BertEmbeddings extends AnnotatorModel[BertEmbeddings] with WriteTensorflowModel with HasEmbeddingsProperties with HasStorageRef with HasCaseSensitiveProperties

Instance Constructors

new BertEmbeddings()

new BertEmbeddings(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

val batchSize: IntParam

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

val caseSensitive: BooleanParam

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

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

def clone(): AnyRef

val configProtoBytes: IntArrayParam

def copy(extra: ParamMap): BertEmbeddings

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

def createDatabaseConnection(database: Name): RocksDBConnection

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

def dfAnnotate: UserDefinedFunction

val dimension: IntParam

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]

def getCaseSensitive: Boolean

final def getClass(): Class[_]

def getConfigProtoBytes: Option[Array[Byte]]

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

def getDimension: Int

def getInputCols: Array[String]

def getLazyAnnotator: Boolean

def getMaxSentenceLength: Int

def getModelIfNotSet: TensorflowBert

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

final def getOutputCol: String

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

def getPoolingLayer: Int

def getStorageRef: String

def getTFhubPath: String

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[String]

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

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit