ContextSpellCheckerModel

Instance Constructors

new ContextSpellCheckerModel()
new ContextSpellCheckerModel(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
implicit class StringTools extends AnyRef

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 $$(feature: TransducerSeqFeature): Seq[SpecialClassParser]

Attributes
protected
Definition Classes
HasTransducerFeatures
def $$(feature: TransducerFeature): VocabParser

Attributes
protected
Definition Classes
HasTransducerFeatures
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]

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
ContextSpellCheckerModel → HasSimpleAnnotate
final def asInstanceOf[T0]: T0

Definition Classes
Any
def backTrack(dist: Array[Array[Float]], s2: String, s1: String, j: Int, i: Int, acc: Seq[(String, String)]): Seq[(String, String)]

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

Definition Classes
ContextSpellCheckerModel → AnnotatorModel
val caseStrategy: IntParam
final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

Attributes
protected
Definition Classes
HasInputAnnotationCols
val classes: MapFeature[Int, (Int, Int)]
final def clear(param: Param[_]): ContextSpellCheckerModel.this.type

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
val compareLowcase: BooleanParam
def computeMask(annotations: Seq[Annotation]): Array[Boolean]
def computeTrellis(annotations: Seq[Annotation], mask: Seq[Boolean]): Array[Array[(String, Double, String)]]
val configProtoBytes: IntArrayParam
def copy(extra: ParamMap): ContextSpellCheckerModel

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
val correctSymbols: BooleanParam
def decodeViterbi(trellis: Array[Array[(String, Double, String)]]): (Array[String], Double)
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
val errorThreshold: FloatParam
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] )
val gamma: FloatParam
def get(feature: TransducerSeqFeature): Option[Seq[SpecialClassParser]]

Attributes
protected
Definition Classes
HasTransducerFeatures
def get(feature: TransducerFeature): Option[VocabParser]

Attributes
protected
Definition Classes
HasTransducerFeatures
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
def getClassCandidates(transducer: ITransducer[Candidate], token: String, label: String, maxDist: Int, limit: Int = 2): Seq[(String, String, Float)]
def getConfigProtoBytes: Option[Array[Byte]]
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
def getModelIfNotSet: TensorflowSpell
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 getVocabCandidates(token: String, maxDist: Int): List[(String, String, Float)]
def getWordClasses(): Seq[(String, 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
val idsVocab: MapFeature[Int, String]
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
ContextSpellCheckerModel → 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 learnDist(s1: String, s2: String): Seq[(String, String)]

Definition Classes
WeightedLevenshtein
def levenshteinDist(s11: String, s22: String)(cost: (String, String) ⇒ Float): Float

Definition Classes
WeightedLevenshtein
def loadWeights(filename: String): Map[String, Map[String, Float]]

Definition Classes
WeightedLevenshtein
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 maxCandidates: IntParam
val maxWindowLen: 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
ContextSpellCheckerModel → ParamsAndFeaturesWritable
val outputAnnotatorType: AnnotatorType

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

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

Definition Classes
Params
var parent: Estimator[ContextSpellCheckerModel]

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

Definition Classes
MLWritable
Annotations
@Since( "1.6.0" ) @throws( ... )
def set(feature: TransducerSeqFeature, value: Seq[SpecialClassParser]): ContextSpellCheckerModel.this.type

Attributes
protected
Definition Classes
HasTransducerFeatures
def set(feature: TransducerFeature, value: VocabParser): ContextSpellCheckerModel.this.type

Attributes
protected
Definition Classes
HasTransducerFeatures
def set[T](feature: StructFeature[T], value: T): ContextSpellCheckerModel.this.type

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

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

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

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

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

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

Definition Classes
Params
def setCaseStrategy(k: Int): ContextSpellCheckerModel.this.type
def setClasses(c: Map[Int, (Int, Int)]): ContextSpellCheckerModel.this.type
def setCompareLowcase(value: Boolean): ContextSpellCheckerModel.this.type
def setConfigProtoBytes(bytes: Array[Int]): ContextSpellCheckerModel
def setCorrectSymbols(value: Boolean): ContextSpellCheckerModel.this.type
def setDefault(feature: TransducerSeqFeature, value: () ⇒ Seq[SpecialClassParser]): ContextSpellCheckerModel.this.type

Attributes
protected
Definition Classes
HasTransducerFeatures
def setDefault(feature: TransducerFeature, value: () ⇒ VocabParser): ContextSpellCheckerModel.this.type

Attributes
protected
Definition Classes
HasTransducerFeatures
def setDefault[T](feature: StructFeature[T], value: () ⇒ T): ContextSpellCheckerModel.this.type

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

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

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

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

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

Attributes
protected
Definition Classes
Params
def setErrorThreshold(t: Float): ContextSpellCheckerModel.this.type
def setGamma(g: Float): ContextSpellCheckerModel.this.type
final def setInputCols(value: String*): ContextSpellCheckerModel.this.type

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

Definition Classes
CanBeLazy
def setMaxCandidates(k: Int): ContextSpellCheckerModel.this.type
def setMaxWindowLen(w: Int): ContextSpellCheckerModel.this.type
def setModelIfNotSet(spark: SparkSession, tensorflow: TensorflowWrapper): ContextSpellCheckerModel.this.type
final def setOutputCol(value: String): ContextSpellCheckerModel.this.type

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

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

Definition Classes
Model
def setSpecialClassesTransducers(transducers: Seq[SpecialClassParser]): ContextSpellCheckerModel.this.type
def setTradeOff(lambda: Float): ContextSpellCheckerModel.this.type
def setUseNewLines(useIt: Boolean): ContextSpellCheckerModel.this.type
def setVocabFreq(v: Map[String, Double]): ContextSpellCheckerModel.this.type
def setVocabIds(v: Map[String, Int]): ContextSpellCheckerModel.this.type
def setVocabTransducer(trans: ITransducer[Candidate]): ContextSpellCheckerModel.this.type
def setWeights(w: HashMap[String, HashMap[String, Double]]): ContextSpellCheckerModel.this.type
def setWeights(w: Map[String, Map[String, Float]]): ContextSpellCheckerModel.this.type
def setWordMaxDist(k: Int): ContextSpellCheckerModel.this.type
val specialTransducers: TransducerSeqFeature
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toOption(boolean: Boolean): Option[Boolean]
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
val tradeoff: FloatParam
val transducer: TransducerFeature
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
ContextSpellCheckerModel → Identifiable
def updateRegexClass(label: String, regex: String): ContextSpellCheckerModel
def updateVocabClass(label: String, vocabList: ArrayList[String], append: Boolean = true): ContextSpellCheckerModel
val useNewLines: BooleanParam
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
val vocabFreq: MapFeature[String, Double]
val vocabIds: MapFeature[String, Int]
def wLevenshteinDist(s1: String, s2: String, weights: Map[String, Map[String, Float]]): Float

Definition Classes
WeightedLevenshtein
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( ... )
val weights: MapFeature[String, Map[String, Float]]
val wordMaxDistance: IntParam
def wrapColumnMetadata(col: Column): Column

Attributes
protected
Definition Classes
RawAnnotator
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
def writeTensorflowModelV2(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]] = None): Unit

Definition Classes
WriteTensorflowModel

Related Docs: object ContextSpellCheckerModel | package context

class ContextSpellCheckerModel extends AnnotatorModel[ContextSpellCheckerModel] with HasSimpleAnnotate[ContextSpellCheckerModel] with WeightedLevenshtein with WriteTensorflowModel with ParamsAndFeaturesWritable with HasTransducerFeatures

Instance Constructors

new ContextSpellCheckerModel()

new ContextSpellCheckerModel(uid: String)

Type Members

type AnnotationContent = Seq[Row]

type AnnotatorType = String

implicit class StringTools extends AnyRef

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

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

def $$(feature: TransducerSeqFeature): Seq[SpecialClassParser]

def $$(feature: TransducerFeature): VocabParser

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 backTrack(dist: Array[Array[Float]], s2: String, s1: String, j: Int, i: Int, acc: Seq[(String, String)]): Seq[(String, String)]

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

val caseStrategy: IntParam

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

val classes: MapFeature[Int, (Int, Int)]

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

def clone(): AnyRef

val compareLowcase: BooleanParam

def computeMask(annotations: Seq[Annotation]): Array[Boolean]

def computeTrellis(annotations: Seq[Annotation], mask: Seq[Boolean]): Array[Array[(String, Double, String)]]

val configProtoBytes: IntArrayParam

def copy(extra: ParamMap): ContextSpellCheckerModel

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

val correctSymbols: BooleanParam

def decodeViterbi(trellis: Array[Array[(String, Double, String)]]): (Array[String], Double)

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

def dfAnnotate: UserDefinedFunction

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

val errorThreshold: FloatParam

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

val gamma: FloatParam

def get(feature: TransducerSeqFeature): Option[Seq[SpecialClassParser]]

def get(feature: TransducerFeature): Option[VocabParser]

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[_]

def getClassCandidates(transducer: ITransducer[Candidate], token: String, label: String, maxDist: Int, limit: Int = 2): Seq[(String, String, Float)]

def getConfigProtoBytes: Option[Array[Byte]]

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

def getInputCols: Array[String]

def getLazyAnnotator: Boolean

def getModelIfNotSet: TensorflowSpell

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

final def getOutputCol: String

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

def getVocabCandidates(token: String, maxDist: Int): List[(String, String, Float)]

def getWordClasses(): Seq[(String, String)]

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

def hasParam(paramName: String): Boolean

def hasParent: Boolean

def hashCode(): Int

val idsVocab: MapFeature[Int, String]

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

def initializeLogIfNecessary(isInterpreter: Boolean): Unit