class ContextSpellCheckerApproach extends AnnotatorApproach[ContextSpellCheckerModel] with HasFeatures with WeightedLevenshtein
- Alphabetic
- By Inheritance
- ContextSpellCheckerApproach
- WeightedLevenshtein
- HasFeatures
- AnnotatorApproach
- CanBeLazy
- DefaultParamsWritable
- MLWritable
- HasOutputAnnotatorType
- HasOutputAnnotationCol
- HasInputAnnotationCols
- Estimator
- PipelineStage
- Logging
- Params
- Serializable
- Serializable
- Identifiable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
Type Members
-
type
AnnotatorType = String
- Definition Classes
- HasOutputAnnotatorType
- implicit class ArrayHelper 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
$$[T](feature: StructFeature[T]): T
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
$$[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
_fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): ContextSpellCheckerModel
- Attributes
- protected
- Definition Classes
- AnnotatorApproach
- def addRegexClass(usrLabel: String, usrRegex: String, userDist: Int = 3): ContextSpellCheckerApproach
- def addVocabClass(usrLabel: String, vocabList: ArrayList[String], userDist: Int = 3): ContextSpellCheckerApproach
-
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
- val batchSize: IntParam
-
def
beforeTraining(spark: SparkSession): Unit
- Definition Classes
- AnnotatorApproach
- val caseStrategy: IntParam
-
final
def
checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
- val classCount: Param[Double]
-
final
def
clear(param: Param[_]): ContextSpellCheckerApproach.this.type
- Definition Classes
- Params
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
- val compoundCount: Param[Int]
- def computeClasses(vocab: HashMap[String, Double], total: Double, k: Int): Map[String, (Int, Int)]
- val configProtoBytes: IntArrayParam
-
final
def
copy(extra: ParamMap): Estimator[ContextSpellCheckerModel]
- Definition Classes
- AnnotatorApproach → Estimator → 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
-
val
description: String
- Definition Classes
- ContextSpellCheckerApproach → AnnotatorApproach
- val epochs: IntParam
-
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
-
final
def
extractParamMap(): ParamMap
- Definition Classes
- Params
-
final
def
extractParamMap(extra: ParamMap): ParamMap
- Definition Classes
- Params
-
val
features: ArrayBuffer[Feature[_, _, _]]
- Definition Classes
- HasFeatures
- val finalRate: FloatParam
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
fit(dataset: Dataset[_]): ContextSpellCheckerModel
- Definition Classes
- AnnotatorApproach → Estimator
-
def
fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[ContextSpellCheckerModel]
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" )
-
def
fit(dataset: Dataset[_], paramMap: ParamMap): ContextSpellCheckerModel
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" )
-
def
fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): ContextSpellCheckerModel
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" ) @varargs()
- def genVocab(dataset: Dataset[_]): (HashMap[String, Double], Map[String, (Int, Int)])
-
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
- Annotations
- @native()
- 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
-
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
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- val initialRate: FloatParam
-
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
- ContextSpellCheckerApproach → 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 languageModelClasses: Param[Int]
-
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 maxSentLen: IntParam
- val maxWindowLen: IntParam
- val minCount: Param[Double]
-
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
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
def
onTrained(model: ContextSpellCheckerModel, spark: SparkSession): Unit
- Definition Classes
- AnnotatorApproach
-
val
outputAnnotatorType: AnnotatorType
- Definition Classes
- ContextSpellCheckerApproach → HasOutputAnnotatorType
-
final
val
outputCol: Param[String]
- Attributes
- protected
- Definition Classes
- HasOutputAnnotationCol
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
-
def
set[T](feature: StructFeature[T], value: T): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[K, V](feature: MapFeature[K, V], value: Map[K, V]): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: SetFeature[T], value: Set[T]): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: ArrayFeature[T], value: Array[T]): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
set(paramPair: ParamPair[_]): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set(param: String, value: Any): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set[T](param: Param[T], value: T): ContextSpellCheckerApproach.this.type
- Definition Classes
- Params
- def setBatchSize(k: Int): ContextSpellCheckerApproach.this.type
- def setBlackListMinFreq(k: Int): ContextSpellCheckerApproach.this.type
- def setCaseStrategy(k: Int): ContextSpellCheckerApproach.this.type
- def setClassThreshold(t: Double): ContextSpellCheckerApproach.this.type
- def setConfigProtoBytes(bytes: Array[Int]): ContextSpellCheckerApproach
-
def
setDefault[T](feature: StructFeature[T], value: () ⇒ T): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
setDefault(paramPairs: ParamPair[_]*): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
setDefault[T](param: Param[T], value: T): ContextSpellCheckerApproach.this.type
- Attributes
- protected
- Definition Classes
- Params
- def setEpochs(k: Int): ContextSpellCheckerApproach.this.type
- def setErrorThreshold(t: Float): ContextSpellCheckerApproach.this.type
- def setFinalLearningRate(r: Float): ContextSpellCheckerApproach.this.type
- def setInitialLearningRate(r: Float): ContextSpellCheckerApproach.this.type
-
final
def
setInputCols(value: String*): ContextSpellCheckerApproach.this.type
- Definition Classes
- HasInputAnnotationCols
-
final
def
setInputCols(value: Array[String]): ContextSpellCheckerApproach.this.type
Overrides required annotators column if different than default
Overrides required annotators column if different than default
- Definition Classes
- HasInputAnnotationCols
- def setLMClasses(k: Int): ContextSpellCheckerApproach.this.type
-
def
setLazyAnnotator(value: Boolean): ContextSpellCheckerApproach.this.type
- Definition Classes
- CanBeLazy
- def setMaxCandidates(k: Int): ContextSpellCheckerApproach.this.type
- def setMaxWindowLen(w: Int): ContextSpellCheckerApproach.this.type
- def setMinCount(threshold: Double): ContextSpellCheckerApproach.this.type
-
final
def
setOutputCol(value: String): ContextSpellCheckerApproach.this.type
Overrides annotation column name when transforming
Overrides annotation column name when transforming
- Definition Classes
- HasOutputAnnotationCol
- def setSpecialClasses(parsers: List[SpecialClassParser]): ContextSpellCheckerApproach.this.type
- def setTradeoff(alpha: Float): ContextSpellCheckerApproach.this.type
- def setValidationFraction(r: Float): ContextSpellCheckerApproach.this.type
- def setWeights(filePath: String): ContextSpellCheckerApproach.this.type
- def setWordMaxDist(k: Int): ContextSpellCheckerApproach.this.type
- val specialClasses: Param[List[SpecialClassParser]]
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- Identifiable → AnyRef → Any
- val tradeoff: Param[Float]
-
def
train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): ContextSpellCheckerModel
- Definition Classes
- ContextSpellCheckerApproach → AnnotatorApproach
-
final
def
transformSchema(schema: StructType): StructType
requirement for pipeline transformation validation.
requirement for pipeline transformation validation. It is called on fit()
- Definition Classes
- AnnotatorApproach → PipelineStage
-
def
transformSchema(schema: StructType, logging: Boolean): StructType
- Attributes
- protected
- Definition Classes
- PipelineStage
- Annotations
- @DeveloperApi()
-
val
uid: String
- Definition Classes
- ContextSpellCheckerApproach → 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
- AnnotatorApproach
- val validationFraction: FloatParam
-
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( ... ) @native()
- val weightedDistPath: Param[String]
- val wordMaxDistance: IntParam
-
def
write: MLWriter
- Definition Classes
- DefaultParamsWritable → MLWritable