class RuleBasedMatcher extends AnnotatorApproach[RuleBasedMatcherModel] with RuleBasedMatcherParams
Rule-based token matcher over multiple Spark NLP annotation columns.
Patterns are supplied as JSON/JSONL rules. Each token pattern contains one or more attribute predicates, and attributes are read from configured annotation columns such as TOKEN, POS, NAMED_ENTITY, DEPENDENCY, or additional TOKEN columns like lemmas.
- Alphabetic
- By Inheritance
- RuleBasedMatcher
- RuleBasedMatcherParams
- AnnotatorApproach
- CanBeLazy
- DefaultParamsWritable
- MLWritable
- HasOutputAnnotatorType
- HasOutputAnnotationCol
- HasInputAnnotationCols
- Estimator
- PipelineStage
- Logging
- Params
- Serializable
- Serializable
- Identifiable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Type Members
-
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
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
_fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): RuleBasedMatcherModel
- Attributes
- protected
- Definition Classes
- AnnotatorApproach
-
val
alignmentMode: Param[String]
- Definition Classes
- RuleBasedMatcherParams
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
val
attributeColumns: StringArrayParam
- Definition Classes
- RuleBasedMatcherParams
-
def
beforeTraining(spark: SparkSession): Unit
- Definition Classes
- AnnotatorApproach
-
final
def
checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
final
def
clear(param: Param[_]): RuleBasedMatcher.this.type
- Definition Classes
- Params
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
columnTypes(schema: StructType): Map[String, String]
- Attributes
- protected
- Definition Classes
- RuleBasedMatcherParams
-
final
def
copy(extra: ParamMap): Estimator[RuleBasedMatcherModel]
- 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
- RuleBasedMatcher → AnnotatorApproach
-
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
-
final
val
extraInputCols: StringArrayParam
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
final
def
extractParamMap(): ParamMap
- Definition Classes
- Params
-
final
def
extractParamMap(extra: ParamMap): ParamMap
- Definition Classes
- Params
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
fit(dataset: Dataset[_]): RuleBasedMatcherModel
- Definition Classes
- AnnotatorApproach → Estimator
-
def
fit(dataset: Dataset[_], paramMaps: Seq[ParamMap]): Seq[RuleBasedMatcherModel]
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" )
-
def
fit(dataset: Dataset[_], paramMap: ParamMap): RuleBasedMatcherModel
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" )
-
def
fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): RuleBasedMatcherModel
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" ) @varargs()
-
final
def
get[T](param: Param[T]): Option[T]
- Definition Classes
- Params
-
def
getAlignmentMode: String
- Definition Classes
- RuleBasedMatcherParams
-
def
getAttributeColumns: Map[String, String]
- Definition Classes
- RuleBasedMatcherParams
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
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
getOverlapStrategy: String
- Definition Classes
- RuleBasedMatcherParams
-
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()
-
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]
Annotator reference id.
Annotator reference id. Used to identify elements in metadata or to refer to this annotator type
- Definition Classes
- RuleBasedMatcher → 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
-
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: RuleBasedMatcherModel, spark: SparkSession): Unit
- Definition Classes
- AnnotatorApproach
-
val
optionalInputAnnotatorTypes: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
val
outputAnnotatorType: AnnotatorType
- Definition Classes
- RuleBasedMatcher → HasOutputAnnotatorType
-
final
val
outputCol: Param[String]
- Attributes
- protected
- Definition Classes
- HasOutputAnnotationCol
-
val
overlapStrategy: Param[String]
- Definition Classes
- RuleBasedMatcherParams
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
def
parseKeyValueEntries(entries: Array[String], paramName: String, normalizeKeys: Boolean = true): Map[String, String]
- Attributes
- protected
- Definition Classes
- RuleBasedMatcherParams
- val rules: Param[String]
- val rulesResource: ExternalResourceParam
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
-
final
def
set(paramPair: ParamPair[_]): RuleBasedMatcher.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set(param: String, value: Any): RuleBasedMatcher.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set[T](param: Param[T], value: T): RuleBasedMatcher.this.type
- Definition Classes
- Params
-
def
setAlignmentMode(value: String): RuleBasedMatcher.this.type
- Definition Classes
- RuleBasedMatcherParams
-
def
setAttributeColumns(value: Array[String]): RuleBasedMatcher.this.type
- Definition Classes
- RuleBasedMatcherParams
-
def
setAttributeColumns(value: Map[String, String]): RuleBasedMatcher.this.type
- Definition Classes
- RuleBasedMatcherParams
-
final
def
setDefault(paramPairs: ParamPair[_]*): RuleBasedMatcher.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
setDefault[T](param: Param[T], value: T): RuleBasedMatcher.this.type
- Attributes
- protected[org.apache.spark.ml]
- Definition Classes
- Params
-
def
setExtraInputCols(value: Array[String]): RuleBasedMatcher.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInputCols(value: Array[String]): RuleBasedMatcher.this.type
- Definition Classes
- RuleBasedMatcherParams
-
final
def
setInputCols(value: String*): RuleBasedMatcher.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setLazyAnnotator(value: Boolean): RuleBasedMatcher.this.type
- Definition Classes
- CanBeLazy
-
final
def
setOutputCol(value: String): RuleBasedMatcher.this.type
Overrides annotation column name when transforming
Overrides annotation column name when transforming
- Definition Classes
- HasOutputAnnotationCol
-
def
setOverlapStrategy(value: String): RuleBasedMatcher.this.type
- Definition Classes
- RuleBasedMatcherParams
- def setRules(value: String): RuleBasedMatcher.this.type
- def setRulesResource(path: String, readAs: Format = ReadAs.TEXT, options: Map[String, String] = Map("format" -> "text")): RuleBasedMatcher.this.type
- def setRulesResource(value: ExternalResource): RuleBasedMatcher.this.type
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- Identifiable → AnyRef → Any
-
def
train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): RuleBasedMatcherModel
- Definition Classes
- RuleBasedMatcher → 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
- RuleBasedMatcher → 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
- RuleBasedMatcher → AnnotatorApproach
-
def
validateInputColumns(schema: StructType): Boolean
- Attributes
- protected
- Definition Classes
- RuleBasedMatcherParams
-
def
validateInputColumnsOrThrow(schema: StructType): Unit
- Attributes
- protected
- Definition Classes
- RuleBasedMatcherParams
-
def
validatePatternSafetyOrThrow(rules: Seq[MatcherRule]): Unit
- Attributes
- protected
- Definition Classes
- RuleBasedMatcherParams
-
def
validateRuleAttributesOrThrow(rules: Seq[MatcherRule], schema: StructType): Unit
- Attributes
- protected
- Definition Classes
- RuleBasedMatcherParams
-
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()
-
def
write: MLWriter
- Definition Classes
- DefaultParamsWritable → MLWritable