class ChunkConverter extends AnnotatorModel[ChunkConverter] with HasSimpleAnnotate[ChunkConverter] with SourceTrackingMetadataParams with CheckLicense
Convert chunks from regexMatcher to chunks with a entity in the metadata. Use the identifier or field as a entity.
Example
val sampleDataset = ResourceHelper.spark.createDataFrame(Seq( (1, "My first sentence with the first rule. This is my second sentence with ceremonies rule.") )).toDF("id", "text") val documentAssembler = new DocumentAssembler().setInputCol("text").setOutputCol("document") val sentence = new SentenceDetector().setInputCols("document").setOutputCol("sentence") val regexMatcher = new RegexMatcher() .setExternalRules(ExternalResource("src/test/resources/regex-matcher/rules.txt", ReadAs.TEXT, Map("delimiter" -> ","))) .setInputCols(Array("sentence")) .setOutputCol("regex") .setStrategy(strategy) val chunkConverter = new ChunkConverter().setInputCols("regex").setOutputCol("chunk") val pipeline = new Pipeline().setStages(Array(documentAssembler, sentence, regexMatcher,chunkConverter)) val results = pipeline.fit(sampleDataset).transform(sampleDataset) results.select("chunk").show(truncate = false) +------------------------------------------------------------------------------------------------+ |col | +------------------------------------------------------------------------------------------------+ |[chunk, 23, 31, the first, [identifier -> NAME, sentence -> 0, chunk -> 0, entity -> NAME], []] | |[chunk, 71, 80, ceremonies, [identifier -> NAME, sentence -> 1, chunk -> 0, entity -> NAME], []]| +------------------------------------------------------------------------------------------------+
- Grouped
- Alphabetic
- By Inheritance
- ChunkConverter
- CheckLicense
- SourceTrackingMetadataParams
- ResetSentenceIndicesParam
- HasSimpleAnnotate
- AnnotatorModel
- CanBeLazy
- RawAnnotator
- HasOutputAnnotationCol
- HasInputAnnotationCols
- HasOutputAnnotatorType
- ParamsAndFeaturesWritable
- HasFeatures
- DefaultParamsWritable
- MLWritable
- Model
- Transformer
- PipelineStage
- Logging
- Params
- Serializable
- Serializable
- Identifiable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
Type Members
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
-
val
allPossibleFieldsToStandardize: StringArrayParam
array with all possible fields containing the value to write in the standard field ordered by priority
array with all possible fields containing the value to write in the standard field ordered by priority
- Definition Classes
- SourceTrackingMetadataParams
-
def
annotate(annotations: Seq[Annotation]): Seq[Annotation]
- annotations
a Sequence of chunks to transform
- returns
a Sequence of Merged CHUNK Annotations
- Definition Classes
- ChunkConverter → 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
-
def
checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String]): Unit
- Definition Classes
- CheckLicense
-
def
checkValidScope(scope: String): Unit
- Definition Classes
- CheckLicense
-
def
checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean): Unit
- Definition Classes
- CheckLicense
-
def
checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean): Unit
- Definition Classes
- CheckLicense
-
final
def
clear(param: Param[_]): ChunkConverter.this.type
- Definition Classes
- Params
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
copy(extra: ParamMap): ChunkConverter
- 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
- 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
- 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[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
getAllPossibleFieldsToStandardize: Array[String]
- Definition Classes
- SourceTrackingMetadataParams
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
getDefault[T](param: Param[T]): Option[T]
- Definition Classes
- Params
-
def
getIncludeOutputColumn: Boolean
- Definition Classes
- SourceTrackingMetadataParams
-
def
getIncludeStandardField: Boolean
- Definition Classes
- SourceTrackingMetadataParams
-
def
getInputCols: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
def
getLazyAnnotator: Boolean
- Definition Classes
- CanBeLazy
-
final
def
getOrDefault[T](param: Param[T]): T
- Definition Classes
- Params
-
final
def
getOutputCol: String
- Definition Classes
- HasOutputAnnotationCol
-
def
getOutputColumnKey: String
- Definition Classes
- SourceTrackingMetadataParams
-
def
getParam(paramName: String): Param[Any]
- Definition Classes
- Params
-
def
getResetSentenceIndices: Boolean
Gets resetSentenceIndices parameter
Gets resetSentenceIndices parameter
- Definition Classes
- ResetSentenceIndicesParam
-
def
getStandardFieldKey: String
- Definition Classes
- SourceTrackingMetadataParams
-
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
- Annotations
- @native()
-
val
includeOutputColumn: BooleanParam
whether or not to include a metadata key/value to specify the output column name for the annotation
whether or not to include a metadata key/value to specify the output column name for the annotation
- Definition Classes
- SourceTrackingMetadataParams
-
val
includeStandardField: BooleanParam
whether to standardize the metadata key for entity, useful for chunk columns
whether to standardize the metadata key for entity, useful for chunk columns
- Definition Classes
- SourceTrackingMetadataParams
-
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 types: DOCUMENT,CHUNK
Input annotator types: DOCUMENT,CHUNK
- Definition Classes
- ChunkConverter → HasInputAnnotationCols
-
final
val
inputCols: StringArrayParam
- 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
onWrite(path: String, spark: SparkSession): Unit
- Attributes
- protected
- Definition Classes
- ParamsAndFeaturesWritable
-
val
optionalInputAnnotatorTypes: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
val
outputAnnotatorType: AnnotatorType
Output annotator types: CHUNK
Output annotator types: CHUNK
- Definition Classes
- ChunkConverter → HasOutputAnnotatorType
-
final
val
outputCol: Param[String]
- Attributes
- protected
- Definition Classes
- HasOutputAnnotationCol
-
val
outputColumnKey: Param[String]
key name for the source column value
key name for the source column value
- Definition Classes
- SourceTrackingMetadataParams
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
var
parent: Estimator[ChunkConverter]
- Definition Classes
- Model
-
def
resetSentenceIndices(metadata: Map[String, String]): Map[String, String]
Reset sentence index in metadata by adding
"sentence" -> "0"
Reset sentence index in metadata by adding
"sentence" -> "0"
- Attributes
- protected
- Definition Classes
- ResetSentenceIndicesParam
-
val
resetSentenceIndices: BooleanParam
Whether to reset sentence indices to treat the entire output as if it originates from a single document.
Whether to reset sentence indices to treat the entire output as if it originates from a single document.
When set to true, the metadata of each entity will be updated by assigning the
sentence
key a value of0
, effectively treating the entire output as if it comes from a single document, regardless of the original sentence boundaries. Default: False.- Definition Classes
- ResetSentenceIndicesParam
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
-
def
set[T](feature: StructFeature[T], value: T): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[K, V](feature: MapFeature[K, V], value: Map[K, V]): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: SetFeature[T], value: Set[T]): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: ArrayFeature[T], value: Array[T]): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
set(paramPair: ParamPair[_]): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set(param: String, value: Any): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set[T](param: Param[T], value: T): ChunkConverter.this.type
- Definition Classes
- Params
-
def
setAllPossibleFieldsToStandardize(v: Array[String]): ChunkConverter.this.type
- Definition Classes
- SourceTrackingMetadataParams
-
def
setDefault[T](feature: StructFeature[T], value: () ⇒ T): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
setDefault(paramPairs: ParamPair[_]*): ChunkConverter.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
setDefault[T](param: Param[T], value: T): ChunkConverter.this.type
- Attributes
- protected[org.apache.spark.ml]
- Definition Classes
- Params
-
def
setIncludeOutputColumn(v: Boolean): ChunkConverter.this.type
- Definition Classes
- SourceTrackingMetadataParams
-
def
setIncludeStandardField(v: Boolean): ChunkConverter.this.type
- Definition Classes
- SourceTrackingMetadataParams
-
final
def
setInputCols(value: String*): ChunkConverter.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInputCols(value: Array[String]): ChunkConverter.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setLazyAnnotator(value: Boolean): ChunkConverter.this.type
- Definition Classes
- CanBeLazy
-
final
def
setOutputCol(value: String): ChunkConverter.this.type
- Definition Classes
- HasOutputAnnotationCol
-
def
setOutputColumnKey(v: String): ChunkConverter.this.type
- Definition Classes
- SourceTrackingMetadataParams
-
def
setParent(parent: Estimator[ChunkConverter]): ChunkConverter
- Definition Classes
- Model
-
def
setResetSentenceIndices(value: Boolean): ChunkConverter.this.type
Set whether to reset sentence indices to treat the entire output as if it originates from a single document.
Set whether to reset sentence indices to treat the entire output as if it originates from a single document.
When set to true, the metadata of each entity will be updated by assigning the
sentence
key a value of0
, effectively treating the entire output as if it comes from a single document, regardless of the original sentence boundaries. Default: False.- Definition Classes
- ResetSentenceIndicesParam
-
def
setStandardFieldKey(v: String): ChunkConverter.this.type
- Definition Classes
- SourceTrackingMetadataParams
-
val
standardFieldKey: Param[String]
key name for the standard homogenized field
key name for the standard homogenized field
- Definition Classes
- SourceTrackingMetadataParams
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- Identifiable → AnyRef → Any
-
final
def
transform(dataset: Dataset[_]): DataFrame
- 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
- Definition Classes
- RawAnnotator → PipelineStage
-
def
transformSchema(schema: StructType, logging: Boolean): StructType
- Attributes
- protected
- Definition Classes
- PipelineStage
- Annotations
- @DeveloperApi()
-
val
uid: String
- Definition Classes
- ChunkConverter → Identifiable
-
def
updateMetadataWithSource(metadata: Map[String, String]): Map[String, String]
- Definition Classes
- SourceTrackingMetadataParams
-
def
validate(schema: StructType): Boolean
- 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( ... ) @native()
-
def
wrapColumnMetadata(col: Column): Column
- Attributes
- protected
- Definition Classes
- RawAnnotator
-
def
write: MLWriter
- Definition Classes
- ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
Inherited from CheckLicense
Inherited from SourceTrackingMetadataParams
Inherited from ResetSentenceIndicesParam
Inherited from HasSimpleAnnotate[ChunkConverter]
Inherited from AnnotatorModel[ChunkConverter]
Inherited from CanBeLazy
Inherited from RawAnnotator[ChunkConverter]
Inherited from HasOutputAnnotationCol
Inherited from HasInputAnnotationCols
Inherited from HasOutputAnnotatorType
Inherited from ParamsAndFeaturesWritable
Inherited from HasFeatures
Inherited from DefaultParamsWritable
Inherited from MLWritable
Inherited from Model[ChunkConverter]
Inherited from Transformer
Inherited from PipelineStage
Inherited from Logging
Inherited from Params
Inherited from Serializable
Inherited from Serializable
Inherited from Identifiable
Inherited from AnyRef
Inherited from Any
Parameters
Annotator types
Required input and expected output annotator types