class REChunkMerger extends AnnotatorModel[REChunkMerger] with HasSimpleAnnotate[REChunkMerger]
REChunkMerger annotator merges relation chunks to create a new chunk.
Example
val documentAssembler = new DocumentAssembler() .setInputCol("text") .setOutputCol("document") val tokenizer = new Tokenizer() .setInputCols(Array("document")) .setOutputCol("tokens") val sentencer = new SentenceDetector() .setInputCols(Array("document")) .setOutputCol("sentences") val embedder = WordEmbeddingsModel .pretrained("embeddings_clinical", "en", "clinical/models") .setInputCols(Array("document", "tokens")) .setOutputCol("embeddings") val posTagger = PerceptronModel .pretrained("pos_clinical", "en", "clinical/models") .setInputCols(Array("sentences", "tokens")) .setOutputCol("posTags") val nerTagger = MedicalNerModel .pretrained("ner_clinical", "en", "clinical/models") .setInputCols(Array("sentences", "tokens", "embeddings")) .setOutputCol("nerTags") val nerConverter = new NerConverterInternal() .setInputCols(Array("sentences", "tokens", "nerTags")) .setOutputCol("nerChunks") val depencyParser = DependencyParserModel .pretrained("dependency_conllu", "en") .setInputCols(Array("document", "posTags", "tokens")) .setOutputCol("dependencies") val re = RelationExtractionModel .pretrained("re_clinical", "en", "clinical/models") .setInputCols(Array("embeddings", "posTags", "nerChunks", "dependencies")) .setOutputCol("relations_t") val REChunkMerger = new REChunkMerger() .setInputCols("relations_t") .setOutputCol("relation_chunk") .setSeparator(" & ") val flattener = new Flattener() .setInputCols("relation_chunk") .setExplodeSelectedFields(Map("relation_chunk" -> Array( "result as result", "begin as begin", "end as end", "metadata.relation_type as relationType", "metadata.sentence as sentence" ))) val pipeline = new Pipeline() .setStages(Array( documentAssembler, sentencer, tokenizer, embedder, posTagger, nerTagger, nerConverter, depencyParser, re, REChunkMerger, flattener )) import spark.implicits._ val data = Seq("A 28-year-old female with a history of gestational diabetes mellitus diagnosed eight years prior to " + "presentation and subsequent type two diabetes mellitus ( T2DM ). one prior episode of HTG-induced pancreatitis " + "three years prior to presentation , associated with an acute hepatitis , and obesity with a body mass index ") .toDS() .toDF("text") val result = pipeline.fit(data).transform(data)
Show Results
+---------------------------------------------------------------------+-----+---+------------+--------+ |result |begin|end|relationType|sentence| +---------------------------------------------------------------------+-----+---+------------+--------+ |gestational diabetes mellitus & subsequent type two diabetes mellitus|39 |153|TeRP |0 | |gestational diabetes mellitus & T2DM |39 |160|TeRP |0 | |subsequent type two diabetes mellitus & T2DM |117 |160|TeRP |0 | +---------------------------------------------------------------------+-----+---+------------+--------+
Linear Supertypes
Ordering
- Grouped
- Alphabetic
- By Inheritance
Inherited
- REChunkMerger
- 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
Visibility
- Public
- All
Instance Constructors
Type Members
-
type
AnnotationContent = Seq[Row]
- Attributes
- protected
- Definition Classes
- AnnotatorModel
-
type
AnnotatorType = String
- Definition Classes
- HasOutputAnnotatorType
- implicit class MetadataKey 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
_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]
- Definition Classes
- REChunkMerger → 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
-
final
def
clear(param: Param[_]): REChunkMerger.this.type
- Definition Classes
- Params
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
copy(extra: ParamMap): REChunkMerger
- 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
-
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]
- 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
getParam(paramName: String): Param[Any]
- Definition Classes
- Params
-
def
getSeparator: String
Gets the separator to add between the results.
Gets the separator to add between the results. Default: " ".
-
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()
-
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 type: CATEGORY
Input annotator type: CATEGORY
- Definition Classes
- REChunkMerger → 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
- REChunkMerger → HasOutputAnnotatorType
-
final
val
outputCol: Param[String]
- Attributes
- protected
- Definition Classes
- HasOutputAnnotationCol
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
var
parent: Estimator[REChunkMerger]
- Definition Classes
- Model
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
-
val
separator: Param[String]
Separator to add between the chunks.
Separator to add between the chunks. Default: " ".
-
def
set[T](feature: StructFeature[T], value: T): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[K, V](feature: MapFeature[K, V], value: Map[K, V]): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: SetFeature[T], value: Set[T]): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: ArrayFeature[T], value: Array[T]): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
set(paramPair: ParamPair[_]): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set(param: String, value: Any): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set[T](param: Param[T], value: T): REChunkMerger.this.type
- Definition Classes
- Params
-
def
setDefault[T](feature: StructFeature[T], value: () ⇒ T): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
setDefault(paramPairs: ParamPair[_]*): REChunkMerger.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
setDefault[T](param: Param[T], value: T): REChunkMerger.this.type
- Attributes
- protected[org.apache.spark.ml]
- Definition Classes
- Params
-
final
def
setInputCols(value: String*): REChunkMerger.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInputCols(value: Array[String]): REChunkMerger.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setLazyAnnotator(value: Boolean): REChunkMerger.this.type
- Definition Classes
- CanBeLazy
-
final
def
setOutputCol(value: String): REChunkMerger.this.type
- Definition Classes
- HasOutputAnnotationCol
-
def
setParent(parent: Estimator[REChunkMerger]): REChunkMerger
- Definition Classes
- Model
-
def
setSeparator(value: String): REChunkMerger.this.type
Sets the separator to add between the results.
Sets the separator to add between the results. Default: " ".
-
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
- REChunkMerger → Identifiable
-
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 HasSimpleAnnotate[REChunkMerger]
Inherited from AnnotatorModel[REChunkMerger]
Inherited from CanBeLazy
Inherited from RawAnnotator[REChunkMerger]
Inherited from HasOutputAnnotationCol
Inherited from HasInputAnnotationCols
Inherited from HasOutputAnnotatorType
Inherited from ParamsAndFeaturesWritable
Inherited from HasFeatures
Inherited from DefaultParamsWritable
Inherited from MLWritable
Inherited from Model[REChunkMerger]
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