c
com.johnsnowlabs.nlp.annotators.ner
MedicalNerDLGraphChecker
Companion object MedicalNerDLGraphChecker
class MedicalNerDLGraphChecker extends NerDLGraphChecker
Checks whether a suitable MedicalNerApproach graph is available for the given training dataset, before any computations/training is done. This annotator is useful for custom training cases, where specialized graphs might not be available and we want to check before embeddings are evaluated.
Important: This annotator should be used or positioned before any embedding or MedicalNerApproach annotators in the pipeline and will process the whole dataset to extract the required graph parameters.
This annotator requires a dataset with at least two columns: one with tokens and one with the labels. In addition, it requires the used embedding annotator in the pipeline to extract the suitable embedding dimension.
Example
import com.johnsnowlabs.nlp.annotator._ import com.johnsnowlabs.nlp.jsl.annotator._ import com.johnsnowlabs.nlp.training.CoNLL import org.apache.spark.ml.Pipeline // This CoNLL dataset already includes a sentence, token and label column with their respective annotator types. val conll = CoNLL() val trainingData = conll.readDataset(spark, "PATH/TO/YOUR/TRAINING/DATA") val embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models") .setInputCols("sentence", "token") .setOutputCol("embeddings") // Requires the data for MedicalNerApproach graphs: text, tokens, labels and the embedding model val nerDLGraphChecker = new MedicalNerDLGraphChecker() .setInputCols("sentence", "token") .setLabelColumn("label") .setEmbeddingsModel(embeddings) val nerTagger = new MedicalNerApproach() .setInputCols("sentence", "token", "embeddings") .setLabelColumn("label") .setOutputCol("ner") .setMaxEpochs(1) .setRandomSeed(42) .setVerbose(0) .setEarlyStoppingCriterion(0.50f) .setEnableOutputLogs(false) .setUseBestModel(true) val pipeline = new Pipeline().setStages( Array(nerDLGraphChecker, embeddings, nerTagger)) // Will throw an exception if no suitable graph is found val pipelineModel = pipeline.fit(trainingData)
Linear Supertypes
Ordering
- Alphabetic
- By Inheritance
Inherited
- MedicalNerDLGraphChecker
- NerDLGraphChecker
- ParamsAndFeaturesWritable
- HasFeatures
- DefaultParamsWritable
- MLWritable
- HasInputAnnotationCols
- Estimator
- PipelineStage
- Logging
- Params
- Serializable
- Serializable
- Identifiable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- All
Instance Constructors
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
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
final
def
checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
final
def
clear(param: Param[_]): MedicalNerDLGraphChecker.this.type
- Definition Classes
- Params
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
copy(extra: ParamMap): Estimator[NerDLGraphCheckerModel]
- Definition Classes
- NerDLGraphChecker → 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
embeddingsDim: IntParam
- Definition Classes
- NerDLGraphChecker
-
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
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
fit(dataset: Dataset[_]): NerDLGraphCheckerModel
- Definition Classes
- NerDLGraphChecker → Estimator
-
def
fit(dataset: Dataset[_], paramMaps: Seq[ParamMap]): Seq[NerDLGraphCheckerModel]
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" )
-
def
fit(dataset: Dataset[_], paramMap: ParamMap): NerDLGraphCheckerModel
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" )
-
def
fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): NerDLGraphCheckerModel
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" ) @varargs()
-
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
getEmbeddingsDim: Int
- Definition Classes
- NerDLGraphChecker
-
def
getGraphFolder: Option[String]
- Attributes
- protected
- Definition Classes
- NerDLGraphChecker
-
def
getGraphParamsDs(dataset: Dataset[_], inputCols: Array[String], labelsCol: String): (Int, Int, Int)
- Attributes
- protected
- Definition Classes
- NerDLGraphChecker
-
def
getInputCols: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
def
getLabelColumn: String
- Definition Classes
- NerDLGraphChecker
-
final
def
getOrDefault[T](param: Param[T]): T
- Definition Classes
- Params
-
def
getParam(paramName: String): Param[Any]
- Definition Classes
- Params
-
val
graphFolder: Param[String]
- Definition Classes
- NerDLGraphChecker
-
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[String]
- Definition Classes
- NerDLGraphChecker → 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
labelColumn: Param[String]
- Definition Classes
- NerDLGraphChecker
-
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
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
-
def
searchForSuitableGraph(nLabels: Int, nChars: Int, embeddingsDim: Int): String
- Attributes
- protected
- Definition Classes
- MedicalNerDLGraphChecker → NerDLGraphChecker
-
def
set[T](feature: StructFeature[T], value: T): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[K, V](feature: MapFeature[K, V], value: Map[K, V]): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: SetFeature[T], value: Set[T]): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: ArrayFeature[T], value: Array[T]): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
set(paramPair: ParamPair[_]): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set(param: String, value: Any): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set[T](param: Param[T], value: T): MedicalNerDLGraphChecker.this.type
- Definition Classes
- Params
-
def
setDefault[T](feature: StructFeature[T], value: () ⇒ T): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
setDefault(paramPairs: ParamPair[_]*): MedicalNerDLGraphChecker.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
setDefault[T](param: Param[T], value: T): MedicalNerDLGraphChecker.this.type
- Attributes
- protected[org.apache.spark.ml]
- Definition Classes
- Params
-
def
setEmbeddingsDim(d: Int): MedicalNerDLGraphChecker.this.type
- Definition Classes
- NerDLGraphChecker
-
def
setEmbeddingsModel(model: AnnotatorModel[_] with HasEmbeddingsProperties): MedicalNerDLGraphChecker.this.type
- Definition Classes
- NerDLGraphChecker
-
final
def
setInputCols(value: String*): MedicalNerDLGraphChecker.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInputCols(value: Array[String]): MedicalNerDLGraphChecker.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setLabelColumn(value: String): MedicalNerDLGraphChecker.this.type
- Definition Classes
- NerDLGraphChecker
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- Identifiable → AnyRef → Any
-
def
transformSchema(schema: StructType): StructType
- Definition Classes
- NerDLGraphChecker → PipelineStage
-
def
transformSchema(schema: StructType, logging: Boolean): StructType
- Attributes
- protected
- Definition Classes
- PipelineStage
- Annotations
- @DeveloperApi()
-
val
uid: String
- Definition Classes
- MedicalNerDLGraphChecker → NerDLGraphChecker → Identifiable
-
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
- ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable