class NerDLGraphChecker extends Estimator[NerDLGraphCheckerModel] with HasInputAnnotationCols with ParamsAndFeaturesWritable

Checks whether a suitable NerDL 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 NerDLApproach 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.

For extended examples of usage, see the Examples and the NerDLGraphCheckerTestSpec.

Example

import com.johnsnowlabs.nlp.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. If a custom dataset is used,
// these need to be defined with for example:
val conll = CoNLL()
val trainingData = conll.readDataset(spark, "src/test/resources/conll2003/eng.train")

val embeddings = BertEmbeddings
  .pretrained()
  .setInputCols("sentence", "token")
  .setOutputCol("embeddings")

// Requires the data for NerDLApproach graphs: text, tokens, labels and the embedding model
val nerDLGraphChecker = new NerDLGraphChecker()
  .setInputCols("sentence", "token")
  .setLabelColumn("label")
  .setEmbeddingsModel(embeddings)

val nerTagger = new NerDLApproach()
  .setInputCols("sentence", "token", "embeddings")
  .setLabelColumn("label")
  .setOutputCol("ner")
  .setMaxEpochs(1)
  .setRandomSeed(0)
  .setVerbose(0)

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
ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, HasInputAnnotationCols, Estimator[NerDLGraphCheckerModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. NerDLGraphChecker
  2. ParamsAndFeaturesWritable
  3. HasFeatures
  4. DefaultParamsWritable
  5. MLWritable
  6. HasInputAnnotationCols
  7. Estimator
  8. PipelineStage
  9. Logging
  10. Params
  11. Serializable
  12. Serializable
  13. Identifiable
  14. AnyRef
  15. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new NerDLGraphChecker()
  2. new NerDLGraphChecker(uid: String)

    uid

    required uid for storing annotator to disk

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T
    Attributes
    protected
    Definition Classes
    Params
  4. def $$[T](feature: StructFeature[T]): T
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  10. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  11. final def clear(param: Param[_]): NerDLGraphChecker.this.type
    Definition Classes
    Params
  12. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  13. def copy(extra: ParamMap): Estimator[NerDLGraphCheckerModel]
    Definition Classes
    NerDLGraphChecker → Estimator → PipelineStage → Params
  14. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  15. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  16. val embeddingsDim: IntParam

    Dimensionality of embeddings

  17. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  18. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  19. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  20. def explainParams(): String
    Definition Classes
    Params
  21. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  22. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  23. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  24. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  25. def fit(dataset: Dataset[_]): NerDLGraphCheckerModel
    Definition Classes
    NerDLGraphChecker → Estimator
  26. def fit(dataset: Dataset[_], paramMaps: Seq[ParamMap]): Seq[NerDLGraphCheckerModel]
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  27. def fit(dataset: Dataset[_], paramMap: ParamMap): NerDLGraphCheckerModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  28. def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): NerDLGraphCheckerModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" ) @varargs()
  29. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  30. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  31. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  32. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  33. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  34. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  35. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  36. def getEmbeddingsDim: Int

  37. def getGraphFolder: Option[String]

    Attributes
    protected
  38. def getGraphParamsDs(dataset: Dataset[_], inputCols: Array[String], labelsCol: String): (Int, Int, Int)

    Extracts the graph hyperparameters from the training data (dataset).

    Extracts the graph hyperparameters from the training data (dataset).

    * @param dataset the training dataset

    inputCols

    the input columns that contain the tokens and embeddings

    labelsCol

    the column that contains the labels

    returns

    a tuple containing the number of labels, number of unique characters, and the embedding dim

    Attributes
    protected
    Exceptions thrown

    IllegalArgumentException if the token input column is not found in the dataset schema*

  39. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  40. def getLabelColumn: String

  41. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  42. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  43. val graphFolder: Param[String]

    Folder path that contain external graph files

  44. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  45. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  46. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  47. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  48. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  49. 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
    NerDLGraphCheckerHasInputAnnotationCols
  50. 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
  51. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  52. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  53. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  54. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  55. val labelColumn: Param[String]

    Column with label per each token

  56. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  57. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  58. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  59. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  60. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  61. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  62. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  63. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  64. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  65. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  66. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  69. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  70. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  71. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  72. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  73. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  74. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  75. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  76. def searchForSuitableGraph(nLabels: Int, nChars: Int, embeddingsDim: Int): String
    Attributes
    protected
  77. def set[T](feature: StructFeature[T], value: T): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  78. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  79. def set[T](feature: SetFeature[T], value: Set[T]): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  80. def set[T](feature: ArrayFeature[T], value: Array[T]): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  81. final def set(paramPair: ParamPair[_]): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    Params
  82. final def set(param: String, value: Any): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    Params
  83. final def set[T](param: Param[T], value: T): NerDLGraphChecker.this.type
    Definition Classes
    Params
  84. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  85. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  86. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  87. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  88. final def setDefault(paramPairs: ParamPair[_]*): NerDLGraphChecker.this.type
    Attributes
    protected
    Definition Classes
    Params
  89. final def setDefault[T](param: Param[T], value: T): NerDLGraphChecker.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  90. def setEmbeddingsDim(d: Int): NerDLGraphChecker.this.type

  91. def setEmbeddingsModel(model: AnnotatorModel[_] with HasEmbeddingsProperties): NerDLGraphChecker.this.type

  92. final def setInputCols(value: String*): NerDLGraphChecker.this.type
    Definition Classes
    HasInputAnnotationCols
  93. def setInputCols(value: Array[String]): NerDLGraphChecker.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  94. def setLabelColumn(value: String): NerDLGraphChecker.this.type

  95. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  96. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  97. def transformSchema(schema: StructType): StructType
    Definition Classes
    NerDLGraphChecker → PipelineStage
  98. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  99. val uid: String
    Definition Classes
    NerDLGraphChecker → Identifiable
  100. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  101. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  102. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  103. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasInputAnnotationCols

Inherited from Estimator[NerDLGraphCheckerModel]

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

A list of (hyper-)parameter keys this annotator can take. Users can set and get the parameter values through setters and getters, respectively.

Members

Parameter setters

Parameter getters