Packages

class NerOverwriter extends AnnotatorModel[NerOverwriter] with HasSimpleAnnotate[NerOverwriter]

Overwrites entities of specified strings.

The input for this Annotator have to be entities that are already extracted, Annotator type NAMED_ENTITY. The strings specified with setStopWords will have new entities assigned to, specified with setNewResult.

Example

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.sbd.pragmatic.SentenceDetector
import com.johnsnowlabs.nlp.embeddings.WordEmbeddingsModel
import com.johnsnowlabs.nlp.annotators.ner.dl.NerDLModel
import com.johnsnowlabs.nlp.annotators.ner.NerOverwriter
import org.apache.spark.ml.Pipeline

// First extract the prerequisite Entities
val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentence = new SentenceDetector()
  .setInputCols("document")
  .setOutputCol("sentence")

val tokenizer = new Tokenizer()
  .setInputCols("sentence")
  .setOutputCol("token")

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

val nerTagger = NerDLModel.pretrained()
  .setInputCols("sentence", "token", "embeddings")
  .setOutputCol("ner")

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  sentence,
  tokenizer,
  embeddings,
  nerTagger
))

val data = Seq("Spark NLP Crosses Five Million Downloads, John Snow Labs Announces.").toDF("text")
val result = pipeline.fit(data).transform(data)

result.selectExpr("explode(ner)").show(false)
/*
+------------------------------------------------------+
|col                                                   |
+------------------------------------------------------+
|[named_entity, 0, 4, B-ORG, [word -> Spark], []]      |
|[named_entity, 6, 8, I-ORG, [word -> NLP], []]        |
|[named_entity, 10, 16, O, [word -> Crosses], []]      |
|[named_entity, 18, 21, O, [word -> Five], []]         |
|[named_entity, 23, 29, O, [word -> Million], []]      |
|[named_entity, 31, 39, O, [word -> Downloads], []]    |
|[named_entity, 40, 40, O, [word -> ,], []]            |
|[named_entity, 42, 45, B-ORG, [word -> John], []]     |
|[named_entity, 47, 50, I-ORG, [word -> Snow], []]     |
|[named_entity, 52, 55, I-ORG, [word -> Labs], []]     |
|[named_entity, 57, 65, I-ORG, [word -> Announces], []]|
|[named_entity, 66, 66, O, [word -> .], []]            |
+------------------------------------------------------+
*/
// The recognized entities can then be overwritten
val nerOverwriter = new NerOverwriter()
  .setInputCols("ner")
  .setOutputCol("ner_overwritten")
  .setNerWords(Array("Million"))
  .setNerNewEntity,("B-CARDINAL")

nerOverwriter.transform(result).selectExpr("explode(ner_overwritten)").show(false)
+---------------------------------------------------------+
|col                                                      |
+---------------------------------------------------------+
|[named_entity, 0, 4, B-ORG, [word -> Spark], []]         |
|[named_entity, 6, 8, I-ORG, [word -> NLP], []]           |
|[named_entity, 10, 16, O, [word -> Crosses], []]         |
|[named_entity, 18, 21, O, [word -> Five], []]            |
|[named_entity, 23, 29, B-CARDINAL, [word -> Million], []]|
|[named_entity, 31, 39, O, [word -> Downloads], []]       |
|[named_entity, 40, 40, O, [word -> ,], []]               |
|[named_entity, 42, 45, B-ORG, [word -> John], []]        |
|[named_entity, 47, 50, I-ORG, [word -> Snow], []]        |
|[named_entity, 52, 55, I-ORG, [word -> Labs], []]        |
|[named_entity, 57, 65, I-ORG, [word -> Announces], []]   |
|[named_entity, 66, 66, O, [word -> .], []]               |
+---------------------------------------------------------+
Linear Supertypes
HasSimpleAnnotate[NerOverwriter], AnnotatorModel[NerOverwriter], CanBeLazy, RawAnnotator[NerOverwriter], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[NerOverwriter], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. NerOverwriter
  2. HasSimpleAnnotate
  3. AnnotatorModel
  4. CanBeLazy
  5. RawAnnotator
  6. HasOutputAnnotationCol
  7. HasInputAnnotationCols
  8. HasOutputAnnotatorType
  9. ParamsAndFeaturesWritable
  10. HasFeatures
  11. DefaultParamsWritable
  12. MLWritable
  13. Model
  14. Transformer
  15. PipelineStage
  16. Logging
  17. Params
  18. Serializable
  19. Serializable
  20. Identifiable
  21. AnyRef
  22. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

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

Type Members

  1. type AnnotationContent = Seq[Row]

    internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

    internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

    Attributes
    protected
    Definition Classes
    AnnotatorModel
  2. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType

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. def _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  10. def afterAnnotate(dataset: DataFrame): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  11. def annotate(annotations: Seq[Annotation]): Seq[Annotation]

    takes a document and annotations and produces new annotations of this annotator's annotation type

    takes a document and annotations and produces new annotations of this annotator's annotation type

    annotations

    Annotations that correspond to inputAnnotationCols generated by previous annotators if any

    returns

    any number of annotations processed for every input annotation. Not necessary one to one relationship

    Definition Classes
    NerOverwriterHasSimpleAnnotate
  12. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  13. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  14. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  15. final def clear(param: Param[_]): NerOverwriter.this.type
    Definition Classes
    Params
  16. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  17. def copy(extra: ParamMap): NerOverwriter

    requirement for annotators copies

    requirement for annotators copies

    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  18. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  19. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  20. def dfAnnotate: UserDefinedFunction

    Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column

    Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column

    returns

    udf function to be applied to inputCols using this annotator's annotate function as part of ML transformation

    Definition Classes
    HasSimpleAnnotate
  21. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  22. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  23. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  24. def explainParams(): String
    Definition Classes
    Params
  25. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  26. def extraValidateMsg: String

    Override for additional custom schema checks

    Override for additional custom schema checks

    Attributes
    protected
    Definition Classes
    RawAnnotator
  27. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  28. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  29. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  30. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  31. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  32. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  33. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  34. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  35. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  36. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  37. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  38. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  39. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  40. def getNerWords: Array[String]

    The words to be filtered out.

  41. def getNewNerEntity: String

    New NER class to overwrite

  42. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  43. final def getOutputCol: String

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  44. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  45. def getReplaceEntities: Map[String, String]
  46. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  47. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  48. def hasParent: Boolean
    Definition Classes
    Model
  49. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  50. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  51. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  52. val inputAnnotatorTypes: Array[AnnotatorType]

    Input Annotator Type : NAMED_ENTITY

    Input Annotator Type : NAMED_ENTITY

    Definition Classes
    NerOverwriterHasInputAnnotationCols
  53. 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
  54. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  55. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  56. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  57. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  58. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  59. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  60. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  61. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  62. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  63. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  64. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  65. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  66. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  67. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  72. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  73. val nerWords: StringArrayParam

    The words to be filtered out.

  74. val newNerEntity: Param[String]

    New NER class to overwrite

  75. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  76. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  77. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  78. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  79. val outputAnnotatorType: AnnotatorType

    Output Annotator Type : NAMED_ENTITY

    Output Annotator Type : NAMED_ENTITY

    Definition Classes
    NerOverwriterHasOutputAnnotatorType
  80. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  81. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  82. var parent: Estimator[NerOverwriter]
    Definition Classes
    Model
  83. val replaceEntities: MapFeature[String, String]
  84. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  85. def set[T](feature: StructFeature[T], value: T): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  86. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  87. def set[T](feature: SetFeature[T], value: Set[T]): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  88. def set[T](feature: ArrayFeature[T], value: Array[T]): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  89. final def set(paramPair: ParamPair[_]): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    Params
  90. final def set(param: String, value: Any): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    Params
  91. final def set[T](param: Param[T], value: T): NerOverwriter.this.type
    Definition Classes
    Params
  92. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  93. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  94. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  95. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  96. final def setDefault(paramPairs: ParamPair[_]*): NerOverwriter.this.type
    Attributes
    protected
    Definition Classes
    Params
  97. final def setDefault[T](param: Param[T], value: T): NerOverwriter.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  98. final def setInputCols(value: String*): NerOverwriter.this.type
    Definition Classes
    HasInputAnnotationCols
  99. def setInputCols(value: Array[String]): NerOverwriter.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  100. def setLazyAnnotator(value: Boolean): NerOverwriter.this.type
    Definition Classes
    CanBeLazy
  101. def setNerWords(value: Array[String]): NerOverwriter.this.type

    The words to be filtered out.

  102. def setNewNerEntity(r: String): NerOverwriter.this.type

    New NER class to overwrite

  103. final def setOutputCol(value: String): NerOverwriter.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  104. def setParent(parent: Estimator[NerOverwriter]): NerOverwriter
    Definition Classes
    Model
  105. def setReplaceEntities(w: HashMap[String, String]): NerOverwriter.this.type

  106. def setReplaceEntities(w: Map[String, String]): NerOverwriter.this.type
  107. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  108. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  109. final def transform(dataset: Dataset[_]): DataFrame

    Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content

    Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content

    dataset

    Dataset[Row]

    Definition Classes
    AnnotatorModel → Transformer
  110. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  111. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  112. final def transformSchema(schema: StructType): StructType

    requirement for pipeline transformation validation.

    requirement for pipeline transformation validation. It is called on fit()

    Definition Classes
    RawAnnotator → PipelineStage
  113. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  114. val uid: String
    Definition Classes
    NerOverwriter → Identifiable
  115. 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
    RawAnnotator
  116. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  117. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  118. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  119. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  120. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from AnnotatorModel[NerOverwriter]

Inherited from CanBeLazy

Inherited from RawAnnotator[NerOverwriter]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[NerOverwriter]

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

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

Annotator types

Required input and expected output annotator types

Members

Parameter setters

Parameter getters