class LargeFewShotClassifierModel extends AnnotatorModel[LargeFewShotClassifierModel] with HasStorageRef with WriteOnnxModel with HasCaseSensitiveProperties with ParamsAndFeaturesWritable with HasBatchedAnnotate[LargeFewShotClassifierModel] with CheckLicense

LargeFewShotClassifierModel annotator can run large (LLMS based) few shot classifiers based on the SetFit approach.

Example

Define pipeline stages to prepare the data

val document_assembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")


 val largeFewShotClassifier = LargeFewShotClassifierModel.pretrained()
   .setInputCols(Array("document"))
   .setBatchSize(1)
   .setOutputCol("label")

 val pipeline = new Pipeline().setStages(Array(
  document_assembler,
  largeFewShotClassifier))

 val model = pipeline.fit(Seq().toDS.toDF("text"))
 val results = model.transform(
   Seq("I felt a bit drowsy and had blurred vision after taking Aspirin.").toDS.toDF("text"))

 results
   .selectExpr("explode(label) as label")
   .select("label.result", "label.metadata.confidence").show()
+------+----------+
|result|confidence|
+------+----------+
|   ADE| 0.9672883|
+------+----------+
See also

LargeFewShotClassifierModel for instantiated models

https://arxiv.org/abs/2209.11055 for details about the SetFit approach

Linear Supertypes
CheckLicense, HasBatchedAnnotate[LargeFewShotClassifierModel], HasCaseSensitiveProperties, WriteOnnxModel, HasStorageRef, AnnotatorModel[LargeFewShotClassifierModel], CanBeLazy, RawAnnotator[LargeFewShotClassifierModel], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[LargeFewShotClassifierModel], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. LargeFewShotClassifierModel
  2. CheckLicense
  3. HasBatchedAnnotate
  4. HasCaseSensitiveProperties
  5. WriteOnnxModel
  6. HasStorageRef
  7. AnnotatorModel
  8. CanBeLazy
  9. RawAnnotator
  10. HasOutputAnnotationCol
  11. HasInputAnnotationCols
  12. HasOutputAnnotatorType
  13. ParamsAndFeaturesWritable
  14. HasFeatures
  15. DefaultParamsWritable
  16. MLWritable
  17. Model
  18. Transformer
  19. PipelineStage
  20. Logging
  21. Params
  22. Serializable
  23. Serializable
  24. Identifiable
  25. AnyRef
  26. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

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

    uid

    a unique identifier for the instantiated AnnotatorModel

Type Members

  1. type AnnotationContent = Seq[Row]
    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. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  12. def batchAnnotate(batchedAnnotations: Seq[Array[Annotation]]): Seq[Seq[Annotation]]
    Definition Classes
    LargeFewShotClassifierModel → HasBatchedAnnotate
  13. def batchProcess(rows: Iterator[_]): Iterator[Row]
    Definition Classes
    HasBatchedAnnotate
  14. val batchSize: IntParam
    Definition Classes
    HasBatchedAnnotate
  15. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  16. val caseSensitive: BooleanParam
    Definition Classes
    HasCaseSensitiveProperties
  17. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  18. def checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String]): Unit
    Definition Classes
    CheckLicense
  19. def checkValidScope(scope: String): Unit
    Definition Classes
    CheckLicense
  20. def checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean): Unit
    Definition Classes
    CheckLicense
  21. def checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean): Unit
    Definition Classes
    CheckLicense
  22. final def clear(param: Param[_]): LargeFewShotClassifierModel.this.type
    Definition Classes
    Params
  23. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  24. def copy(extra: ParamMap): LargeFewShotClassifierModel
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  25. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  26. def createDatabaseConnection(database: Name): RocksDBConnection
    Definition Classes
    HasStorageRef
  27. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  28. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  29. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  30. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  31. def explainParams(): String
    Definition Classes
    Params
  32. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  33. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  34. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  35. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  36. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  37. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  38. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  39. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  40. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  41. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  42. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  43. def getBatchSize: Int
    Definition Classes
    HasBatchedAnnotate
  44. def getCaseSensitive: Boolean
    Definition Classes
    HasCaseSensitiveProperties
  45. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  46. def getClasses: Array[String]

    Returns labels used to train this model

  47. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  48. def getHasDifferentiableHead: Boolean

    Whether the model has a differentiable head or not

  49. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  50. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  51. def getMaxSentenceLength: Int

  52. def getModelArchitecture: String

    Get the architecture of the the sentence embeddings model.

  53. def getModelIfNotSet: OnnxSetFitClassifier
  54. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  55. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  56. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  57. def getStorageRef: String
    Definition Classes
    HasStorageRef
  58. def getVocabulary(): Map[String, Int]
  59. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  60. val hasDifferentiableHead: BooleanParam

    Whether the model has a differentiable head or not

  61. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  62. def hasParent: Boolean
    Definition Classes
    Model
  63. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  64. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  65. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  66. val inputAnnotatorTypes: Array[String]

    Input Annotator Types: DOCUMENT, TOKEN

    Input Annotator Types: DOCUMENT, TOKEN

    Definition Classes
    LargeFewShotClassifierModel → HasInputAnnotationCols
  67. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  68. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  69. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  70. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  71. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  72. val labels: MapFeature[Int, String]

    Labels used to decode predicted IDs back to string tags

  73. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  74. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  75. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  76. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  80. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  81. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  82. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  83. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  84. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  85. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  86. val maxSentenceLength: IntParam

    Max sentence length to process (Default: 128)

  87. val modelArchitecture: Param[String]

    Architecture of the sentence embeddings model.

  88. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  89. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  90. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  91. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  92. def onWrite(path: String, spark: SparkSession): Unit
    Definition Classes
    LargeFewShotClassifierModel → ParamsAndFeaturesWritable
  93. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  94. val outputAnnotatorType: AnnotatorType

    Output Annotator Types: WORD_EMBEDDINGS

    Output Annotator Types: WORD_EMBEDDINGS

    Definition Classes
    LargeFewShotClassifierModel → HasOutputAnnotatorType
  95. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  96. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  97. var parent: Estimator[LargeFewShotClassifierModel]
    Definition Classes
    Model
  98. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  99. def set[T](feature: StructFeature[T], value: T): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  100. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  101. def set[T](feature: SetFeature[T], value: Set[T]): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  102. def set[T](feature: ArrayFeature[T], value: Array[T]): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  103. final def set(paramPair: ParamPair[_]): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  104. final def set(param: String, value: Any): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  105. final def set[T](param: Param[T], value: T): LargeFewShotClassifierModel.this.type
    Definition Classes
    Params
  106. def setBatchSize(size: Int): LargeFewShotClassifierModel.this.type
    Definition Classes
    HasBatchedAnnotate
  107. def setCaseSensitive(value: Boolean): LargeFewShotClassifierModel.this.type
    Definition Classes
    HasCaseSensitiveProperties
  108. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  109. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  110. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  111. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  112. final def setDefault(paramPairs: ParamPair[_]*): LargeFewShotClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  113. final def setDefault[T](param: Param[T], value: T): LargeFewShotClassifierModel.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  114. def setHasDifferentiableHead(value: Boolean): LargeFewShotClassifierModel.this.type

    Whether the model has a differentiable head or not

  115. final def setInputCols(value: String*): LargeFewShotClassifierModel.this.type
    Definition Classes
    HasInputAnnotationCols
  116. def setInputCols(value: Array[String]): LargeFewShotClassifierModel.this.type
    Definition Classes
    HasInputAnnotationCols
  117. def setLabels(value: Map[Int, String]): LargeFewShotClassifierModel.this.type

  118. def setLazyAnnotator(value: Boolean): LargeFewShotClassifierModel.this.type
    Definition Classes
    CanBeLazy
  119. def setMaxSentenceLength(value: Int): LargeFewShotClassifierModel.this.type

  120. def setModelArchitecture(value: String): LargeFewShotClassifierModel.this.type

    Set the architecture of the the sentence embeddings model.

  121. def setModelIfNotSet(spark: SparkSession, embeddingsOnnxWrapper: OnnxWrapper, classifierOnnxWrapper: OnnxWrapper, tokenizer: SetFitTokenizer): LargeFewShotClassifierModel.this.type
  122. final def setOutputCol(value: String): LargeFewShotClassifierModel.this.type
    Definition Classes
    HasOutputAnnotationCol
  123. def setParent(parent: Estimator[LargeFewShotClassifierModel]): LargeFewShotClassifierModel
    Definition Classes
    Model
  124. def setStorageRef(value: String): LargeFewShotClassifierModel.this.type
    Definition Classes
    HasStorageRef
  125. def setVocabulary(value: Map[String, Int]): LargeFewShotClassifierModel.this.type

  126. val storageRef: Param[String]
    Definition Classes
    HasStorageRef
  127. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  128. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  129. final def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    AnnotatorModel → Transformer
  130. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  131. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  132. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  133. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  134. val uid: String
    Definition Classes
    LargeFewShotClassifierModel → Identifiable
  135. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  136. def validateStorageRef(dataset: Dataset[_], inputCols: Array[String], annotatorType: String): Unit
    Definition Classes
    HasStorageRef
  137. val vocabulary: MapFeature[String, Int]

    Vocabulary used to encode the words to ids with WordPieceEncoder

  138. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  139. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  140. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  141. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  142. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
  143. def writeOnnxModel(path: String, spark: SparkSession, onnxWrapper: OnnxWrapper, suffix: String, fileName: String): Unit
    Definition Classes
    WriteOnnxModel
  144. def writeOnnxModels(path: String, spark: SparkSession, onnxWrappersWithNames: Seq[(OnnxWrapper, String)], suffix: String): Unit
    Definition Classes
    WriteOnnxModel

Inherited from CheckLicense

Inherited from HasBatchedAnnotate[LargeFewShotClassifierModel]

Inherited from HasCaseSensitiveProperties

Inherited from WriteOnnxModel

Inherited from HasStorageRef

Inherited from AnnotatorModel[LargeFewShotClassifierModel]

Inherited from CanBeLazy

Inherited from RawAnnotator[LargeFewShotClassifierModel]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[LargeFewShotClassifierModel]

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

Members

Parameter setters

Parameter getters