com.johnsnowlabs.nlp.annotators.classification
LargeFewShotClassifierModel
Companion object LargeFewShotClassifierModel
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
- Grouped
- Alphabetic
- By Inheritance
- LargeFewShotClassifierModel
- CheckLicense
- HasBatchedAnnotate
- HasCaseSensitiveProperties
- WriteOnnxModel
- HasStorageRef
- AnnotatorModel
- CanBeLazy
- RawAnnotator
- HasOutputAnnotationCol
- HasInputAnnotationCols
- HasOutputAnnotatorType
- ParamsAndFeaturesWritable
- HasFeatures
- DefaultParamsWritable
- MLWritable
- Model
- Transformer
- PipelineStage
- Logging
- Params
- Serializable
- Serializable
- Identifiable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
Type Members
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
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
batchAnnotate(batchedAnnotations: Seq[Array[Annotation]]): Seq[Seq[Annotation]]
- Definition Classes
- LargeFewShotClassifierModel → HasBatchedAnnotate
-
def
batchProcess(rows: Iterator[_]): Iterator[Row]
- Definition Classes
- HasBatchedAnnotate
-
val
batchSize: IntParam
- Definition Classes
- HasBatchedAnnotate
-
def
beforeAnnotate(dataset: Dataset[_]): Dataset[_]
- Attributes
- protected
- Definition Classes
- AnnotatorModel
-
val
caseSensitive: BooleanParam
- Definition Classes
- HasCaseSensitiveProperties
-
final
def
checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
def
checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String]): Unit
- Definition Classes
- CheckLicense
-
def
checkValidScope(scope: String): Unit
- Definition Classes
- CheckLicense
-
def
checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean): Unit
- Definition Classes
- CheckLicense
-
def
checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean): Unit
- Definition Classes
- CheckLicense
-
final
def
clear(param: Param[_]): LargeFewShotClassifierModel.this.type
- Definition Classes
- Params
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
copy(extra: ParamMap): LargeFewShotClassifierModel
- Definition Classes
- RawAnnotator → Model → Transformer → PipelineStage → Params
-
def
copyValues[T <: Params](to: T, extra: ParamMap): T
- Attributes
- protected
- Definition Classes
- Params
-
def
createDatabaseConnection(database: Name): RocksDBConnection
- Definition Classes
- HasStorageRef
-
final
def
defaultCopy[T <: Params](extra: ParamMap): T
- Attributes
- protected
- Definition Classes
- Params
-
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
-
def
getBatchSize: Int
- Definition Classes
- HasBatchedAnnotate
-
def
getCaseSensitive: Boolean
- Definition Classes
- HasCaseSensitiveProperties
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
getClasses: Array[String]
Returns labels used to train this model
-
final
def
getDefault[T](param: Param[T]): Option[T]
- Definition Classes
- Params
-
def
getHasDifferentiableHead: Boolean
Whether the model has a differentiable head or not
-
def
getInputCols: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
def
getLazyAnnotator: Boolean
- Definition Classes
- CanBeLazy
- def getMaxSentenceLength: Int
-
def
getModelArchitecture: String
Get the architecture of the the sentence embeddings model.
- def getModelIfNotSet: OnnxSetFitClassifier
-
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
getStorageRef: String
- Definition Classes
- HasStorageRef
- def getVocabulary(): Map[String, Int]
-
final
def
hasDefault[T](param: Param[T]): Boolean
- Definition Classes
- Params
-
val
hasDifferentiableHead: BooleanParam
Whether the model has a differentiable head or not
-
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[String]
Input Annotator Types: DOCUMENT, TOKEN
Input Annotator Types: DOCUMENT, TOKEN
- Definition Classes
- LargeFewShotClassifierModel → 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
labels: MapFeature[Int, String]
Labels used to decode predicted IDs back to string tags
-
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
-
val
maxSentenceLength: IntParam
Max sentence length to process (Default:
128
) -
val
modelArchitecture: Param[String]
Architecture of the sentence embeddings model.
-
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
- Definition Classes
- LargeFewShotClassifierModel → ParamsAndFeaturesWritable
-
val
optionalInputAnnotatorTypes: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
val
outputAnnotatorType: AnnotatorType
Output Annotator Types: WORD_EMBEDDINGS
Output Annotator Types: WORD_EMBEDDINGS
- Definition Classes
- LargeFewShotClassifierModel → HasOutputAnnotatorType
-
final
val
outputCol: Param[String]
- Attributes
- protected
- Definition Classes
- HasOutputAnnotationCol
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
var
parent: Estimator[LargeFewShotClassifierModel]
- Definition Classes
- Model
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
-
def
set[T](feature: StructFeature[T], value: T): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[K, V](feature: MapFeature[K, V], value: Map[K, V]): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: SetFeature[T], value: Set[T]): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: ArrayFeature[T], value: Array[T]): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
set(paramPair: ParamPair[_]): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set(param: String, value: Any): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set[T](param: Param[T], value: T): LargeFewShotClassifierModel.this.type
- Definition Classes
- Params
-
def
setBatchSize(size: Int): LargeFewShotClassifierModel.this.type
- Definition Classes
- HasBatchedAnnotate
-
def
setCaseSensitive(value: Boolean): LargeFewShotClassifierModel.this.type
- Definition Classes
- HasCaseSensitiveProperties
-
def
setDefault[T](feature: StructFeature[T], value: () ⇒ T): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
setDefault(paramPairs: ParamPair[_]*): LargeFewShotClassifierModel.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
setDefault[T](param: Param[T], value: T): LargeFewShotClassifierModel.this.type
- Attributes
- protected[org.apache.spark.ml]
- Definition Classes
- Params
-
def
setHasDifferentiableHead(value: Boolean): LargeFewShotClassifierModel.this.type
Whether the model has a differentiable head or not
-
final
def
setInputCols(value: String*): LargeFewShotClassifierModel.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInputCols(value: Array[String]): LargeFewShotClassifierModel.this.type
- Definition Classes
- HasInputAnnotationCols
- def setLabels(value: Map[Int, String]): LargeFewShotClassifierModel.this.type
-
def
setLazyAnnotator(value: Boolean): LargeFewShotClassifierModel.this.type
- Definition Classes
- CanBeLazy
- def setMaxSentenceLength(value: Int): LargeFewShotClassifierModel.this.type
-
def
setModelArchitecture(value: String): LargeFewShotClassifierModel.this.type
Set the architecture of the the sentence embeddings model.
- def setModelIfNotSet(spark: SparkSession, embeddingsOnnxWrapper: OnnxWrapper, classifierOnnxWrapper: OnnxWrapper, tokenizer: SetFitTokenizer): LargeFewShotClassifierModel.this.type
-
final
def
setOutputCol(value: String): LargeFewShotClassifierModel.this.type
- Definition Classes
- HasOutputAnnotationCol
-
def
setParent(parent: Estimator[LargeFewShotClassifierModel]): LargeFewShotClassifierModel
- Definition Classes
- Model
-
def
setStorageRef(value: String): LargeFewShotClassifierModel.this.type
- Definition Classes
- HasStorageRef
- def setVocabulary(value: Map[String, Int]): LargeFewShotClassifierModel.this.type
-
val
storageRef: Param[String]
- Definition Classes
- HasStorageRef
-
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
- LargeFewShotClassifierModel → Identifiable
-
def
validate(schema: StructType): Boolean
- Attributes
- protected
- Definition Classes
- RawAnnotator
-
def
validateStorageRef(dataset: Dataset[_], inputCols: Array[String], annotatorType: String): Unit
- Definition Classes
- HasStorageRef
-
val
vocabulary: MapFeature[String, Int]
Vocabulary used to encode the words to ids with WordPieceEncoder
-
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
-
def
writeOnnxModel(path: String, spark: SparkSession, onnxWrapper: OnnxWrapper, suffix: String, fileName: String): Unit
- Definition Classes
- WriteOnnxModel
-
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