c
com.johnsnowlabs.nlp.annotators.embeddings
ExtractiveSummarization
Companion object ExtractiveSummarization
class ExtractiveSummarization extends AnnotatorModel[ExtractiveSummarization] with HasSimpleAnnotate[ExtractiveSummarization] with CheckLicense
Linear Supertypes
Ordering
- Grouped
- Alphabetic
- By Inheritance
Inherited
- ExtractiveSummarization
- CheckLicense
- HasSimpleAnnotate
- AnnotatorModel
- CanBeLazy
- RawAnnotator
- HasOutputAnnotationCol
- HasInputAnnotationCols
- HasOutputAnnotatorType
- ParamsAndFeaturesWritable
- HasFeatures
- DefaultParamsWritable
- MLWritable
- Model
- Transformer
- PipelineStage
- Logging
- Params
- Serializable
- Serializable
- Identifiable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- All
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
-
def
annotate(annotations: Seq[Annotation]): Seq[Annotation]
- Definition Classes
- ExtractiveSummarization → HasSimpleAnnotate
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
beforeAnnotate(dataset: Dataset[_]): Dataset[_]
- Attributes
- protected
- Definition Classes
- AnnotatorModel
-
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[_]): ExtractiveSummarization.this.type
- Definition Classes
- Params
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
- def computeCentralityScores(vectors: Array[Array[Float]], threshold: Option[Float] = None, increasePower: Boolean = true, maxIterations: Int = 10000, convergenceThreshold: Float = 0.00001f, doNormalization: Boolean = false): Array[Float]
-
def
computeEigenVector(matrix: Array[Array[Float]], maxIterations: Int, increasePower: Boolean = true, convergenceThreshold: Float): Array[Float]
- Attributes
- protected
-
def
computeSimilarity(vector1: Array[Float], vector2: Array[Float]): Float
- Attributes
- protected
-
def
computeSimilarityMatrix(vectors: Array[Array[Float]]): Array[Array[Float]]
- Attributes
- protected
-
def
copy(extra: ParamMap): ExtractiveSummarization
- Definition Classes
- RawAnnotator → Model → Transformer → PipelineStage → Params
-
def
copyValues[T <: Params](to: T, extra: ParamMap): T
- Attributes
- protected
- Definition Classes
- Params
-
def
createMarkovChainMatrix(similarityMatrix: Array[Array[Float]], threshold: Option[Float] = None, minDifference: Float = 0.0001f): Array[Array[Float]]
- Attributes
- protected
-
final
def
defaultCopy[T <: Params](extra: ParamMap): T
- Attributes
- protected
- Definition Classes
- Params
-
def
dfAnnotate: UserDefinedFunction
- Definition Classes
- HasSimpleAnnotate
-
def
dotProduct(xx: Array[Array[Float]], yy: Array[Array[Float]]): Array[Array[Float]]
- Attributes
- protected
-
def
dotProduct(xx: Array[Array[Float]], y: Array[Float]): Array[Float]
- Attributes
- protected
-
def
dotProduct(x: Array[Float], y: Array[Float]): Float
- Attributes
- protected
-
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
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
getDefault[T](param: Param[T]): Option[T]
- Definition Classes
- Params
-
def
getGraphComponents(matrix: Array[Array[Float]]): Array[Int]
- Attributes
- protected
-
def
getInputCols: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
def
getLazyAnnotator: Boolean
- Definition Classes
- CanBeLazy
-
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
getReturnSingleDocument: Boolean
Checks if selected sentences are compiled into a single document.
-
def
getSimilarityThreshold: Float
Get the relative value of the chunk embeddings.
-
def
getSummarySize: Int
Gets the number of sentences to summarize the text
-
final
def
hasDefault[T](param: Param[T]): Boolean
- Definition Classes
- Params
-
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[AnnotatorType]
Input annotator types: DOCUMENT, SENTENCE_EMBEDDINGS
Input annotator types: DOCUMENT, SENTENCE_EMBEDDINGS
- Definition Classes
- ExtractiveSummarization → 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
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
-
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
-
val
outputAnnotatorType: AnnotatorType
Output annotator types: DOCUMENT
Output annotator types: DOCUMENT
- Definition Classes
- ExtractiveSummarization → HasOutputAnnotatorType
-
final
val
outputCol: Param[String]
- Attributes
- protected
- Definition Classes
- HasOutputAnnotationCol
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
var
parent: Estimator[ExtractiveSummarization]
- Definition Classes
- Model
-
val
returnSingleDocument: BooleanParam
Compile the selected sentences into a single document.
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
-
def
set[T](feature: StructFeature[T], value: T): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[K, V](feature: MapFeature[K, V], value: Map[K, V]): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: SetFeature[T], value: Set[T]): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: ArrayFeature[T], value: Array[T]): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
set(paramPair: ParamPair[_]): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set(param: String, value: Any): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set[T](param: Param[T], value: T): ExtractiveSummarization.this.type
- Definition Classes
- Params
-
def
setDefault[T](feature: StructFeature[T], value: () ⇒ T): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
setDefault(paramPairs: ParamPair[_]*): ExtractiveSummarization.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
setDefault[T](param: Param[T], value: T): ExtractiveSummarization.this.type
- Attributes
- protected[org.apache.spark.ml]
- Definition Classes
- Params
-
final
def
setInputCols(value: String*): ExtractiveSummarization.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInputCols(value: Array[String]): ExtractiveSummarization.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setLazyAnnotator(value: Boolean): ExtractiveSummarization.this.type
- Definition Classes
- CanBeLazy
-
final
def
setOutputCol(value: String): ExtractiveSummarization.this.type
- Definition Classes
- HasOutputAnnotationCol
-
def
setParent(parent: Estimator[ExtractiveSummarization]): ExtractiveSummarization
- Definition Classes
- Model
-
def
setReturnSingleDocument(value: Boolean): ExtractiveSummarization.this.type
Determines whether to compile the selected sentences into a single document.
-
def
setSimilarityThreshold(value: Float): ExtractiveSummarization.this.type
Sets the minimal cosine similarity between sentences to consider them similar.
-
def
setSummarySize(value: Int): ExtractiveSummarization.this.type
Sets the number of sentences to summarize the text
-
val
similarityThreshold: FloatParam
Minimal cosine similarity between sentences to consider them similar.
-
def
softmax(matrix: Array[Array[Float]]): Array[Array[Float]]
- Attributes
- protected
-
val
summarySize: IntParam
Number of sentences to summarize the text
-
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()
-
def
traverseGraphNode(matrix: Array[Array[Float]], components: ArrayBuffer[Option[Int]], node: Int, currentComponent: Int): ArrayBuffer[Option[Int]]
- Attributes
- protected
-
val
uid: String
- Definition Classes
- ExtractiveSummarization → Identifiable
-
def
validate(schema: StructType): Boolean
- Attributes
- protected
- Definition Classes
- RawAnnotator
-
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