Packages

class FeaturesAssembler extends AnnotatorModel[FeaturesAssembler] with HasStorageRef with HasSimpleAnnotate[FeaturesAssembler] with CheckLicense

The FeaturesAssembler is used to collect features from different columns. It can collect features from single value columns (anything which can be cast to a float, if casts fails then the value is set to 0), array columns or SparkNLP annotations (if the annotation is an embedding, it takes the embedding, otherwise tries to cast the result field). The output of the transformer is a FEATURE_VECTOR annotation (the numeric vector is in the embeddings field).

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

Instance Constructors

  1. new FeaturesAssembler()
  2. new FeaturesAssembler(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
    Definition Classes
    FeaturesAssembler → AnnotatorModel
  10. def afterAnnotate(dataset: DataFrame): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  11. def annotate(annotations: Seq[Annotation]): Seq[Annotation]
    Definition Classes
    FeaturesAssembler → HasSimpleAnnotate
  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. def checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String]): Unit
    Definition Classes
    CheckLicense
  16. def checkValidScope(scope: String): Unit
    Definition Classes
    CheckLicense
  17. def checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean): Unit
    Definition Classes
    CheckLicense
  18. def checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean): Unit
    Definition Classes
    CheckLicense
  19. final def clear(param: Param[_]): FeaturesAssembler.this.type
    Definition Classes
    Params
  20. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  21. def copy(extra: ParamMap): FeaturesAssembler
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  22. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  23. def createDatabaseConnection(database: Name): RocksDBConnection
    Definition Classes
    HasStorageRef
  24. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  25. def dfAnnotate: UserDefinedFunction
    Definition Classes
    HasSimpleAnnotate
  26. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  27. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  28. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  29. def explainParams(): String
    Definition Classes
    Params
  30. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  31. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  32. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  33. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  34. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  35. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  36. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  38. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  39. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  40. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  41. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  42. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  43. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  44. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  45. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  46. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  47. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  48. def getStorageRef: String
    Definition Classes
    HasStorageRef
  49. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  50. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  51. def hasParent: Boolean
    Definition Classes
    Model
  52. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  53. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  54. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  55. val inputAnnotatorTypes: Array[AnnotatorType]

    Input column annotation types - this is actually not used

    Input column annotation types - this is actually not used

    Definition Classes
    FeaturesAssembler → HasInputAnnotationCols
  56. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  57. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  58. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  59. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  60. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  61. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  62. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  63. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  64. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  65. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  66. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  70. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  75. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  76. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  77. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  78. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  79. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  80. val outputAnnotatorType: AnnotatorType

    Output annotator type: FEATURE_VECTOR

    Output annotator type: FEATURE_VECTOR

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

    Override input columns setter, ignore validation as the number of input columns is not fixed

    Override input columns setter, ignore validation as the number of input columns is not fixed

    Definition Classes
    FeaturesAssembler → HasInputAnnotationCols
  99. final def setInputCols(value: String*): FeaturesAssembler.this.type
    Definition Classes
    HasInputAnnotationCols
  100. def setLazyAnnotator(value: Boolean): FeaturesAssembler.this.type
    Definition Classes
    CanBeLazy
  101. final def setOutputCol(value: String): FeaturesAssembler.this.type
    Definition Classes
    HasOutputAnnotationCol
  102. def setParent(parent: Estimator[FeaturesAssembler]): FeaturesAssembler
    Definition Classes
    Model
  103. def setStorageRef(value: String): FeaturesAssembler.this.type
    Definition Classes
    HasStorageRef
  104. val storageRef: Param[String]
    Definition Classes
    HasStorageRef
  105. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  106. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  107. final def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    AnnotatorModel → Transformer
  108. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  109. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  110. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  111. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  112. val uid: String
    Definition Classes
    FeaturesAssembler → Identifiable
  113. def validate(schema: StructType): Boolean

    Override column annotation validation: input columns are not necessary SparkNLP annotations

    Override column annotation validation: input columns are not necessary SparkNLP annotations

    Attributes
    protected
    Definition Classes
    FeaturesAssembler → RawAnnotator
  114. def validateStorageRef(dataset: Dataset[_], inputCols: Array[String], annotatorType: String): Unit
    Definition Classes
    HasStorageRef
  115. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  116. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  117. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  118. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  119. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from CheckLicense

Inherited from HasSimpleAnnotate[FeaturesAssembler]

Inherited from HasStorageRef

Inherited from AnnotatorModel[FeaturesAssembler]

Inherited from CanBeLazy

Inherited from RawAnnotator[FeaturesAssembler]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[FeaturesAssembler]

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

Members