class DocumentMLClassifierModel extends Model[DocumentMLClassifierModel] with RawAnnotator[DocumentMLClassifierModel] with DocumentMLClassifierParams with CanBeLazy with CheckLicense

Classifies documents with a Logarithmic Regression algorithm. Currently there are no pretrained models available. Please see DocumentMLClassifierApproach to train your own model.

Please check out the Models Hub for available models in the future.

Linear Supertypes
CheckLicense, CanBeLazy, DocumentMLClassifierParams, RawAnnotator[DocumentMLClassifierModel], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[DocumentMLClassifierModel], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Known Subclasses
FinanceDocumentMLClassifierModel, LegalDocumentMLClassifierModel
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. DocumentMLClassifierModel
  2. CheckLicense
  3. CanBeLazy
  4. DocumentMLClassifierParams
  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 DocumentMLClassifierModel()
  2. new DocumentMLClassifierModel(uid: String)

    uid

    a unique identifier for the instantiated AnnotatorModel

Type Members

  1. 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. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  10. def calculateNgramsUdf: UserDefinedFunction
    Definition Classes
    DocumentMLClassifierParams
  11. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  12. def checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String]): Unit
    Definition Classes
    CheckLicense
  13. def checkValidScope(scope: String): Unit
    Definition Classes
    CheckLicense
  14. def checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean): Unit
    Definition Classes
    CheckLicense
  15. def checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean): Unit
    Definition Classes
    CheckLicense
  16. val classificationModel: StructFeature[OneVsRestModel]
  17. lazy val classificationPipeline: Pipeline
  18. final def clear(param: Param[_]): DocumentMLClassifierModel.this.type
    Definition Classes
    Params
  19. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  20. def copy(extra: ParamMap): DocumentMLClassifierModel
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  21. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  22. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  23. lazy val docCol: String
  24. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  25. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  26. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  27. def explainParams(): String
    Definition Classes
    Params
  28. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  29. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  30. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  31. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  32. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  33. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  34. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  35. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  38. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  39. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  40. def getClassificationModel: OneVsRestModel
  41. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  42. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  43. def getLabels: Array[String]

    array to output the label in the original form.

    array to output the label in the original form.

    Definition Classes
    DocumentMLClassifierParams
  44. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  45. def getMaxTokenNgramFingerprint: Int
    Definition Classes
    DocumentMLClassifierParams
  46. def getMergeChunks: Boolean

    whether to merge all chunks in a document or not (Default: false)

    whether to merge all chunks in a document or not (Default: false)

    Definition Classes
    DocumentMLClassifierParams
  47. def getMinTokenNgramFingerprint: Int
    Definition Classes
    DocumentMLClassifierParams
  48. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  49. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  50. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  51. def getVectorizationModel: PipelineModel
  52. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  53. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  54. def hasParent: Boolean
    Definition Classes
    Model
  55. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  56. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  57. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  58. val inputAnnotatorTypes: Array[AnnotatorType]

    Input annotator types: TOKEN

    Input annotator types: TOKEN

    Definition Classes
    DocumentMLClassifierModel → HasInputAnnotationCols
  59. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  60. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  61. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  62. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  63. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  64. lazy val labelArray: Array[String]
  65. val labels: StringArrayParam

    array to output the label in the original form.

    array to output the label in the original form.

    Definition Classes
    DocumentMLClassifierParams
  66. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  67. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  68. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  75. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  76. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. val maxTokenNgram: IntParam

    the max number of tokens for Ngrams

    the max number of tokens for Ngrams

    Definition Classes
    DocumentMLClassifierParams
  80. val mergeChunks: BooleanParam

    whether to merge all chunks in a document or not (Default: false)

    whether to merge all chunks in a document or not (Default: false)

    Definition Classes
    DocumentMLClassifierParams
  81. val minTokenNgram: IntParam

    the min number of tokens for Ngrams

    the min number of tokens for Ngrams

    Definition Classes
    DocumentMLClassifierParams
  82. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  83. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  84. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  85. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  86. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  87. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  88. val outputAnnotatorType: AnnotatorType

    Output annotator types: CATEGORY

    Output annotator types: CATEGORY

    Definition Classes
    DocumentMLClassifierModel → HasOutputAnnotatorType
  89. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  90. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  91. var parent: Estimator[DocumentMLClassifierModel]
    Definition Classes
    Model
  92. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  93. def set[T](feature: StructFeature[T], value: T): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  94. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  95. def set[T](feature: SetFeature[T], value: Set[T]): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  96. def set[T](feature: ArrayFeature[T], value: Array[T]): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  97. final def set(paramPair: ParamPair[_]): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  98. final def set(param: String, value: Any): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  99. final def set[T](param: Param[T], value: T): DocumentMLClassifierModel.this.type
    Definition Classes
    Params
  100. def setClassificationModel(value: OneVsRestModel): DocumentMLClassifierModel.this.type
  101. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  102. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  103. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  104. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  105. final def setDefault(paramPairs: ParamPair[_]*): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  106. final def setDefault[T](param: Param[T], value: T): DocumentMLClassifierModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  107. final def setInputCols(value: String*): DocumentMLClassifierModel.this.type
    Definition Classes
    HasInputAnnotationCols
  108. def setInputCols(value: Array[String]): DocumentMLClassifierModel.this.type
    Definition Classes
    HasInputAnnotationCols
  109. def setLabels(value: Array[String]): DocumentMLClassifierModel.this.type

    array to output the label in the original form.

    array to output the label in the original form.

    Definition Classes
    DocumentMLClassifierParams
  110. def setLazyAnnotator(value: Boolean): DocumentMLClassifierModel.this.type
    Definition Classes
    CanBeLazy
  111. def setMaxTokenNgramFingerprint(value: Int): DocumentMLClassifierModel.this.type
    Definition Classes
    DocumentMLClassifierParams
  112. def setMergeChunks(value: Boolean): DocumentMLClassifierModel.this.type

    whether to merge all chunks in a document or not (Default: false)

    whether to merge all chunks in a document or not (Default: false)

    Definition Classes
    DocumentMLClassifierParams
  113. def setMinTokenNgramFingerprint(value: Int): DocumentMLClassifierModel.this.type
    Definition Classes
    DocumentMLClassifierParams
  114. final def setOutputCol(value: String): DocumentMLClassifierModel.this.type
    Definition Classes
    HasOutputAnnotationCol
  115. def setParent(parent: Estimator[DocumentMLClassifierModel]): DocumentMLClassifierModel
    Definition Classes
    Model
  116. def setVectorizationModel(value: PipelineModel): DocumentMLClassifierModel.this.type
  117. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  118. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  119. lazy val tokenAnnotationCol: String
  120. lazy val tokenRawCol: String
  121. def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    DocumentMLClassifierModel → Transformer
  122. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  123. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  124. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  125. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  126. val uid: String
    Definition Classes
    DocumentMLClassifierModel → Identifiable
  127. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  128. val vectorizationModel: StructFeature[PipelineModel]
  129. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  130. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  131. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  132. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  133. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from CheckLicense

Inherited from CanBeLazy

Inherited from DocumentMLClassifierParams

Inherited from RawAnnotator[DocumentMLClassifierModel]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[DocumentMLClassifierModel]

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