Packages

class AssertionLogRegApproach extends AnnotatorApproach[AssertionLogRegModel] with Windowing with Licensed

This is a classification method, which uses LogisticRegression algorithm Contains all the methods for training a AssertionLogRegModel, together with trainWithChunk, trainWithStartEnd.

Example

Training with Glove Embeddings

First define pipeline stages to extract embeddings and text chunks

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

val tokenizer = new Tokenizer()
  .setInputCols("document")
  .setOutputCol("token")

val glove = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")
  .setInputCols("document", "token")
  .setOutputCol("word_embeddings")
  .setCaseSensitive(false)

val chunkAssembler = new Doc2Chunk()
  .setInputCols("document")
  .setChunkCol("target")
  .setOutputCol("chunk")

Then the AssertionLogRegApproach model is defined. Label column is needed in the dataset for training.

val assertion = new AssertionLogRegApproach()
  .setLabelCol("label")
  .setInputCols("document", "chunk", "word_embeddings")
  .setOutputCol("assertion")
  .setReg(0.01)
  .setBefore(11)
  .setAfter(13)
  .setStartCol("start")
  .setEndCol("end")

val assertionPipeline = new Pipeline().setStages(Array(
  documentAssembler,
  sentenceDetector,
  tokenizer,
  embeddings,
  nerModel,
  nerConverter,
  assertion
))

val assertionModel = assertionPipeline.fit(dataset)
Linear Supertypes
Licensed, Windowing, AnnotatorApproach[AssertionLogRegModel], CanBeLazy, DefaultParamsWritable, MLWritable, HasOutputAnnotatorType, HasOutputAnnotationCol, HasInputAnnotationCols, Estimator[AssertionLogRegModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. AssertionLogRegApproach
  2. Licensed
  3. Windowing
  4. AnnotatorApproach
  5. CanBeLazy
  6. DefaultParamsWritable
  7. MLWritable
  8. HasOutputAnnotatorType
  9. HasOutputAnnotationCol
  10. HasInputAnnotationCols
  11. Estimator
  12. PipelineStage
  13. Logging
  14. Params
  15. Serializable
  16. Serializable
  17. Identifiable
  18. AnyRef
  19. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

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

    uid

    a unique identifier for the instantiated AnnotatorModel

Type Members

  1. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType
  2. case class VectorizedChunk(vector: Vector, begin: Int, end: Int, sentenceId: Int, chunkId: Int) extends Product with Serializable
    Attributes
    protected
    Definition Classes
    Windowing

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. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  5. def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): AssertionLogRegModel
    Attributes
    protected
    Definition Classes
    AnnotatorApproach
  6. lazy val after: Int
    Definition Classes
    AssertionLogRegApproach → Windowing
  7. val afterParam: IntParam

    Amount of tokens from the context after the target (Default: 10)

  8. def applyWindow(tokenizedSentence: WordpieceEmbeddingsSentence, s: Int, e: Int, embeddingsDim: Int): Array[Double]
    Definition Classes
    Windowing
  9. def applyWindowContext(tokenizedSentence: WordpieceEmbeddingsSentence, s: Int, e: Int, embeddingsDim: Int): (Array[Array[Float]], Array[Array[Float]], Array[Array[Float]])
    Definition Classes
    Windowing
  10. def applyWindowUdf(embeddingsDim: Int): UserDefinedFunction
    Definition Classes
    Windowing
  11. def applyWindowUdfChunk(embeddingsDim: Int): UserDefinedFunction
    Definition Classes
    Windowing
  12. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  13. lazy val before: Int
    Definition Classes
    AssertionLogRegApproach → Windowing
  14. val beforeParam: IntParam

    Amount of tokens from the context before the target (Default: 10)

  15. def beforeTraining(spark: SparkSession): Unit
    Definition Classes
    AnnotatorApproach
  16. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  17. final def clear(param: Param[_]): AssertionLogRegApproach.this.type
    Definition Classes
    Params
  18. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  19. final def copy(extra: ParamMap): Estimator[AssertionLogRegModel]
    Definition Classes
    AnnotatorApproach → Estimator → PipelineStage → Params
  20. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  21. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  22. val description: String
    Definition Classes
    AssertionLogRegApproach → AnnotatorApproach
  23. val eNetParam: DoubleParam

    Elastic net parameter (Default: 0.9)

  24. val endCol: Param[String]

    Column that contains the token number for the end of the target

  25. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  26. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  27. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  28. def explainParams(): String
    Definition Classes
    Params
  29. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  30. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  31. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  32. final def fit(dataset: Dataset[_]): AssertionLogRegModel
    Definition Classes
    AnnotatorApproach → Estimator
  33. def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[AssertionLogRegModel]
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  34. def fit(dataset: Dataset[_], paramMap: ParamMap): AssertionLogRegModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  35. def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): AssertionLogRegModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" ) @varargs()
  36. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  37. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  38. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  39. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  40. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  41. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  42. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  43. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  44. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  45. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  46. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  47. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  48. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  49. val inputAnnotatorTypes: Array[String]

    Input annotator types: DOCUMENT, CHUNK, WORD_EMBEDDINGS

    Input annotator types: DOCUMENT, CHUNK, WORD_EMBEDDINGS

    Definition Classes
    AssertionLogRegApproach → HasInputAnnotationCols
  50. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  51. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  52. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  53. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  54. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  55. def l2norm(xs: Array[Double]): Double
    Definition Classes
    Windowing
  56. val label: Param[String]

    Column with one label per document

  57. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  58. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  59. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  60. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  61. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  62. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  63. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  64. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  65. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  66. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. val maxIter: IntParam

    Max number of iterations for algorithm (Default: 26)

  71. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  72. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  73. def normalize(vec: Array[Double]): Array[Double]
    Definition Classes
    Windowing
  74. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  75. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  76. def onTrained(model: AssertionLogRegModel, spark: SparkSession): Unit
    Definition Classes
    AnnotatorApproach
  77. val outputAnnotatorType: AnnotatorType

    Output annotator types: ASSERTION

    Output annotator types: ASSERTION

    Definition Classes
    AssertionLogRegApproach → HasOutputAnnotatorType
  78. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  79. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  80. val regParam: DoubleParam

    Regularization parameter (Default: 0.00192)

  81. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  82. final def set(paramPair: ParamPair[_]): AssertionLogRegApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  83. final def set(param: String, value: Any): AssertionLogRegApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  84. final def set[T](param: Param[T], value: T): AssertionLogRegApproach.this.type
    Definition Classes
    Params
  85. def setAfter(a: Int): AssertionLogRegApproach.this.type

    Amount of tokens from the context after the target (Default: 10)

  86. def setBefore(b: Int): AssertionLogRegApproach.this.type

    Amount of tokens from the context before the target (Default: 10)

  87. final def setDefault(paramPairs: ParamPair[_]*): AssertionLogRegApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  88. final def setDefault[T](param: Param[T], value: T): AssertionLogRegApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  89. def setEndCol(end: String): AssertionLogRegApproach.this.type

    Column that contains the token number for the end of the target

  90. def setEnet(enet: Double): AssertionLogRegApproach.this.type

    Elastic net parameter (Default: 0.9)

  91. final def setInputCols(value: String*): AssertionLogRegApproach.this.type
    Definition Classes
    HasInputAnnotationCols
  92. final def setInputCols(value: Array[String]): AssertionLogRegApproach.this.type
    Definition Classes
    HasInputAnnotationCols
  93. def setLabelCol(label: String): AssertionLogRegApproach.this.type

    Column with one label per document

  94. def setLazyAnnotator(value: Boolean): AssertionLogRegApproach.this.type
    Definition Classes
    CanBeLazy
  95. def setMaxIter(max: Int): AssertionLogRegApproach.this.type

    Max number of iterations for algorithm (Default: 26)

  96. final def setOutputCol(value: String): AssertionLogRegApproach.this.type
    Definition Classes
    HasOutputAnnotationCol
  97. def setReg(lambda: Double): AssertionLogRegApproach.this.type

    Regularization parameter (Default: 0.00192)

  98. def setStartCol(start: String): AssertionLogRegApproach.this.type

    Column that contains the token number for the start of the target

  99. val startCol: Param[String]

    Column that contains the token number for the start of the target

  100. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  101. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  102. def tokenIndexToChunkIndex(doc: Array[TokenPieceEmbeddings], start: Int, end: Int): (Int, Int)
    Definition Classes
    Windowing
  103. def train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel] = None): AssertionLogRegModel

    This is a main point of interest of this class.

    This is a main point of interest of this class. It trains the dataset with recursive pipeline and uses methods trainWithChunk() and trainwithStartEnd() The choice of training happens based on the startCol value of the DL Approach

    dataset

    a collection of inputs to train

    recursivePipeline

    an instance of PipelineModel

    returns

    an instance of trained AssertionLogRegModel

    Definition Classes
    AssertionLogRegApproach → AnnotatorApproach
  104. final def transformSchema(schema: StructType): StructType
    Definition Classes
    AnnotatorApproach → PipelineStage
  105. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  106. val uid: String
    Definition Classes
    AssertionLogRegApproach → Identifiable
  107. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    AnnotatorApproach
  108. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  109. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  110. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  111. def write: MLWriter
    Definition Classes
    DefaultParamsWritable → MLWritable

Inherited from Licensed

Inherited from Windowing

Inherited from AnnotatorApproach[AssertionLogRegModel]

Inherited from CanBeLazy

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputAnnotatorType

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from Estimator[AssertionLogRegModel]

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