Packages

trait ClassifierEncoder extends EvaluationDLParams

Linear Supertypes
EvaluationDLParams, Params, Serializable, Identifiable, AnyRef, Any
Known Subclasses
ClassifierDLApproach, MultiClassifierDLApproach, SentimentDLApproach
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. ClassifierEncoder
  2. EvaluationDLParams
  3. Params
  4. Serializable
  5. Identifiable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Abstract Value Members

  1. abstract def copy(extra: ParamMap): Params
    Definition Classes
    Params
  2. abstract val uid: String
    Definition Classes
    Identifiable

Concrete 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. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  6. val batchSize: IntParam

    Batch size (Default: 64)

  7. def buildDatasetWithLabels(dataset: Dataset[_], inputCols: String): (DataFrame, Array[String])
    Attributes
    protected
  8. final def clear(param: Param[_]): ClassifierEncoder.this.type
    Definition Classes
    Params
  9. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.CloneNotSupportedException]) @HotSpotIntrinsicCandidate() @native()
  10. val configProtoBytes: IntArrayParam

    ConfigProto from tensorflow, serialized into byte array.

    ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()

  11. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  12. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  13. val enableOutputLogs: BooleanParam

    Whether to output to annotators log folder (Default: false)

    Whether to output to annotators log folder (Default: false)

    Definition Classes
    EvaluationDLParams
  14. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  15. def equals(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef → Any
  16. val evaluationLogExtended: BooleanParam

    Whether logs for validation to be extended (Default: false): it displays time and evaluation of each label

    Whether logs for validation to be extended (Default: false): it displays time and evaluation of each label

    Definition Classes
    EvaluationDLParams
  17. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  18. def explainParams(): String
    Definition Classes
    Params
  19. def extractInputs(encoder: ClassifierDatasetEncoder, dataframe: DataFrame): (Array[Array[Float]], Array[String])
    Attributes
    protected
  20. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  21. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  22. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  23. def getBatchSize: Int

    Batch size (Default: 64)

  24. final def getClass(): Class[_ <: AnyRef]
    Definition Classes
    AnyRef → Any
    Annotations
    @HotSpotIntrinsicCandidate() @native()
  25. def getConfigProtoBytes: Option[Array[Byte]]

    Tensorflow config Protobytes passed to the TF session

  26. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  27. def getEnableOutputLogs: Boolean

    Whether to output to annotators log folder (Default: false)

    Whether to output to annotators log folder (Default: false)

    Definition Classes
    EvaluationDLParams
  28. def getLabelColumn: String

    Column with label per each document

  29. def getLr: Float

    Learning Rate (Default: 5e-3f)

  30. def getMaxEpochs: Int

    Maximum number of epochs to train (Default: 10)

  31. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  32. def getOutputLogsPath: String

    Folder path to save training logs (Default: "")

    Folder path to save training logs (Default: "")

    Definition Classes
    EvaluationDLParams
  33. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  34. def getRandomSeed: Int

    Random seed

  35. def getValidationSplit: Float

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f).

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f). The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

    Definition Classes
    EvaluationDLParams
  36. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  37. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  38. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @HotSpotIntrinsicCandidate() @native()
  39. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  40. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  41. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  42. val labelColumn: Param[String]

    Column with label per each document

  43. val lr: FloatParam

    Learning Rate (Default: 5e-3f)

  44. val maxEpochs: IntParam

    Maximum number of epochs to train (Default: 10)

  45. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  46. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @HotSpotIntrinsicCandidate() @native()
  47. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @HotSpotIntrinsicCandidate() @native()
  48. val outputLogsPath: Param[String]

    Folder path to save training logs (Default: "")

    Folder path to save training logs (Default: "")

    Definition Classes
    EvaluationDLParams
  49. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  50. val randomSeed: IntParam

    Random seed for shuffling the dataset

  51. final def set(paramPair: ParamPair[_]): ClassifierEncoder.this.type
    Attributes
    protected
    Definition Classes
    Params
  52. final def set(param: String, value: Any): ClassifierEncoder.this.type
    Attributes
    protected
    Definition Classes
    Params
  53. final def set[T](param: Param[T], value: T): ClassifierEncoder.this.type
    Definition Classes
    Params
  54. def setBatchSize(batch: Int): ClassifierEncoder.this.type

    Batch size (Default: 64)

  55. def setConfigProtoBytes(bytes: Array[Int]): ClassifierEncoder.this.type

    Tensorflow config Protobytes passed to the TF session

  56. final def setDefault(paramPairs: ParamPair[_]*): ClassifierEncoder.this.type
    Attributes
    protected
    Definition Classes
    Params
  57. final def setDefault[T](param: Param[T], value: T): ClassifierEncoder.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  58. def setEnableOutputLogs(enableOutputLogs: Boolean): ClassifierEncoder.this.type

    Whether to output to annotators log folder (Default: false)

    Whether to output to annotators log folder (Default: false)

    Definition Classes
    EvaluationDLParams
  59. def setEvaluationLogExtended(evaluationLogExtended: Boolean): ClassifierEncoder.this.type

    Whether logs for validation to be extended: it displays time and evaluation of each label.

    Whether logs for validation to be extended: it displays time and evaluation of each label. Default is false.

    Definition Classes
    EvaluationDLParams
  60. def setLabelColumn(column: String): ClassifierEncoder.this.type

    Column with label per each document

  61. def setLr(lr: Float): ClassifierEncoder.this.type

    Learning Rate (Default: 5e-3f)

  62. def setMaxEpochs(epochs: Int): ClassifierEncoder.this.type

    Maximum number of epochs to train (Default: 10)

  63. def setOutputLogsPath(path: String): ClassifierEncoder.this.type

    Folder path to save training logs (Default: "")

    Folder path to save training logs (Default: "")

    Definition Classes
    EvaluationDLParams
  64. def setRandomSeed(seed: Int): ClassifierEncoder.this.type

    Random seed

  65. def setTestDataset(er: ExternalResource): ClassifierEncoder.this.type

    ExternalResource to a parquet file of a test dataset.

    ExternalResource to a parquet file of a test dataset. If set, it is used to calculate statistics on it during training.

    When using an ExternalResource, only parquet files are accepted for this function.

    The parquet file must be a dataframe that has the same columns as the model that is being trained. For example, if the model needs as input DOCUMENT, TOKEN, WORD_EMBEDDINGS (Features) and NAMED_ENTITY (label) then these columns also need to be present while saving the dataframe. The pre-processing steps for the training dataframe should also be applied to the test dataframe.

    An example on how to create such a parquet file could be:

    // assuming preProcessingPipeline
val Array(train, test) = data.randomSplit(Array(0.8, 0.2))

preProcessingPipeline
  .fit(test)
  .transform(test)
  .write
  .mode("overwrite")
  .parquet("test_data")

annotator.setTestDataset("test_data")
    Definition Classes
    EvaluationDLParams
  66. def setTestDataset(path: String, readAs: Format = ReadAs.SPARK, options: Map[String, String] = Map("format" -> "parquet")): ClassifierEncoder.this.type

    Path to a parquet file of a test dataset.

    Path to a parquet file of a test dataset. If set, it is used to calculate statistics on it during training.

    The parquet file must be a dataframe that has the same columns as the model that is being trained. For example, if the model needs as input DOCUMENT, TOKEN, WORD_EMBEDDINGS (Features) and NAMED_ENTITY (label) then these columns also need to be present while saving the dataframe. The pre-processing steps for the training dataframe should also be applied to the test dataframe.

    An example on how to create such a parquet file could be:

    // assuming preProcessingPipeline
val Array(train, test) = data.randomSplit(Array(0.8, 0.2))

preProcessingPipeline
  .fit(test)
  .transform(test)
  .write
  .mode("overwrite")
  .parquet("test_data")

annotator.setTestDataset("test_data")
    Definition Classes
    EvaluationDLParams
  67. def setValidationSplit(validationSplit: Float): ClassifierEncoder.this.type

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f).

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f). The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

    Definition Classes
    EvaluationDLParams
  68. def setVerbose(verbose: Level): ClassifierEncoder.this.type

    Level of verbosity during training (Default: Verbose.Silent.id)

    Level of verbosity during training (Default: Verbose.Silent.id)

    Definition Classes
    EvaluationDLParams
  69. def setVerbose(verbose: Int): ClassifierEncoder.this.type

    Level of verbosity during training (Default: Verbose.Silent.id)

    Level of verbosity during training (Default: Verbose.Silent.id)

    Definition Classes
    EvaluationDLParams
  70. final def synchronized[T0](arg0: => T0): T0
    Definition Classes
    AnyRef
  71. val testDataset: ExternalResourceParam

    Path to a parquet file of a test dataset.

    Path to a parquet file of a test dataset. If set, it is used to calculate statistics on it during training.

    Definition Classes
    EvaluationDLParams
  72. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  73. val validationSplit: FloatParam

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f).

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f). The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

    Definition Classes
    EvaluationDLParams
  74. val verbose: IntParam

    Level of verbosity during training (Default: Verbose.Silent.id)

    Level of verbosity during training (Default: Verbose.Silent.id)

    Definition Classes
    EvaluationDLParams
  75. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  76. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException]) @native()
  77. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])

Deprecated Value Members

  1. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.Throwable]) @Deprecated
    Deprecated

    (Since version 9)

Inherited from EvaluationDLParams

Inherited from Params

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

getParam

param

setParam

Ungrouped