Packages

package explainers

Ordering
  1. Alphabetic
Visibility
  1. Public
  2. All

Type Members

  1. trait CanValidateSchema extends AnyRef
  2. trait HasBackgroundData extends Params with CanValidateSchema
  3. trait HasExplainTarget extends Params with CanValidateSchema
  4. trait HasMetricsCol extends Params with CanValidateSchema
  5. trait HasModel extends Params with CanValidateSchema
  6. trait HasNumSamples extends Params with CanValidateSchema
  7. trait HasSamplingFraction extends Params with CanValidateSchema
  8. trait HasSuperpixelCol extends Params with CanValidateSchema
  9. trait HasTokensCol extends Params with CanValidateSchema
  10. case class ICECategoricalFeature(name: String, numTopValues: Option[Int] = None, outputColName: Option[String] = None) extends ICEFeature with Product with Serializable

    Represents a single categorical feature to be explained by ICE explainer.

    Represents a single categorical feature to be explained by ICE explainer.

    name

    The name of the categorical feature.

    numTopValues

    The max number of top-occurring values to be included in the categorical feature. Default: 100.

    outputColName

    The name for output column with explanations for the feature. Default: input name of the feature + _dependence.

  11. trait ICEFeatureParams extends Params with HasNumSamples
  12. case class ICENumericFeature(name: String, numSplits: Option[Int] = None, rangeMin: Option[Double] = None, rangeMax: Option[Double] = None, outputColName: Option[String] = None) extends ICEFeature with Product with Serializable

    Represents a single numeric feature to be explained by ICE explainer.

    Represents a single numeric feature to be explained by ICE explainer.

    name

    The name of the numeric feature.

    numSplits

    The number of splits for the value range for the numeric feature. Default: 10.0

    rangeMin

    Specifies the min value of the range for the numeric feature. If not specified, it will be computed from the background dataset.

    rangeMax

    Specifies the max value of the range for the numeric feature. If not specified, it will be computed from the background dataset.

    outputColName

    The name for output column with explanations for the feature. Default: input name of the feature + "_dependence"

  13. class ICETransformer extends Transformer with HasExplainTarget with HasModel with ICEFeatureParams with Wrappable with ComplexParamsWritable

    ICETransformer displays the model dependence on specified features with the given dataframe as background dataset.

    ICETransformer displays the model dependence on specified features with the given dataframe as background dataset. It supports 2 types of plots: individual - dependence per instance and average - across all the samples in the dataset. Note: This transformer only supports one-way dependence plot.

    Annotations
    @Experimental()
  14. trait ImageExplainer extends AnyRef

    Common preprocessing logic for image explainers

  15. class ImageLIME extends LIMEBase with ImageLIMEParams with ImageExplainer
  16. trait ImageLIMEParams extends LIMEParams with HasSamplingFraction with HasCellSize with HasModifier with HasInputCol with HasSuperpixelCol
  17. class ImageSHAP extends KernelSHAPBase with ImageSHAPParams with ImageExplainer
  18. trait ImageSHAPParams extends KernelSHAPParams with HasCellSize with HasModifier with HasInputCol with HasSuperpixelCol
  19. abstract class KernelSHAPBase extends Transformer with LocalExplainer with KernelSHAPParams with Wrappable with BasicLogging
  20. trait KernelSHAPParams extends HasNumSamples with HasMetricsCol
  21. abstract class LIMEBase extends Transformer with LocalExplainer with LIMEParams with Wrappable with BasicLogging
  22. trait LIMEParams extends HasNumSamples with HasMetricsCol
  23. final class LassoRegression extends RegressionBase
  24. final class LeastSquaresRegression extends RegressionBase
  25. trait LocalExplainer extends Transformer with HasExplainTarget with HasOutputCol with HasModel with ComplexParamsWritable
  26. abstract class RegressionBase extends AnyRef

    The RegressionBase class centers and rescales the input matrix and output vector to support fitting intercept and specifying sampleWeights.

    The RegressionBase class centers and rescales the input matrix and output vector to support fitting intercept and specifying sampleWeights. The underlying regression algorithm does not need to support fitting intercept and sample weights.

  27. case class RegressionResult(coefficients: DenseVector[Double], intercept: Double, rSquared: Double, loss: Double) extends (DenseVector[Double]) ⇒ Double with Product with Serializable
  28. class TabularLIME extends LIMEBase with HasInputCols with HasBackgroundData
  29. class TabularSHAP extends KernelSHAPBase with HasInputCols with HasBackgroundData
  30. trait TextExplainer extends AnyRef

    Common preprocessing logic for text explainers

  31. class TextLIME extends LIMEBase with TextLIMEParams with TextExplainer
  32. trait TextLIMEParams extends LIMEParams with HasSamplingFraction with HasInputCol with HasTokensCol
  33. class TextSHAP extends KernelSHAPBase with TextSHAPParams with TextExplainer
  34. trait TextSHAPParams extends KernelSHAPParams with HasInputCol with HasTokensCol
  35. class VectorLIME extends LIMEBase with HasInputCol with HasBackgroundData
  36. class VectorSHAP extends KernelSHAPBase with HasInputCol with HasBackgroundData

Value Members

  1. object ICECategoricalFeature extends Serializable

    Companion object to provide JSON serializer and deserializer for ICECategoricalFeature.

  2. object ICENumericFeature extends Serializable

    Companion object to provide JSON serializer and deserializer for ICENumericFeature.

  3. object ICETransformer extends ComplexParamsReadable[ICETransformer] with Serializable
  4. object ImageLIME extends ComplexParamsReadable[ImageLIME] with Serializable
  5. object ImageSHAP extends ComplexParamsReadable[ImageSHAP] with Serializable
  6. object KernelSHAPBase extends Serializable
  7. object LIMEUtils extends Logging
  8. object LocalExplainer extends Serializable
  9. object TabularLIME extends ComplexParamsReadable[TabularLIME] with Serializable
  10. object TabularSHAP extends ComplexParamsReadable[TabularSHAP] with Serializable
  11. object TextLIME extends ComplexParamsReadable[TextLIME] with Serializable
  12. object TextSHAP extends ComplexParamsReadable[TextSHAP] with Serializable
  13. object VectorLIME extends ComplexParamsReadable[VectorLIME] with Serializable
  14. object VectorSHAP extends ComplexParamsReadable[VectorSHAP] with Serializable

Ungrouped