package explainers
- Alphabetic
- Public
- All
Type Members
- trait CanValidateSchema extends AnyRef
- trait HasBackgroundData extends Params with CanValidateSchema
- trait HasExplainTarget extends Params with CanValidateSchema
- trait HasMetricsCol extends Params with CanValidateSchema
- trait HasModel extends Params with CanValidateSchema
- trait HasNumSamples extends Params with CanValidateSchema
- trait HasSamplingFraction extends Params with CanValidateSchema
- trait HasSuperpixelCol extends Params with CanValidateSchema
- trait HasTokensCol extends Params with CanValidateSchema
-
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.
- trait ICEFeatureParams extends Params with HasNumSamples
-
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"
-
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()
-
trait
ImageExplainer extends AnyRef
Common preprocessing logic for image explainers
- class ImageLIME extends LIMEBase with ImageLIMEParams with ImageExplainer
- trait ImageLIMEParams extends LIMEParams with HasSamplingFraction with HasCellSize with HasModifier with HasInputCol with HasSuperpixelCol
- class ImageSHAP extends KernelSHAPBase with ImageSHAPParams with ImageExplainer
- trait ImageSHAPParams extends KernelSHAPParams with HasCellSize with HasModifier with HasInputCol with HasSuperpixelCol
- abstract class KernelSHAPBase extends Transformer with LocalExplainer with KernelSHAPParams with Wrappable with BasicLogging
- trait KernelSHAPParams extends HasNumSamples with HasMetricsCol
- abstract class LIMEBase extends Transformer with LocalExplainer with LIMEParams with Wrappable with BasicLogging
- trait LIMEParams extends HasNumSamples with HasMetricsCol
- final class LassoRegression extends RegressionBase
- final class LeastSquaresRegression extends RegressionBase
- trait LocalExplainer extends Transformer with HasExplainTarget with HasOutputCol with HasModel with ComplexParamsWritable
-
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.
- case class RegressionResult(coefficients: DenseVector[Double], intercept: Double, rSquared: Double, loss: Double) extends (DenseVector[Double]) ⇒ Double with Product with Serializable
- class TabularLIME extends LIMEBase with HasInputCols with HasBackgroundData
- class TabularSHAP extends KernelSHAPBase with HasInputCols with HasBackgroundData
-
trait
TextExplainer extends AnyRef
Common preprocessing logic for text explainers
- class TextLIME extends LIMEBase with TextLIMEParams with TextExplainer
- trait TextLIMEParams extends LIMEParams with HasSamplingFraction with HasInputCol with HasTokensCol
- class TextSHAP extends KernelSHAPBase with TextSHAPParams with TextExplainer
- trait TextSHAPParams extends KernelSHAPParams with HasInputCol with HasTokensCol
- class VectorLIME extends LIMEBase with HasInputCol with HasBackgroundData
- class VectorSHAP extends KernelSHAPBase with HasInputCol with HasBackgroundData
Value Members
-
object
ICECategoricalFeature extends Serializable
Companion object to provide JSON serializer and deserializer for ICECategoricalFeature.
-
object
ICENumericFeature extends Serializable
Companion object to provide JSON serializer and deserializer for ICENumericFeature.
- object ICETransformer extends ComplexParamsReadable[ICETransformer] with Serializable
- object ImageLIME extends ComplexParamsReadable[ImageLIME] with Serializable
- object ImageSHAP extends ComplexParamsReadable[ImageSHAP] with Serializable
- object KernelSHAPBase extends Serializable
- object LocalExplainer extends Serializable
- object TabularLIME extends ComplexParamsReadable[TabularLIME] with Serializable
- object TabularSHAP extends ComplexParamsReadable[TabularSHAP] with Serializable
- object TextLIME extends ComplexParamsReadable[TextLIME] with Serializable
- object TextSHAP extends ComplexParamsReadable[TextSHAP] with Serializable
- object VectorLIME extends ComplexParamsReadable[VectorLIME] with Serializable
- object VectorSHAP extends ComplexParamsReadable[VectorSHAP] with Serializable