Package

com.microsoft.ml.spark

automl

Permalink

package automl

Visibility
  1. Public
  2. All

Type Members

  1. class BestModel extends Model[BestModel] with ConstructorWritable[BestModel]

    Permalink

    Model produced by FindBestModel.

    Model produced by FindBestModel.

    Annotations
    @InternalWrapper()
  2. class DiscreteHyperParam[T] extends Dist[T]

    Permalink
  3. abstract class Dist[T] extends AnyRef

    Permalink

    Represents a distribution of values.

    Represents a distribution of values.

    T

    The type T of the values generated.

  4. class DoubleRangeHyperParam extends RangeHyperParam[Double]

    Permalink
  5. class FindBestModel extends Estimator[BestModel] with FindBestModelParams

    Permalink

    Evaluates and chooses the best model from a list of models.

    Evaluates and chooses the best model from a list of models.

    Annotations
    @InternalWrapper()
  6. trait FindBestModelParams extends Wrappable with ComplexParamsWritable with HasEvaluationMetric

    Permalink
  7. class FloatRangeHyperParam extends RangeHyperParam[Float]

    Permalink
  8. class GridSpace extends ParamSpace

    Permalink

    Represents a parameter grid for tuning with discrete values.

    Represents a parameter grid for tuning with discrete values. Can be generated with the ParamGridBuilder.

  9. class HyperparamBuilder extends AnyRef

    Permalink

    Specifies the search space for hyperparameters.

  10. class IntRangeHyperParam extends RangeHyperParam[Int]

    Permalink
  11. class LongRangeHyperParam extends RangeHyperParam[Long]

    Permalink
  12. class RandomSpace extends ParamSpace

    Permalink

    Represents a generator of parameters with specified distributions added by the HyperparamBuilder.

  13. abstract class RangeHyperParam[T] extends Dist[T]

    Permalink
  14. class TuneHyperparameters extends Estimator[TuneHyperparametersModel] with Wrappable with ComplexParamsWritable with HasEvaluationMetric

    Permalink

    Tunes model hyperparameters

    Tunes model hyperparameters

    Allows user to specify multiple untrained models to tune using various search strategies. Currently supports cross validation with random grid search.

    Annotations
    @InternalWrapper()
  15. class TuneHyperparametersModel extends Model[TuneHyperparametersModel] with ConstructorWritable[TuneHyperparametersModel]

    Permalink

    Model produced by TuneHyperparameters.

    Model produced by TuneHyperparameters.

    Annotations
    @InternalWrapper()

Value Members

  1. object BestModel extends ConstructorReadable[BestModel] with Serializable

    Permalink
  2. object DefaultHyperparams

    Permalink

    Provides good default hyperparameter ranges and values for sweeping.

    Provides good default hyperparameter ranges and values for sweeping. Publicly visible to users so they can easily select the parameters for sweeping.

  3. object EvaluationUtils

    Permalink
  4. object FindBestModel extends ComplexParamsReadable[FindBestModel] with Serializable

    Permalink
  5. object HyperParamUtils

    Permalink
  6. object TuneHyperparameters extends ComplexParamsReadable[TuneHyperparameters] with Serializable

    Permalink
  7. object TuneHyperparametersModel extends ConstructorReadable[TuneHyperparametersModel] with Serializable

    Permalink

Ungrouped