Packages

package train

Ordering
  1. Alphabetic
Visibility
  1. Public
  2. All

Type Members

  1. abstract class AutoTrainedModel[TrainedModel <: Model[TrainedModel]] extends Model[TrainedModel] with ComplexParamsWritable with HasLabelCol with HasFeaturesCol

    Defines common inheritance and functions across auto trained models.

  2. trait AutoTrainer[TrainedModel <: Model[TrainedModel]] extends Estimator[TrainedModel] with HasLabelCol with ComplexParamsWritable with HasFeaturesCol with Wrappable

    Defines common inheritance and parameters across trainers.

  3. trait CPISParams extends Wrappable with DefaultParamsWritable with HasLabelCol with HasScoresCol with HasScoredLabelsCol with HasScoredProbabilitiesCol with HasEvaluationMetric
  4. class ComputeModelStatistics extends Transformer with ComputeModelStatisticsParams with BasicLogging

    Evaluates the given scored dataset.

  5. trait ComputeModelStatisticsParams extends Wrappable with DefaultParamsWritable with HasLabelCol with HasScoresCol with HasScoredLabelsCol with HasEvaluationMetric
  6. class ComputePerInstanceStatistics extends Transformer with CPISParams with BasicLogging

    Evaluates the given scored dataset with per instance metrics.

    Evaluates the given scored dataset with per instance metrics.

    The Regression metrics are: - L1_loss - L2_loss

    The Classification metrics are: - log_loss

  7. class MetricsLogger extends AnyRef

    Helper class for logging metrics to log4j.

  8. class TrainClassifier extends Estimator[TrainedClassifierModel] with AutoTrainer[TrainedClassifierModel] with BasicLogging

    Trains a classification model.

    Trains a classification model. Featurizes the given data into a vector of doubles.

    Note the behavior of the reindex and labels parameters, the parameters interact as:

    reindex -> false labels -> false (Empty) Assume all double values, don't use metadata, assume natural ordering

    reindex -> true labels -> false (Empty) Index, use natural ordering of string indexer

    reindex -> false labels -> true (Specified) Assume user knows indexing, apply label values. Currently only string type supported.

    reindex -> true labels -> true (Specified) Validate labels matches column type, try to recast to label type, reindex label column

    The currently supported classifiers are: Logistic Regression Classifier Decision Tree Classifier Random Forest Classifier Gradient Boosted Trees Classifier Naive Bayes Classifier Multilayer Perceptron Classifier In addition to any generic learner that inherits from Predictor.

  9. class TrainRegressor extends Estimator[TrainedRegressorModel] with AutoTrainer[TrainedRegressorModel] with BasicLogging

    Trains a regression model.

  10. class TrainedClassifierModel extends AutoTrainedModel[TrainedClassifierModel] with Wrappable with BasicLogging

    Model produced by TrainClassifier.

  11. class TrainedRegressorModel extends AutoTrainedModel[TrainedRegressorModel] with Wrappable with BasicLogging

    Model produced by TrainRegressor.

Ungrouped