Interface IsotonicRegressionBase

All Superinterfaces:
HasFeaturesCol, HasLabelCol, HasPredictionCol, HasWeightCol, Identifiable, org.apache.spark.internal.Logging, Params, Serializable
All Known Implementing Classes:
IsotonicRegression, IsotonicRegressionModel

public interface IsotonicRegressionBase extends Params, HasFeaturesCol, HasLabelCol, HasPredictionCol, HasWeightCol, org.apache.spark.internal.Logging
Params for isotonic regression.
  • Method Details

    • extractWeightedLabeledPoints

      RDD<scala.Tuple3<Object,Object,Object>> extractWeightedLabeledPoints(Dataset<?> dataset)
      Extracts (label, feature, weight) from input dataset.
      Parameters:
      dataset - (undocumented)
      Returns:
      (undocumented)
    • featureIndex

      IntParam featureIndex()
      Param for the index of the feature if featuresCol is a vector column (default: 0), no effect otherwise.
      Returns:
      (undocumented)
    • getFeatureIndex

      int getFeatureIndex()
    • getIsotonic

      boolean getIsotonic()
    • hasWeightCol

      boolean hasWeightCol()
      Checks whether the input has weight column.
    • isotonic

      BooleanParam isotonic()
      Param for whether the output sequence should be isotonic/increasing (true) or antitonic/decreasing (false). Default: true
      Returns:
      (undocumented)
    • validateAndTransformSchema

      StructType validateAndTransformSchema(StructType schema, boolean fitting)
      Validates and transforms input schema.
      Parameters:
      schema - input schema
      fitting - whether this is in fitting or prediction
      Returns:
      output schema