Class XGBoostClassificationConverter

java.lang.Object
org.tribuo.classification.xgboost.XGBoostClassificationConverter
All Implemented Interfaces:
Serializable, XGBoostOutputConverter<Label>

public final class XGBoostClassificationConverter extends Object implements XGBoostOutputConverter<Label>
Converts XGBoost outputs into Label Predictions.
See Also:
  • Constructor Details

    • XGBoostClassificationConverter

      public XGBoostClassificationConverter()
      Constructs an XGBoostClassificationConverter.
  • Method Details

    • generatesProbabilities

      public boolean generatesProbabilities()
      Description copied from interface: XGBoostOutputConverter
      Does this converter produce probabilities?
      Specified by:
      generatesProbabilities in interface XGBoostOutputConverter<Label>
      Returns:
      True if it produces probabilities.
    • convertOutput

      public Prediction<Label> convertOutput(ImmutableOutputInfo<Label> info, List<float[]> probabilitiesList, int numValidFeatures, Example<Label> example)
      Description copied from interface: XGBoostOutputConverter
      Converts a list of float arrays from XGBoost Boosters into a Tribuo Prediction.
      Specified by:
      convertOutput in interface XGBoostOutputConverter<Label>
      Parameters:
      info - The output info.
      probabilitiesList - The XGBoost output.
      numValidFeatures - The number of valid features used in the prediction.
      example - The example this prediction was generated from.
      Returns:
      The prediction object.
    • convertBatchOutput

      public List<Prediction<Label>> convertBatchOutput(ImmutableOutputInfo<Label> info, List<float[][]> probabilitiesList, int[] numValidFeatures, Example<Label>[] examples)
      Description copied from interface: XGBoostOutputConverter
      Converts a list of float arrays from XGBoost Boosters into a Tribuo Prediction.
      Specified by:
      convertBatchOutput in interface XGBoostOutputConverter<Label>
      Parameters:
      info - The output info.
      probabilitiesList - The XGBoost output, list dimension is across models, first array dimension is across examples, second array dimension is across outputs.
      numValidFeatures - The number of valid features used in each prediction.
      examples - The examples these predictions were generated from.
      Returns:
      The prediction object.