File predictor_probability_auto.hpp

namespace boosting

class AutomaticProbabilityPredictorConfig : public IProbabilityPredictorConfig

#include <predictor_probability_auto.hpp>

Allows to configure a predictor that automatically decides for a method that is used to predict probabilities for given query examples, which estimate the chance of individual labels to be relevant.

Public Functions

AutomaticProbabilityPredictorConfig(ReadableProperty<IClassificationLossConfig> lossConfig, ReadableProperty<IMultiThreadingConfig> multiThreadingConfig)

Parameters:

• lossConfig – A ReadableProperty that allows to access the IClassificationLossConfig that stores the configuration of the loss function

• multiThreadingConfig – A ReadableProperty that allows to access the IMultiThreadingConfig that stores the configuration of the multi-threading behavior that should be used to predict for several query examples in parallel

std::unique_ptr<IProbabilityPredictorFactory> createPredictorFactory(const IRowWiseFeatureMatrix &featureMatrix, uint32 numOutputs) const override

See also

IProbabilityPredictorConfig::createPredictorFactory

bool isLabelVectorSetNeeded() const override

See also

IPredictorConfig::isLabelVectorSetNeeded

Private Members

const ReadableProperty<IClassificationLossConfig> lossConfig_

const ReadableProperty<IMultiThreadingConfig> multiThreadingConfig_