com.emphysic.myriad.core.data.roi

Interface ROIProbability

All Known Implementing Classes:

AdaptiveSGDROIFinder, GradMachineROIFinder, MLROIConfFinder, PassiveAggressiveROIFinder

public interface ROIProbability

ROIProbability - the implementing class can return probabilities of a given sample being in a given class. Created by ccoughlin on 9/21/2016.

Method Summary

Modifier and Type	Method and Description
org.apache.mahout.math.Vector	classify(org.apache.mahout.math.DenseVector d)
default double[]	predict_proba(Dataset dataset) Returns the probability of the sample being in each of the classes recognized by the current model.
default double[]	predict_proba(double[] data) Returns the probability of the sample being in each of the classes recognized by the current model.

Method Detail

predict_proba

default double[] predict_proba(double[] data)

Returns the probability of the sample being in each of the classes recognized by the current model. Element 0 is the probability of the "negative" class i.e. no ROI.

Parameters:

data - sample data to classify

Returns:

array of probabilities between 0 and 1 of the sample being in the specified class.

predict_proba

default double[] predict_proba(Dataset dataset)

Returns the probability of the sample being in each of the classes recognized by the current model. Element 0 is the probability of the "negative" class i.e. no ROI.

Parameters:

dataset - sample data to classify

Returns:

array of probabilities between 0 and 1 of the sample being in the specified class.

classify

org.apache.mahout.math.Vector classify(org.apache.mahout.math.DenseVector d)