QuadraticDiscriminantAnalysis.MahalanobisDistances Property

public Matrix<double> MahalanobisDistances { get; }

Public ReadOnly Property MahalanobisDistances As Matrix(Of Double)
	Get

public:
property Matrix<double>^ MahalanobisDistances {
	Matrix<double>^ get ();
}

member MahalanobisDistances : Matrix<float> with get

Property Value

The Mahalanobis distances matrix contains pairwise distances between class centroids, taking into account the covariance structure of the classes. For each pair of classes (i,j), the matrix contains two distances: one computed using class i's covariance matrix and another using class j's covariance matrix.

These distances provide a measure of class separation that accounts for the scale and correlation of the features. Larger distances indicate better separation between classes, while smaller distances suggest potential classification difficulties between those classes.

This property is only available when the model is fitted. It throws an InvalidOperationException if the model is empty or deployed.

Reference