Package jsat.linear.distancemetrics

Interface Summary

Interface	Description
DenseSparseMetric	Many algorithms require computing the distances from a small set of points to many other points.
DistanceMetric	A distance metric defines the distance between two points in a metric space.

Class Summary

Class	Description
ChebyshevDistance	Chebyshev Distance is the L∞ norm.
CosineDistance	The Cosine Distance is a adaption of the Cosine Similarity's range from [-1, 1] into the range [0, 1].
CosineDistanceNormalized	This distance metric returns the same cosine distance as CosineDistance.
DistanceCounter	This class exists primarily as a sanity/benchmarking utility.
EuclideanDistance	Euclidean Distance is the L2 norm.
KernelDistance	Creates a distance metric from a given kernel trick.
MahalanobisDistance	The Mahalanobis Distance is a metric that takes into account the variance of the data.
ManhattanDistance	Manhattan Distance is the L1 norm.
MinkowskiDistance	Minkowski Distance is the Lp norm.
NormalizedEuclideanDistance	Implementation of the Normalized Euclidean Distance Metric.
PearsonDistance	A valid distance metric formed from the Pearson Correlation between two vectors.
SquaredEuclideanDistance	In many applications, the squared EuclideanDistance is used because it avoids an expensive Math.sqrt(double) operation.
TrainableDistanceMetric	Some Distance Metrics require information that can be learned from the data set.
WeightedEuclideanDistance	Implements the weighted Euclidean distance such that d(a, b) = ∑∀ i ∈ |w| wi (xi-yi)2 When used with a weight vector of ones, it degenerates into the EuclideanDistance.