@Title("K-means Initialization Strategies")
Initialization strategies for k-means.
Interface Summary Interface Description KMeansInitializationInterface for initializing K-Means
Class Summary Class Description AbstractKMeansInitializationAbstract base class for common k-means initializations. AbstractKMeansInitialization.ParParameterization class. AFKMC2AFK-MC² initialization AFKMC2.InstanceAbstract instance implementing the weight handling. AFKMC2.ParParameterization class. FarthestPoints<O>K-Means initialization by repeatedly choosing the farthest point (by the minimum distance to earlier points). FarthestPoints.Par<O>Parameterization class. FarthestSumPoints<O>K-Means initialization by repeatedly choosing the farthest point (by the sum of distances to previous objects). FarthestSumPoints.Par<V>Parameterization class. FirstK<O>Initialize K-means by using the first k objects as initial means. FirstK.Par<V extends NumberVector>Parameterization class. KMC2K-MC² initialization KMC2.InstanceAbstract instance implementing the weight handling. KMC2.ParParameterization class. KMeansPlusPlus<O>K-Means++ initialization for k-means. KMeansPlusPlus.Instance<T>Abstract instance implementing the weight handling. KMeansPlusPlus.MedoidsInstanceInstance for k-medoids. KMeansPlusPlus.NumberVectorInstanceInstance for k-means, number vector based. KMeansPlusPlus.Par<V>Parameterization class. OstrovskyOstrovsky initial means, a variant of k-means++ that is expected to give slightly better results on average, but only works for k-means and not for, e.g., PAM (k-medoids). Ostrovsky.ParParameterization class. PredefinedRun k-means with prespecified initial means. Predefined.ParParameterization class. RandomlyChosen<O>Initialize K-means by randomly choosing k existing elements as initial cluster centers. RandomlyChosen.Par<V>Parameterization class. RandomNormalGeneratedInitialize k-means by generating random vectors (normal distributed with \(N(\mu,\sigma)\) in each dimension). RandomNormalGenerated.ParParameterization class. RandomUniformGeneratedInitialize k-means by generating random vectors (uniform, within the value range of the data set). RandomUniformGenerated.ParParameterization class. SampleKMeans<V extends NumberVector>Initialize k-means by running k-means on a sample of the data set only. SphericalAFKMC2Spherical K-Means++ initialization with markov chains. SphericalAFKMC2.InstanceAbstract instance implementing the weight handling. SphericalAFKMC2.ParParameterization class. SphericalKMeansPlusPlus<O>Spherical K-Means++ initialization for k-means. SphericalKMeansPlusPlus.InstanceAbstract instance implementing the weight handling. SphericalKMeansPlusPlus.Par<V>Parameterization class.