Clustering

143 public types in this namespace, organized by kind.

Models & Types (82)

Type Summary
AdjustedMutualInformation<T> Adjusted Mutual Information (AMI) for comparing clustering results.
AdjustedRandIndex<T> Adjusted Rand Index for comparing cluster assignments.
AffinityPropagation<T> Affinity Propagation clustering implementation.
AgglomerativeClustering<T> Agglomerative Hierarchical Clustering implementation.
BCSS<T> Between-Cluster Sum of Squares (BCSS) metric for evaluating cluster separation.
BIRCH<T> BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) clustering.
BallTree<T> Ball Tree for efficient nearest neighbor queries with arbitrary distance metrics.
BisectingKMeans<T> Bisecting K-Means clustering algorithm implementation.
BootstrapAnalysisResult Result of bootstrap analysis across multiple K values.
BootstrapResult Result of bootstrap validation for a single K value.
BootstrapValidation<T> Bootstrap validation for evaluating clustering quality and confidence.
CFEntry<T> Represents a Clustering Feature (CF) entry.
CLARANS<T> CLARANS (Clustering Large Applications based on Randomized Search) implementation.
CLIQUE<T> CLIQUE (CLustering In QUEst) subspace clustering algorithm.
COPKMeans<T> COP-KMeans (Constrained K-Means) implementation with must-link and cannot-link constraints.
CURE<T> CURE (Clustering Using REpresentatives) hierarchical clustering algorithm.
CalinskiHarabaszIndex<T> Calinski-Harabasz Index (Variance Ratio Criterion) for evaluating cluster quality.
ChebyshevDistance<T> Computes Chebyshev (Lāˆž) distance between vectors.
ClusterMetrics<T> Convenience class for computing multiple cluster evaluation metrics at once.
ClusteringAutoMLResult<T> Complete result from ClusteringAutoML.
ClusteringAutoML<T> Automatic machine learning for clustering - selects best algorithm and parameters.
ClusteringComparisonResult Results from comparing multiple clusterings.
ClusteringEntropy<T> Entropy-based metrics for evaluating clustering against ground truth labels.
ClusteringEvaluationResult Results from clustering evaluation.
ClusteringEvaluator<T> Comprehensive evaluator for clustering results.
ClusteringGridSearch<T> Grid search for clustering hyperparameter optimization.
ClusteringScores Contains the results of cluster evaluation metrics.
ClusteringTrialResult<T> Result from a single AutoML trial.
Completeness<T> Completeness score - measures if all members of a given class are assigned to the same cluster.
ConditionalEntropy<T> Conditional Entropy H(C|K) - entropy of true classes given clusters.
ConfidenceInterval A confidence interval for a metric.
ConnectivityIndex<T> Computes the Connectivity Index for cluster validity assessment.
ConsensusClustering<T> Consensus (Ensemble) Clustering implementation.
CosineDistance<T> Computes Cosine distance between vectors.
DBSCAN<T> DBSCAN (Density-Based Spatial Clustering of Applications with Noise) implementation.
DaviesBouldinIndex<T> Davies-Bouldin Index for evaluating cluster quality.
Denclue<T> DENCLUE (DENsity-based CLUstEring) implementation.
DunnIndex<T> Computes the Dunn Index for cluster validity assessment.
ElbowMethodResult Results from Elbow Method analysis.
ElbowMethod<T> Elbow Method for determining the optimal number of clusters.
EuclideanDistance<T> Computes Euclidean (L2) distance between vectors.
FMeasure<T> F-Measure (F-Score) for comparing clustering results against ground truth.
FowlkesMallowsIndex<T> Computes the Fowlkes-Mallows Index for cluster-label agreement.
FuzzyCMeans<T> Fuzzy C-Means (FCM) soft clustering implementation.
GMeans<T> G-Means clustering with automatic K determination using Gaussian tests.
GapStatisticResult Results from Gap Statistic analysis.
GapStatistic<T> Gap Statistic for determining the optimal number of clusters.
GaussianMixtureModel<T> Gaussian Mixture Model clustering using Expectation-Maximization.
GridSearchCVResult<T> Complete result from cross-validation grid search.
GridSearchCVTrialResult<T> Result from a single cross-validation grid search trial.
GridSearchResult<T> Complete result from grid search.
GridSearchTrialResult<T> Result from a single grid search trial.
HDBSCAN<T> HDBSCAN (Hierarchical Density-Based Spatial Clustering of Applications with Noise).
Homogeneity<T> Homogeneity score - measures if clusters contain only members of a single class.
JaccardIndex<T> Jaccard Index for comparing clustering results against ground truth.
KDTree<T> K-dimensional tree for efficient nearest neighbor queries.
KMeans<T> K-Means clustering algorithm implementation.
KMedoids<T> K-Medoids (PAM - Partitioning Around Medoids) clustering implementation.
MahalanobisDistance<T> Computes Mahalanobis distance between vectors.
ManhattanDistance<T> Computes Manhattan (L1) distance between vectors.
MeanShift<T> Mean Shift clustering implementation.
MiniBatchKMeans<T> Mini-Batch K-Means clustering algorithm for large-scale clustering.
MinkowskiDistance<T> Computes Minkowski (Lp) distance between vectors.
NormalizedMutualInformation<T> Normalized Mutual Information for comparing cluster assignments.
OPTICS<T> OPTICS (Ordering Points To Identify the Clustering Structure) implementation.
OnlineKMeans<T> Online K-Means clustering for streaming data.
OptimalKAnalysis Analysis results for finding optimal K.
Purity<T> Purity metric for evaluating clustering against ground truth labels.
RandIndex<T> Rand Index and Adjusted Rand Index for comparing clustering results.
SUBCLU<T> SUBCLU (SUBspace CLUstering) density-connected subspace clustering algorithm.
SeededKMeans<T> Seeded K-Means implementation with labeled initialization points.
SelfOrganizingMap<T> Self-Organizing Map (SOM) / Kohonen Network implementation.
SilhouetteScore<T> Silhouette Score for evaluating cluster quality.
SpectralClustering<T> Spectral Clustering implementation using graph Laplacian eigendecomposition.
StabilityAnalysisResult Result of stability analysis across multiple K values.
StabilityResult Result of stability validation for a single K value.
StabilityValidation<T> Stability-based validation for evaluating clustering quality.
SubspaceCluster Represents a cluster discovered in a subspace.
VMeasure<T> Computes the V-Measure for cluster-label agreement.
VariationOfInformation<T> Variation of Information (VI) for comparing clustering results.
WCSS<T> Within-Cluster Sum of Squares (WCSS) metric for evaluating cluster compactness.
XMeans<T> X-Means clustering with automatic K determination using BIC.

Base Classes (3)

Type Summary
ClusteringBase<T> Provides a base implementation for clustering algorithms that group similar data points together.
DistanceMetricBase<T> Abstract base class for distance metrics providing common functionality.
ExternalClusterMetricBase<T> Base class for external cluster evaluation metrics that compare against ground truth.

Interfaces (4)

Type Summary
IClusterMetric<T> Interface for cluster evaluation metrics.
IClustering<T> Defines the common interface for all clustering algorithms in the AiDotNet library.
IDistanceMetric<T> Defines an interface for computing distance or similarity between vectors.
IExternalClusterMetric<T> Interface for external cluster metrics that require ground truth.

Enums (23)

Type Summary
AffinityPropagationAffinityType Types of affinity computation for Affinity Propagation.
AffinityType Types of affinity/similarity computation.
BisectionClusterSelection Methods for selecting which cluster to bisect next.
ConsensusMethod Methods for combining multiple clusterings.
CovarianceType Type of covariance parameters to estimate.
EigenSolver Eigenvalue solver methods.
FinalClusteringAlgorithm Algorithm for final clustering of consensus matrix.
GMMInitMethod Initialization methods for GMM.
HDBSCANClusterSelection Cluster selection methods for HDBSCAN.
InformationCriterion Information criteria for model selection.
KMeansAlgorithm KMeans algorithm variants.
KMeansInitMethod Methods for initializing KMeans cluster centers.
KMedoidsAlgorithm Algorithm variants for K-Medoids.
KMedoidsInit Initialization methods for K-Medoids.
LaplacianNormalization Laplacian matrix normalization types.
LinkageMethod Linkage methods for hierarchical clustering.
NMINormalization Normalization methods for NMI.
NeighborAlgorithm Algorithms for computing nearest neighbors.
NeighborhoodFunction Neighborhood function types for SOM.
OPTICSExtractionMethod Methods for extracting clusters from OPTICS output.
PrecomputeOption Options for precomputing distances.
SOMTopology SOM grid topology types.
SpectralAssignment Label assignment methods after spectral embedding.

Structs (1)

Type Summary
CondensedTreeNode<T> Represents a node in the condensed tree.

Options & Configuration (28)

Type Summary
AffinityPropagationOptions<T> Configuration options for Affinity Propagation clustering.
BIRCHOptions<T> Configuration options for BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies).
BisectingKMeansOptions<T> Configuration options for Bisecting K-Means clustering.
CLARANSOptions<T> Configuration options for CLARANS (Clustering Large Applications based on Randomized Search).
CLIQUEOptions<T> Configuration options for CLIQUE subspace clustering.
COPKMeansOptions<T> Configuration options for COP-KMeans (Constrained K-Means).
CUREOptions<T> Configuration options for CURE clustering algorithm.
ClusteringAutoMLOptions Configuration options for ClusteringAutoML.
ClusteringOptions<T> Base configuration options for clustering algorithms.
ConsensusClusteringOptions<T> Configuration options for Consensus (Ensemble) Clustering.
DBSCANOptions<T> Configuration options for DBSCAN clustering.
DenclueOptions<T> Configuration options for DENCLUE clustering.
FuzzyCMeansOptions<T> Configuration options for Fuzzy C-Means clustering.
GMMOptions<T> Configuration options for Gaussian Mixture Model clustering.
GMeansOptions<T> Configuration options for G-Means clustering.
HDBSCANOptions<T> Configuration options for HDBSCAN (Hierarchical DBSCAN).
HierarchicalOptions<T> Configuration options for Hierarchical (Agglomerative) clustering.
KMeansOptions<T> Configuration options specific to KMeans clustering.
KMedoidsOptions<T> Configuration options for K-Medoids (PAM) clustering.
MeanShiftOptions<T> Configuration options for Mean Shift clustering.
MiniBatchKMeansOptions<T> Configuration options specific to MiniBatch K-Means clustering.
OPTICSOptions<T> Configuration options for OPTICS clustering.
OnlineKMeansOptions<T> Configuration options for Online/Streaming K-Means.
SOMOptions<T> Configuration options for Self-Organizing Maps (SOM).
SUBCLUOptions<T> Configuration options for SUBCLU subspace clustering.
SeededKMeansOptions<T> Configuration options for Seeded K-Means.
SpectralOptions<T> Configuration options for Spectral Clustering.
XMeansOptions<T> Configuration options for X-Means clustering.

Helpers & Utilities (2)

Type Summary
BisectionNode Represents a node in the bisection hierarchy tree.
CFNode<T> Represents a node in the CF-tree.