Package | Description |
---|---|
de.lmu.ifi.dbs.elki.algorithm |
Algorithms suitable as a task for the
KDDTask
main routine. |
de.lmu.ifi.dbs.elki.algorithm.clustering.hierarchical |
Hierarchical agglomerative clustering (HAC).
|
de.lmu.ifi.dbs.elki.algorithm.outlier.spatial |
Spatial outlier detection algorithms
|
de.lmu.ifi.dbs.elki.algorithm.outlier.subspace |
Subspace outlier detection methods
Methods that detect outliers in subspaces (projections) of the data set.
|
de.lmu.ifi.dbs.elki.application.greedyensemble |
Greedy ensembles for outlier detection.
|
de.lmu.ifi.dbs.elki.database.query.distance |
Prepared queries for distances
|
de.lmu.ifi.dbs.elki.database.query.knn |
Prepared queries for k nearest neighbor (kNN) queries
|
de.lmu.ifi.dbs.elki.database.query.range |
Prepared queries for ε-range queries, that return all objects within
the radius ε
|
de.lmu.ifi.dbs.elki.datasource.filter.transform |
Data space transformations
|
de.lmu.ifi.dbs.elki.distance.distancefunction |
Distance functions for use within ELKI.
|
de.lmu.ifi.dbs.elki.distance.distancefunction.colorhistogram |
Distance functions using correlations
|
de.lmu.ifi.dbs.elki.distance.distancefunction.correlation |
Distance functions using correlations
|
de.lmu.ifi.dbs.elki.distance.distancefunction.geo |
Geographic (earth) distance functions
|
de.lmu.ifi.dbs.elki.distance.distancefunction.histogram |
Distance functions for one-dimensional histograms.
|
de.lmu.ifi.dbs.elki.distance.distancefunction.minkowski |
Minkowski space Lp norms such as the popular Euclidean and
Manhattan distances.
|
de.lmu.ifi.dbs.elki.distance.distancefunction.probabilistic |
Distance from probability theory, mostly divergences such as K-L-divergence,
J-divergence, F-divergence, χ²-divergence, etc.
|
de.lmu.ifi.dbs.elki.distance.distancefunction.set |
Distance functions for binary and set type data.
|
de.lmu.ifi.dbs.elki.distance.distancefunction.strings |
Distance functions for strings
|
de.lmu.ifi.dbs.elki.distance.distancefunction.subspace |
Distance functions based on subspaces
|
de.lmu.ifi.dbs.elki.distance.distancefunction.timeseries |
Distance functions designed for time series
Note that some regular distance functions (e.g., Euclidean) are also used on
time series.
|
de.lmu.ifi.dbs.elki.distance.similarityfunction |
Similarity functions
|
de.lmu.ifi.dbs.elki.distance.similarityfunction.cluster |
Similarity measures for comparing clusters.
|
de.lmu.ifi.dbs.elki.distance.similarityfunction.kernel |
Kernel functions.
|
de.lmu.ifi.dbs.elki.evaluation.clustering.internal |
Internal evaluation measures for clusterings.
|
de.lmu.ifi.dbs.elki.math.linearalgebra.pca |
Principal Component Analysis (PCA) and Eigenvector processing
|
tutorial.distancefunction |
Classes from the tutorial on implementing distance functions
|
Modifier and Type | Field and Description |
---|---|
protected PrimitiveDistanceFunction<? super O> |
AbstractPrimitiveDistanceBasedAlgorithm.distanceFunction
Holds the instance of the distance function specified by
DistanceBasedAlgorithm.DISTANCE_FUNCTION_ID . |
protected PrimitiveDistanceFunction<O> |
AbstractPrimitiveDistanceBasedAlgorithm.Parameterizer.distanceFunction
Distance function to use.
|
Modifier and Type | Method and Description |
---|---|
PrimitiveDistanceFunction<? super O> |
AbstractPrimitiveDistanceBasedAlgorithm.getDistanceFunction()
Returns the distanceFunction.
|
Constructor and Description |
---|
AbstractPrimitiveDistanceBasedAlgorithm(PrimitiveDistanceFunction<? super O> distanceFunction)
Constructor.
|
Modifier and Type | Method and Description |
---|---|
private void |
SLINK.step2primitive(DBIDRef id,
DBIDArrayIter it,
int n,
Relation<? extends O> relation,
PrimitiveDistanceFunction<? super O> distFunc,
WritableDoubleDataStore m)
Second step: Determine the pairwise distances from all objects in the
pointer representation to the new object with the specified id.
|
Modifier and Type | Field and Description |
---|---|
protected PrimitiveDistanceFunction<O> |
AbstractDistanceBasedSpatialOutlier.Parameterizer.distanceFunction
The distance function to use on the non-spatial attributes.
|
Constructor and Description |
---|
SLOM(NeighborSetPredicate.Factory<N> npred,
PrimitiveDistanceFunction<O> nonSpatialDistanceFunction)
Constructor.
|
SOF(NeighborSetPredicate.Factory<N> npred,
PrimitiveDistanceFunction<O> nonSpatialDistanceFunction)
Constructor.
|
Modifier and Type | Method and Description |
---|---|
private DoubleDBIDList |
OUTRES.initialRange(DBIDRef obj,
DBIDs cands,
PrimitiveDistanceFunction<? super NumberVector> df,
double eps,
OUTRES.KernelDensityEstimator kernel,
ModifiableDoubleDBIDList n)
Initial range query.
|
private DoubleDBIDList |
OUTRES.subsetNeighborhoodQuery(DoubleDBIDList neighc,
DBIDRef dbid,
PrimitiveDistanceFunction<? super NumberVector> df,
double adjustedEps,
OUTRES.KernelDensityEstimator kernel,
ModifiableDoubleDBIDList n)
Refine neighbors within a subset.
|
Modifier and Type | Method and Description |
---|---|
private PrimitiveDistanceFunction<NumberVector> |
GreedyEnsembleExperiment.getDistanceFunction(double[] estimated_weights) |
Modifier and Type | Field and Description |
---|---|
protected PrimitiveDistanceFunction<? super O> |
PrimitiveDistanceQuery.distanceFunction
The distance function we use.
|
Modifier and Type | Method and Description |
---|---|
PrimitiveDistanceFunction<? super O> |
PrimitiveDistanceQuery.getDistanceFunction() |
Constructor and Description |
---|
PrimitiveDistanceQuery(Relation<? extends O> relation,
PrimitiveDistanceFunction<? super O> distanceFunction)
Constructor.
|
PrimitiveDistanceSimilarityQuery(Relation<? extends O> relation,
PrimitiveDistanceFunction<? super O> distanceFunction,
PrimitiveSimilarityFunction<? super O> similarityFunction)
Constructor.
|
Modifier and Type | Field and Description |
---|---|
private PrimitiveDistanceFunction<? super O> |
LinearScanPrimitiveDistanceKNNQuery.rawdist
Unboxed distance function.
|
Modifier and Type | Field and Description |
---|---|
private PrimitiveDistanceFunction<? super O> |
LinearScanPrimitiveDistanceRangeQuery.rawdist
Unboxed distance function.
|
Modifier and Type | Field and Description |
---|---|
(package private) PrimitiveDistanceFunction<? super I> |
FastMultidimensionalScalingTransform.dist
Distance function to use.
|
(package private) PrimitiveDistanceFunction<? super I> |
FastMultidimensionalScalingTransform.Parameterizer.dist
Distance function to use.
|
(package private) PrimitiveDistanceFunction<? super I> |
ClassicMultidimensionalScalingTransform.dist
Distance function to use.
|
(package private) PrimitiveDistanceFunction<? super I> |
ClassicMultidimensionalScalingTransform.Parameterizer.dist
Distance function to use.
|
Modifier and Type | Method and Description |
---|---|
protected static <I> double[][] |
ClassicMultidimensionalScalingTransform.computeSquaredDistanceMatrix(java.util.List<I> col,
PrimitiveDistanceFunction<? super I> dist)
Compute the squared distance matrix.
|
Constructor and Description |
---|
ClassicMultidimensionalScalingTransform(int tdim,
PrimitiveDistanceFunction<? super I> dist,
NumberVector.Factory<O> factory)
Constructor.
|
FastMultidimensionalScalingTransform(int tdim,
PrimitiveDistanceFunction<? super I> dist,
NumberVector.Factory<O> factory,
RandomFactory random)
Constructor.
|
Modifier and Type | Interface and Description |
---|---|
interface |
Norm<O>
Abstract interface for a mathematical norm.
|
interface |
NumberVectorDistanceFunction<O>
Base interface for the common case of distance functions defined on numerical
vectors.
|
interface |
SpatialPrimitiveDistanceFunction<V extends SpatialComparable>
API for a spatial primitive distance function.
|
interface |
WeightedNumberVectorDistanceFunction<V>
Distance functions where each dimension is assigned a weight.
|
Modifier and Type | Class and Description |
---|---|
class |
AbstractNumberVectorDistanceFunction
Abstract base class for the most common family of distance functions: defined
on number vectors and returning double values.
|
class |
ArcCosineDistanceFunction
Arcus cosine distance function for feature vectors.
|
class |
ArcCosineUnitlengthDistanceFunction
Arcus cosine distance function for feature vectors.
|
class |
BrayCurtisDistanceFunction
Bray-Curtis distance function / Sørensen–Dice coefficient for continuous
vector spaces (not only binary data).
|
class |
CanberraDistanceFunction
Canberra distance function, a variation of Manhattan distance.
|
class |
ClarkDistanceFunction
Clark distance function for vector spaces.
|
class |
CosineDistanceFunction
Cosine distance function for feature vectors.
|
class |
CosineUnitlengthDistanceFunction
Cosine distance function for unit length feature vectors.
|
class |
MahalanobisDistanceFunction
Mahalanobis quadratic form distance for feature vectors.
|
class |
MatrixWeightedQuadraticDistanceFunction
Matrix weighted quadratic distance, the squared form of
MahalanobisDistanceFunction . |
class |
WeightedCanberraDistanceFunction
Weighted Canberra distance function, a variation of Manhattan distance.
|
Modifier and Type | Class and Description |
---|---|
class |
HistogramIntersectionDistanceFunction
Intersection distance for color histograms.
|
class |
HSBHistogramQuadraticDistanceFunction
Distance function for HSB color histograms based on a quadratic form and
color similarity.
|
class |
RGBHistogramQuadraticDistanceFunction
Distance function for RGB color histograms based on a quadratic form and
color similarity.
|
Modifier and Type | Class and Description |
---|---|
class |
AbsolutePearsonCorrelationDistanceFunction
Absolute Pearson correlation distance function for feature vectors.
|
class |
AbsoluteUncenteredCorrelationDistanceFunction
Absolute uncentered correlation distance function for feature vectors.
|
class |
PearsonCorrelationDistanceFunction
Pearson correlation distance function for feature vectors.
|
class |
SquaredPearsonCorrelationDistanceFunction
Squared Pearson correlation distance function for feature vectors.
|
class |
SquaredUncenteredCorrelationDistanceFunction
Squared uncentered correlation distance function for feature vectors.
|
class |
UncenteredCorrelationDistanceFunction
Uncentered correlation distance.
|
class |
WeightedPearsonCorrelationDistanceFunction
Pearson correlation distance function for feature vectors.
|
class |
WeightedSquaredPearsonCorrelationDistanceFunction
Weighted squared Pearson correlation distance function for feature vectors.
|
Modifier and Type | Class and Description |
---|---|
class |
DimensionSelectingLatLngDistanceFunction
Distance function for 2D vectors in Latitude, Longitude form.
|
class |
LatLngDistanceFunction
Distance function for 2D vectors in Latitude, Longitude form.
|
class |
LngLatDistanceFunction
Distance function for 2D vectors in Longitude, Latitude form.
|
Modifier and Type | Class and Description |
---|---|
class |
HistogramMatchDistanceFunction
Distance function based on histogram matching, i.e., Manhattan distance on
the cumulative density function.
|
class |
KolmogorovSmirnovDistanceFunction
Distance function based on the Kolmogorov-Smirnov goodness of fit test.
|
Modifier and Type | Class and Description |
---|---|
class |
EuclideanDistanceFunction
Euclidean distance for
NumberVector s. |
class |
LPIntegerNormDistanceFunction
Lp-Norm for
NumberVector s, optimized version for integer
values of p. |
class |
LPNormDistanceFunction
Lp-Norm (Minkowski norms) are a family of distances for
NumberVector s. |
class |
ManhattanDistanceFunction
Manhattan distance for
NumberVector s. |
class |
MaximumDistanceFunction
Maximum distance for
NumberVector s. |
class |
MinimumDistanceFunction
Minimum distance for
NumberVector s. |
class |
SparseEuclideanDistanceFunction
Euclidean distance function, optimized for
SparseNumberVector s. |
class |
SparseLPNormDistanceFunction
Lp-Norm, optimized for
SparseNumberVector s. |
class |
SparseManhattanDistanceFunction
Manhattan distance, optimized for
SparseNumberVector s. |
class |
SparseMaximumDistanceFunction
Maximum distance, optimized for
SparseNumberVector s. |
class |
SparseSquaredEuclideanDistanceFunction
Squared Euclidean distance function, optimized for
SparseNumberVector s. |
class |
SquaredEuclideanDistanceFunction
Squared Euclidean distance, optimized for
SparseNumberVector s. |
class |
WeightedEuclideanDistanceFunction
Weighted Euclidean distance for
NumberVector s. |
class |
WeightedLPNormDistanceFunction
Weighted version of the Minkowski Lp norm distance for
NumberVector . |
class |
WeightedManhattanDistanceFunction
Weighted version of the Manhattan (L1) metric.
|
class |
WeightedMaximumDistanceFunction
Weighted version of the maximum distance function for
NumberVector s. |
class |
WeightedSquaredEuclideanDistanceFunction
Weighted squared Euclidean distance for
NumberVector s. |
Modifier and Type | Class and Description |
---|---|
class |
ChiDistanceFunction
χ distance function, symmetric version.
|
class |
ChiSquaredDistanceFunction
χ² distance function, symmetric version.
|
class |
FisherRaoDistanceFunction
Fisher-Rao riemannian metric for (discrete) probability distributions.
|
class |
HellingerDistanceFunction
Hellinger metric / affinity / kernel, Bhattacharyya coefficient, fidelity
similarity, Matusita distance, Hellinger-Kakutani metric on a probability
distribution.
|
class |
JeffreyDivergenceDistanceFunction
Jeffrey Divergence for
NumberVector s is a symmetric, smoothened
version of the KullbackLeiblerDivergenceAsymmetricDistanceFunction . |
class |
JensenShannonDivergenceDistanceFunction
Jensen-Shannon Divergence for
NumberVector s is a symmetric,
smoothened version of the
KullbackLeiblerDivergenceAsymmetricDistanceFunction . |
class |
KullbackLeiblerDivergenceAsymmetricDistanceFunction
Kullback-Leibler divergence, also known as relative entropy,
information deviation, or just KL-distance (albeit asymmetric).
|
class |
KullbackLeiblerDivergenceReverseAsymmetricDistanceFunction
Kullback-Leibler divergence, also known as relative entropy, information
deviation or just KL-distance (albeit asymmetric).
|
class |
SqrtJensenShannonDivergenceDistanceFunction
The square root of Jensen-Shannon divergence is a metric.
|
class |
TriangularDiscriminationDistanceFunction
Triangular Discrimination has relatively tight upper and lower bounds to the
Jensen-Shannon divergence, but is much less expensive.
|
class |
TriangularDistanceFunction
Triangular Distance has relatively tight upper and lower bounds to the
(square root of the) Jensen-Shannon divergence, but is much less expensive.
|
Modifier and Type | Class and Description |
---|---|
class |
AbstractSetDistanceFunction<O>
Abstract base class for set distance functions.
|
class |
HammingDistanceFunction
Computes the Hamming distance of arbitrary vectors - i.e. counting, on how
many places they differ.
|
class |
JaccardSimilarityDistanceFunction
A flexible extension of Jaccard similarity to non-binary vectors.
|
Modifier and Type | Class and Description |
---|---|
class |
LevenshteinDistanceFunction
Classic Levenshtein distance on strings.
|
class |
NormalizedLevenshteinDistanceFunction
Levenshtein distance on strings, normalized by string length.
|
Modifier and Type | Class and Description |
---|---|
class |
AbstractDimensionsSelectingDistanceFunction<V extends FeatureVector<?>>
Abstract base class for distances computed only in subspaces.
|
class |
OnedimensionalDistanceFunction
Distance function that computes the distance between feature vectors as the
absolute difference of their values in a specified dimension only.
|
class |
SubspaceEuclideanDistanceFunction
Euclidean distance function between
NumberVector s only in specified
dimensions. |
class |
SubspaceLPNormDistanceFunction
Lp-Norm distance function between
NumberVector s only in
specified dimensions. |
class |
SubspaceManhattanDistanceFunction
Manhattan distance function between
NumberVector s only in specified
dimensions. |
class |
SubspaceMaximumDistanceFunction
Maximum distance function between
NumberVector s only in specified
dimensions. |
Modifier and Type | Class and Description |
---|---|
class |
AbstractEditDistanceFunction
Edit Distance for FeatureVectors.
|
class |
DerivativeDTWDistanceFunction
Derivative Dynamic Time Warping distance for numerical vectors.
|
class |
DTWDistanceFunction
Dynamic Time Warping distance (DTW) for numerical vectors.
|
class |
EDRDistanceFunction
Edit Distance on Real Sequence distance for numerical vectors.
|
class |
ERPDistanceFunction
Edit Distance With Real Penalty distance for numerical vectors.
|
class |
LCSSDistanceFunction
Longest Common Subsequence distance for numerical vectors.
|
Modifier and Type | Class and Description |
---|---|
class |
Kulczynski1SimilarityFunction
Kulczynski similarity 1.
|
Modifier and Type | Field and Description |
---|---|
protected PrimitiveDistanceFunction<? super O> |
InvertedDistanceSimilarityFunction.distanceFunction
Holds the similarity function.
|
Modifier and Type | Interface and Description |
---|---|
interface |
ClusteringDistanceSimilarityFunction
Distance and similarity measure for clusterings.
|
Modifier and Type | Class and Description |
---|---|
class |
ClusteringAdjustedRandIndexSimilarityFunction
Measure the similarity of clusters via the Adjusted Rand Index.
|
class |
ClusteringBCubedF1SimilarityFunction
Measure the similarity of clusters via the BCubed F1 Index.
|
class |
ClusteringFowlkesMallowsSimilarityFunction
Measure the similarity of clusters via the Fowlkes-Mallows Index.
|
class |
ClusteringRandIndexSimilarityFunction
Measure the similarity of clusters via the Rand Index.
|
class |
ClusterIntersectionSimilarityFunction
Measure the similarity of clusters via the intersection size.
|
class |
ClusterJaccardSimilarityFunction
Measure the similarity of clusters via the Jaccard coefficient.
|
Modifier and Type | Class and Description |
---|---|
class |
LinearKernelFunction
Linear Kernel function that computes a similarity between the two feature
vectors x and y defined by \(x^T\cdot y\).
|
class |
PolynomialKernelFunction
Polynomial Kernel function that computes a similarity between the two feature
vectors x and y defined by \((x^T\cdot y+b)^{\text{degree}}\).
|
Modifier and Type | Field and Description |
---|---|
private PrimitiveDistanceFunction<NumberVector> |
EvaluateConcordantPairs.Parameterizer.distance
Distance function to use.
|
private PrimitiveDistanceFunction<? super NumberVector> |
EvaluateConcordantPairs.distanceFunction
Distance function to use.
|
Constructor and Description |
---|
EvaluateConcordantPairs(PrimitiveDistanceFunction<? super NumberVector> distance,
NoiseHandling noiseHandling)
Constructor.
|
Modifier and Type | Field and Description |
---|---|
private PrimitiveDistanceFunction<? super NumberVector> |
WeightedCovarianceMatrixBuilder.weightDistance
Holds the distance function used for weight calculation.
|
Modifier and Type | Class and Description |
---|---|
class |
MultiLPNorm
Tutorial example Minowski-distance variation with different exponents for
different dimensions for ELKI.
|
class |
TutorialDistanceFunction
Tutorial distance function example for ELKI.
|
Copyright © 2019 ELKI Development Team. License information.