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 |
Clustering algorithms.
|
de.lmu.ifi.dbs.elki.database.datastore |
General data store layer API (along the lines of
Map<DBID, T> - use everywhere!) |
de.lmu.ifi.dbs.elki.database.datastore.memory |
Memory data store implementation for ELKI.
|
de.lmu.ifi.dbs.elki.index.preprocessed |
Index structure based on preprocessors
|
de.lmu.ifi.dbs.elki.index.preprocessed.knn |
Indexes providing KNN and rKNN data.
|
de.lmu.ifi.dbs.elki.result.optics |
Result classes for OPTICS.
|
tutorial.clustering |
Classes from the tutorial on implementing a custom k-means variation.
|
Modifier and Type | Method and Description |
---|---|
WritableDataStore<KNNResult<D>> |
KNNJoin.run(Database database,
Relation<V> relation)
Joins in the given spatial database to each object its k-nearest neighbors.
|
Modifier and Type | Field and Description |
---|---|
private WritableDataStore<double[]> |
EM.probClusterIGivenX
Store the individual probabilities, for use by EMOutlierDetection etc.
|
Modifier and Type | Method and Description |
---|---|
protected double |
EM.assignProbabilitiesToInstances(Relation<V> database,
double[] normDistrFactor,
List<Vector> means,
List<Matrix> invCovMatr,
double[] clusterWeights,
WritableDataStore<double[]> probClusterIGivenX)
Assigns the current probability values to the instances in the database and
compute the expectation value of the current mixture of distributions.
|
private void |
SLINK.step1(DBIDRef id,
WritableDBIDDataStore pi,
WritableDataStore<D> lambda)
First step: Initialize P(id) = id, L(id) = infinity.
|
private void |
SLINK.step2(DBIDRef id,
DBIDs processedIDs,
DistanceQuery<O,D> distFunc,
WritableDataStore<D> m)
Second step: Determine the pairwise distances from all objects in the
pointer representation to the new object with the specified id.
|
private void |
SLINK.step3(DBIDRef id,
WritableDBIDDataStore pi,
WritableDataStore<D> lambda,
DBIDs processedIDs,
WritableDataStore<D> m)
Third step: Determine the values for P and L
|
private void |
SLINK.step3(DBIDRef id,
WritableDBIDDataStore pi,
WritableDataStore<D> lambda,
DBIDs processedIDs,
WritableDataStore<D> m)
Third step: Determine the values for P and L
|
private void |
SLINK.step4(DBIDRef id,
WritableDBIDDataStore pi,
WritableDataStore<D> lambda,
DBIDs processedIDs)
Fourth step: Actualize the clusters if necessary
|
Modifier and Type | Interface and Description |
---|---|
interface |
WritableDBIDDataStore
Data store specialized for doubles.
|
interface |
WritableDoubleDataStore
Data store specialized for doubles.
|
interface |
WritableDoubleDistanceDataStore
Data store specialized for doubles.
|
interface |
WritableIntegerDataStore
Data store specialized for doubles.
|
Modifier and Type | Method and Description |
---|---|
<T> WritableDataStore<T> |
WritableRecordStore.getStorage(int col,
Class<? super T> datatype)
Get a
WritableDataStore instance for a particular record column. |
static <T> WritableDataStore<T> |
DataStoreUtil.makeStorage(DBIDs ids,
int hints,
Class<? super T> dataclass)
Make a new storage, to associate the given ids with an object of class
dataclass.
|
<T> WritableDataStore<T> |
DataStoreFactory.makeStorage(DBIDs ids,
int hints,
Class<? super T> dataclass)
Make a new storage, to associate the given ids with an object of class
dataclass.
|
Modifier and Type | Class and Description |
---|---|
class |
ArrayDBIDStore
A class to answer representation queries using the stored Array.
|
class |
ArrayDoubleDistanceStore
A class to answer representation queries using the stored Array.
|
class |
ArrayDoubleStore
A class to answer representation queries using the stored Array.
|
class |
ArrayIntegerStore
A class to answer representation queries using the stored Array.
|
protected class |
ArrayRecordStore.StorageAccessor<T>
Access a single record in the given data.
|
class |
ArrayStore<T>
A class to answer representation queries using the stored Array.
|
class |
MapIntegerDBIDDBIDStore
Writable data store for double values.
|
class |
MapIntegerDBIDDoubleDistanceStore
Writable data store for double values.
|
class |
MapIntegerDBIDDoubleStore
Writable data store for double values.
|
class |
MapIntegerDBIDIntegerStore
Writable data store for double values.
|
protected class |
MapIntegerDBIDRecordStore.StorageAccessor<T>
Access a single record in the given data.
|
class |
MapIntegerDBIDStore<T>
A class to answer representation queries using a map.
|
protected class |
MapRecordStore.StorageAccessor<T>
Access a single record in the given data.
|
class |
MapStore<T>
A class to answer representation queries using a map.
|
Modifier and Type | Method and Description |
---|---|
<T> WritableDataStore<T> |
MapRecordStore.getStorage(int col,
Class<? super T> datatype) |
<T> WritableDataStore<T> |
MapIntegerDBIDRecordStore.getStorage(int col,
Class<? super T> datatype) |
<T> WritableDataStore<T> |
ArrayRecordStore.getStorage(int col,
Class<? super T> datatype) |
<T> WritableDataStore<T> |
MemoryDataStoreFactory.makeStorage(DBIDs ids,
int hints,
Class<? super T> dataclass) |
Modifier and Type | Field and Description |
---|---|
protected WritableDataStore<R> |
AbstractPreprocessorIndex.storage
The data store.
|
Modifier and Type | Field and Description |
---|---|
private WritableDataStore<TreeSet<DistanceDBIDPair<D>>> |
MaterializeKNNAndRKNNPreprocessor.materialized_RkNN
Additional data storage for RkNN.
|
Modifier and Type | Field and Description |
---|---|
private WritableDataStore<ClusterOrderEntry<D>> |
ClusterOrderResult.map
Map of object IDs to their cluster order entry
|
Modifier and Type | Method and Description |
---|---|
protected WritableDataStore<SameSizeKMeansAlgorithm.Meta> |
SameSizeKMeansAlgorithm.initializeMeta(Relation<V> relation,
List<? extends NumberVector<?>> means)
Initialize the metadata storage.
|
Modifier and Type | Method and Description |
---|---|
protected ArrayModifiableDBIDs |
SameSizeKMeansAlgorithm.initialAssignment(List<ModifiableDBIDs> clusters,
WritableDataStore<SameSizeKMeansAlgorithm.Meta> metas,
DBIDs ids) |
protected List<? extends NumberVector<?>> |
SameSizeKMeansAlgorithm.refineResult(Relation<V> relation,
List<? extends NumberVector<?>> means,
List<ModifiableDBIDs> clusters,
WritableDataStore<SameSizeKMeansAlgorithm.Meta> metas,
ArrayModifiableDBIDs tids)
Perform k-means style iterations to improve the clustering result.
|
protected void |
SameSizeKMeansAlgorithm.transfer(WritableDataStore<SameSizeKMeansAlgorithm.Meta> metas,
SameSizeKMeansAlgorithm.Meta meta,
ModifiableDBIDs src,
ModifiableDBIDs dst,
DBIDRef id,
Integer dstnum)
Transfer a single element from one cluster to another.
|
protected void |
SameSizeKMeansAlgorithm.updateDistances(Relation<V> relation,
List<? extends NumberVector<?>> means,
WritableDataStore<SameSizeKMeansAlgorithm.Meta> metas,
PrimitiveDoubleDistanceFunction<NumberVector<?>> df)
Compute the distances of each object to all means.
|