diff options
Diffstat (limited to 'src/de/lmu/ifi/dbs/elki/data/projection')
5 files changed, 357 insertions, 0 deletions
diff --git a/src/de/lmu/ifi/dbs/elki/data/projection/AbstractFeatureSelection.java b/src/de/lmu/ifi/dbs/elki/data/projection/AbstractFeatureSelection.java new file mode 100644 index 00000000..fcd5fd84 --- /dev/null +++ b/src/de/lmu/ifi/dbs/elki/data/projection/AbstractFeatureSelection.java @@ -0,0 +1,64 @@ +package de.lmu.ifi.dbs.elki.data.projection; + +import de.lmu.ifi.dbs.elki.data.FeatureVector; +/* + This file is part of ELKI: + Environment for Developing KDD-Applications Supported by Index-Structures + + Copyright (C) 2012 + Ludwig-Maximilians-Universität München + Lehr- und Forschungseinheit für Datenbanksysteme + ELKI Development Team + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +import de.lmu.ifi.dbs.elki.data.type.SimpleTypeInformation; +import de.lmu.ifi.dbs.elki.data.type.TypeInformation; +import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.SubsetArrayAdapter; + +/** + * Abstract feature selection projection + * + * @author Erich Schubert + * + * @param <V> Vector type + * @param <F> Feature type + */ +public abstract class AbstractFeatureSelection<V extends FeatureVector<V, F>, F> implements Projection<V, V> { + /** + * Array adapter + */ + protected SubsetArrayAdapter<F, V> adapter; + + /** + * Constructor. + * + * @param adapter Data adapter + */ + public AbstractFeatureSelection(SubsetArrayAdapter<F, V> adapter) { + super(); + this.adapter = adapter; + } + + @Override + public V project(V data) { + return data.newFeatureVector(data, adapter); + } + + @Override + abstract public SimpleTypeInformation<V> getOutputDataTypeInformation(); + + @Override + abstract public TypeInformation getInputDataTypeInformation(); +}
\ No newline at end of file diff --git a/src/de/lmu/ifi/dbs/elki/data/projection/FeatureSelection.java b/src/de/lmu/ifi/dbs/elki/data/projection/FeatureSelection.java new file mode 100644 index 00000000..fca75e3f --- /dev/null +++ b/src/de/lmu/ifi/dbs/elki/data/projection/FeatureSelection.java @@ -0,0 +1,104 @@ +package de.lmu.ifi.dbs.elki.data.projection; +/* + This file is part of ELKI: + Environment for Developing KDD-Applications Supported by Index-Structures + + Copyright (C) 2012 + Ludwig-Maximilians-Universität München + Lehr- und Forschungseinheit für Datenbanksysteme + ELKI Development Team + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +import de.lmu.ifi.dbs.elki.data.FeatureVector; +import de.lmu.ifi.dbs.elki.data.NumberVector; +import de.lmu.ifi.dbs.elki.data.type.SimpleTypeInformation; +import de.lmu.ifi.dbs.elki.data.type.TypeInformation; +import de.lmu.ifi.dbs.elki.data.type.VectorTypeInformation; +import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.ArrayAdapter; +import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.ArrayLikeUtil; +import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.SubsetArrayAdapter; + +/** + * Projection class for number vectors. + * + * @author Erich Schubert + * + * @param <V> Vector type + * @param <F> Feature type + */ +public class FeatureSelection<V extends FeatureVector<V, F>, F> extends AbstractFeatureSelection<V, F> { + /** + * Minimum dimensionality required for projection + */ + private int mindim; + + /** + * Object factory + */ + private V factory; + + /** + * Output dimensionality + */ + private int dimensionality; + + /** + * Constructor. + * + * @param dims Dimensions + * @param factory Object factory + */ + public FeatureSelection(int[] dims, V factory) { + super(new SubsetArrayAdapter<F, V>(getAdapter(factory), dims)); + this.factory = factory; + this.dimensionality = dims.length; + + int mindim = 0; + for(int dim : dims) { + mindim = Math.max(mindim, dim + 1); + } + this.mindim = mindim; + } + + /** + * Choose the best adapter for this. + * + * @param factory Object factory, for type inference + * @return Adapter + */ + @SuppressWarnings("unchecked") + private static <V extends FeatureVector<V, F>, F> ArrayAdapter<F, ? super V> getAdapter(V factory) { + if(factory instanceof NumberVector) { + ArrayAdapter<?, ?> ret = ArrayLikeUtil.numberVectorAdapter((NumberVector<?, ?>) factory); + return (ArrayAdapter<F, ? super V>) ret; + } + return ArrayLikeUtil.featureVectorAdapter(factory); + } + + @Override + public SimpleTypeInformation<V> getOutputDataTypeInformation() { + @SuppressWarnings("unchecked") + final Class<V> cls = (Class<V>) factory.getClass(); + return new VectorTypeInformation<V>(cls, dimensionality, dimensionality); + } + + @Override + public TypeInformation getInputDataTypeInformation() { + @SuppressWarnings("unchecked") + final Class<V> cls = (Class<V>) factory.getClass(); + return new VectorTypeInformation<V>(cls, mindim, Integer.MAX_VALUE); + } +}
\ No newline at end of file diff --git a/src/de/lmu/ifi/dbs/elki/data/projection/NumericalFeatureSelection.java b/src/de/lmu/ifi/dbs/elki/data/projection/NumericalFeatureSelection.java new file mode 100644 index 00000000..7dfd580f --- /dev/null +++ b/src/de/lmu/ifi/dbs/elki/data/projection/NumericalFeatureSelection.java @@ -0,0 +1,104 @@ +package de.lmu.ifi.dbs.elki.data.projection; +/* + This file is part of ELKI: + Environment for Developing KDD-Applications Supported by Index-Structures + + Copyright (C) 2012 + Ludwig-Maximilians-Universität München + Lehr- und Forschungseinheit für Datenbanksysteme + ELKI Development Team + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +import de.lmu.ifi.dbs.elki.data.NumberVector; +import de.lmu.ifi.dbs.elki.data.type.SimpleTypeInformation; +import de.lmu.ifi.dbs.elki.data.type.TypeInformation; +import de.lmu.ifi.dbs.elki.data.type.VectorTypeInformation; +import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.ArrayLikeUtil; +import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.NumberArrayAdapter; +import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.SubsetArrayAdapter; + +/** + * Projection class for number vectors. + * + * @author Erich Schubert + * + * @param <V> Vector type + * @param <N> Number type + */ +public class NumericalFeatureSelection<V extends NumberVector<V, N>, N extends Number> extends AbstractFeatureSelection<V, N> { + /** + * Minimum dimensionality required for projection + */ + private int mindim; + + /** + * Object factory + */ + private V factory; + + /** + * Output dimensionality + */ + private int dimensionality; + + /** + * Constructor. + * + * @param dims Dimensions + * @param factory Object factory + */ + public NumericalFeatureSelection(int[] dims, V factory) { + super(new SubsetArrayAdapter<N, V>(getAdapter(factory), dims)); + this.factory = factory; + this.dimensionality = dims.length; + + int mindim = 0; + for(int dim : dims) { + mindim = Math.max(mindim, dim + 1); + } + this.mindim = mindim; + } + + /** + * Choose the best adapter for this. + * + * @param factory Object factory, for type inference + * @return Adapter + */ + private static <V extends NumberVector<V, N>, N extends Number> NumberArrayAdapter<N, ? super V> getAdapter(V factory) { + return ArrayLikeUtil.numberVectorAdapter(factory); + } + + @SuppressWarnings("unchecked") + @Override + public V project(V data) { + return factory.newNumberVector(data, (NumberArrayAdapter<N, ? super V>) adapter); + } + + @Override + public SimpleTypeInformation<V> getOutputDataTypeInformation() { + @SuppressWarnings("unchecked") + final Class<V> cls = (Class<V>) factory.getClass(); + return new VectorTypeInformation<V>(cls, dimensionality, dimensionality); + } + + @Override + public TypeInformation getInputDataTypeInformation() { + @SuppressWarnings("unchecked") + final Class<V> cls = (Class<V>) factory.getClass(); + return new VectorTypeInformation<V>(cls, mindim, Integer.MAX_VALUE); + } +}
\ No newline at end of file diff --git a/src/de/lmu/ifi/dbs/elki/data/projection/Projection.java b/src/de/lmu/ifi/dbs/elki/data/projection/Projection.java new file mode 100644 index 00000000..c9cd98d2 --- /dev/null +++ b/src/de/lmu/ifi/dbs/elki/data/projection/Projection.java @@ -0,0 +1,59 @@ +package de.lmu.ifi.dbs.elki.data.projection; + +import de.lmu.ifi.dbs.elki.data.type.SimpleTypeInformation; +import de.lmu.ifi.dbs.elki.data.type.TypeInformation; + +/* + This file is part of ELKI: + Environment for Developing KDD-Applications Supported by Index-Structures + + Copyright (C) 2012 + Ludwig-Maximilians-Universität München + Lehr- und Forschungseinheit für Datenbanksysteme + ELKI Development Team + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/** + * Projection interface. + * + * @author Erich Schubert + * + * @param <IN> Input data type + * @param <OUT> Output data type + */ +public interface Projection<IN, OUT> { + /** + * Project a single instance. + * + * @param data Data to project + * @return Projected data + */ + public OUT project(IN data); + + /** + * Output type restriction + * + * @return Output type + */ + public SimpleTypeInformation<OUT> getOutputDataTypeInformation(); + + /** + * Input type information. + * + * @return Type restriction + */ + public TypeInformation getInputDataTypeInformation(); +} diff --git a/src/de/lmu/ifi/dbs/elki/data/projection/package-info.java b/src/de/lmu/ifi/dbs/elki/data/projection/package-info.java new file mode 100644 index 00000000..d39c51ba --- /dev/null +++ b/src/de/lmu/ifi/dbs/elki/data/projection/package-info.java @@ -0,0 +1,26 @@ +/** + * <p>Data projections.</p> + */ +/* +This file is part of ELKI: +Environment for Developing KDD-Applications Supported by Index-Structures + +Copyright (C) 2012 +Ludwig-Maximilians-Universität München +Lehr- und Forschungseinheit für Datenbanksysteme +ELKI Development Team + +This program is free software: you can redistribute it and/or modify +it under the terms of the GNU Affero General Public License as published by +the Free Software Foundation, either version 3 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU Affero General Public License for more details. + +You should have received a copy of the GNU Affero General Public License +along with this program. If not, see <http://www.gnu.org/licenses/>. +*/ +package de.lmu.ifi.dbs.elki.data.projection;
\ No newline at end of file |