You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@commons.apache.org by er...@apache.org on 2015/09/11 11:42:19 UTC
[07/10] [math] MATH-1270
MATH-1270
SOFM visualization: Smoothed data histogram.
Project: http://git-wip-us.apache.org/repos/asf/commons-math/repo
Commit: http://git-wip-us.apache.org/repos/asf/commons-math/commit/012c15ce
Tree: http://git-wip-us.apache.org/repos/asf/commons-math/tree/012c15ce
Diff: http://git-wip-us.apache.org/repos/asf/commons-math/diff/012c15ce
Branch: refs/heads/MATH_3_X
Commit: 012c15ce4d83817217430adb0b3750c92f07ab3e
Parents: d7f6c8d
Author: Gilles <er...@apache.org>
Authored: Fri Sep 11 00:55:00 2015 +0200
Committer: Gilles <er...@apache.org>
Committed: Fri Sep 11 00:55:00 2015 +0200
----------------------------------------------------------------------
.../twod/util/SmoothedDataHistogram.java | 96 ++++++++++++++++++++
1 file changed, 96 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/commons-math/blob/012c15ce/src/main/java/org/apache/commons/math3/ml/neuralnet/twod/util/SmoothedDataHistogram.java
----------------------------------------------------------------------
diff --git a/src/main/java/org/apache/commons/math3/ml/neuralnet/twod/util/SmoothedDataHistogram.java b/src/main/java/org/apache/commons/math3/ml/neuralnet/twod/util/SmoothedDataHistogram.java
new file mode 100644
index 0000000..c8a6d84
--- /dev/null
+++ b/src/main/java/org/apache/commons/math3/ml/neuralnet/twod/util/SmoothedDataHistogram.java
@@ -0,0 +1,96 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.commons.math3.ml.neuralnet.twod.util;
+
+import org.apache.commons.math3.ml.neuralnet.MapUtils;
+import org.apache.commons.math3.ml.neuralnet.Neuron;
+import org.apache.commons.math3.ml.neuralnet.twod.NeuronSquareMesh2D;
+import org.apache.commons.math3.ml.distance.DistanceMeasure;
+import org.apache.commons.math3.exception.NumberIsTooSmallException;
+
+/**
+ * Visualization of high-dimensional data projection on a 2D-map.
+ * The method is described in
+ * <quote>
+ * <em>Using Smoothed Data Histograms for Cluster Visualization in Self-Organizing Maps</em>
+ * <br>
+ * by Elias Pampalk, Andreas Rauber and Dieter Merkl.
+ * </quote>
+ */
+public class SmoothedDataHistogram implements MapDataVisualization {
+ /** Smoothing parameter. */
+ private final int smoothingBins;
+ /** Distance. */
+ private final DistanceMeasure distance;
+ /** Normalization factor. */
+ private final double membershipNormalization;
+
+ /**
+ * @param smoothingBins Number of bins.
+ * @param distance Distance.
+ */
+ public SmoothedDataHistogram(int smoothingBins,
+ DistanceMeasure distance) {
+ this.smoothingBins = smoothingBins;
+ this.distance = distance;
+
+ double sum = 0;
+ for (int i = 0; i < smoothingBins; i++) {
+ sum += smoothingBins - i;
+ }
+
+ this.membershipNormalization = 1d / sum;
+ }
+
+ /**
+ * {@inheritDoc}
+ *
+ * @throws NumberIsTooSmallException if the size of the {@code map}
+ * is smaller than the number of {@link SmoothedDataHistogram(int,DistanceMeasure)
+ * smoothing bins}.
+ */
+ public double[][] computeImage(NeuronSquareMesh2D map,
+ Iterable<double[]> data) {
+ final int nR = map.getNumberOfRows();
+ final int nC = map.getNumberOfColumns();
+
+ final int mapSize = nR * nC;
+ if (mapSize < smoothingBins) {
+ throw new NumberIsTooSmallException(mapSize, smoothingBins, true);
+ }
+
+ final LocationFinder finder = new LocationFinder(map);
+
+ // Histogram bins.
+ final double[][] histo = new double[nR][nC];
+
+ for (double[] sample : data) {
+ final Neuron[] sorted = MapUtils.sort(sample,
+ map.getNetwork(),
+ distance);
+ for (int i = 0; i < smoothingBins; i++) {
+ final LocationFinder.Location loc = finder.getLocation(sorted[i]);
+ final int row = loc.getRow();
+ final int col = loc.getColumn();
+ histo[row][col] += (smoothingBins - i) * membershipNormalization;
+ }
+ }
+
+ return histo;
+ }
+}