Author: luc
Date: Sat Nov 20 21:31:21 2010
New Revision: 1037332
URL: http://svn.apache.org/viewvc?rev=1037332&view=rev
Log:
Added a normalization feature to transform samples so they have zero mean and
unit standard deviation
Jira: MATH-426
Modified:
commons/proper/math/branches/MATH_2_X/src/main/java/org/apache/commons/math/stat/StatUtils.java
commons/proper/math/branches/MATH_2_X/src/site/xdoc/changes.xml
commons/proper/math/branches/MATH_2_X/src/test/java/org/apache/commons/math/stat/StatUtilsTest.java
Modified:
commons/proper/math/branches/MATH_2_X/src/main/java/org/apache/commons/math/stat/StatUtils.java
URL:
http://svn.apache.org/viewvc/commons/proper/math/branches/MATH_2_X/src/main/java/org/apache/commons/math/stat/StatUtils.java?rev=1037332&r1=1037331&r2=1037332&view=diff
==============================================================================
---
commons/proper/math/branches/MATH_2_X/src/main/java/org/apache/commons/math/stat/StatUtils.java
(original)
+++
commons/proper/math/branches/MATH_2_X/src/main/java/org/apache/commons/math/stat/StatUtils.java
Sat Nov 20 21:31:21 2010
@@ -18,6 +18,7 @@ package org.apache.commons.math.stat;
import org.apache.commons.math.MathRuntimeException;
import org.apache.commons.math.exception.util.LocalizedFormats;
+import org.apache.commons.math.stat.descriptive.DescriptiveStatistics;
import org.apache.commons.math.stat.descriptive.UnivariateStatistic;
import org.apache.commons.math.stat.descriptive.moment.GeometricMean;
import org.apache.commons.math.stat.descriptive.moment.Mean;
@@ -628,5 +629,34 @@ public final class StatUtils {
}
return (sum1 - (sum2 * sum2 / n)) / (n - 1);
}
+
+
+ /**
+ * Normalize (standardize) the series, so in the end it is having a
mean of 0 and a standard deviation of 1.
+ *
+ * @param sample sample to normalize
+ * @return normalized (standardized) sample
+ */
+ public static double[] normalize(final double[] sample) {
+ DescriptiveStatistics stats = new DescriptiveStatistics();
+
+ // Add the data from the series to stats
+ for (int i = 0; i < sample.length; i++) {
+ stats.addValue(sample[i]);
+ }
+
+ // Compute mean and standard deviation
+ double mean = stats.getMean();
+ double standardDeviation = stats.getStandardDeviation();
+
+ // initialize the standardizedSample, which has the same length
as the sample
+ double[] standardizedSample = new double[sample.length];
+
+ for (int i = 0; i < sample.length; i++) {
+ // z = (x- mean)/standardDeviation
+ standardizedSample[i] = (sample[i] - mean) /
standardDeviation;
+ }
+ return standardizedSample;
+ }
}
Modified: commons/proper/math/branches/MATH_2_X/src/site/xdoc/changes.xml
URL:
http://svn.apache.org/viewvc/commons/proper/math/branches/MATH_2_X/src/site/xdoc/changes.xml?rev=1037332&r1=1037331&r2=1037332&view=diff
==============================================================================
--- commons/proper/math/branches/MATH_2_X/src/site/xdoc/changes.xml (original)
+++ commons/proper/math/branches/MATH_2_X/src/site/xdoc/changes.xml Sat Nov 20
21:31:21 2010
@@ -52,6 +52,9 @@ The <action> type attribute can be add,u
If the output is not quite correct, check for invisible trailing spaces!
-->
<release version="2.2" date="TBD" description="TBD">
+ <action dev="luc" type="fix" issue="MATH-426" due-to="Erik van Ingen">
+ Added a normalization feature to transform samples so they have zero
mean and unit standard deviation
+ </action>
<action dev="erans" type="add" issue="MATH-440">
Created "MathUserException" class to convey cause of failure between
layers of user code separated by a layer of Commons-Math code.
Deprecated
Modified:
commons/proper/math/branches/MATH_2_X/src/test/java/org/apache/commons/math/stat/StatUtilsTest.java
URL:
http://svn.apache.org/viewvc/commons/proper/math/branches/MATH_2_X/src/test/java/org/apache/commons/math/stat/StatUtilsTest.java?rev=1037332&r1=1037331&r2=1037332&view=diff
==============================================================================
---
commons/proper/math/branches/MATH_2_X/src/test/java/org/apache/commons/math/stat/StatUtilsTest.java
(original)
+++
commons/proper/math/branches/MATH_2_X/src/test/java/org/apache/commons/math/stat/StatUtilsTest.java
Sat Nov 20 21:31:21 2010
@@ -19,6 +19,7 @@ package org.apache.commons.math.stat;
import junit.framework.TestCase;
import org.apache.commons.math.TestUtils;
+import org.apache.commons.math.stat.descriptive.DescriptiveStatistics;
import org.apache.commons.math.util.FastMath;
/**
@@ -420,4 +421,48 @@ public final class StatUtilsTest extends
assertEquals(FastMath.exp(0.5 * StatUtils.sumLog(test, 0, 2)),
StatUtils.geometricMean(test, 0, 2), Double.MIN_VALUE);
}
+
+
+ /**
+ * Run the test with the values 50 and 100 and assume standardized
values
+ */
+
+ public void testNormalize1() {
+ double sample[] = { 50, 100 };
+ double expectedSample[] = { -25 / Math.sqrt(1250), 25 /
Math.sqrt(1250) };
+ double[] out = StatUtils.normalize(sample);
+ for (int i = 0; i < out.length; i++) {
+ assertEquals(out[i], expectedSample[i]);
+ }
+
+ }
+
+ /**
+ * Run with 77 random values, assuming that the outcome has a mean of 0
and a standard deviation of 1 with a
+ * precision of 1E-10.
+ */
+
+ public void testNormalize2() {
+ // create an sample with 77 values
+ int length = 77;
+ double sample[] = new double[length];
+ for (int i = 0; i < length; i++) {
+ sample[i] = Math.random();
+ }
+ // normalize this sample
+ double standardizedSample[] = StatUtils.normalize(sample);
+
+ DescriptiveStatistics stats = new DescriptiveStatistics();
+ // Add the data from the array
+ for (int i = 0; i < length; i++) {
+ stats.addValue(standardizedSample[i]);
+ }
+ // the calculations do have a limited precision
+ double distance = 1E-10;
+ // check the mean an standard deviation
+ assertEquals(0.0, stats.getMean(), distance);
+ assertEquals(1.0, stats.getStandardDeviation(), distance);
+
+ }
+
}
