import static java.lang.System.out;

import java.util.*;

import javastat.*;

import javastat.multivariate.*;

import static javastat.util.Argument.*;

import static javastat.util.Output.*;

import javastat.util.*;

/**

*

* <p>Example: class PCA.</p>

* <p>Data Source: S-PLUS 6 for Windows Guide to Statistics, Volume 2,

* Insightful Corporation, Seattle, WA., pp. 40-41.</p>

*/

public class PCAExample

{

public static void main(String arg[])

{

double[][] testscores = { {36, 62, 31, 76, 46, 12, 39, 30, 22, 9, 32,

40, 64, 36, 24, 50, 42, 2, 56, 59, 28, 19,

36, 54, 14},

{58, 54, 42, 78, 56, 42, 46, 51, 32, 40, 49,

62, 75, 38, 46, 50, 42, 35, 53, 72, 50, 46,

56, 57, 35},

{43, 50, 41, 69, 52, 38, 51, 54, 43, 47, 54,

51, 70, 58, 44, 54, 52, 32, 42, 70, 50, 49,

56, 59, 38},

{36, 46, 40, 66, 56, 38, 54, 52, 28, 30, 37,

40, 66, 62, 55, 52, 38, 22, 40, 66, 42, 40,

54, 62, 29},

{37, 52, 29, 81, 40, 28, 41, 32, 22, 24, 52,

49, 63, 62, 49, 51, 50, 16, 32, 62, 63, 30,

52, 58, 20} };

DataManager dm = new DataManager();

PCA testclass1 = new PCA(0.95, "covariance", testscores);

PCA testclass2 = new PCA();

double[][] principalComponents = testclass2.principalComponents(

testscores);

double[] variance = testclass2.variance(testscores);

Hashtable argument1 = new Hashtable();

argument1.put(LEVEL, 0.95);

argument1.put(COVARIANCE_CHOICE, "covariance");

StatisticalAnalysis testclass3 = new PCA(argument1, testscores).

statisticalAnalysis;

principalComponents = (double[][]) testclass3.output.get(

PRINCIPAL_COMPONENTS);

variance =

(double[]) testclass3.output.get(COMPONENT_VARIANCE);

Hashtable argument2 = new Hashtable();

PCA testclass4 = new PCA(argument2, null);

principalComponents = testclass4.principalComponents(argument2,

testscores);

variance = testclass4.variance(argument2, testscores);

}

}

Results:

Covariance Matrix:

1st component vector =0.598 0.361 0.302 0.389 0.519

2nd component vector = -0.675 -0.245 0.214 0.338 0.57

3rd component vector = -0.185 0.249 0.211 0.7 -0.607

4th component vector = 0.386 -0.829 -0.135 0.375 -0.072

variances of components = 845.481 85.041 45.388 39.188

{COMPONENT_VARIANCE=[D@1270b73,

PRINCIPAL_COMPONENTS=[[D@60aeb0}

Correlation Matrix:

1st component vector = 0.443 0.437 0.462 0.445 0.449

2nd component vector = -0.473 -0.616 0.276 0.47 0.317

3rd component vector = -0.352 0.368 0.21 0.47 -0.69

4th component vector = 0.615 -0.424 -0.338 0.476 -0.318

5th component vector = -0.279 0.339 -0.743 0.367 0.347

variances of components = 4.081 0.374 0.217 0.205 0.124

{COMPONENT_VARIANCE=[D@16caf43,

PRINCIPAL_COMPONENTS=[[D@66848c}