X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FPCA.java;h=47f2d0d8c1e6649cbcd4945e938c650f9765e53b;hb=797df64fa2a0a30773d0f48f5494d4155e5a8be3;hp=c0d264cebf820f5df72f95610bb8f4c5169f3231;hpb=825d80b210b531086eb505419a4034d4f6696be3;p=jalview.git diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java index c0d264c..47f2d0d 100755 --- a/src/jalview/analysis/PCA.java +++ b/src/jalview/analysis/PCA.java @@ -1,191 +1,255 @@ -// PCA.java with an irrelevant comment -// PCA.java with two irrelevant comments -package jalview.analysis; - -import jalview.math.*; -import jalview.datamodel.*; -import jalview.util.*; - -import java.awt.*; -import java.io.*; - -public class PCA implements Runnable { - Matrix m; - Matrix symm; - Matrix m2; - - double[] eigenvalue; - Matrix eigenvector; - - public PCA(Matrix m) { - this.m = m; - } - - public PCA(SequenceI[] s) { - Runtime rt = Runtime.getRuntime(); - - BinarySequence[] bs = new BinarySequence[s.length]; - int ii = 0; - while (ii < s.length && s[ii] != null) { - - bs[ii] = new BinarySequence(s[ii]); - bs[ii].encode(); - ii++; - } - - BinarySequence[] bs2 = new BinarySequence[s.length]; - ii = 0; - while (ii < s.length && s[ii] != null) { - - bs2[ii] = new BinarySequence(s[ii]); - bs2[ii].blosumEncode(); - ii++; - } - - - //System.out.println("Created binary encoding"); - //printMemory(rt); - - int count=0; - while (count < bs.length && bs[count] != null) { - count++; - } - double[][] seqmat = new double[count][bs[0].getDBinary().length]; - double[][] seqmat2 = new double[count][bs2[0].getDBinary().length]; - int i=0; - while (i < count) { - seqmat[i] = bs[i].getDBinary(); - seqmat2[i] = bs2[i].getDBinary(); - i++; - } - //System.out.println("Created array"); - //printMemory(rt); - // System.out.println(" --- Original matrix ---- "); - m = new Matrix(seqmat,count,bs[0].getDBinary().length); - m2 = new Matrix(seqmat2,count,bs2[0].getDBinary().length); - - //System.out.println("Created matrix"); - printMemory(rt); - } - - public static void printMemory(Runtime rt) { - System.out.println("Free memory = " + rt.freeMemory()); - } - - public Matrix getM() { - return m; - } - - public double[] getEigenvector(int i) { - return eigenvector.getColumn(i); - } - - public double getEigenvalue(int i) { - return eigenvector.d[i]; - } - public float[][] getComponents(int l, int n, int mm) { - return getComponents(l,n,mm,1); - } - public float[][] getComponents(int l, int n, int mm, float factor) { - float[][] out = new float[m.rows][3]; - - for (int i = 0; i < m.rows;i++) { - out[i][0] = (float)component(i,l)*factor; - out[i][1] = (float)component(i,n)*factor; - out[i][2] = (float)component(i,mm)*factor; - } - return out; - } - - public double[] component(int n) { - // n = index of eigenvector - double[] out = new double[m.rows]; - - for (int i=0; i < m.rows; i++) { - out[i] = component(i,n); - } - return out; - } - public double component(int row, int n) { - double out = 0.0; - - for (int i = 0; i < symm.cols; i++) { - out += symm.value[row][i] * eigenvector.value[i][n]; - } - return out/eigenvector.d[n]; - } - - public void checkEigenvector(int n,PrintStream ps) { - ps.println(" --- Eigenvector " + n + " --- "); - - double[] eigenv = eigenvector.getColumn(n); - - for (int i=0; i < eigenv.length;i++) { - Format.print(ps,"%15.4f",eigenv[i]); - } - - System.out.println(); - - double[] neigenv = symm.vectorPostMultiply(eigenv); - System.out.println(" --- symmat * eigenv / lambda --- "); - if (eigenvector.d[n] > 1e-4) { - for (int i=0; i < neigenv.length;i++) { - Format.print(System.out,"%15.4f",neigenv[i]/eigenvector.d[n]); - } - } - System.out.println(); - } - - public void run() { - Matrix mt = m.transpose(); - // System.out.println(" --- OrigT * Orig ---- "); - eigenvector = mt.preMultiply(m2); - // eigenvector.print(System.out); - symm = eigenvector.copy(); - - //TextArea ta = new TextArea(25,72); - //TextAreaPrintStream taps = new TextAreaPrintStream(System.out,ta); - //Frame f = new Frame("PCA output"); - //f.resize(500,500); - //f.setLayout(new BorderLayout()); - //f.add("Center",ta); - //f.show(); - //symm.print(taps); - long tstart = System.currentTimeMillis(); - eigenvector.tred(); - long tend = System.currentTimeMillis(); - //taps.println("Time take for tred = " + (tend-tstart) + "ms"); - //taps.println(" ---Tridiag transform matrix ---"); - - //taps.println(" --- D vector ---"); - //eigenvector.printD(taps); - //taps.println(); - //taps.println(" --- E vector ---"); - // eigenvector.printE(taps); - //taps.println(); - - // Now produce the diagonalization matrix - tstart = System.currentTimeMillis(); - eigenvector.tqli(); - tend = System.currentTimeMillis(); - //System.out.println("Time take for tqli = " + (tend-tstart) + " ms"); - - //System.out.println(" --- New diagonalization matrix ---"); - - //System.out.println(" --- Eigenvalues ---"); - //eigenvector.printD(taps); - - //System.out.println(); - - // for (int i=0; i < eigenvector.cols; i++) { - // checkEigenvector(i,taps); - // taps.println(); - // } - - // taps.println(); - // taps.println("Transformed sequences = "); - // Matrix trans = m.preMultiply(eigenvector); - // trans.print(System.out); - } - -} +/* + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7) + * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle + * + * This file is part of Jalview. + * + * Jalview is free software: you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. + * + * Jalview 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 General Public License for more details. + * + * You should have received a copy of the GNU General Public License along with Jalview. If not, see . + */ +package jalview.analysis; + +import java.io.*; + +import jalview.datamodel.*; +import jalview.math.*; + +/** + * Performs Principal Component Analysis on given sequences + * + * @author $author$ + * @version $Revision$ + */ +public class PCA implements Runnable +{ + Matrix m; + + Matrix symm; + + Matrix m2; + + double[] eigenvalue; + + Matrix eigenvector; + + StringBuffer details = new StringBuffer(); + + /** + * Creates a new PCA object. + * + * @param s + * Set of sequences to perform PCA on + */ + public PCA(String[] s) + { + + BinarySequence[] bs = new BinarySequence[s.length]; + int ii = 0; + + while ((ii < s.length) && (s[ii] != null)) + { + bs[ii] = new BinarySequence(s[ii]); + bs[ii].encode(); + ii++; + } + + BinarySequence[] bs2 = new BinarySequence[s.length]; + ii = 0; + + while ((ii < s.length) && (s[ii] != null)) + { + bs2[ii] = new BinarySequence(s[ii]); + bs2[ii].blosumEncode(); + ii++; + } + + // System.out.println("Created binary encoding"); + // printMemory(rt); + int count = 0; + + while ((count < bs.length) && (bs[count] != null)) + { + count++; + } + + double[][] seqmat = new double[count][bs[0].getDBinary().length]; + double[][] seqmat2 = new double[count][bs2[0].getDBinary().length]; + int i = 0; + + while (i < count) + { + seqmat[i] = bs[i].getDBinary(); + seqmat2[i] = bs2[i].getDBinary(); + i++; + } + + // System.out.println("Created array"); + // printMemory(rt); + // System.out.println(" --- Original matrix ---- "); + m = new Matrix(seqmat, count, bs[0].getDBinary().length); + m2 = new Matrix(seqmat2, count, bs2[0].getDBinary().length); + + } + + /** + * Returns the matrix used in PCA calculation + * + * @return java.math.Matrix object + */ + + public Matrix getM() + { + return m; + } + + /** + * Returns Eigenvalue + * + * @param i + * Index of diagonal within matrix + * + * @return Returns value of diagonal from matrix + */ + public double getEigenvalue(int i) + { + return eigenvector.d[i]; + } + + /** + * DOCUMENT ME! + * + * @param l + * DOCUMENT ME! + * @param n + * DOCUMENT ME! + * @param mm + * DOCUMENT ME! + * @param factor + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public float[][] getComponents(int l, int n, int mm, float factor) + { + float[][] out = new float[m.rows][3]; + + for (int i = 0; i < m.rows; i++) + { + out[i][0] = (float) component(i, l) * factor; + out[i][1] = (float) component(i, n) * factor; + out[i][2] = (float) component(i, mm) * factor; + } + + return out; + } + + /** + * DOCUMENT ME! + * + * @param n + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public double[] component(int n) + { + // n = index of eigenvector + double[] out = new double[m.rows]; + + for (int i = 0; i < m.rows; i++) + { + out[i] = component(i, n); + } + + return out; + } + + /** + * DOCUMENT ME! + * + * @param row + * DOCUMENT ME! + * @param n + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + double component(int row, int n) + { + double out = 0.0; + + for (int i = 0; i < symm.cols; i++) + { + out += (symm.value[row][i] * eigenvector.value[i][n]); + } + + return out / eigenvector.d[n]; + } + + public String getDetails() + { + return details.toString(); + } + + /** + * DOCUMENT ME! + */ + public void run() + { + Matrix mt = m.transpose(); + + details.append(" --- OrigT * Orig ---- \n"); + // eigenvector = mt.preMultiply(m); // standard seqspace comparison matrix + eigenvector = mt.preMultiply(m2); // jalview variation on seqsmace method + + PrintStream ps = new PrintStream(System.out) + { + public void print(String x) + { + details.append(x); + } + + public void println() + { + details.append("\n"); + } + }; + + eigenvector.print(ps); + + symm = eigenvector.copy(); + + eigenvector.tred(); + + details.append(" ---Tridiag transform matrix ---\n"); + details.append(" --- D vector ---\n"); + eigenvector.printD(ps); + ps.println(); + details.append("--- E vector ---\n"); + eigenvector.printE(ps); + ps.println(); + + // Now produce the diagonalization matrix + eigenvector.tqli(); + + details.append(" --- New diagonalization matrix ---\n"); + eigenvector.print(ps); + details.append(" --- Eigenvalues ---\n"); + eigenvector.printD(ps); + ps.println(); + /* + * for (int seq=0;seq