RobustPCA.java

import org.rosuda.JRI.REXP;
import org.rosuda.JRI.RMainLoopCallbacks;
import org.rosuda.JRI.Rengine;

/**
 * Wrapper for Robust PCA R method
 *
 * Documentation: http://cran.r-project.org/web/packages/rrcov/index.html
 *
 * In order to work in Windows, the next environmental variables have to be set:
 * PATH          = %YOUR_PATH_TO_R%\R-3.0.2\library\rJava\jri\x64;%YOUR_PATH_TO_R%\R-3.0.2\bin\x64
 * R_DOC_DIR     = %YOUR_PATH_TO_R%\R-3.0.2\doc
 * R_HOME        = %YOUR_PATH_TO_R%\R-3.0.2
 * R_INCLUDE_DIR = %YOUR_PATH_TO_R%\R-3.0.2\include
 * R_SHARE_DIR   = %YOUR_PATH_TO_R%\R-3.0.2\share
 *
 *
 *
 * Beware with Windows environmental variables extension: it's alphabetical!!
 * For example, you can't use %R_HOME% in PATH variable.
 * http://bit.ly/IK2EW2
 *
 * JRI library is provided by rJava package
 * install.packages('rJava', repos='http://cran.ma.imperial.ac.uk/')
 *
 * rrcov package has to be installed in the R library
 * install.packages('rrcov', repos='http://cran.ma.imperial.ac.uk/')
 *
 * @author Manuel Martin <draxus@gmail.com>
 *
 */
public class RobustPCA {
    private Rengine re = null; // initialized in constructor or autowired
    private int NUMBER_OF_COMPONENTS;

    public RobustPCA(){
        NUMBER_OF_COMPONENTS = 0;
    }

    public RobustPCA(int components) throws Exception{
        if (components<0){
            throw new Exception(this, "The number of components has to be positive");
        }
        NUMBER_OF_COMPONENTS = components;
    }

    private void runREngine(){
        if (!Rengine.versionCheck()) {
            System.err.println("** Version mismatch - Java files don't match library version.");
            System.exit(1);
        }

        System.out.println("Creating Rengine");
        re = new Rengine(null, false, new TextConsole());
        System.out.println("Rengine created, waiting for R");
        if (!re.waitForR()) {
            System.out.println("Cannot load R");
        }
    }

    protected void finalize() throws Throwable{
        //close R engine
        if (re!=null){
            re.eval("q()");
            re.end();
            re = null;
        }
    }

    public double[][] process(double[][] input) throws Exception{
        // Assuming that input is a matrix of size nxp
        if(input.length < input[0].length){
            throw new Exception(this, "The number of instances must be greater than the number of attributes to perform Robust PCA");
        }

        if(re == null){
            runREngine();
        }
        else{ //restart REngine for re-training
            re.eval("q()");
            re.end();
            re = null;
            runREngine();
        }

        // Create the matrix in R (except the predicted variables)
        re.eval("m <- " + matrixToR(input));

        // Load library rrcov
        REXP loaded = re.eval("library(rrcov)",false);
        if(loaded==null){
            throw new Exception(this, "The library rrcov has not been found");
        }

        // Remove missing values
        re.eval("m <- na.omit(m)");

        // Robust PCA
        REXP pca = re.eval("pca <- PcaCov(m, k="+NUMBER_OF_COMPONENTS+")"); //don't need to store in Java because REngine is the same
        if(pca==null){
            throw new Exception(this, "There was an error computing PcaCov");
        }

        REXP x = re.eval("scores <- scale(m, center=pca@center, scale=FALSE) %*% pca@loadings");
        double newData[][] = x.asDoubleMatrix();

        // Clean workspace
        re.eval("rm(m)");

        return newData;
    }

    private String matrixToR(double[][] matrix){

        String matrixString = "";
        for(int i=0; i<matrix.length; i++){
            for(int j=0; j<matrix[i].length; j++){
                if (Double.isNaN((Double) matrix[i][j])){ //missing value
                    matrixString += "NA,";
                }
                else{
                    matrixString += String.valueOf(matrix.[i][j]) + ",";
                }

            }
        }
        matrixString = matrixString.substring(0, matrixString.length()-1); //remove the last comma

        // Matrix creation in R
        return "matrix(c("+matrixString+"), nrow="+matrix.length+", ncol="+matrix[0].length+", byrow=TRUE)";
    }
}


class TextConsole implements RMainLoopCallbacks{
    public void rWriteConsole(Rengine re, String text, int oType) {
        System.out.print(text);
    }

    public void rBusy(Rengine re, int which) {
        System.out.println("rBusy("+which+")");
    }

    public String rReadConsole(Rengine re, String prompt, int addToHistory) {
        System.out.print(prompt);
        try {
            BufferedReader br=new BufferedReader(new InputStreamReader(System.in));
            String s=br.readLine();
            return (s==null||s.length()==0)?s:s+"\n";
        } catch (Exception e) {
            System.out.println("jriReadConsole exception: "+e.getMessage());
        }
        return null;
    }

    public void rShowMessage(Rengine re, String message) {
        System.out.println("rShowMessage \""+message+"\"");
    }

    public String rChooseFile(Rengine re, int newFile) {
        FileDialog fd = new FileDialog(new Frame(), (newFile==0)?"Select a file":"Select a new file", (newFile==0)?FileDialog.LOAD:FileDialog.SAVE);
        fd.show();
        String res=null;
        if (fd.getDirectory()!=null) res=fd.getDirectory();
        if (fd.getFile()!=null) res=(res==null)?fd.getFile():(res+fd.getFile());
        return res;
    }

    public void   rFlushConsole (Rengine re) {
    }

    public void   rLoadHistory  (Rengine re, String filename) {
    }

    public void   rSaveHistory  (Rengine re, String filename) {
    }
}