List of usage examples for org.apache.mahout.math Vector zSum
double zSum();
From source file:com.netease.news.classifier.naivebayes.AbstractThetaTrainer.java
License:Apache License
protected AbstractThetaTrainer(Vector weightsPerFeature, Vector weightsPerLabel, double alphaI) { Preconditions.checkNotNull(weightsPerFeature); Preconditions.checkNotNull(weightsPerLabel); this.weightsPerFeature = weightsPerFeature; this.weightsPerLabel = weightsPerLabel; this.alphaI = alphaI; perLabelThetaNormalizer = weightsPerLabel.like(); totalWeightSum = weightsPerLabel.zSum(); numFeatures = weightsPerFeature.getNumNondefaultElements(); }
From source file:com.netease.news.classifier.naivebayes.NaiveBayesModel.java
License:Apache License
public NaiveBayesModel(Matrix weightMatrix, Vector weightsPerFeature, Vector weightsPerLabel, Vector thetaNormalizer, float alphaI) { this.weightsPerLabelAndFeature = weightMatrix; this.weightsPerFeature = weightsPerFeature; this.weightsPerLabel = weightsPerLabel; this.perlabelThetaNormalizer = thetaNormalizer; this.numFeatures = weightsPerFeature.getNumNondefaultElements(); this.totalWeightSum = weightsPerLabel.zSum(); this.alphaI = alphaI; // this.minThetaNormalizer = thetaNormalizer.maxValue(); }
From source file:com.netease.news.classifier.naivebayes.WeightsMapper.java
License:Apache License
@Override protected void map(IntWritable index, VectorWritable value, Context ctx) throws IOException, InterruptedException { Vector instance = value.get(); if (weightsPerFeature == null) { weightsPerFeature = new RandomAccessSparseVector(instance.size(), instance.getNumNondefaultElements()); }/*from www. ja va2 s . c o m*/ int label = index.get(); weightsPerFeature.assign(instance, Functions.PLUS); weightsPerLabel.set(label, weightsPerLabel.get(label) + instance.zSum()); }
From source file:com.scaleunlimited.classify.vectors.TfNormalizer.java
License:Apache License
@Override public void normalize(Vector vector) { double totalCount = vector.zSum(); vector.assign(new DoubleDoubleFunction() { @Override//w w w . j a va2 s .c om public double apply(double curValue, double totalCount) { return curValue / totalCount; } }, totalCount); }
From source file:com.twitter.algebra.AlgebraCommon.java
License:Apache License
/** * @param m/* ww w . ja v a 2 s . co m*/ * matrix * @return m.viewDiagonal().zSum() */ static double trace(Matrix m) { Vector d = m.viewDiagonal(); return d.zSum(); }
From source file:edu.rosehulman.mahout.classifier.naivebayes.NaiveBayesModel.java
License:Apache License
public NaiveBayesModel(Matrix weightMatrix, Vector weightsPerFeature, Vector weightsPerLabel, Vector thetaNormalizer, float alphaI) { this.weightsPerLabelAndFeature = weightMatrix; this.weightsPerFeature = weightsPerFeature; this.weightsPerLabel = weightsPerLabel; this.perlabelThetaNormalizer = thetaNormalizer; this.numFeatures = weightsPerFeature.getNumNondefaultElements(); this.totalWeightSum = weightsPerLabel.zSum(); this.alphaI = alphaI; // this.minThetaNormalizer = thetaNormalizer.maxValue(); }
From source file:mlbench.bayes.train.WeightSummer.java
License:Apache License
@SuppressWarnings("deprecation") public static void main(String[] args) throws MPI_D_Exception, IOException, MPIException { parseArgs(args);// w w w. j a va 2s.c om HashMap<String, String> conf = new HashMap<String, String>(); initConf(conf); MPI_D.Init(args, MPI_D.Mode.Common, conf); if (MPI_D.COMM_BIPARTITE_O != null) { int rank = MPI_D.Comm_rank(MPI_D.COMM_BIPARTITE_O); int size = MPI_D.Comm_size(MPI_D.COMM_BIPARTITE_O); FileSplit[] inputs = DataMPIUtil.HDFSDataLocalLocator.getTaskInputs(MPI_D.COMM_BIPARTITE_O, (JobConf) config, inDir, rank); Vector weightsPerFeature = null; Vector weightsPerLabel = new DenseVector(labNum); for (int i = 0; i < inputs.length; i++) { FileSplit fsplit = inputs[i]; SequenceFileRecordReader<IntWritable, VectorWritable> kvrr = new SequenceFileRecordReader<>(config, fsplit); IntWritable index = kvrr.createKey(); VectorWritable value = kvrr.createValue(); while (kvrr.next(index, value)) { Vector instance = value.get(); if (weightsPerFeature == null) { weightsPerFeature = new RandomAccessSparseVector(instance.size(), instance.getNumNondefaultElements()); } int label = index.get(); weightsPerFeature.assign(instance, Functions.PLUS); weightsPerLabel.set(label, weightsPerLabel.get(label) + instance.zSum()); } } if (weightsPerFeature != null) { MPI_D.Send(new Text(WEIGHTS_PER_FEATURE), new VectorWritable(weightsPerFeature)); MPI_D.Send(new Text(WEIGHTS_PER_LABEL), new VectorWritable(weightsPerLabel)); } } else if (MPI_D.COMM_BIPARTITE_A != null) { int rank = MPI_D.Comm_rank(MPI_D.COMM_BIPARTITE_A); config.set(MAPRED_OUTPUT_DIR, outDirW); config.set("mapred.task.id", DataMPIUtil.getHadoopTaskAttemptID().toString().toString()); ((JobConf) config).setOutputKeyClass(Text.class); ((JobConf) config).setOutputValueClass(VectorWritable.class); TaskAttemptContext taskContext = new TaskAttemptContextImpl(config, DataMPIUtil.getHadoopTaskAttemptID()); SequenceFileOutputFormat<Text, VectorWritable> outfile = new SequenceFileOutputFormat<>(); FileSystem fs = FileSystem.get(config); Path output = new Path(config.get(MAPRED_OUTPUT_DIR)); FileOutputCommitter fcommitter = new FileOutputCommitter(output, taskContext); RecordWriter<Text, VectorWritable> outrw = null; try { fcommitter.setupJob(taskContext); outrw = outfile.getRecordWriter(fs, (JobConf) config, getOutputName(rank), null); } catch (IOException e) { e.printStackTrace(); System.err.println("ERROR: Please set the HDFS configuration properly\n"); System.exit(-1); } Text key = null, newKey = null; VectorWritable point = null, newPoint = null; Vector vector = null; Object[] vals = MPI_D.Recv(); while (vals != null) { newKey = (Text) vals[0]; newPoint = (VectorWritable) vals[1]; if (key == null && point == null) { } else if (!key.equals(newKey)) { outrw.write(key, new VectorWritable(vector)); vector = null; } if (vector == null) { vector = newPoint.get(); } else { vector.assign(newPoint.get(), Functions.PLUS); } key = newKey; point = newPoint; vals = MPI_D.Recv(); } if (newKey != null && newPoint != null) { outrw.write(key, new VectorWritable(vector)); } outrw.close(null); if (fcommitter.needsTaskCommit(taskContext)) { fcommitter.commitTask(taskContext); } MPI_D.COMM_BIPARTITE_A.Barrier(); if (rank == 0) { Path resOut = new Path(outDir); NaiveBayesModel naiveBayesModel = BayesUtils.readModelFromDir(new Path(outDir), config); naiveBayesModel.serialize(resOut, config); } } MPI_D.Finalize(); }
From source file:org.qcri.pca.SPCADriver.java
/** * Run PPCA sequentially given the small input Y which fit into memory This * could be used also on sampled data from a distributed matrix * // w ww .j a v a 2s .c o m * Note: this implementation ignore NaN values by replacing them with 0 * * @param conf * the configuration * @param centralY * the input matrix * @param initVal * the initial values for C and ss * @param MAX_ROUNDS * maximum number of iterations * @return the error * @throws Exception */ double runSequential(Configuration conf, Matrix centralY, InitialValues initVal, final int MAX_ROUNDS) throws Exception { Matrix centralC = initVal.C; double ss = initVal.ss; final int nRows = centralY.numRows(); final int nCols = centralY.numCols(); final int nPCs = centralC.numCols(); final float threshold = 0.00001f; log.info("tracec= " + PCACommon.trace(centralC)); //ignore NaN elements by replacing them with 0 for (int r = 0; r < nRows; r++) for (int c = 0; c < nCols; c++) if (new Double(centralY.getQuick(r, c)).isNaN()) { centralY.setQuick(r, c, 0); } //centralize and normalize the input matrix Vector mean = centralY.aggregateColumns(new VectorFunction() { @Override public double apply(Vector v) { return v.zSum() / nRows; } }); //also normalize the matrix by dividing each element by its columns range Vector spanVector = new DenseVector(nCols); for (int c = 0; c < nCols; c++) { Vector col = centralY.viewColumn(c); double max = col.maxValue(); double min = col.minValue(); double span = max - min; spanVector.setQuick(c, span); } for (int r = 0; r < nRows; r++) for (int c = 0; c < nCols; c++) centralY.set(r, c, (centralY.get(r, c) - mean.get(c)) / (spanVector.getQuick(c) != 0 ? spanVector.getQuick(c) : 1)); Matrix centralCtC = centralC.transpose().times(centralC); log.info("tracectc= " + PCACommon.trace(centralCtC)); log.info("traceinvctc= " + PCACommon.trace(inv(centralCtC))); log.info("traceye= " + PCACommon.trace(centralY)); log.info("SSSSSSSSSSSSSSSSSSSSSSSSSSSS " + ss); int count = 1; // old = Inf; double old = Double.MAX_VALUE; // -------------------------- EM Iterations // while count Matrix centralX = null; int round = 0; while (round < MAX_ROUNDS && count > 0) { round++; // Sx = inv( eye(d) + CtC/ss ); Matrix Sx = eye(nPCs).times(ss).plus(centralCtC); Sx = inv(Sx); // X = Ye*C*(Sx/ss); centralX = centralY.times(centralC).times(Sx.transpose()); // XtX = X'*X + ss * Sx; Matrix centralXtX = centralX.transpose().times(centralX).plus(Sx.times(ss)); // C = (Ye'*X) / XtX; Matrix tmpInv = inv(centralXtX); centralC = centralY.transpose().times(centralX).times(tmpInv); // CtC = C'*C; centralCtC = centralC.transpose().times(centralC); // ss = ( sum(sum( (X*C'-Ye).^2 )) + trace(XtX*CtC) - 2*xcty ) /(N*D); double norm2 = centralY.clone().assign(new DoubleFunction() { @Override public double apply(double arg1) { return arg1 * arg1; } }).zSum(); ss = norm2 + PCACommon.trace(centralXtX.times(centralCtC)); //ss3 = sum (X(i:0) * C' * Y(i,:)') DenseVector resVector = new DenseVector(nCols); double xctyt = 0; for (int i = 0; i < nRows; i++) { PCACommon.vectorTimesMatrixTranspose(centralX.viewRow(i), centralC, resVector); double res = resVector.dot(centralY.viewRow(i)); xctyt += res; } ss -= 2 * xctyt; ss /= (nRows * nCols); log.info("SSSSSSSSSSSSSSSSSSSSSSSSSSSS " + ss); double traceSx = PCACommon.trace(Sx); double traceX = PCACommon.trace(centralX); double traceSumXtX = PCACommon.trace(centralXtX); double traceC = PCACommon.trace(centralC); double traceCtC = PCACommon.trace(centralCtC); log.info("TTTTTTTTTTTTTTTTT " + traceSx + " " + traceX + " " + traceSumXtX + " " + traceC + " " + traceCtC + " " + 0); double objective = ss; double rel_ch = Math.abs(1 - objective / old); old = objective; count++; if (rel_ch < threshold && count > 5) count = 0; log.info("Objective: %.6f relative change: %.6f \n", objective, rel_ch); } double norm1Y = centralY.aggregateColumns(new VectorNorm1()).maxValue(); log.info("Norm1 of Ye is: " + norm1Y); Matrix newYerror = centralY.minus(centralX.times(centralC.transpose())); double norm1Err = newYerror.aggregateColumns(new VectorNorm1()).maxValue(); log.info("Norm1 of the reconstruction error is: " + norm1Err); initVal.C = centralC; initVal.ss = ss; return norm1Err / norm1Y; }
From source file:org.qcri.pca.SPCADriver.java
/** * Run PPCA sequentially given the small input Y which fit into memory This * could be used also on sampled data from a distributed matrix * //from w w w . j av a2 s . co m * Note: this implementation ignore NaN values by replacing them with 0 * * @param conf * the configuration * @param centralY * the input matrix * @param initVal * the initial values for C and ss * @param MAX_ROUNDS * maximum number of iterations * @return the error * @throws Exception */ double runSequential_JacobVersion(Configuration conf, Matrix centralY, InitialValues initVal, final int MAX_ROUNDS) { Matrix centralC = initVal.C;// the current implementation doesn't use initial ss of // initVal final int nRows = centralY.numRows(); final int nCols = centralY.numCols(); final int nPCs = centralC.numCols(); final float threshold = 0.00001f; log.info("tracec= " + PCACommon.trace(centralC)); // Y = Y - mean(Ye) // Also normalize the matrix for (int r = 0; r < nRows; r++) for (int c = 0; c < nCols; c++) if (new Double(centralY.getQuick(r, c)).isNaN()) { centralY.setQuick(r, c, 0); } Vector mean = centralY.aggregateColumns(new VectorFunction() { @Override public double apply(Vector v) { return v.zSum() / nRows; } }); Vector spanVector = new DenseVector(nCols); for (int c = 0; c < nCols; c++) { Vector col = centralY.viewColumn(c); double max = col.maxValue(); double min = col.minValue(); double span = max - min; spanVector.setQuick(c, span); } for (int r = 0; r < nRows; r++) for (int c = 0; c < nCols; c++) centralY.set(r, c, (centralY.get(r, c) - mean.get(c)) / (spanVector.getQuick(c) != 0 ? spanVector.getQuick(c) : 1)); // -------------------------- initialization // CtC = C'*C; Matrix centralCtC = centralC.transpose().times(centralC); log.info("tracectc= " + PCACommon.trace(centralCtC)); log.info("traceinvctc= " + PCACommon.trace(inv(centralCtC))); log.info("traceye= " + PCACommon.trace(centralY)); // X = Ye * C * inv(CtC); Matrix centralX = centralY.times(centralC).times(inv(centralCtC)); log.info("tracex= " + PCACommon.trace(centralX)); // recon = X * C'; Matrix recon = centralX.times(centralC.transpose()); log.info("tracerec= " + PCACommon.trace(recon)); // ss = sum(sum((recon-Ye).^2)) / (N*D-missing); double ss = recon.minus(centralY).assign(new DoubleFunction() { @Override public double apply(double arg1) { return arg1 * arg1; } }).zSum() / (nRows * nCols); log.info("SSSSSSSSSSSSSSSSSSSSSSSSSSSS " + ss); int count = 1; // old = Inf; double old = Double.MAX_VALUE; // -------------------------- EM Iterations // while count int round = 0; while (round < MAX_ROUNDS && count > 0) { round++; // ------------------ E-step, (co)variances // Sx = inv( eye(d) + CtC/ss ); Matrix centralSx = eye(nPCs).plus(centralCtC.divide(ss)); centralSx = inv(centralSx); // ------------------ E-step expected value // X = Ye*C*(Sx/ss); centralX = centralY.times(centralC).times(centralSx.divide(ss)); // ------------------ M-step // SumXtX = X'*X; Matrix centralSumXtX = centralX.transpose().times(centralX); // C = (Ye'*X) / (SumXtX + N*Sx ); Matrix tmpInv = inv(centralSumXtX.plus(centralSx.times(nRows))); centralC = centralY.transpose().times(centralX).times(tmpInv); // CtC = C'*C; centralCtC = centralC.transpose().times(centralC); // ss = ( sum(sum( (X*C'-Ye).^2 )) + N*sum(sum(CtC.*Sx)) + // missing*ss_old ) /(N*D); recon = centralX.times(centralC.transpose()); double error = recon.minus(centralY).assign(new DoubleFunction() { @Override public double apply(double arg1) { return arg1 * arg1; } }).zSum(); ss = error + nRows * dot(centralCtC.clone(), centralSx).zSum(); ss /= (nRows * nCols); log.info("SSSSSSSSSSSSSSSSSSSSSSSSSSSS " + ss); double traceSx = PCACommon.trace(centralSx); double traceX = PCACommon.trace(centralX); double traceSumXtX = PCACommon.trace(centralSumXtX); double traceC = PCACommon.trace(centralC); double traceCtC = PCACommon.trace(centralCtC); log.info("TTTTTTTTTTTTTTTTT " + traceSx + " " + traceX + " " + traceSumXtX + " " + traceC + " " + traceCtC + " " + 0); // objective = N*D + N*(D*log(ss) +PCACommon.trace(Sx)-log(det(Sx)) ) // +PCACommon.trace(SumXtX) -missing*log(ss_old); double objective = nRows * nCols + nRows * (nCols * Math.log(ss) + PCACommon.trace(centralSx) - Math.log(centralSx.determinant())) + PCACommon.trace(centralSumXtX); double rel_ch = Math.abs(1 - objective / old); old = objective; count++; if (rel_ch < threshold && count > 5) count = 0; System.out.printf("Objective: %.6f relative change: %.6f \n", objective, rel_ch); } double norm1Y = centralY.aggregateColumns(new VectorNorm1()).maxValue(); log.info("Norm1 of Y is: " + norm1Y); Matrix newYerror = centralY.minus(centralX.times(centralC.transpose())); double norm1Err = newYerror.aggregateColumns(new VectorNorm1()).maxValue(); log.info("Norm1 of the reconstruction error is: " + norm1Err); initVal.C = centralC; initVal.ss = ss; return norm1Err / norm1Y; }
From source file:org.qcri.sparkpca.PCAUtils.java
/** * @param m matrix/* w w w . j a v a 2 s . c o m*/ * @return trace of matrix m */ static double trace(Matrix m) { Vector d = m.viewDiagonal(); return d.zSum(); }