List of usage examples for org.apache.mahout.math Matrix viewRow
Vector viewRow(int row);
From source file:com.innometrics.integration.app.recommender.ml.als.AlternatingLeastSquaresSolver.java
License:Apache License
private static Matrix miTimesMiTransposePlusLambdaTimesNuiTimesE(Matrix MiIi, double lambda, int nui) { double lambdaTimesNui = lambda * nui; int rows = MiIi.numRows(); double[][] result = new double[rows][rows]; for (int i = 0; i < rows; i++) { for (int j = i; j < rows; j++) { double dot = MiIi.viewRow(i).dot(MiIi.viewRow(j)); if (i != j) { result[i][j] = dot;/*from w w w.j ava 2s .com*/ result[j][i] = dot; } else { result[i][i] = dot + lambdaTimesNui; } } } return new DenseMatrix(result, true); }
From source file:com.innometrics.integration.app.recommender.ml.als.ImplicitFeedbackAlternatingLeastSquaresSolver.java
License:Apache License
/** Y' (Cu - I) Y + I */ private Matrix getYtransponseCuMinusIYPlusLambdaI(Vector userRatings) { Preconditions.checkArgument(userRatings.isSequentialAccess(), "need sequential access to ratings!"); /* (Cu -I) Y */ OpenIntObjectHashMap<Vector> CuMinusIY = new OpenIntObjectHashMap<Vector>( userRatings.getNumNondefaultElements()); for (Element e : userRatings.nonZeroes()) { CuMinusIY.put(e.index(), Y.get(e.index()).times(confidence(e.get()) - 1)); }// w ww .j a va 2s. c o m Matrix YtransponseCuMinusIY = new DenseMatrix(numFeatures, numFeatures); /* Y' (Cu -I) Y by outer products */ for (Element e : userRatings.nonZeroes()) { for (Vector.Element feature : Y.get(e.index()).all()) { Vector partial = CuMinusIY.get(e.index()).times(feature.get()); YtransponseCuMinusIY.viewRow(feature.index()).assign(partial, Functions.PLUS); } } /* Y' (Cu - I) Y + I add lambda on the diagonal */ for (int feature = 0; feature < numFeatures; feature++) { YtransponseCuMinusIY.setQuick(feature, feature, YtransponseCuMinusIY.getQuick(feature, feature) + lambda); } return YtransponseCuMinusIY; }
From source file:com.skp.experiment.cf.als.hadoop.ParallelALSFactorizationJobTest.java
License:Apache License
/** * small integration test that runs the full job * * <pre>//from w ww . j av a 2 s . co m * * user-item-matrix * * burger hotdog berries icecream * dog 5 5 2 - * rabbit 2 - 3 5 * cow - 5 - 3 * donkey 3 - - 5 * * </pre> */ @Test public void completeJobToyExample() throws Exception { Double na = Double.NaN; Matrix preferences = new SparseRowMatrix(4, 4, new Vector[] { new DenseVector(new double[] { 5.0, 5.0, 2.0, na }), new DenseVector(new double[] { 2.0, na, 3.0, 5.0 }), new DenseVector(new double[] { na, 5.0, na, 3.0 }), new DenseVector(new double[] { 3.0, na, na, 5.0 }) }); writeLines(inputFile, preferencesAsText(preferences)); indexSizeFile.deleteOnExit(); writeLines(indexSizeFile, "0,4\n1,4"); ParallelALSFactorizationJob alsFactorization = new ParallelALSFactorizationJob(); alsFactorization.setConf(conf); int numFeatures = 3; int numIterations = 5; double lambda = 0.065; alsFactorization .run(new String[] { "--input", inputFile.getAbsolutePath(), "--output", outputDir.getAbsolutePath(), "--tempDir", tmpDir.getAbsolutePath(), "--lambda", String.valueOf(lambda), "--numFeatures", String.valueOf(numFeatures), "--numIterations", String.valueOf(numIterations), "--indexSizes", indexSizeFile.toString(), "--useTransform", "false" }); Matrix u = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(), "U/part-m-00000"), preferences.numRows(), numFeatures); Matrix m = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(), "M/part-m-00000"), preferences.numCols(), numFeatures); StringBuilder info = new StringBuilder(); info.append("\nA - users x items\n\n"); info.append(MathHelper.nice(preferences)); info.append("\nU - users x features\n\n"); info.append(MathHelper.nice(u)); info.append("\nM - items x features\n\n"); info.append(MathHelper.nice(m)); Matrix Ak = u.times(m.transpose()); info.append("\nAk - users x items\n\n"); info.append(MathHelper.nice(Ak)); info.append('\n'); log.info(info.toString()); RunningAverage avg = new FullRunningAverage(); Iterator<MatrixSlice> sliceIterator = preferences.iterateAll(); while (sliceIterator.hasNext()) { MatrixSlice slice = sliceIterator.next(); Iterator<Vector.Element> elementIterator = slice.vector().iterateNonZero(); while (elementIterator.hasNext()) { Vector.Element e = elementIterator.next(); if (!Double.isNaN(e.get())) { double pref = e.get(); double estimate = u.viewRow(slice.index()).dot(m.viewRow(e.index())); double err = pref - estimate; avg.addDatum(err * err); log.info("Comparing preference of user [{}] towards item [{}], was [{}] estimate is [{}]", new Object[] { slice.index(), e.index(), pref, estimate }); } } } double rmse = Math.sqrt(avg.getAverage()); log.info("RMSE: {}", rmse); assertTrue(rmse < 0.2); }
From source file:com.skp.experiment.cf.als.hadoop.ParallelALSFactorizationJobTest.java
License:Apache License
@Test public void completeJobImplicitToyExample() throws Exception { Matrix observations = new SparseRowMatrix(4, 4, new Vector[] { new DenseVector(new double[] { 5.0, 5.0, 2.0, 0 }), new DenseVector(new double[] { 2.0, 0, 3.0, 5.0 }), new DenseVector(new double[] { 0, 5.0, 0, 3.0 }), new DenseVector(new double[] { 3.0, 0, 0, 5.0 }) }); Matrix preferences = new SparseRowMatrix(4, 4, new Vector[] { new DenseVector(new double[] { 1.0, 1.0, 1.0, 0 }), new DenseVector(new double[] { 1.0, 0, 1.0, 1.0 }), new DenseVector(new double[] { 0, 1.0, 0, 1.0 }), new DenseVector(new double[] { 1.0, 0, 0, 1.0 }) }); writeLines(inputFile, preferencesAsText(observations)); writeLines(indexSizeFile, "0,4\n1,4"); ParallelALSFactorizationJob alsFactorization = new ParallelALSFactorizationJob(); alsFactorization.setConf(conf);//from ww w . ja v a2s. c o m int numFeatures = 3; int numIterations = 5; double lambda = 0.065; double alpha = 20; alsFactorization.run(new String[] { "--input", inputFile.getAbsolutePath(), "--output", outputDir.getAbsolutePath(), "--tempDir", tmpDir.getAbsolutePath(), "--lambda", String.valueOf(lambda), "--implicitFeedback", String.valueOf(true), "--alpha", String.valueOf(alpha), "--numFeatures", String.valueOf(numFeatures), "--numIterations", String.valueOf(numIterations), "--indexSizes", indexSizeFile.toString(), "--useTransform", "false" }); Matrix u = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(), "U/part-m-00000"), observations.numRows(), numFeatures); Matrix m = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(), "M/part-m-00000"), observations.numCols(), numFeatures); StringBuilder info = new StringBuilder(); info.append("\nObservations - users x items\n"); info.append(MathHelper.nice(observations)); info.append("\nA - users x items\n\n"); info.append(MathHelper.nice(preferences)); info.append("\nU - users x features\n\n"); info.append(MathHelper.nice(u)); info.append("\nM - items x features\n\n"); info.append(MathHelper.nice(m)); Matrix Ak = u.times(m.transpose()); info.append("\nAk - users x items\n\n"); info.append(MathHelper.nice(Ak)); info.append('\n'); log.info(info.toString()); RunningAverage avg = new FullRunningAverage(); Iterator<MatrixSlice> sliceIterator = preferences.iterateAll(); while (sliceIterator.hasNext()) { MatrixSlice slice = sliceIterator.next(); for (Vector.Element e : slice.vector()) { if (!Double.isNaN(e.get())) { double pref = e.get(); double estimate = u.viewRow(slice.index()).dot(m.viewRow(e.index())); double confidence = 1 + alpha * observations.getQuick(slice.index(), e.index()); double err = confidence * (pref - estimate) * (pref - estimate); avg.addDatum(err); log.info( "Comparing preference of user [{}] towards item [{}], was [{}] with confidence [{}] " + "estimate is [{}]", new Object[] { slice.index(), e.index(), pref, confidence, estimate }); } } } double rmse = Math.sqrt(avg.getAverage()); log.info("RMSE: {}", rmse); assertTrue(rmse < 0.4); }
From source file:com.skp.experiment.common.MathHelper.java
License:Apache License
public static String nice(Matrix matrix) { StringBuilder info = new StringBuilder(); for (int n = 0; n < matrix.numRows(); n++) { info.append(nice(matrix.viewRow(n))).append('\n'); }//from w w w . j a v a 2 s .co m return info.toString(); }
From source file:com.skp.experiment.math.als.hadoop.DistributedImplicitFeedbackAlternatingLeastSquaresSolver.java
License:Apache License
public Vector solve(Vector userRatings) throws IOException { Preconditions.checkArgument(userRatings.isSequentialAccess(), "need sequential access to ratings!"); //Matrix sparseY = getSparseMatrix(userRatings); getSparseMatrix(userRatings);/* w ww. j a va 2 s. co m*/ /* Y' (Cu - I) Y + I */ /* Y' Cu p(u) */ Vector YtransponseCuPu = new DenseVector(numFeatures); /* (Cu -I) Y */ OpenIntObjectHashMap<Vector> CuMinusIY = new OpenIntObjectHashMap<Vector>(); Iterator<Vector.Element> ratings = userRatings.iterateNonZero(); while (ratings.hasNext()) { Vector.Element e = ratings.next(); CuMinusIY.put(e.index(), sparseY.get(e.index()).times(confidence(e.get()) - 1)); /* Y' Cu p(u) */ YtransponseCuPu.assign(sparseY.get(e.index()).times(confidence(e.get())), Functions.PLUS); } Matrix YtransponseCuMinusIY = new DenseMatrix(numFeatures, numFeatures); /* Y' (Cu -I) Y by outer products */ ratings = userRatings.iterateNonZero(); while (ratings.hasNext()) { Vector.Element e = ratings.next(); for (Vector.Element feature : sparseY.get(e.index())) { Vector partial = CuMinusIY.get(e.index()).times(feature.get()); YtransponseCuMinusIY.viewRow(feature.index()).assign(partial, Functions.PLUS); } } /* Y' (Cu - I) Y + I add lambda on the diagonal */ for (int feature = 0; feature < numFeatures; feature++) { YtransponseCuMinusIY.setQuick(feature, feature, YtransponseCuMinusIY.getQuick(feature, feature) + lambda); } Matrix YtransposeCuPu = columnVectorAsMatrix(YtransponseCuPu); return solve(YtransposeY.plus(YtransponseCuMinusIY), YtransposeCuPu); //return YtransponseCuMinusIY; }
From source file:com.skp.experiment.math.als.hadoop.ImplicitFeedbackAlternatingLeastSquaresReasonSolver.java
License:Apache License
/** Y' (Cu - I) Y + I */ private Matrix YtransponseCuMinusIYPlusLambdaI(Vector userRatings) { Preconditions.checkArgument(userRatings.isSequentialAccess(), "need sequential access to ratings!"); /* (Cu -I) Y */ OpenIntObjectHashMap<Vector> CuMinusIY = new OpenIntObjectHashMap<Vector>(); Iterator<Vector.Element> ratings = userRatings.iterateNonZero(); while (ratings.hasNext()) { Vector.Element e = ratings.next(); CuMinusIY.put(e.index(), Y.get(e.index()).times(confidence(e.get()) - 1)); }//from www . jav a 2s . com Matrix YtransponseCuMinusIY = new DenseMatrix(numFeatures, numFeatures); /* Y' (Cu -I) Y by outer products */ ratings = userRatings.iterateNonZero(); while (ratings.hasNext()) { Vector.Element e = ratings.next(); for (Vector.Element feature : Y.get(e.index())) { Vector partial = CuMinusIY.get(e.index()).times(feature.get()); YtransponseCuMinusIY.viewRow(feature.index()).assign(partial, Functions.PLUS); } } /* Y' (Cu - I) Y + I add lambda on the diagonal */ for (int feature = 0; feature < numFeatures; feature++) { YtransponseCuMinusIY.setQuick(feature, feature, YtransponseCuMinusIY.getQuick(feature, feature) + lambda); } return YtransponseCuMinusIY; }
From source file:com.skp.experiment.math.als.hadoop.ImplicitFeedbackAlternatingLeastSquaresSolver.java
License:Apache License
/** Y' (Cu - I) Y + I */ private Matrix YtransponseCuMinusIYPlusLambdaI(Vector userRatings) { Preconditions.checkArgument(userRatings.isSequentialAccess(), "need sequential access to ratings!"); /* (Cu -I) Y */ OpenIntObjectHashMap<Vector> CuMinusIY = new OpenIntObjectHashMap<Vector>(); Iterator<Vector.Element> ratings = userRatings.iterateNonZero(); while (ratings.hasNext()) { Vector.Element e = ratings.next(); CuMinusIY.put(e.index(), Y.viewRow(e.index()).times(confidence(e.get()) - 1)); //CuMinusIY.put(e.index(), Y.get(e.index()).times(confidence(e.get()) - 1)); }// w w w .jav a 2s . c om Matrix YtransponseCuMinusIY = new DenseMatrix(numFeatures, numFeatures); /* Y' (Cu -I) Y by outer products */ ratings = userRatings.iterateNonZero(); while (ratings.hasNext()) { Vector.Element e = ratings.next(); //for (Vector.Element feature : Y.get(e.index())) { for (Vector.Element feature : Y.viewRow(e.index())) { Vector partial = CuMinusIY.get(e.index()).times(feature.get()); YtransponseCuMinusIY.viewRow(feature.index()).assign(partial, Functions.PLUS); } } /* Y' (Cu - I) Y + I add lambda on the diagonal */ for (int feature = 0; feature < numFeatures; feature++) { YtransponseCuMinusIY.setQuick(feature, feature, YtransponseCuMinusIY.getQuick(feature, feature) + lambda); } return YtransponseCuMinusIY; }
From source file:com.twitter.algebra.AlgebraCommon.java
License:Apache License
/** * Multiply a vector with transpose of a matrix * @param vector V//from ww w. ja va 2 s. c o m * @param transpose of matrix M * @param resVector will be filled with V * M * @return V * M */ public static Vector vectorTimesMatrixTranspose(Vector vector, Matrix matrixTranspose, Vector resVector) { int nCols = matrixTranspose.numRows(); for (int c = 0; c < nCols; c++) { Vector col = matrixTranspose.viewRow(c); double resDouble = 0d; boolean hasNonZero = col.getNumNondefaultElements() != 0; if (hasNonZero) resDouble = vector.dot(col); resVector.set(c, resDouble); } return resVector; }
From source file:com.twitter.algebra.AlgebraCommon.java
License:Apache License
/** * Convert an in-memory representation of a matrix to a distributed MapDir * format. It then can be used in distributed jobs * /*w ww . j av a 2 s. c o m*/ * @param oriMatrix * @return path that will contain the matrix files * @throws Exception */ public static DistributedRowMatrix toMapDir(Matrix origMatrix, Path outPath, Path tmpPath, String label) throws Exception { Configuration conf = new Configuration(); Path outputDir = new Path(outPath, label + origMatrix.numRows() + "x" + origMatrix.numCols()); FileSystem fs = FileSystem.get(outputDir.toUri(), conf); if (!fs.exists(outputDir)) { Path mapDir = new Path(outputDir, "matrix-k-0"); Path outputFile = new Path(mapDir, "data"); @SuppressWarnings("deprecation") SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf, outputFile, IntWritable.class, VectorWritable.class); VectorWritable vectorw = new VectorWritable(); IntWritable intw = new IntWritable(); try { for (int r = 0; r < origMatrix.numRows(); r++) { Vector vector = origMatrix.viewRow(r); vectorw.set(vector); intw.set(r); writer.append(intw, vectorw); } } finally { writer.close(); } MapFile.fix(fs, mapDir, IntWritable.class, VectorWritable.class, false, conf); } else { log.warn("----------- Skip matrix " + outputDir + " - already exists"); } DistributedRowMatrix dMatrix = new DistributedRowMatrix(outputDir, tmpPath, origMatrix.numRows(), origMatrix.numCols()); dMatrix.setConf(conf); return dMatrix; }