You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mahout.apache.org by sr...@apache.org on 2013/06/05 07:20:36 UTC
svn commit: r1489707 [1/2] - in /mahout/trunk:
core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/
core/src/main/java/org/apache/mahout/cf/taste/hadoop/slopeone/
core/src/main/java/org/apache/mahout/cf/taste/impl/similarity/precompute/
core/src/m...
Author: srowen
Date: Wed Jun 5 05:20:34 2013
New Revision: 1489707
URL: http://svn.apache.org/r1489707
Log:
More inspection cleanup
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/ParallelALSFactorizationJob.java
mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SharingMapper.java
mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveExplicitFeedbackMapper.java
mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveImplicitFeedbackMapper.java
mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/slopeone/FullRunningAverageAndStdDevWritable.java
mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/impl/similarity/precompute/MultithreadedBatchItemSimilarities.java
mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/SimilarItems.java
mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ConfusionMatrix.java
mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ResultAnalyzer.java
mahout/trunk/core/src/main/java/org/apache/mahout/classifier/df/builder/DecisionTreeBuilder.java
mahout/trunk/core/src/main/java/org/apache/mahout/classifier/sequencelearning/hmm/HmmTrainer.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusteringUtils.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/cvb/InMemoryCollapsedVariationalBayes0.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/spectral/kmeans/SpectralKMeansDriver.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeans.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansMapper.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansReducer.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansUtilsMR.java
mahout/trunk/core/src/main/java/org/apache/mahout/common/AbstractJob.java
mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/convertors/ContextWriteOutputCollector.java
mahout/trunk/core/src/main/java/org/apache/mahout/math/VectorWritable.java
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/MatrixColumnMeansJob.java
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/decomposer/HdfsBackedLanczosState.java
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/solver/DistributedConjugateGradientSolver.java
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/stochasticsvd/qr/GivensThinSolver.java
mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/FastProjectionSearch.java
mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/ProjectionSearch.java
mahout/trunk/core/src/main/java/org/apache/mahout/math/random/RandomProjector.java
mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/SparseVectorsFromSequenceFiles.java
mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyPartitioner.java
mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/LLRReducer.java
mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/item/ToUserVectorsReducerTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/AllUnknownItemsCandidateItemsStrategyTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/BiasedItemBasedRecommenderTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/GenericItemBasedRecommenderTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/PreferredItemsNeighborhoodCandidateItemsStrategyTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/transforms/InverseUserFrequencyTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/classifier/ConfusionMatrixTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/classifier/df/data/DataLoaderTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/classify/ClusterClassificationDriverTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/minhash/TestMinHashClustering.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/BallKMeansTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/DataUtils.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeansTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansTestMR.java
mahout/trunk/core/src/test/java/org/apache/mahout/common/distance/CosineDistanceMeasureTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasuresTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/solver/TestDistributedConjugateGradientSolver.java
mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/LocalitySensitiveHashSearchTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchQualityTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchSanityTest.java
mahout/trunk/core/src/test/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyGroupComparatorTest.java
mahout/trunk/examples/src/main/java/org/apache/mahout/cf/taste/example/kddcup/track1/svd/ParallelArraysSGDFactorizer.java
mahout/trunk/examples/src/main/java/org/apache/mahout/cf/taste/example/kddcup/track2/TrackItemSimilarity.java
mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/sequencelearning/hmm/PosTagger.java
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/fuzzykmeans/Job.java
mahout/trunk/integration/src/main/java/org/apache/mahout/benchmark/BenchmarkRunner.java
mahout/trunk/integration/src/main/java/org/apache/mahout/benchmark/DotBenchmark.java
mahout/trunk/integration/src/main/java/org/apache/mahout/benchmark/VectorBenchmarks.java
mahout/trunk/integration/src/main/java/org/apache/mahout/cf/taste/impl/model/mongodb/MongoDBDataModel.java
mahout/trunk/integration/src/main/java/org/apache/mahout/text/WikipediaToSequenceFile.java
mahout/trunk/integration/src/main/java/org/apache/mahout/text/wikipedia/WikipediaDatasetCreatorDriver.java
mahout/trunk/integration/src/main/java/org/apache/mahout/utils/vectors/VectorHelper.java
mahout/trunk/integration/src/test/java/org/apache/mahout/clustering/TestClusterDumper.java
mahout/trunk/integration/src/test/java/org/apache/mahout/clustering/TestClusterEvaluator.java
mahout/trunk/integration/src/test/java/org/apache/mahout/clustering/cdbw/TestCDbwEvaluator.java
mahout/trunk/integration/src/test/java/org/apache/mahout/clustering/dirichlet/TestL1ModelClustering.java
mahout/trunk/math/src/main/java/org/apache/mahout/collections/Arithmetic.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/AbstractMatrix.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/AbstractVector.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/BinarySearch.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/DenseVector.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/FileBasedMatrix.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/MatrixVectorView.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/OrderedIntDoubleMapping.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/RandomAccessSparseVector.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/VectorBinaryAggregate.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/VectorBinaryAssign.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/jet/math/Arithmetic.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/jet/math/Constants.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/jet/random/AbstractDiscreteDistribution.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/jet/random/Poisson.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/jet/random/Uniform.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/jet/random/engine/RandomEngine.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/jet/stat/Probability.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/map/HashFunctions.java
mahout/trunk/math/src/main/java/org/apache/mahout/math/random/IndianBuffet.java
mahout/trunk/math/src/test/java/org/apache/mahout/math/QRDecompositionTest.java
mahout/trunk/math/src/test/java/org/apache/mahout/math/VectorBinaryAggregateCostTest.java
mahout/trunk/math/src/test/java/org/apache/mahout/math/VectorBinaryAssignCostTest.java
mahout/trunk/math/src/test/java/org/apache/mahout/math/VectorTest.java
mahout/trunk/math/src/test/java/org/apache/mahout/math/WeightedVectorTest.java
mahout/trunk/math/src/test/java/org/apache/mahout/math/jet/random/engine/MersenneTwisterTest.java
mahout/trunk/math/src/test/java/org/apache/mahout/math/randomized/RandomBlasting.java
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/ParallelALSFactorizationJob.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/ParallelALSFactorizationJob.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/ParallelALSFactorizationJob.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/ParallelALSFactorizationJob.java Wed Jun 5 05:20:34 2013
@@ -298,12 +298,12 @@ public class ParallelALSFactorizationJob
if (implicitFeedback) {
solverMapperClassInternal = SolveImplicitFeedbackMapper.class;
- name = "Recompute " + matrixName + ", iteration (" + (iterationNumber + 1) + "/" + numIterations + "), "
- + "(" + numThreadsPerSolver + " threads, " + numFeatures +" features, implicit feedback)";
+ name = "Recompute " + matrixName + ", iteration (" + (iterationNumber + 1) + '/' + numIterations + "), "
+ + '(' + numThreadsPerSolver + " threads, " + numFeatures +" features, implicit feedback)";
} else {
solverMapperClassInternal = SolveExplicitFeedbackMapper.class;
- name = "Recompute " + matrixName + ", iteration (" + (iterationNumber + 1) + "/" + numIterations + "), "
- + "(" + numThreadsPerSolver + " threads, " + numFeatures + " features, explicit feedback)";
+ name = "Recompute " + matrixName + ", iteration (" + (iterationNumber + 1) + '/' + numIterations + "), "
+ + '(' + numThreadsPerSolver + " threads, " + numFeatures + " features, explicit feedback)";
}
Job solverForUorI = prepareJob(ratings, output, SequenceFileInputFormat.class, MultithreadedSharingMapper.class,
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SharingMapper.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SharingMapper.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SharingMapper.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SharingMapper.java Wed Jun 5 05:20:34 2013
@@ -53,7 +53,7 @@ public abstract class SharingMapper<K1,V
return (S) SHARED_INSTANCE;
}
- final static void reset() {
+ static void reset() {
SHARED_INSTANCE = null;
}
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveExplicitFeedbackMapper.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveExplicitFeedbackMapper.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveExplicitFeedbackMapper.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveExplicitFeedbackMapper.java Wed Jun 5 05:20:34 2013
@@ -19,7 +19,6 @@ package org.apache.mahout.cf.taste.hadoo
import com.google.common.base.Preconditions;
import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.mahout.math.Vector;
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveImplicitFeedbackMapper.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveImplicitFeedbackMapper.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveImplicitFeedbackMapper.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/als/SolveImplicitFeedbackMapper.java Wed Jun 5 05:20:34 2013
@@ -19,7 +19,6 @@ package org.apache.mahout.cf.taste.hadoo
import com.google.common.base.Preconditions;
import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.mahout.math.VectorWritable;
import org.apache.mahout.math.als.ImplicitFeedbackAlternatingLeastSquaresSolver;
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/slopeone/FullRunningAverageAndStdDevWritable.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/slopeone/FullRunningAverageAndStdDevWritable.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/slopeone/FullRunningAverageAndStdDevWritable.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/slopeone/FullRunningAverageAndStdDevWritable.java Wed Jun 5 05:20:34 2013
@@ -29,7 +29,7 @@ final class FullRunningAverageAndStdDevW
private FullRunningAverageAndStdDev average;
- public FullRunningAverageAndStdDevWritable(FullRunningAverageAndStdDev average) {
+ FullRunningAverageAndStdDevWritable(FullRunningAverageAndStdDev average) {
this.average = average;
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/impl/similarity/precompute/MultithreadedBatchItemSimilarities.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/impl/similarity/precompute/MultithreadedBatchItemSimilarities.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/impl/similarity/precompute/MultithreadedBatchItemSimilarities.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/impl/similarity/precompute/MultithreadedBatchItemSimilarities.java Wed Jun 5 05:20:34 2013
@@ -112,7 +112,7 @@ public class MultithreadedBatchItemSimil
return output.getNumSimilaritiesProcessed();
}
- private BlockingQueue<long[]> queueItemIDsInBatches(DataModel dataModel, int batchSize) throws TasteException {
+ private static BlockingQueue<long[]> queueItemIDsInBatches(DataModel dataModel, int batchSize) throws TasteException {
LongPrimitiveIterator itemIDs = dataModel.getItemIDs();
int numItems = dataModel.getNumItems();
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/SimilarItems.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/SimilarItems.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/SimilarItems.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/SimilarItems.java Wed Jun 5 05:20:34 2013
@@ -22,6 +22,7 @@ import org.apache.mahout.cf.taste.recomm
import java.util.Iterator;
import java.util.List;
+import java.util.NoSuchElementException;
/**
* Compact representation of all similar items for an item
@@ -73,6 +74,9 @@ public class SimilarItems {
@Override
public SimilarItem next() {
+ if (!hasNext()) {
+ throw new NoSuchElementException();
+ }
index++;
return new SimilarItem(similarItemIDs[index], similarities[index]);
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ConfusionMatrix.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ConfusionMatrix.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ConfusionMatrix.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ConfusionMatrix.java Wed Jun 5 05:20:34 2013
@@ -26,7 +26,6 @@ import org.apache.mahout.cf.taste.impl.c
import org.apache.mahout.cf.taste.impl.common.RunningAverageAndStdDev;
import org.apache.mahout.math.DenseMatrix;
import org.apache.mahout.math.Matrix;
-import org.apache.mahout.math.stats.OnlineSummarizer;
import com.google.common.base.Preconditions;
import com.google.common.collect.Maps;
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ResultAnalyzer.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ResultAnalyzer.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ResultAnalyzer.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/classifier/ResultAnalyzer.java Wed Jun 5 05:20:34 2013
@@ -79,7 +79,7 @@ public class ResultAnalyzer {
public String toString() {
StringBuilder returnString = new StringBuilder();
- returnString.append("\n");
+ returnString.append('\n');
returnString.append("=======================================================\n");
returnString.append("Summary\n");
returnString.append("-------------------------------------------------------\n");
@@ -111,7 +111,7 @@ public class ResultAnalyzer {
returnString.append(StringUtils.rightPad("Reliability", 40)).append(
StringUtils.leftPad(decimalFormatter.format(normStats.getAverage() * 100.00000001), 10)).append("%\n");
returnString.append(StringUtils.rightPad("Reliability (standard deviation)", 40)).append(
- StringUtils.leftPad(decimalFormatter.format(normStats.getStandardDeviation()), 10)).append("\n");
+ StringUtils.leftPad(decimalFormatter.format(normStats.getStandardDeviation()), 10)).append('\n');
if (hasLL) {
returnString.append(StringUtils.rightPad("Log-likelihood", 30)).append("mean : ").append(
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/classifier/df/builder/DecisionTreeBuilder.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/classifier/df/builder/DecisionTreeBuilder.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/classifier/df/builder/DecisionTreeBuilder.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/classifier/df/builder/DecisionTreeBuilder.java Wed Jun 5 05:20:34 2013
@@ -209,7 +209,7 @@ public class DecisionTreeBuilder impleme
return new Leaf(label);
}
- log.debug("best split attr:{}, split:{}, ig:{}", best.getIg(), best.getAttr(), best.getSplit(), best.getIg());
+ log.debug("best split attr:{}, split:{}, ig:{}", best.getAttr(), best.getSplit(), best.getIg());
boolean alreadySelected = selected[best.getAttr()];
if (alreadySelected) {
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/classifier/sequencelearning/hmm/HmmTrainer.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/classifier/sequencelearning/hmm/HmmTrainer.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/classifier/sequencelearning/hmm/HmmTrainer.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/classifier/sequencelearning/hmm/HmmTrainer.java Wed Jun 5 05:20:34 2013
@@ -66,7 +66,7 @@ public final class HmmTrainer {
// given no prior knowledge, we have to assume that all initial hidden
// states are equally likely
DenseVector initialProbabilities = new DenseVector(nrOfHiddenStates);
- initialProbabilities.assign(1.0 / (double) nrOfHiddenStates);
+ initialProbabilities.assign(1.0 / nrOfHiddenStates);
// now loop over the sequences to count the number of transitions
countTransitions(transitionMatrix, emissionMatrix, observedSequence,
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusteringUtils.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusteringUtils.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusteringUtils.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusteringUtils.java Wed Jun 5 05:20:34 2013
@@ -19,7 +19,10 @@ import org.apache.mahout.math.neighborho
import org.apache.mahout.math.random.WeightedThing;
import org.apache.mahout.math.stats.OnlineSummarizer;
-public class ClusteringUtils {
+public final class ClusteringUtils {
+ private ClusteringUtils() {
+ }
+
/**
* Computes the summaries for the distances in each cluster.
* @param datapoints iterable of datapoints.
@@ -238,7 +241,6 @@ public class ClusteringUtils {
int numRows = confusionMatrix.numRows();
int numCols = confusionMatrix.numCols();
double rowChoiceSum = 0;
- double columnChoiceSum = 0;
double totalChoiceSum = 0;
double total = 0;
for (int i = 0; i < numRows; ++i) {
@@ -250,6 +252,7 @@ public class ClusteringUtils {
total += rowSum;
rowChoiceSum += choose2(rowSum);
}
+ double columnChoiceSum = 0;
for (int j = 0; j < numCols; ++j) {
double columnSum = 0;
for (int i = 0; i < numRows; ++i) {
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java Wed Jun 5 05:20:34 2013
@@ -36,7 +36,6 @@ import org.apache.mahout.common.HadoopUt
import org.apache.mahout.common.commandline.DefaultOptionCreator;
import org.apache.mahout.common.distance.DistanceMeasure;
import org.apache.mahout.common.distance.SquaredEuclideanDistanceMeasure;
-import org.apache.mahout.math.VectorWritable;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -142,8 +141,7 @@ public class KMeansDriver extends Abstra
if (log.isInfoEnabled()) {
log.info("Input: {} Clusters In: {} Out: {} Distance: {}", input, clustersIn, output,
measure.getClass().getName());
- log.info("convergence: {} max Iterations: {} num Reduce Tasks: {} Input Vectors: {}", convergenceDelta,
- maxIterations, VectorWritable.class.getName());
+ log.info("convergence: {} max Iterations: {}", convergenceDelta, maxIterations);
}
Path clustersOut = buildClusters(conf, input, clustersIn, output, measure, maxIterations, delta, runSequential);
if (runClustering) {
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/cvb/InMemoryCollapsedVariationalBayes0.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/cvb/InMemoryCollapsedVariationalBayes0.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/cvb/InMemoryCollapsedVariationalBayes0.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/cvb/InMemoryCollapsedVariationalBayes0.java Wed Jun 5 05:20:34 2013
@@ -262,7 +262,7 @@ public class InMemoryCollapsedVariationa
}
private static void logTime(String label, long nanos) {
- log.info("{} time: {}ms", label, (double) nanos / 1.0e6);
+ log.info("{} time: {}ms", label, nanos / 1.0e6);
}
public static int main2(String[] args, Configuration conf) throws Exception {
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java Wed Jun 5 05:20:34 2013
@@ -357,7 +357,7 @@ public class MeanShiftCanopyDriver exten
int iteration = 1;
while (!converged && iteration <= maxIterations) {
int numReducers = Integer.valueOf(conf.get(MAPRED_REDUCE_TASKS, "1"));
- log.info("Mean Shift Iteration: {}, numReducers {}", new Object[] { iteration, numReducers });
+ log.info("Mean Shift Iteration: {}, numReducers {}", iteration, numReducers);
// point the output to a new directory per iteration
Path clustersOut = new Path(output, Cluster.CLUSTERS_DIR + iteration);
Path controlOut = new Path(output, CONTROL_CONVERGED);
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/spectral/kmeans/SpectralKMeansDriver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/spectral/kmeans/SpectralKMeansDriver.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/spectral/kmeans/SpectralKMeansDriver.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/spectral/kmeans/SpectralKMeansDriver.java Wed Jun 5 05:20:34 2013
@@ -61,8 +61,7 @@ public class SpectralKMeansDriver extend
}
@Override
- public int run(String[] arg0)
- throws IOException, ClassNotFoundException, InstantiationException, IllegalAccessException, InterruptedException {
+ public int run(String[] arg0) throws Exception {
Configuration conf = getConf();
addInputOption();
@@ -216,9 +215,9 @@ public class SpectralKMeansDriver extend
// since some of the eigen-output is spurious and will be eliminated
// upon verification, we have to aim to overshoot and then discard
// unnecessary vectors later
- int overshoot = Math.min((int) ((double) clusters * OVERSHOOTMULTIPLIER), numDims);
+ int overshoot = Math.min((int) (clusters * OVERSHOOTMULTIPLIER), numDims);
DistributedLanczosSolver solver = new DistributedLanczosSolver();
- LanczosState state = new LanczosState(L, overshoot, solver.getInitialVector(L));
+ LanczosState state = new LanczosState(L, overshoot, DistributedLanczosSolver.getInitialVector(L));
Path lanczosSeqFiles = new Path(outputCalc, "eigenvectors");
solver.runJob(conf,
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeans.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeans.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeans.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeans.java Wed Jun 5 05:20:34 2013
@@ -20,6 +20,7 @@ package org.apache.mahout.clustering.str
import java.util.Collections;
import java.util.Iterator;
import java.util.List;
+import java.util.NoSuchElementException;
import java.util.Random;
import com.google.common.base.Function;
@@ -127,7 +128,7 @@ public class StreamingKMeans implements
/**
* Random object to sample values from.
*/
- private Random random = RandomUtils.getRandom();
+ private final Random random = RandomUtils.getRandom();
/**
* Calls StreamingKMeans(searcher, numClusters, 1.3, 10, 2).
@@ -231,6 +232,9 @@ public class StreamingKMeans implements
@Override
public Centroid next() {
+ if (!hasNext()) {
+ throw new NoSuchElementException();
+ }
accessed = true;
return datapoint;
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java Wed Jun 5 05:20:34 2013
@@ -405,8 +405,7 @@ public final class StreamingKMeansDriver
* @return 0 on success, -1 on failure.
*/
@SuppressWarnings("unchecked")
- public static int run(Configuration conf, Path input, Path output)
- throws IOException, InterruptedException, ClassNotFoundException, ExecutionException {
+ public static int run(Configuration conf, Path input, Path output) throws Exception {
log.info("Starting StreamingKMeans clustering for vectors in {}; results are output to {}",
input.toString(), output.toString());
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansMapper.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansMapper.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansMapper.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansMapper.java Wed Jun 5 05:20:34 2013
@@ -48,7 +48,7 @@ public class StreamingKMeansMapper exten
int numClusters = conf.getInt(StreamingKMeansDriver.ESTIMATED_NUM_MAP_CLUSTERS, 1);
// There is no way of estimating the distance cutoff unless we have some data.
clusterer = new StreamingKMeans(searcher, numClusters,
- conf.getFloat(StreamingKMeansDriver.ESTIMATED_DISTANCE_CUTOFF, 1e-4f));
+ conf.getFloat(StreamingKMeansDriver.ESTIMATED_DISTANCE_CUTOFF, 1.0e-4f));
}
@Override
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansReducer.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansReducer.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansReducer.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansReducer.java Wed Jun 5 05:20:34 2013
@@ -53,7 +53,7 @@ public class StreamingKMeansReducer exte
UpdatableSearcher searcher = StreamingKMeansUtilsMR.searcherFromConfiguration(conf);
// There is no way of estimating the distance cutoff unless we have some data.
return new StreamingKMeans(searcher, numClusters,
- conf.getFloat(StreamingKMeansDriver.ESTIMATED_DISTANCE_CUTOFF, 1e-4f));
+ conf.getFloat(StreamingKMeansDriver.ESTIMATED_DISTANCE_CUTOFF, 1.0e-4f));
}
@Override
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansUtilsMR.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansUtilsMR.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansUtilsMR.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansUtilsMR.java Wed Jun 5 05:20:34 2013
@@ -24,7 +24,10 @@ import org.apache.mahout.math.neighborho
import org.apache.mahout.math.neighborhood.ProjectionSearch;
import org.apache.mahout.math.neighborhood.UpdatableSearcher;
-public class StreamingKMeansUtilsMR {
+public final class StreamingKMeansUtilsMR {
+
+ private StreamingKMeansUtilsMR() {
+ }
/**
* Instantiates a searcher from a given configuration.
@@ -37,7 +40,7 @@ public class StreamingKMeansUtilsMR {
DistanceMeasure distanceMeasure;
String distanceMeasureClass = conf.get(DefaultOptionCreator.DISTANCE_MEASURE_OPTION);
try {
- distanceMeasure = (DistanceMeasure)Class.forName(distanceMeasureClass).newInstance();
+ distanceMeasure = (DistanceMeasure)Class.forName(distanceMeasureClass).getConstructor().newInstance();
} catch (Exception e) {
throw new RuntimeException("Failed to instantiate distanceMeasure", e);
}
@@ -90,7 +93,7 @@ public class StreamingKMeansUtilsMR {
* @param input Iterable of Vectors to cast
* @return the new Centroids
*/
- public static Iterable<Centroid> castVectorsToCentroids(final Iterable<Vector> input) {
+ public static Iterable<Centroid> castVectorsToCentroids(Iterable<Vector> input) {
return Iterables.transform(input, new Function<Vector, Centroid>() {
private int numVectors = 0;
@Override
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/common/AbstractJob.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/common/AbstractJob.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/common/AbstractJob.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/common/AbstractJob.java Wed Jun 5 05:20:34 2013
@@ -163,8 +163,9 @@ public abstract class AbstractJob extend
@Override
public Configuration getConf() {
Configuration result = super.getConf();
- if (result == null)
+ if (result == null) {
return new Configuration();
+ }
return result;
}
@@ -446,11 +447,10 @@ public abstract class AbstractJob extend
Writable row = ClassUtils.instantiateAs(reader.getKeyClass().asSubclass(Writable.class), Writable.class);
- VectorWritable vectorWritable = new VectorWritable();
-
Preconditions.checkArgument(reader.getValueClass().equals(VectorWritable.class),
"value type of sequencefile must be a VectorWritable");
+ VectorWritable vectorWritable = new VectorWritable();
boolean hasAtLeastOneRow = reader.next(row, vectorWritable);
Preconditions.checkState(hasAtLeastOneRow, "matrix must have at least one row");
@@ -642,7 +642,7 @@ public abstract class AbstractJob extend
String oozieActionConfXml = System.getProperty("oozie.action.conf.xml");
if (oozieActionConfXml != null && conf != null) {
conf.addResource(new Path("file:///", oozieActionConfXml));
- log.info("Added Oozie action Configuration resource {0} to the Hadoop Configuration", oozieActionConfXml);
+ log.info("Added Oozie action Configuration resource {} to the Hadoop Configuration", oozieActionConfXml);
}
}
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/convertors/ContextWriteOutputCollector.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/convertors/ContextWriteOutputCollector.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/convertors/ContextWriteOutputCollector.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/convertors/ContextWriteOutputCollector.java Wed Jun 5 05:20:34 2013
@@ -51,7 +51,7 @@ public class ContextWriteOutputCollector
context.setStatus("Writing Top K patterns for: " + key);
context.write(key, value);
} catch (InterruptedException e) {
- log.error("{}", e);
+ log.error("{}", e.toString());
}
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/math/VectorWritable.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/VectorWritable.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/math/VectorWritable.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/math/VectorWritable.java Wed Jun 5 05:20:34 2013
@@ -205,9 +205,7 @@ public final class VectorWritable extend
while (vectors.hasNext()) {
VectorWritable v = vectors.next();
if (v != null) {
- Iterator<Element> nonZeroElements = v.get().nonZeroes().iterator();
- while (nonZeroElements.hasNext()) {
- Vector.Element nonZeroElement = nonZeroElements.next();
+ for (Element nonZeroElement : v.get().nonZeroes()) {
accumulator.setQuick(nonZeroElement.index(), nonZeroElement.get());
}
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/MatrixColumnMeansJob.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/MatrixColumnMeansJob.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/MatrixColumnMeansJob.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/MatrixColumnMeansJob.java Wed Jun 5 05:20:34 2013
@@ -118,12 +118,10 @@ public final class MatrixColumnMeansJob
} finally {
Closeables.closeQuietly(iterator);
}
+ } catch (IOException ioe) {
+ throw ioe;
} catch (Throwable thr) {
- if (thr instanceof IOException) {
- throw (IOException) thr;
- } else {
- throw new IOException(thr);
- }
+ throw new IOException(thr);
}
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/decomposer/HdfsBackedLanczosState.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/decomposer/HdfsBackedLanczosState.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/decomposer/HdfsBackedLanczosState.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/decomposer/HdfsBackedLanczosState.java Wed Jun 5 05:20:34 2013
@@ -68,7 +68,7 @@ public class HdfsBackedLanczosState exte
setupDirs();
updateHdfsState();
} catch (IOException e) {
- log.error("Could not retrieve filesystem: ", conf, e);
+ log.error("Could not retrieve filesystem: {}", conf, e);
}
}
@@ -174,7 +174,7 @@ public class HdfsBackedLanczosState exte
Vector v = fetchVector(new Path(basisPath, BASIS_PREFIX + '_' + i), i);
basis.put(i, v);
} catch (IOException e) {
- log.error("Could not load basis vector: ", i, e);
+ log.error("Could not load basis vector: {}", i, e);
}
}
return super.getBasisVector(i);
@@ -187,7 +187,7 @@ public class HdfsBackedLanczosState exte
Vector v = fetchVector(new Path(singularVectorPath, BASIS_PREFIX + '_' + i), i);
singularVectors.put(i, v);
} catch (IOException e) {
- log.error("Could not load singular vector: ", i, e);
+ log.error("Could not load singular vector: {}", i, e);
}
}
return super.getRightSingularVector(i);
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/solver/DistributedConjugateGradientSolver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/solver/DistributedConjugateGradientSolver.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/solver/DistributedConjugateGradientSolver.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/solver/DistributedConjugateGradientSolver.java Wed Jun 5 05:20:34 2013
@@ -113,8 +113,8 @@ public class DistributedConjugateGradien
private Vector loadInputVector(Path path) throws IOException {
FileSystem fs = path.getFileSystem(conf);
SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
- VectorWritable value = new VectorWritable();
try {
+ VectorWritable value = new VectorWritable();
if (!reader.next(new IntWritable(), value)) {
throw new IOException("Input vector file is empty.");
}
@@ -163,8 +163,9 @@ public class DistributedConjugateGradien
return -1;
} else {
Configuration conf = getConf();
- if (conf == null)
+ if (conf == null) {
conf = new Configuration();
+ }
DistributedConjugateGradientSolver.this.setConf(conf);
return DistributedConjugateGradientSolver.this.run(args);
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/stochasticsvd/qr/GivensThinSolver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/stochasticsvd/qr/GivensThinSolver.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/stochasticsvd/qr/GivensThinSolver.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/stochasticsvd/qr/GivensThinSolver.java Wed Jun 5 05:20:34 2013
@@ -626,8 +626,8 @@ public class GivensThinSolver {
*/
@Override
public void mergeUpdates(OrderedIntDoubleMapping updates) {
- int indices[] = updates.getIndices();
- double values[] = updates.getValues();
+ int[] indices = updates.getIndices();
+ double[] values = updates.getValues();
for (int i = 0; i < updates.getNumMappings(); ++i) {
viewed.setQuick(rowNum, indices[i], values[i]);
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/FastProjectionSearch.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/FastProjectionSearch.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/FastProjectionSearch.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/FastProjectionSearch.java Wed Jun 5 05:20:34 2013
@@ -27,7 +27,7 @@ import org.apache.mahout.math.random.Wei
*/
public class FastProjectionSearch extends UpdatableSearcher {
// The list of vectors that have not yet been projected (that are pending).
- private List<Vector> pendingAdditions = Lists.newArrayList();
+ private final List<Vector> pendingAdditions = Lists.newArrayList();
// The list of basis vectors. Populated when the first vector's dimension is know by calling
// initialize once.
@@ -41,11 +41,11 @@ public class FastProjectionSearch extend
private List<List<WeightedThing<Vector>>> scalarProjections;
// The number of projection used for approximating the distance.
- private int numProjections;
+ private final int numProjections;
// The number of elements to keep on both sides of the closest estimated distance as possible
// candidates for the best actual distance.
- private int searchSize;
+ private final int searchSize;
// Initially, the dimension of the vectors searched by this searcher is unknown. After adding
// the first vector, the basis will be initialized. This marks whether initialization has
@@ -57,8 +57,8 @@ public class FastProjectionSearch extend
// "impossible" values in the array) so they can be removed when updating the structure.
private int numPendingRemovals = 0;
- private final static double ADDITION_THRESHOLD = 0.05;
- private final static double REMOVAL_THRESHOLD = 0.02;
+ private static final double ADDITION_THRESHOLD = 0.05;
+ private static final double REMOVAL_THRESHOLD = 0.02;
public FastProjectionSearch(DistanceMeasure distanceMeasure, int numProjections, int searchSize) {
super(distanceMeasure);
@@ -199,7 +199,7 @@ public class FastProjectionSearch extend
}
boolean isProjected = true;
- final Vector projection = basisMatrix.times(vector);
+ Vector projection = basisMatrix.times(vector);
for (int i = 0; i < basisMatrix.numRows(); ++i) {
List<WeightedThing<Vector>> currProjections = scalarProjections.get(i);
WeightedThing<Vector> searchedThing = new WeightedThing<Vector>(projection.get(i));
@@ -294,12 +294,11 @@ public class FastProjectionSearch extend
Iterator<WeightedThing<Vector>> data = scalarProjections.get(0).iterator();
@Override
protected Vector computeNext() {
- WeightedThing<Vector> next;
do {
if (!data.hasNext()) {
return endOfData();
}
- next = data.next();
+ WeightedThing<Vector> next = data.next();
if (next.getValue() != null) {
return next.getValue();
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/ProjectionSearch.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/ProjectionSearch.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/ProjectionSearch.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/math/neighborhood/ProjectionSearch.java Wed Jun 5 05:20:34 2013
@@ -59,9 +59,9 @@ public class ProjectionSearch extends Up
* The number of elements to consider on both sides in the ball around the vector found by the
* search in a TreeSet from scalarProjections.
*/
- private int searchSize;
+ private final int searchSize;
- private int numProjections;
+ private final int numProjections;
private boolean initialized = false;
private void initialize(int numDimensions) {
@@ -115,6 +115,7 @@ public class ProjectionSearch extends Up
* Returns the number of scalarProjections that we can search
* @return The number of scalarProjections added to the search so far.
*/
+ @Override
public int size() {
if (scalarProjections == null) {
return 0;
@@ -130,7 +131,8 @@ public class ProjectionSearch extends Up
* @return a list of Vectors wrapped in WeightedThings where the "thing"'s weight is the
* distance.
*/
- public List<WeightedThing<Vector>> search(final Vector query, int limit) {
+ @Override
+ public List<WeightedThing<Vector>> search(Vector query, int limit) {
Set<Vector> candidates = Sets.newHashSet();
Iterator<? extends Vector> projections = basisMatrix.iterator();
@@ -192,7 +194,7 @@ public class ProjectionSearch extends Up
@Override
public Iterator<Vector> iterator() {
return new AbstractIterator<Vector>() {
- private Iterator<WeightedThing<Vector>> projected = scalarProjections.get(0).iterator();
+ private final Iterator<WeightedThing<Vector>> projected = scalarProjections.get(0).iterator();
@Override
protected Vector computeNext() {
if (!projected.hasNext()) {
@@ -203,6 +205,7 @@ public class ProjectionSearch extends Up
};
}
+ @Override
public boolean remove(Vector vector, double epsilon) {
WeightedThing<Vector> toRemove = searchFirst(vector, false);
if (toRemove.getWeight() < epsilon) {
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/math/random/RandomProjector.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/random/RandomProjector.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/math/random/RandomProjector.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/math/random/RandomProjector.java Wed Jun 5 05:20:34 2013
@@ -11,7 +11,10 @@ import org.apache.mahout.math.MatrixSlic
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.function.DoubleFunction;
-public class RandomProjector {
+public final class RandomProjector {
+ private RandomProjector() {
+ }
+
/**
* Generates a basis matrix of size projectedVectorSize x vectorSize. Multiplying a a vector by
* this matrix results in the projected vector.
@@ -50,7 +53,7 @@ public class RandomProjector {
Matrix basisMatrix = new DenseMatrix(projectedVectorSize, vectorSize);
for (int i = 0; i < projectedVectorSize; ++i) {
for (int j = 0; j < vectorSize; ++j) {
- basisMatrix.set(i, j, RandomUtils.nextInt(2) == 0 ? +1 : -1);
+ basisMatrix.set(i, j, RandomUtils.nextInt(2) == 0 ? 1 : -1);
}
}
for (MatrixSlice row : basisMatrix) {
@@ -79,7 +82,7 @@ public class RandomProjector {
Matrix basisMatrix = new DenseMatrix(projectedVectorSize, vectorSize);
Multinomial<Double> choice = new Multinomial<Double>();
choice.add(0.0, 2/3.0);
- choice.add(+Math.sqrt(3.0), 1 / 6.0);
+ choice.add(Math.sqrt(3.0), 1 / 6.0);
choice.add(-Math.sqrt(3.0), 1 / 6.0);
for (int i = 0; i < projectedVectorSize; ++i) {
for (int j = 0; j < vectorSize; ++j) {
@@ -100,7 +103,7 @@ public class RandomProjector {
* @return a list of projection vectors
*/
public static List<Vector> generateVectorBasis(int projectedVectorSize, int vectorSize) {
- final DoubleFunction random = new Normal();
+ DoubleFunction random = new Normal();
List<Vector> basisVectors = Lists.newArrayList();
for (int i = 0; i < projectedVectorSize; ++i) {
Vector basisVector = new DenseVector(vectorSize);
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/SparseVectorsFromSequenceFiles.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/SparseVectorsFromSequenceFiles.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/SparseVectorsFromSequenceFiles.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/SparseVectorsFromSequenceFiles.java Wed Jun 5 05:20:34 2013
@@ -318,7 +318,7 @@ public final class SparseVectorsFromSequ
maxDF = (int) (100.0 * maxDFSigma * stdDev / vectorCount);
}
- long maxDFThreshold = (long) (vectorCount * ((float) maxDF / 100f));
+ long maxDFThreshold = (long) (vectorCount * (maxDF / 100.0f));
// Prune the term frequency vectors
Path tfDir = new Path(outputDir, tfDirName);
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyPartitioner.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyPartitioner.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyPartitioner.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyPartitioner.java Wed Jun 5 05:20:34 2013
@@ -32,7 +32,7 @@ public final class GramKeyPartitioner ex
int length = key.getPrimaryLength();
// Copied from WritableComparator.hashBytes(); skips first byte, type byte
for (int i = 1; i < length; i++) {
- hash = (31 * hash) + (int) bytes[i];
+ hash = (31 * hash) + bytes[i];
}
return (hash & Integer.MAX_VALUE) % numPartitions;
}
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/LLRReducer.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/LLRReducer.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/LLRReducer.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/vectorizer/collocations/llr/LLRReducer.java Wed Jun 5 05:20:34 2013
@@ -112,7 +112,7 @@ public class LLRReducer extends Reducer<
} catch (IllegalArgumentException ex) {
context.getCounter(Skipped.LLR_CALCULATION_ERROR).increment(1);
log.warn("Problem calculating LLR ratio for ngram {}, HEAD {}:{}, TAIL {}:{}, k11/k12/k21/k22: {}/{}/{}/{}",
- new Object[] {ngram, gram[0], gramFreq[0], gram[1], gramFreq[1], k11, k12, k21, k22}, ex);
+ ngram, gram[0], gramFreq[0], gram[1], gramFreq[1], k11, k12, k21, k22, ex);
return;
}
if (llr < minLLRValue) {
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/item/ToUserVectorsReducerTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/item/ToUserVectorsReducerTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/item/ToUserVectorsReducerTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/item/ToUserVectorsReducerTest.java Wed Jun 5 05:20:34 2013
@@ -28,6 +28,7 @@ import org.easymock.EasyMock;
import org.junit.Test;
import java.util.Arrays;
+import java.util.Collections;
/**
* tests {@link ToUserVectorsReducer}
@@ -44,7 +45,7 @@ public class ToUserVectorsReducerTest ex
EasyMock.replay(context);
- reducer.reduce(new VarLongWritable(123), Arrays.asList(new VarLongWritable(456)), context);
+ reducer.reduce(new VarLongWritable(123), Collections.singletonList(new VarLongWritable(456)), context);
EasyMock.verify(context);
}
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/AllUnknownItemsCandidateItemsStrategyTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/AllUnknownItemsCandidateItemsStrategyTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/AllUnknownItemsCandidateItemsStrategyTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/AllUnknownItemsCandidateItemsStrategyTest.java Wed Jun 5 05:20:34 2013
@@ -28,7 +28,7 @@ import org.apache.mahout.cf.taste.recomm
import org.easymock.EasyMock;
import org.junit.Test;
-import java.util.Arrays;
+import java.util.Collections;
/**
* Tests {@link AllUnknownItemsCandidateItemsStrategyTest}
@@ -47,7 +47,7 @@ public final class AllUnknownItemsCandid
EasyMock.expect(dataModel.getNumItems()).andReturn(3);
EasyMock.expect(dataModel.getItemIDs()).andReturn(allItemIDs.iterator());
- PreferenceArray prefArrayOfUser123 = new GenericUserPreferenceArray(Arrays.asList(
+ PreferenceArray prefArrayOfUser123 = new GenericUserPreferenceArray(Collections.singletonList(
new GenericPreference(123L, 2L, 1.0f)));
CandidateItemsStrategy strategy = new AllUnknownItemsCandidateItemsStrategy();
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/BiasedItemBasedRecommenderTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/BiasedItemBasedRecommenderTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/BiasedItemBasedRecommenderTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/BiasedItemBasedRecommenderTest.java Wed Jun 5 05:20:34 2013
@@ -27,24 +27,24 @@ public class BiasedItemBasedRecommenderT
@Test
public void sorting() {
- double[] similarities = new double[] { 0.1, 1.0, 0.5 };
- float[] ratings = new float[] { 3, 1, 2 };
- long[] itemIDs = new long[] { 3, 1, 2 };
+ double[] similarities = { 0.1, 1.0, 0.5 };
+ float[] ratings = { 3, 1, 2 };
+ long[] itemIDs = { 3, 1, 2 };
Sorting.quickSort(0, similarities.length, new BiasedItemBasedRecommender.SimilaritiesComparator(similarities),
new BiasedItemBasedRecommender.SimilaritiesRatingsItemIDsSwapper(similarities, ratings, itemIDs));
- assertEquals(1d, similarities[0], 0d);
- assertEquals(0.5d, similarities[1], 0d);
- assertEquals(0.1d, similarities[2], 0d);
-
- assertEquals(1f, ratings[0], 0f);
- assertEquals(2f, ratings[1], 0f);
- assertEquals(3f, ratings[2], 0f);
-
- assertEquals(1l, itemIDs[0]);
- assertEquals(2l, itemIDs[1]);
- assertEquals(3l, itemIDs[2]);
+ assertEquals(1.0d, similarities[0], 0.0d);
+ assertEquals(0.5d, similarities[1], 0.0d);
+ assertEquals(0.1d, similarities[2], 0.0d);
+
+ assertEquals(1.0f, ratings[0], 0.0f);
+ assertEquals(2.0f, ratings[1], 0.0f);
+ assertEquals(3.0f, ratings[2], 0.0f);
+
+ assertEquals(1L, itemIDs[0]);
+ assertEquals(2L, itemIDs[1]);
+ assertEquals(3L, itemIDs[2]);
}
}
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/GenericItemBasedRecommenderTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/GenericItemBasedRecommenderTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/GenericItemBasedRecommenderTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/GenericItemBasedRecommenderTest.java Wed Jun 5 05:20:34 2013
@@ -74,7 +74,7 @@ public final class GenericItemBasedRecom
for (int i = 0; i < 6; i++) {
for (int j = i + 1; j < 6; j++) {
similarities.add(
- new GenericItemSimilarity.ItemItemSimilarity(i, j, 1.0 / (1.0 + (double) i + (double) j)));
+ new GenericItemSimilarity.ItemItemSimilarity(i, j, 1.0 / (1.0 + i + j)));
}
}
ItemSimilarity similarity = new GenericItemSimilarity(similarities);
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/PreferredItemsNeighborhoodCandidateItemsStrategyTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/PreferredItemsNeighborhoodCandidateItemsStrategyTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/PreferredItemsNeighborhoodCandidateItemsStrategyTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/recommender/PreferredItemsNeighborhoodCandidateItemsStrategyTest.java Wed Jun 5 05:20:34 2013
@@ -17,7 +17,7 @@
package org.apache.mahout.cf.taste.impl.recommender;
-import java.util.Arrays;
+import java.util.Collections;
import java.util.List;
import com.google.common.collect.Lists;
@@ -59,7 +59,7 @@ public final class PreferredItemsNeighbo
EasyMock.expect(dataModel.getItemIDsFromUser(456L)).andReturn(itemIDsFromUser456);
PreferenceArray prefArrayOfUser123 =
- new GenericUserPreferenceArray(Arrays.asList(new GenericPreference(123L, 1L, 1.0f)));
+ new GenericUserPreferenceArray(Collections.singletonList(new GenericPreference(123L, 1L, 1.0f)));
CandidateItemsStrategy strategy = new PreferredItemsNeighborhoodCandidateItemsStrategy();
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/transforms/InverseUserFrequencyTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/transforms/InverseUserFrequencyTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/transforms/InverseUserFrequencyTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/impl/transforms/InverseUserFrequencyTest.java Wed Jun 5 05:20:34 2013
@@ -44,7 +44,7 @@ public final class InverseUserFrequencyT
for (int i = 0; i < 5; i++) {
Preference pref = user5Prefs.get(i);
assertNotNull(pref);
- assertEquals(Math.log(5.0 / (double) (5 - i)) / Math.log(iuf.getLogBase()),
+ assertEquals(Math.log(5.0 / (5.0 - i)) / Math.log(iuf.getLogBase()),
iuf.getTransformedValue(pref),
EPSILON);
}
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/classifier/ConfusionMatrixTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/classifier/ConfusionMatrixTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/classifier/ConfusionMatrixTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/classifier/ConfusionMatrixTest.java Wed Jun 5 05:20:34 2013
@@ -86,7 +86,7 @@ public final class ConfusionMatrixTest e
labelList.add(labels[0]);
labelList.add(labels[1]);
ConfusionMatrix cm = new ConfusionMatrix(labelList, defaultLabel);
- int[][] v = cm.getConfusionMatrix();
+ //int[][] v = cm.getConfusionMatrix();
cm.putCount("Label1", "Label1", values[0][0]);
cm.putCount("Label1", "Label2", values[0][1]);
cm.putCount("Label2", "Label1", values[1][0]);
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/classifier/df/data/DataLoaderTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/classifier/df/data/DataLoaderTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/classifier/df/data/DataLoaderTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/classifier/df/data/DataLoaderTest.java Wed Jun 5 05:20:34 2013
@@ -224,7 +224,7 @@ public final class DataLoaderTest extend
if (!loaded.getDataset().isNumerical(aId)) {
double nValue = instance.get(aId);
String oValue = Double.toString(data[index][attr]);
- assertEquals((double) loaded.getDataset().valueOf(aId, oValue), nValue, EPSILON);
+ assertEquals(loaded.getDataset().valueOf(aId, oValue), nValue, EPSILON);
}
} else {
assertEquals(attrs[attr].isNumerical(), loaded.getDataset().isNumerical(aId));
@@ -232,7 +232,7 @@ public final class DataLoaderTest extend
if (attrs[attr].isCategorical()) {
double nValue = instance.get(aId);
String oValue = Double.toString(data[index][attr]);
- assertEquals((double) loaded.getDataset().valueOf(aId, oValue), nValue, EPSILON);
+ assertEquals(loaded.getDataset().valueOf(aId, oValue), nValue, EPSILON);
}
}
aId++;
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/clustering/classify/ClusterClassificationDriverTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/classify/ClusterClassificationDriverTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/clustering/classify/ClusterClassificationDriverTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/clustering/classify/ClusterClassificationDriverTest.java Wed Jun 5 05:20:34 2013
@@ -30,7 +30,6 @@ import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Writable;
-import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.clustering.ClusteringTestUtils;
import org.apache.mahout.clustering.canopy.CanopyDriver;
import org.apache.mahout.clustering.iterator.CanopyClusteringPolicy;
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/clustering/minhash/TestMinHashClustering.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/minhash/TestMinHashClustering.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/clustering/minhash/TestMinHashClustering.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/clustering/minhash/TestMinHashClustering.java Wed Jun 5 05:20:34 2013
@@ -101,11 +101,13 @@ public final class TestMinHashClustering
private static Set<Integer> getValues(Vector vector, String dimensionToHash) {
Set<Integer> values = Sets.newHashSet();
if ("value".equalsIgnoreCase(dimensionToHash)) {
- for (Vector.Element e : vector.nonZeroes())
+ for (Vector.Element e : vector.nonZeroes()) {
values.add((int) e.get());
+ }
} else {
- for (Vector.Element e : vector.nonZeroes())
+ for (Vector.Element e : vector.nonZeroes()) {
values.add(e.index());
+ }
}
return values;
}
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/BallKMeansTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/BallKMeansTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/BallKMeansTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/BallKMeansTest.java Wed Jun 5 05:20:34 2013
@@ -83,7 +83,7 @@ public class BallKMeansTest {
clusterer.cluster(syntheticData.getFirst());
long endTime = System.currentTimeMillis();
- assertEquals("Total weight not preserved", totalWeight(syntheticData.getFirst()), totalWeight(clusterer), 1e-9);
+ assertEquals("Total weight not preserved", totalWeight(syntheticData.getFirst()), totalWeight(clusterer), 1.0e-9);
// Verify that each corner of the cube has a centroid very nearby.
// This is probably FALSE for large-dimensional spaces!
@@ -98,7 +98,7 @@ public class BallKMeansTest {
double clusterTime = (endTime - startTime) / 1000.0;
System.out.printf("%s\n%.2f for clustering\n%.1f us per row\n\n",
searcher.getClass().getName(), clusterTime,
- clusterTime / syntheticData.getFirst().size() * 1e6);
+ clusterTime / syntheticData.getFirst().size() * 1.0e6);
// Verify that the total weight of the centroids near each corner is correct.
double[] cornerWeights = new double[1 << NUM_DIMENSIONS];
@@ -155,7 +155,7 @@ public class BallKMeansTest {
assertEquals(5, s.norm(1), 0.05);
}
- private List<? extends WeightedVector> cubishTestData(double radius) {
+ private static List<? extends WeightedVector> cubishTestData(double radius) {
List<WeightedVector> data = Lists.newArrayListWithCapacity(K1 + 5000);
int row = 0;
@@ -166,7 +166,7 @@ public class BallKMeansTest {
for (int i = 0; i < 5; i++) {
Vector m = new DenseVector(10);
- m.set(i, i == 0 ? 6 : 6);
+ m.set(i, 6); // This was originally i == 0 ? 6 : 6 which can't be right
MultiNormal gx = new MultiNormal(radius, m);
for (int j = 0; j < 1000; j++) {
data.add(new WeightedVector(gx.sample(), 1, row++));
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/DataUtils.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/DataUtils.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/DataUtils.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/DataUtils.java Wed Jun 5 05:20:34 2013
@@ -30,7 +30,10 @@ import org.apache.mahout.math.random.Mul
* A collection of miscellaneous utility functions for working with data to be clustered.
* Includes methods for generating synthetic data and estimating distance cutoff.
*/
-public class DataUtils {
+public final class DataUtils {
+ private DataUtils() {
+ }
+
/**
* Samples numDatapoints vectors of numDimensions cardinality centered around the vertices of a
* numDimensions order hypercube. The distribution of points around these vertices is
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeansTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeansTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeansTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/cluster/StreamingKMeansTest.java Wed Jun 5 05:20:34 2013
@@ -42,7 +42,7 @@ import static org.junit.Assert.assertTru
import static org.junit.runners.Parameterized.Parameters;
-@RunWith(value = Parameterized.class)
+@RunWith(Parameterized.class)
public class StreamingKMeansTest {
private static final int NUM_DATA_POINTS = 1 << 16;
private static final int NUM_DIMENSIONS = 6;
@@ -82,7 +82,7 @@ public class StreamingKMeansTest {
searcher.clear();
int numStreamingClusters = (int)Math.log(syntheticData.getFirst().size()) * (1 <<
NUM_DIMENSIONS);
- double distanceCutoff = 1e-6;
+ double distanceCutoff = 1.0e-6;
double estimatedCutoff = ClusteringUtils.estimateDistanceCutoff(syntheticData.getFirst(),
searcher.getDistanceMeasure(), 100);
System.out.printf("[%d] Generated synthetic data [magic] %f [estimate] %f\n", i, distanceCutoff, estimatedCutoff);
@@ -125,7 +125,7 @@ public class StreamingKMeansTest {
System.out.printf("Weights: %f %f\n", ClusteringUtils.totalWeight(syntheticData.getFirst()),
ClusteringUtils.totalWeight(clusterer));
assertEquals("Total weight not preserved", ClusteringUtils.totalWeight(syntheticData.getFirst()),
- ClusteringUtils.totalWeight(clusterer), 1e-9);
+ ClusteringUtils.totalWeight(clusterer), 1.0e-9);
// and verify that each corner of the cube has a centroid very nearby
double maxWeight = 0;
@@ -137,7 +137,7 @@ public class StreamingKMeansTest {
double clusterTime = (endTime - startTime) / 1000.0;
System.out.printf("%s\n%.2f for clustering\n%.1f us per row\n\n",
searcher.getClass().getName(), clusterTime,
- clusterTime / syntheticData.getFirst().size() * 1e6);
+ clusterTime / syntheticData.getFirst().size() * 1.0e6);
// verify that the total weight of the centroids near each corner is correct
double[] cornerWeights = new double[1 << NUM_DIMENSIONS];
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansTestMR.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansTestMR.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansTestMR.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansTestMR.java Wed Jun 5 05:20:34 2013
@@ -54,20 +54,20 @@ import org.junit.runners.Parameterized;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;
-@RunWith(value = Parameterized.class)
+@RunWith(Parameterized.class)
public class StreamingKMeansTestMR {
private static final int NUM_DATA_POINTS = 1 << 15;
private static final int NUM_DIMENSIONS = 8;
private static final int NUM_PROJECTIONS = 3;
private static final int SEARCH_SIZE = 5;
private static final int MAX_NUM_ITERATIONS = 10;
- private static final double DISTANCE_CUTOFF = 1e-6;
+ private static final double DISTANCE_CUTOFF = 1.0e-6;
- private static Pair<List<Centroid>, List<Centroid>> syntheticData =
- DataUtils.sampleMultiNormalHypercube(NUM_DIMENSIONS, NUM_DATA_POINTS, 1e-4);
+ private static final Pair<List<Centroid>, List<Centroid>> syntheticData =
+ DataUtils.sampleMultiNormalHypercube(NUM_DIMENSIONS, NUM_DATA_POINTS, 1.0e-4);
- private String searcherClassName;
- private String distanceMeasureClassName;
+ private final String searcherClassName;
+ private final String distanceMeasureClassName;
public StreamingKMeansTestMR(String searcherClassName, String distanceMeasureClassName) {
this.searcherClassName = searcherClassName;
@@ -224,8 +224,7 @@ public class StreamingKMeansTestMR {
}
@Test
- public void testHypercubeMapReduceRunSequentially()
- throws IOException, InterruptedException, ExecutionException, ClassNotFoundException {
+ public void testHypercubeMapReduceRunSequentially() throws Exception {
Configuration configuration = new Configuration();
configure(configuration);
configuration.set(DefaultOptionCreator.METHOD_OPTION, DefaultOptionCreator.SEQUENTIAL_METHOD);
@@ -251,10 +250,10 @@ public class StreamingKMeansTestMR {
})));
}
- private void testReducerResults(int totalWeight, List<org.apache.hadoop.mrunit.types.Pair<IntWritable,
+ private static void testReducerResults(int totalWeight, List<org.apache.hadoop.mrunit.types.Pair<IntWritable,
CentroidWritable>> results) {
int expectedNumClusters = 1 << NUM_DIMENSIONS;
- double expectedWeight = totalWeight / expectedNumClusters;
+ double expectedWeight = (double) totalWeight / expectedNumClusters;
int numClusters = 0;
int numUnbalancedClusters = 0;
int totalReducerWeight = 0;
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/common/distance/CosineDistanceMeasureTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/common/distance/CosineDistanceMeasureTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/common/distance/CosineDistanceMeasureTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/common/distance/CosineDistanceMeasureTest.java Wed Jun 5 05:20:34 2013
@@ -57,8 +57,10 @@ public final class CosineDistanceMeasure
assertTrue(distanceMatrix[2][1] > distanceMatrix[2][2]);
// Two equal vectors (despite them being zero) should have 0 distance.
- assertEquals(distanceMeasure.distance(new SequentialAccessSparseVector(1),
- new SequentialAccessSparseVector(1)), 0, EPSILON);
+ assertEquals(0,
+ distanceMeasure.distance(new SequentialAccessSparseVector(1),
+ new SequentialAccessSparseVector(1)),
+ EPSILON);
}
}
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasuresTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasuresTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasuresTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasuresTest.java Wed Jun 5 05:20:34 2013
@@ -33,9 +33,9 @@ public class VectorSimilarityMeasuresTes
double rand = computeSimilarity(one, two, similarityMeasureClass, new RandomAccessSparseVector(one.length));
double seq = computeSimilarity(one, two, similarityMeasureClass, new SequentialAccessSparseVector(one.length));
double dense = computeSimilarity(one, two, similarityMeasureClass, new DenseVector(one.length));
- assertEquals(seq, rand, 1e-10);
- assertEquals(seq, dense, 1e-10);
- assertEquals(dense, rand, 1e-10);
+ assertEquals(seq, rand, 1.0e-10);
+ assertEquals(seq, dense, 1.0e-10);
+ assertEquals(dense, rand, 1.0e-10);
return seq;
}
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/solver/TestDistributedConjugateGradientSolver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/solver/TestDistributedConjugateGradientSolver.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/solver/TestDistributedConjugateGradientSolver.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/solver/TestDistributedConjugateGradientSolver.java Wed Jun 5 05:20:34 2013
@@ -20,7 +20,6 @@ package org.apache.mahout.math.hadoop.so
import java.io.File;
import java.util.Random;
-import org.apache.hadoop.conf.Configuration;
import org.apache.mahout.common.MahoutTestCase;
import org.apache.mahout.common.RandomUtils;
import org.apache.mahout.math.DenseVector;
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/LocalitySensitiveHashSearchTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/LocalitySensitiveHashSearchTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/LocalitySensitiveHashSearchTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/LocalitySensitiveHashSearchTest.java Wed Jun 5 05:20:34 2013
@@ -57,7 +57,7 @@ public class LocalitySensitiveHashSearch
cut.setRaiseHashLimitStrategy(strategy);
OnlineSummarizer t1 = evaluateStrategy(testData, ref, cut);
int evals = cut.resetEvaluationCount();
- final double speedup = 10e6 / evals;
+ final double speedup = 10.0e6 / evals;
System.out.printf("%.1f,%.2f,%.2f,%.2f\n", speedup, t1.getQuartile(1),
t1.getQuartile(2), t1.getQuartile(3));
assertTrue(t1.getQuartile(2) > 0.45);
@@ -66,8 +66,8 @@ public class LocalitySensitiveHashSearch
}
}
- private OnlineSummarizer evaluateStrategy(Matrix testData, BruteSearch ref,
- LocalitySensitiveHashSearch cut) {
+ private static OnlineSummarizer evaluateStrategy(Matrix testData, BruteSearch ref,
+ LocalitySensitiveHashSearch cut) {
OnlineSummarizer t1 = new OnlineSummarizer();
for (int i = 0; i < 100; i++) {
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchQualityTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchQualityTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchQualityTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchQualityTest.java Wed Jun 5 05:20:34 2013
@@ -20,7 +20,7 @@ import org.junit.runners.Parameterized;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;
-@RunWith(value = Parameterized.class)
+@RunWith(Parameterized.class)
public class SearchQualityTest {
private static final int NUM_DATA_POINTS = 1 << 14;
private static final int NUM_QUERIES = 1 << 10;
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchSanityTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchSanityTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchSanityTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/math/neighborhood/SearchSanityTest.java Wed Jun 5 05:20:34 2013
@@ -36,7 +36,7 @@ import org.junit.Test;
import org.junit.runner.RunWith;
import org.junit.runners.Parameterized;
-@RunWith(value = Parameterized.class)
+@RunWith(Parameterized.class)
public class SearchSanityTest extends MahoutTestCase {
private static final int NUM_DATA_POINTS = 1 << 13;
private static final int NUM_DIMENSIONS = 20;
@@ -85,7 +85,7 @@ public class SearchSanityTest extends Ma
Vector q = Iterables.get(data, 0).vector();
List<WeightedThing<Vector>> r = searcher.search(q, 2);
- assertEquals(0, r.get(0).getValue().minus(q).norm(1), 1e-8);
+ assertEquals(0, r.get(0).getValue().minus(q).norm(1), 1.0e-8);
final Iterable<MatrixSlice> batch2 = Iterables.limit(Iterables.skip(data, 300), 10);
searcher.addAllMatrixSlices(batch2);
@@ -93,16 +93,16 @@ public class SearchSanityTest extends Ma
q = Iterables.get(data, 302).vector();
r = searcher.search(q, 2);
- assertEquals(0, r.get(0).getValue().minus(q).norm(1), 1e-8);
+ assertEquals(0, r.get(0).getValue().minus(q).norm(1), 1.0e-8);
searcher.addAllMatrixSlices(Iterables.skip(data, 310));
assertEquals(dataPoints.numRows(), searcher.size());
for (MatrixSlice query : queries) {
r = searcher.search(query.vector(), 2);
- assertEquals("Distance has to be about zero", 0, r.get(0).getWeight(), 1e-6);
+ assertEquals("Distance has to be about zero", 0, r.get(0).getWeight(), 1.0e-6);
assertEquals("Answer must be substantially the same as query", 0,
- r.get(0).getValue().minus(query.vector()).norm(1), 1e-8);
+ r.get(0).getValue().minus(query.vector()).norm(1), 1.0e-8);
assertTrue("Wrong answer must have non-zero distance",
r.get(1).getWeight() > r.get(0).getWeight());
}
@@ -120,9 +120,9 @@ public class SearchSanityTest extends Ma
final Vector epsilon = noise.sample();
List<WeightedThing<Vector>> r = searcher.search(query, 2);
query = query.plus(epsilon);
- assertEquals("Distance has to be small", epsilon.norm(2), r.get(0).getWeight(), 1e-1);
+ assertEquals("Distance has to be small", epsilon.norm(2), r.get(0).getWeight(), 1.0e-1);
assertEquals("Answer must be substantially the same as query", epsilon.norm(2),
- r.get(0).getValue().minus(query).norm(2), 1e-1);
+ r.get(0).getValue().minus(query).norm(2), 1.0e-1);
assertTrue("Wrong answer must be further away", r.get(1).getWeight() > r.get(0).getWeight());
}
}
@@ -158,15 +158,15 @@ public class SearchSanityTest extends Ma
List<WeightedThing<Vector>> r0 = searcher.search(x.get(0), 2);
- searcher.remove(x.get(0), 1e-7);
+ searcher.remove(x.get(0), 1.0e-7);
assertEquals(size0 - 1, searcher.size());
List<WeightedThing<Vector>> r = searcher.search(x.get(0), 1);
assertTrue("Vector should be gone", r.get(0).getWeight() > 0);
assertEquals("Previous second neighbor should be first", 0,
- r.get(0).getValue().minus(r0.get(1).getValue()).norm (1), 1e-8);
+ r.get(0).getValue().minus(r0.get(1).getValue()).norm (1), 1.0e-8);
- searcher.remove(x.get(1), 1e-7);
+ searcher.remove(x.get(1), 1.0e-7);
assertEquals(size0 - 2, searcher.size());
r = searcher.search(x.get(1), 1);
@@ -174,13 +174,13 @@ public class SearchSanityTest extends Ma
// Vectors don't show up in iterator.
for (Vector v : searcher) {
- assertTrue(x.get(0).minus(v).norm(1) > 1e-6);
- assertTrue(x.get(1).minus(v).norm(1) > 1e-6);
+ assertTrue(x.get(0).minus(v).norm(1) > 1.0e-6);
+ assertTrue(x.get(1).minus(v).norm(1) > 1.0e-6);
}
} else {
try {
List<Vector> x = Lists.newArrayList(Iterables.limit(searcher, 2));
- searcher.remove(x.get(0), 1e-7);
+ searcher.remove(x.get(0), 1.0e-7);
fail("Shouldn't be able to delete from " + searcher.getClass().getName());
} catch (UnsupportedOperationException e) {
// good enough that UOE is thrown
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyGroupComparatorTest.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyGroupComparatorTest.java?rev=1489707&r1=1489706&r2=1489707&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyGroupComparatorTest.java (original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/vectorizer/collocations/llr/GramKeyGroupComparatorTest.java Wed Jun 5 05:20:34 2013
@@ -25,7 +25,7 @@ public final class GramKeyGroupComparato
@Test
public void testComparator() {
byte[] foo = new byte[1];
- foo[0] = (byte) 1;
+ foo[0] = 1;
byte[] empty = new byte[0];
GramKey a = new GramKey(new Gram("foo", 1, Gram.Type.HEAD), empty); // base