All Projects : Mahout (Key: MAHOUT)

Project Lead: Grant Ingersoll
URL: http://lucene.apache.org/mahout/
Description:
Mahout's goal is to build scalable, Apache licensed machine learning libraries.

Release Notes

 Select:   Open Issues   Road Map   Change Log   Popular Issues   Subversion Commits   Releases   Versions   Components   

Road Map

Progress: 
  59 of 59 issues have been resolved
First Minor Release
   Bug MAHOUT-75 FIXED asFormatString tests fail Critical Closed
   Task MAHOUT-69 FIXED 0.1 RELEASE TODO Major Resolved
   Improvement MAHOUT-53 FIXED Add documentation for Taste Major Resolved
   Task MAHOUT-110 FIXED Ant script for building Taste web app Major Resolved
   Bug MAHOUT-82 FIXED Canopy map intermediate file structure should be keyed by canopyId. Major Resolved
   Improvement MAHOUT-88 FIXED Convert to doubles, other changes Major Resolved
   Bug MAHOUT-23 FIXED Getting a row or column from a matrix view gives a row or column from the wrapped matrix. Major Resolved
   Improvement MAHOUT-99 FIXED Improving speed of KMeans Major Resolved
   Improvement MAHOUT-79 FIXED Improving the speed of Fuzzy K-Means by optimizing data transfer between map and reduce tasks Major Resolved
   New Feature MAHOUT-15 FIXED Investigate Mean Shift Clustering Major Resolved
   Bug MAHOUT-112 FIXED Maven jetty plugin has been relocated Major Resolved
   Task MAHOUT-20 FIXED Migrate Canopy and KMeans Implementations to Vectors Major Resolved
   New Feature MAHOUT-6 FIXED Need a matrix implementation Major Resolved
   Improvement MAHOUT-47 FIXED Point class is now redundant and should be removed Major Resolved
   Improvement MAHOUT-58 FIXED Remove deprecated distance(Float[], Float[]), AbstractDistanceMeasure? Major Resolved
   New Feature MAHOUT-37 FIXED Tarball for Mahout-ified Taste code Major Resolved
   Bug MAHOUT-80 FIXED Taste build fix Major Resolved
   Task MAHOUT-89 FIXED To test hudson, I just made a 'Patch Available' issue. Major Resolved
   New Feature MAHOUT-38 FIXED Ant job jar task Major Closed
   Bug MAHOUT-27 FIXED Canopy/KMeans unit tests failing Major Closed
   New Feature MAHOUT-34 FIXED Iterator interface for Vectors Major Closed
   Bug MAHOUT-118 FIXED Mahout needs to respect the file system type when getting a FileSystem for an input or output path Major Closed
   Bug MAHOUT-26 FIXED Matrix implementation bug fix and little addition Major Closed
   Improvement MAHOUT-33 FIXED Matrix tests share code that can be placed in an abstract class Major Closed
   New Feature MAHOUT-49 FIXED ParameterEnumerable Major Closed
   New Feature MAHOUT-42 FIXED Tanimoto coefficient distance measure Major Closed
   Improvement MAHOUT-50 FIXED Vector extends Writable Major Closed
   Improvement MAHOUT-39 FIXED Vector improvments Major Closed
   New Feature MAHOUT-41 FIXED VectorWritable Major Closed
   Improvement MAHOUT-36 FIXED WeightedDistanceMeasure Major Closed
   New Feature MAHOUT-86 FIXED A New Vector Assignment Operator Minor Resolved
   Bug MAHOUT-92 FIXED BayesFeatureMapper doesn't properly extract features Minor Resolved
   New Feature MAHOUT-3 FIXED Build initial canopy clustering prototype Minor Resolved
   Sub-task MAHOUT-60 FIXED MAHOUT-9
Complementary Naive Bayes
Minor Resolved
   New Feature MAHOUT-74 FIXED Fuzzy K-Means clustering Minor Resolved
   New Feature MAHOUT-9 FIXED Implement MapReduce BayesianClassifier Minor Resolved
   New Feature MAHOUT-5 FIXED Implement a k-means clustering prototype Minor Resolved
   Bug MAHOUT-25 FIXED Minor bugs/issues from code inspection Minor Resolved
   Improvement MAHOUT-104 FIXED Move to Maven for Build, drop Ant Minor Resolved
   Improvement MAHOUT-10 FIXED Replace fall-through exception handlers with propagated unchecked exception. Minor Resolved
   Improvement MAHOUT-72 FIXED Separate out Examples from Core Minor Resolved
   Improvement MAHOUT-52 FIXED Standardize on java.util.logging, Commons Logging, log4j? Minor Resolved
   Improvement MAHOUT-55 FIXED Update to Hadoop 0.16.4 Minor Resolved
   Improvement MAHOUT-102 FIXED Use Watchmaker 0.5.0 instead of 0.4.3 Minor Resolved
   Improvement MAHOUT-95 FIXED UserSimilarity-based NearestNNeighborhood Minor Resolved
   Task MAHOUT-56 FIXED Watchmaker Integration Minor Resolved
   Bug MAHOUT-91 FIXED Wikipedia Example has incorrect input Key Minor Resolved
   Improvement MAHOUT-62 FIXED generate html test results Minor Resolved
   Improvement MAHOUT-17 FIXED Maven support Minor Closed
   Improvement MAHOUT-44 FIXED Override zSum and dot for SparseVector Minor Closed
   Bug MAHOUT-22 FIXED Several matrix exceptions are checked exceptions, but should be unchecked Minor Closed
   Improvement MAHOUT-13 FIXED Investigate Mahout jar loading Trivial Resolved
   Improvement MAHOUT-57 FIXED Mahout Project Logo Trivial Resolved
   Bug MAHOUT-1 FIXED Mahout site doesn't link to mailing list archives. Trivial Resolved
   Improvement MAHOUT-12 FIXED Point formatting and parsing improved (StringBuilder, no need for trailing comma). Trivial Resolved
   Improvement MAHOUT-111 FIXED Redirect Test output to file Trivial Resolved
   Bug MAHOUT-48 FIXED isConverged() and converge flag OK? Trivial Resolved
   Improvement MAHOUT-51 FIXED Upgrade to Hadoop 0.16.3 Trivial Closed
   Improvement MAHOUT-87 FIXED Upgrade to Hadoop 0.18.1 Trivial Closed
Progress: 
  61 of 61 issues have been resolved
   Bug MAHOUT-159 FIXED SparseVector and DenseVector hashCode does not conform to the Java standard Critical Closed
   Task MAHOUT-35 FIXED Benchmark performance of Vector.iterator() when reusing Element instances. Major Resolved
   Improvement MAHOUT-161 FIXED Add Vector.norm to compute k-norms of vectors Major Closed
   Improvement MAHOUT-162 FIXED Added support for mapping String to long IDs in CF code Major Closed
   Improvement MAHOUT-136 FIXED Change Canopy MR Implementation to use Vector Writable Major Closed
   Bug MAHOUT-186 FIXED Classifier PriorityQueue returns erroneous results Major Closed
   Improvement MAHOUT-188 FIXED Cleanup of Bayes/CBayes for 0.2 Major Closed
   Improvement MAHOUT-198 FIXED Cleanup pom, remove lib dependencies, etc. Major Closed
   Improvement MAHOUT-160 FIXED ClusterDumper utility to output all the clusters in all sequence files and points Major Closed
   Improvement MAHOUT-148 FIXED Convert Classification Algs to use richer Writable syntax Major Closed
   Improvement MAHOUT-137 FIXED Convert Clustering Algs to use Vector Writable Major Closed
   Bug MAHOUT-181 FIXED DistanceMeasure is broken: iteration is done over nonZeroElements of v1.plus(v2), not v1.minus(v2) Major Closed
   Improvement MAHOUT-170 FIXED Enable Java compile optimize flag during build Major Closed
   New Feature MAHOUT-157 FIXED Frequent Pattern Mining using Parallel FP-Growth Major Closed
   New Feature MAHOUT-123 FIXED Implement Latent Dirichlet Allocation Major Closed
   New Feature MAHOUT-115 FIXED Interpolated Knn and SVD Recommender Major Closed
   New Feature MAHOUT-7 FIXED Lucene indexes should act as matrix factories Major Closed
   Bug MAHOUT-118 FIXED Mahout needs to respect the file system type when getting a FileSystem for an input or output path Major Closed
   Improvement MAHOUT-139 FIXED Make use of Vector Iterator capabilities where appropriate Major Closed
   Improvement MAHOUT-171 FIXED Move deployment to repository.apache.org Major Closed
   New Feature MAHOUT-124 FIXED Online Classification using HBase Major Closed
   New Feature MAHOUT-126 FIXED Prepare document vectors from the text Major Closed
   Task MAHOUT-122 FIXED Random Forests Reference Implementation Major Closed
   Bug MAHOUT-187 FIXED RandomUtils>>isNotPrime throws IllegalArgumentException when argument is less than 2. Major Closed
   Improvement MAHOUT-154 FIXED Reduce memory usage with smarter data structures Major Closed
   Improvement MAHOUT-158 FIXED Replace all ID values with long Major Closed
   Improvement MAHOUT-121 FIXED Speed up distance calculations for sparse vectors Major Closed
   Improvement MAHOUT-149 FIXED The Great User/Item Removal Phase 1: de-generify implementations Major Closed
   Improvement MAHOUT-150 FIXED The Great User/Item Removal Phase 2 Major Closed
   Improvement MAHOUT-151 FIXED The Great User/Item Removal Phase 3 Major Closed
   Bug MAHOUT-172 FIXED When running on a Hadoop cluster LDA fails with Caused by: java.io.IOException: Cannot open filename /user/*/output/state-*/_logs Major Closed
   Bug MAHOUT-183 FIXED WikipediaXmlSplitter spits one chunk per line Major Closed
   Improvement MAHOUT-134 FIXED [PATCH] Cluster decode error handling Major Closed
   Improvement MAHOUT-133 FIXED [PATCH] Kmeans Clustering Example Tidy Up Major Closed
   Improvement MAHOUT-132 FIXED [PATCH] Push magic names into public constants Major Closed
   Task MAHOUT-108 WON'T FIX Implementation of Assoication Rules learning by Apriori algorithm Major Closed
   Improvement MAHOUT-164 FIXED "Potpourri": a collection of small possible bugs and improvements Minor Closed
   Improvement MAHOUT-135 FIXED Allow FileDataModel to transpose users and items Minor Closed
   Bug MAHOUT-113 FIXED CDInfosToolTest.testGatherInfos failure in Mahout examples Minor Closed
   Improvement MAHOUT-184 FIXED Code tweaks for .df.* code Minor Closed
   Improvement MAHOUT-138 FIXED Convert main() methods to use Commons CLI for argument processing Minor Closed
   Bug MAHOUT-177 FIXED Fix for "java.lang.ClassNotFoundException Exception" Minor Closed
   New Feature MAHOUT-140 FIXED In-memory mapreduce Random Forests Minor Closed
   Improvement MAHOUT-146 FIXED Make Wikipedia Example Classifier more generic Minor Closed
   Wish MAHOUT-199 FIXED Parent POM missing in public maven repository Minor Closed
   New Feature MAHOUT-145 FIXED PartialData mapreduce Random Forests Minor Closed
   Improvement MAHOUT-166 FIXED Potpourri 2 Minor Closed
   Improvement MAHOUT-178 FIXED Rationalize 'utils' and 'common' stuff Minor Closed
   Bug MAHOUT-114 FIXED Release Process Needs to sign published dependencies such as Hadoop, etc. Minor Closed
   Improvement MAHOUT-176 FIXED Remove VectorIterable in favor of just using Iterable<Vector> Minor Closed
   Improvement MAHOUT-127 FIXED Remove warnings Minor Closed
   Question MAHOUT-179 FIXED Taste Demo Help Minor Closed
   Task MAHOUT-174 FIXED Unify Pair implementation, Random number generation Minor Closed
   Improvement MAHOUT-200 FIXED Update information on Mahout site Minor Closed
   Improvement MAHOUT-142 FIXED Upgrade to Hadoop 0.20.0 Minor Closed
   Improvement MAHOUT-175 FIXED Use IOUtils, FileLineIterable/Iterator across the project Minor Closed
   Improvement MAHOUT-131 FIXED Vector improvements Minor Closed
   Improvement MAHOUT-147 FIXED Wikipedia Example improvements Minor Closed
   Improvement MAHOUT-107 FIXED make MySQLJDBCDataModel not final Minor Closed
   Improvement MAHOUT-77 WON'T FIX DistanceMeasure calculation slow for SparseVector Minor Closed
   Improvement MAHOUT-93 DUPLICATE Refactor Bayes and CBayes to share more common code Minor Closed
Progress: 
  8 of 21 issues have been resolved
   New Feature MAHOUT-185 UNRESOLVED Add mahout shell script for easy launching of various algorithms Major Open
   Improvement MAHOUT-204 UNRESOLVED Better integration of Mahout matrix capabilities with Colt Matrix additions Major Open
   Improvement MAHOUT-163 UNRESOLVED Get (better) cluster labels using Log Likelihood Ratio Major Open
   Improvement MAHOUT-206 UNRESOLVED Separate and clearly label different SparseVector implementations Major Open
   Bug MAHOUT-193 UNRESOLVED SparseVectors created with the wrong cardinality in SparseMatrix Major Open
   Bug MAHOUT-11 UNRESOLVED Static fields used throughout clustering code (Canopy, K-Means). Major Open
   Improvement MAHOUT-165 UNRESOLVED Using better primitives hash for sparse vector for performance gains Major Open
   Bug MAHOUT-208 UNRESOLVED Vector.getLengthSquared() is dangerously optimized Major Open
   Bug MAHOUT-207 UNRESOLVED AbstractVector.hashCode() should not care about the order of iteration over elements Major Patch Available
   New Feature MAHOUT-155 UNRESOLVED ARFF VectorIterable Minor Open
   Improvement MAHOUT-209 UNRESOLVED Add aggregate() methods for Vector Minor Open
   Improvement MAHOUT-205 UNRESOLVED Pull Writable (and anything else hadoop dependent) out of the matrix module Minor Open
   New Feature MAHOUT-106 UNRESOLVED PLSI/EM in pig based on hofmann's ACM 04 paper. Minor Patch Available
   Bug MAHOUT-192 FIXED RMSRecommenderEvaluator does not catch NoSuchItemException Major Resolved
   Improvement MAHOUT-201 DUPLICATE OrderedIntDoubleMapping / SparseVector is unnecessarily slow Major Resolved
   Improvement MAHOUT-190 FIXED Make all instance fields private Minor Resolved
   Improvement MAHOUT-182 FIXED New helper methods for Matrix: times(Vector), timesSquared(Vector), numRows() and numCols() Minor Resolved
   Improvement MAHOUT-125 FIXED Remove Deprecated Ant builds Minor Resolved
   Improvement MAHOUT-189 FIXED Standardize use of assert keyword Minor Resolved
   Improvement MAHOUT-196 FIXED bounded values for RecommenderEvaluator Minor Resolved
   Question MAHOUT-195 FIXED doubt about SlopeOneRecommender Minor Resolved

Reports

Recently Created Issues Report
Created vs Resolved Issues Report
Resolution Time Report
Average Age Report
Pie Chart Report
Contribution Report
User Workload Report
Version Workload Report
Time Tracking Report
Single Level Group By Report

Preset Filters


Project Summary

Open Open 42
   20%
Resolved Resolved 84
   40%
Closed Closed 78
   37%
Patch Available Patch Available 5
   2%

Open Issues

By Priority
Major Major 27
   57%
Minor Minor 18
   38%
Trivial Trivial 2
   4%

By Assignee
Ankur 1
   2%
Grant Ingersoll 8
   17%
Isabel Drost 1
   2%
Jeff Eastman 1
   2%
Jeff Eastman 1
   2%
Karl Wettin 3
   6%
Ted Dunning 1
   2%
Unassigned 31
   66%