Repository: mahout Updated Branches: refs/heads/master 9b169e7e7 -> ec8a5a006
MAHOUT-1639: streamingkmeans doesn't properly validate estimatedNumMapClusters -km Project: http://git-wip-us.apache.org/repos/asf/mahout/repo Commit: http://git-wip-us.apache.org/repos/asf/mahout/commit/ec8a5a00 Tree: http://git-wip-us.apache.org/repos/asf/mahout/tree/ec8a5a00 Diff: http://git-wip-us.apache.org/repos/asf/mahout/diff/ec8a5a00 Branch: refs/heads/master Commit: ec8a5a006385c0ecf25f1d982ace83bb3c41e052 Parents: 9b169e7 Author: Suneel Marthi <[email protected]> Authored: Tue Mar 24 23:20:17 2015 -0400 Committer: Suneel Marthi <[email protected]> Committed: Tue Mar 24 23:31:09 2015 -0400 ---------------------------------------------------------------------- CHANGELOG | 4 +++- .../clustering/streaming/mapreduce/StreamingKMeansDriver.java | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/mahout/blob/ec8a5a00/CHANGELOG ---------------------------------------------------------------------- diff --git a/CHANGELOG b/CHANGELOG index 7b1aa09..deadda6 100644 --- a/CHANGELOG +++ b/CHANGELOG @@ -1,6 +1,8 @@ Mahout Change Log -Release 1.0 - unreleased +Release 0.10.0 - unreleased + + MAHOUT-1639: Streamingkmeans doesn't properly validate estimatedNumMapClusters -km (smarthi) MAHOUT-1493: Port Naive Bayes to Scala DSL (apalumbo) http://git-wip-us.apache.org/repos/asf/mahout/blob/ec8a5a00/mrlegacy/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java ---------------------------------------------------------------------- diff --git a/mrlegacy/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java b/mrlegacy/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java index c8f061f..73776b9 100644 --- a/mrlegacy/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java +++ b/mrlegacy/src/main/java/org/apache/mahout/clustering/streaming/mapreduce/StreamingKMeansDriver.java @@ -169,7 +169,7 @@ public final class StreamingKMeansDriver extends AbstractJob { addOption(ESTIMATED_NUM_MAP_CLUSTERS, "km", "The estimated number of clusters to use for the " + "Map phase of the job when running StreamingKMeans. This should be around k * log(n), " + "where k is the final number of clusters and n is the total number of data points to " - + "cluster."); + + "cluster.", String.valueOf(1)); addOption(ESTIMATED_DISTANCE_CUTOFF, "e", "The initial estimated distance cutoff between two " + "points for forming new clusters. If no value is given, it's estimated from the data set",
