Repository: mahout Updated Branches: refs/heads/master 16aeaba99 -> 3aefb18d7
MAHOUT-1593: cluster-reuters.sh does not work complaining java.lang.IllegalStateException Project: http://git-wip-us.apache.org/repos/asf/mahout/repo Commit: http://git-wip-us.apache.org/repos/asf/mahout/commit/3aefb18d Tree: http://git-wip-us.apache.org/repos/asf/mahout/tree/3aefb18d Diff: http://git-wip-us.apache.org/repos/asf/mahout/diff/3aefb18d Branch: refs/heads/master Commit: 3aefb18d73e2df241f38a06d69b001f1669c1d8e Parents: 16aeaba Author: Andrew Musselman <[email protected]> Authored: Fri Apr 3 16:16:31 2015 -0700 Committer: Andrew Musselman <[email protected]> Committed: Fri Apr 3 16:16:31 2015 -0700 ---------------------------------------------------------------------- CHANGELOG | 2 ++ examples/bin/cluster-reuters.sh | 8 ++++---- 2 files changed, 6 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/mahout/blob/3aefb18d/CHANGELOG ---------------------------------------------------------------------- diff --git a/CHANGELOG b/CHANGELOG index 6c9be5b..f44d8ea 100644 --- a/CHANGELOG +++ b/CHANGELOG @@ -2,6 +2,8 @@ Mahout Change Log Release 0.10.0 - unreleased + MAHOUT-1593: cluster-reuters.sh does not work complaining java.lang.IllegalStateException (smarthi via akm) + MAHOUT-1661: All Lanczos modules marked as @Deprecated and slated for removal in future releases (Shannon Quinn) MAHOUT-1638: H2O bindings fail at drmParallelizeWithRowLabels(...) (Anand Avati via apalumbo) http://git-wip-us.apache.org/repos/asf/mahout/blob/3aefb18d/examples/bin/cluster-reuters.sh ---------------------------------------------------------------------- diff --git a/examples/bin/cluster-reuters.sh b/examples/bin/cluster-reuters.sh index 973a1da..7200140 100755 --- a/examples/bin/cluster-reuters.sh +++ b/examples/bin/cluster-reuters.sh @@ -114,14 +114,14 @@ if [ "x$clustertype" == "xkmeans" ]; then -i ${WORK_DIR}/reuters-out-seqdir-sparse-kmeans/tfidf-vectors/ \ -c ${WORK_DIR}/reuters-kmeans-clusters \ -o ${WORK_DIR}/reuters-kmeans \ - -dm org.apache.mahout.common.distance.CosineDistanceMeasure \ + -dm org.apache.mahout.common.distance.EuclideanDistanceMeasure \ -x 10 -k 20 -ow --clustering \ && \ $MAHOUT clusterdump \ - -i ${WORK_DIR}/reuters-kmeans/clusters-*-final \ + -i `hadoop dfs -ls -d ${WORK_DIR}/reuters-kmeans/clusters-*-final | awk'{print $8}'` \ -o ${WORK_DIR}/reuters-kmeans/clusterdump \ -d ${WORK_DIR}/reuters-out-seqdir-sparse-kmeans/dictionary.file-0 \ - -dt sequencefile -b 100 -n 20 --evaluate -dm org.apache.mahout.common.distance.CosineDistanceMeasure -sp 0 \ + -dt sequencefile -b 100 -n 20 --evaluate -dm org.apache.mahout.common.distance.EuclideanDistanceMeasure -sp 0 \ --pointsDir ${WORK_DIR}/reuters-kmeans/clusteredPoints \ && \ cat ${WORK_DIR}/reuters-kmeans/clusterdump @@ -134,7 +134,7 @@ elif [ "x$clustertype" == "xfuzzykmeans" ]; then -i ${WORK_DIR}/reuters-out-seqdir-sparse-fkmeans/tfidf-vectors/ \ -c ${WORK_DIR}/reuters-fkmeans-clusters \ -o ${WORK_DIR}/reuters-fkmeans \ - -dm org.apache.mahout.common.distance.CosineDistanceMeasure \ + -dm org.apache.mahout.common.distance.EuclideanDistanceMeasure \ -x 10 -k 20 -ow -m 1.1 \ && \ $MAHOUT clusterdump \
