Author: jeastman
Date: Tue May 18 21:53:52 2010
New Revision: 945913
URL: http://svn.apache.org/viewvc?rev=945913&view=rev
Log:
added clusterdump and ldatopics to build-reuters.sh
Modified:
mahout/trunk/conf/lda.props
mahout/trunk/examples/bin/ (props changed)
mahout/trunk/examples/bin/build-reuters.sh
Modified: mahout/trunk/conf/lda.props
URL:
http://svn.apache.org/viewvc/mahout/trunk/conf/lda.props?rev=945913&r1=945912&r2=945913&view=diff
==============================================================================
--- mahout/trunk/conf/lda.props (original)
+++ mahout/trunk/conf/lda.props Tue May 18 21:53:52 2010
@@ -6,6 +6,6 @@
# The following parameters all have default values if not specified
#a|topicSmoothing = <topic smoothing. Default: 50/numTopics>
-#maxIter|maxIter = <maximum number of iterations. Default: -1 (until
converged)>
-#numReducers|numReducers = <the number of reducers. Default: 2>
+#x|maxIter = <maximum number of iterations. Default: -1 (until converged)>
+#r|numReducers = <the number of reducers. Default: 2>
Propchange: mahout/trunk/examples/bin/
------------------------------------------------------------------------------
--- svn:ignore (added)
+++ svn:ignore Tue May 18 21:53:52 2010
@@ -0,0 +1 @@
+work
Modified: mahout/trunk/examples/bin/build-reuters.sh
URL:
http://svn.apache.org/viewvc/mahout/trunk/examples/bin/build-reuters.sh?rev=945913&r1=945912&r2=945913&view=diff
==============================================================================
--- mahout/trunk/examples/bin/build-reuters.sh (original)
+++ mahout/trunk/examples/bin/build-reuters.sh Tue May 18 21:53:52 2010
@@ -40,6 +40,12 @@ cd ../..
./bin/mahout org.apache.lucene.benchmark.utils.ExtractReuters
./examples/bin/work/reuters-sgm/ ./examples/bin/work/reuters-out/
./bin/mahout seqdirectory -i ./examples/bin/work/reuters-out/ -o
./examples/bin/work/reuters-out-seqdir -c UTF-8
./bin/mahout seq2sparse -i ./examples/bin/work/reuters-out-seqdir/ -o
./examples/bin/work/reuters-out-seqdir-sparse
-#./bin/mahout kmeans -i
./examples/bin/work/reuters-out-seqdir-sparse/tfidf/vectors/ -c
./examples/bin/work/clusters -o ./examples/bin/work/reuters-kmeans -k 20 -ow
+
+# to use k-Means clustering, uncomment the next two lines
+#./bin/mahout kmeans -i
./examples/bin/work/reuters-out-seqdir-sparse/tfidf/vectors/ -c
./examples/bin/work/clusters -o ./examples/bin/work/reuters-kmeans -x 10 -k 20
-ow
+#./bin/mahout clusterdump -s examples/bin/work/reuters-kmeans/clusters-10 -d
examples/bin/work/reuters-out-seqdir-sparse/dictionary.file-0 -dt sequencefile
-b 100 -n 20
+
+# to use LDA clustering, uncomment the next two lines
#./bin/mahout lda -i
./examples/bin/work/reuters-out-seqdir-sparse/tfidf/vectors -o
./examples/bin/work/reuters-lda -k 20 -v 50000 -ow
+#./bin/mahout ldatopics -i ./examples/bin/work/reuters-lda/state-9 -d
./examples/bin/work/reuters-out-seqdir-sparse/dictionary.file-0 -dt sequencefile
