You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mahout.apache.org by gs...@apache.org on 2012/01/12 21:54:44 UTC

svn commit: r1230780 - in /mahout/trunk: core/src/main/java/org/apache/mahout/clustering/minhash/MinHashDriver.java examples/bin/cluster-reuters.sh

Author: gsingers
Date: Thu Jan 12 20:54:44 2012
New Revision: 1230780

URL: http://svn.apache.org/viewvc?rev=1230780&view=rev
Log:
MAHOUT-854: add in overwrite option for Minhash

Modified:
    mahout/trunk/core/src/main/java/org/apache/mahout/clustering/minhash/MinHashDriver.java
    mahout/trunk/examples/bin/cluster-reuters.sh

Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/minhash/MinHashDriver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/minhash/MinHashDriver.java?rev=1230780&r1=1230779&r2=1230780&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/minhash/MinHashDriver.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/minhash/MinHashDriver.java Thu Jan 12 20:54:44 2012
@@ -30,6 +30,8 @@ import org.apache.hadoop.mapreduce.lib.o
 import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
 import org.apache.hadoop.util.ToolRunner;
 import org.apache.mahout.common.AbstractJob;
+import org.apache.mahout.common.HadoopUtil;
+import org.apache.mahout.common.commandline.DefaultOptionCreator;
 import org.apache.mahout.common.commandline.MinhashOptionCreator;
 import org.apache.mahout.math.VectorWritable;
 
@@ -97,6 +99,7 @@ public final class MinHashDriver extends
     addOption(MinhashOptionCreator.keyGroupsOption().create());
     addOption(MinhashOptionCreator.numReducersOption().create());
     addOption(MinhashOptionCreator.debugOutputOption().create());
+    addOption(DefaultOptionCreator.overwriteOption().create());
 
     if (parseArguments(args) == null) {
       return -1;
@@ -104,6 +107,9 @@ public final class MinHashDriver extends
 
     Path input = getInputPath();
     Path output = getOutputPath();
+    if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
+      HadoopUtil.delete(getConf(), output);
+    }
     int minClusterSize = Integer.valueOf(getOption(MinhashOptionCreator.MIN_CLUSTER_SIZE));
     int minVectorSize = Integer.valueOf(getOption(MinhashOptionCreator.MIN_VECTOR_SIZE));
     String hashType = getOption(MinhashOptionCreator.HASH_TYPE);

Modified: mahout/trunk/examples/bin/cluster-reuters.sh
URL: http://svn.apache.org/viewvc/mahout/trunk/examples/bin/cluster-reuters.sh?rev=1230780&r1=1230779&r2=1230780&view=diff
==============================================================================
--- mahout/trunk/examples/bin/cluster-reuters.sh (original)
+++ mahout/trunk/examples/bin/cluster-reuters.sh Thu Jan 12 20:54:44 2012
@@ -164,7 +164,7 @@ elif [ "x$clustertype" == "xminhash" ]; 
   && \
   $MAHOUT org.apache.mahout.clustering.minhash.MinHashDriver \
     -i ${WORK_DIR}/reuters-out-seqdir-sparse-minhash/tfidf-vectors \
-    -o ${WORK_DIR}/reuters-minhash
+    -o ${WORK_DIR}/reuters-minhash --overwrite
 else 
   echo "unknown cluster type: $clustertype"
 fi