You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mahout.apache.org by ss...@apache.org on 2013/03/20 12:29:01 UTC

svn commit: r1458769 - in /mahout/trunk: core/src/main/java/org/apache/mahout/cf/taste/hadoop/similarity/item/ItemSimilarityJob.java examples/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/example/BatchItemSimilaritiesGroupLens.java

Author: ssc
Date: Wed Mar 20 11:29:01 2013
New Revision: 1458769

URL: http://svn.apache.org/r1458769
Log:
small fixes and javadoc

Modified:
    mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/similarity/item/ItemSimilarityJob.java
    mahout/trunk/examples/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/example/BatchItemSimilaritiesGroupLens.java

Modified: mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/similarity/item/ItemSimilarityJob.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/similarity/item/ItemSimilarityJob.java?rev=1458769&r1=1458768&r2=1458769&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/similarity/item/ItemSimilarityJob.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/similarity/item/ItemSimilarityJob.java Wed Mar 20 11:29:01 2013
@@ -66,13 +66,16 @@ import org.apache.mahout.math.map.OpenIn
  * <p>Command line arguments specific to this class are:</p>
  *
  * <ol>
- * <li>-Dmapred.input.dir=(path): Directory containing one or more text files with the preference data</li>
- * <li>-Dmapred.output.dir=(path): output path where similarity data should be written</li>
- * <li>--similarityClassname (classname): Name of distributed similarity measure class to instantiate or a predefined similarity
- *  from {@link org.apache.mahout.math.hadoop.similarity.cooccurrence.measures.VectorSimilarityMeasure}</li>
+ * <li>--input (path): Directory containing one or more text files with the preference data</li>
+ * <li>--output (path): output path where similarity data should be written</li>
+ * <li>--similarityClassname (classname): Name of distributed similarity measure class to instantiate or a predefined
+ *  similarity from {@link org.apache.mahout.math.hadoop.similarity.cooccurrence.measures.VectorSimilarityMeasure}</li>
  * <li>--maxSimilaritiesPerItem (integer): Maximum number of similarities considered per item (100)</li>
- * <li>--maxCooccurrencesPerItem (integer): Maximum number of cooccurrences considered per item (100)</li>
+ * <li>--maxPrefsPerUser (integer): max number of preferences to consider per user, users with more preferences will
+ *  be sampled down (1000)</li>
+ * <li>--minPrefsPerUser (integer): ignore users with less preferences than this (1)</li>
  * <li>--booleanData (boolean): Treat input data as having no pref values (false)</li>
+ * <li>--threshold (double): discard item pairs with a similarity value below this</li>
  * </ol>
  *
  * <p>General command line options are documented in {@link AbstractJob}.</p>
@@ -86,7 +89,7 @@ public final class ItemSimilarityJob ext
 
   private static final int DEFAULT_MAX_SIMILAR_ITEMS_PER_ITEM = 100;
   private static final int DEFAULT_MAX_PREFS_PER_USER = 1000;
-  private static final int DEFAULT_MIN_PREFS_PER_USER = 1;
+  private static final int DEFAULT_MIN_PREFS_PER_USER = 2;
 
   public static void main(String[] args) throws Exception {
     ToolRunner.run(new ItemSimilarityJob(), args);

Modified: mahout/trunk/examples/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/example/BatchItemSimilaritiesGroupLens.java
URL: http://svn.apache.org/viewvc/mahout/trunk/examples/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/example/BatchItemSimilaritiesGroupLens.java?rev=1458769&r1=1458768&r2=1458769&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/example/BatchItemSimilaritiesGroupLens.java (original)
+++ mahout/trunk/examples/src/main/java/org/apache/mahout/cf/taste/similarity/precompute/example/BatchItemSimilaritiesGroupLens.java Wed Mar 20 11:29:01 2013
@@ -18,11 +18,11 @@
 package org.apache.mahout.cf.taste.similarity.precompute.example;
 
 import org.apache.mahout.cf.taste.example.grouplens.GroupLensDataModel;
-import org.apache.mahout.cf.taste.impl.model.file.FileDataModel;
 import org.apache.mahout.cf.taste.impl.recommender.GenericItemBasedRecommender;
 import org.apache.mahout.cf.taste.impl.similarity.LogLikelihoodSimilarity;
 import org.apache.mahout.cf.taste.impl.similarity.precompute.FileSimilarItemsWriter;
 import org.apache.mahout.cf.taste.impl.similarity.precompute.MultithreadedBatchItemSimilarities;
+import org.apache.mahout.cf.taste.model.DataModel;
 import org.apache.mahout.cf.taste.similarity.precompute.BatchItemSimilarities;
 
 import java.io.File;
@@ -48,7 +48,7 @@ public class BatchItemSimilaritiesGroupL
       resultFile.delete();
     }
 
-    FileDataModel dataModel = new GroupLensDataModel(new File(args[0]));
+    DataModel dataModel = new GroupLensDataModel(new File(args[0]));
     GenericItemBasedRecommender recommender = new GenericItemBasedRecommender(dataModel,
         new LogLikelihoodSimilarity(dataModel));
     BatchItemSimilarities batch = new MultithreadedBatchItemSimilarities(recommender, 5);