mahout-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
Subject svn commit: r701656 - /lucene/mahout/site/src/documentation/content/xdocs/taste.xml
Date Sat, 04 Oct 2008 15:42:49 GMT
Author: srowen
Date: Sat Oct  4 08:42:49 2008
New Revision: 701656

Updated references to Correlation to Similarity


Modified: lucene/mahout/site/src/documentation/content/xdocs/taste.xml
--- lucene/mahout/site/src/documentation/content/xdocs/taste.xml (original)
+++ lucene/mahout/site/src/documentation/content/xdocs/taste.xml Sat Oct  4 08:42:49 2008
@@ -23,7 +23,7 @@
-  <li><code>UserCorrelation</code> and <code>ItemCorrelation</code></li>
+  <li><code>UserSimilarity</code> and <code>ItemSimilarity</code></li>
@@ -69,11 +69,11 @@
-<section><title>UserCorrelation, ItemCorrelation</title>
+<section><title>UserSimilarity, ItemSimilarity</title>
-<p>A <code>UserCorrelation</code> defines a notion of similarity between
two <code>User</code>s.
+<p>A <code>UserSimilarity</code> defines a notion of similarity between
two <code>User</code>s.
 This is a crucial part of a recommendation engine. These are attached to a <code>Neighborhood</code>
-<code>ItemCorrelation</code>s are analagous, but find similarity between <code>Item</code>s.</p>
+<code>ItemSimilarity</code>s are analagous, but find similarity between <code>Item</code>s.</p>
@@ -82,7 +82,7 @@
 <p>In a user-based recommender, recommendations are produced by finding a "neighborhood"
 similar users near a given user. A <code>UserNeighborhood</code> defines a means
of determining
 that neighborhood &#8212; for example, nearest 10 users. Implementations typically need
-<code>UserCorrelation</code> to operate.</p>
+<code>UserSimilarity</code> to operate.</p>
@@ -171,24 +171,24 @@
 <pre>DataModel model = new FileDataModel(new File("data.txt"));
-<p>We'll use the PearsonCorrelation implementation of <code>UserCorrelation</code>
as our user
+<p>We'll use the PearsonCorrelationSimilarity implementation of <code>UserSimilarity</code>
as our user
 correlation algorithm, and add an optional preference inference algorithm:</p>
-<pre>UserCorrelation userCorrelation = new PearsonCorrelation(model);
+<pre>UserSimilarity userSimilarity = new PearsonCorrelationSimilarity(model);
 // Optional:
-userCorrelation.setPreferenceInferrer(new AveragingPreferenceInferrer());
+userSimilarity.setPreferenceInferrer(new AveragingPreferenceInferrer());
 <p>Now we create a <code>UserNeighborhood</code> algorithm. Here we use
 <pre>UserNeighborhood neighborhood =
-  new NearestNUserNeighborhood(3, userCorrelation, model);
+  new NearestNUserNeighborhood(3, userSimilarity, model);
 <p>Now we can create our <code>Recommender</code>, and add a caching decorator:</p>
 <pre>Recommender recommender =
-  new GenericUserBasedRecommender(model, neighborhood, userCorrelation);
+  new GenericUserBasedRecommender(model, neighborhood, userSimilarity);
 Recommender cachingRecommender = new CachingRecommender(recommender);
@@ -214,23 +214,23 @@
 <pre>DataModel model = new FileDataModel(new File("data.txt"));
-<p>We'll also need an <code>ItemCorrelation</code>. We could use <code>PearsonCorrelation</code>,
+<p>We'll also need an <code>ItemSimilarity</code>. We could use <code>PearsonCorrelationSimilarity</code>,
 which computes item similarity in realtime, but, this is generally too slow to be useful.
 Instead, in a real application, you would feed a list of pre-computed correlations to
-a <code>GenericItemCorrelation</code>:</p>
+a <code>GenericItemSimilarity</code>:</p>
 <pre>// Construct the list of pre-compted correlations
-Collection&lt;GenericItemCorrelation.ItemItemCorrelation&gt; correlations =
+Collection&lt;GenericItemSimilarity.ItemItemSimilarity&gt; correlations =
-ItemCorrelation itemCorrelation =
-  new GenericItemCorrelation(correlations);
+ItemSimilarity itemSimilarity =
+  new GenericItemSimilarity(correlations);
 <p>Then we can finish as before to produce recommendations:</p>
 <pre>Recommender recommender =
-  new GenericItemBasedRecommender(model, itemCorrelation);
+  new GenericItemBasedRecommender(model, itemSimilarity);
 Recommender cachingRecommender = new CachingRecommender(recommender);
 List&lt;RecommendedItem&gt; recommendations =

View raw message