You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mahout.apache.org by ro...@apache.org on 2010/02/14 01:19:31 UTC
svn commit: r909938 - in /lucene/mahout/trunk/core/src:
main/java/org/apache/mahout/clustering/canopy/
test/java/org/apache/mahout/clustering/canopy/
Author: robinanil
Date: Sun Feb 14 00:19:31 2010
New Revision: 909938
URL: http://svn.apache.org/viewvc?rev=909938&view=rev
Log:
CanopyClusterer now reports status information
Modified:
lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyClusterer.java
lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java
lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/ClusterMapper.java
lucene/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/canopy/TestCanopyCreation.java
Modified: lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyClusterer.java
URL: http://svn.apache.org/viewvc/lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyClusterer.java?rev=909938&r1=909937&r2=909938&view=diff
==============================================================================
--- lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyClusterer.java (original)
+++ lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyClusterer.java Sun Feb 14 00:19:31 2010
@@ -154,10 +154,13 @@
* the List<Canopy> to be appended
* @param collector
* an OutputCollector in which to emit the point
+ * @param reporter
+ * to report status of the job
*/
public void emitPointToExistingCanopies(Vector point,
List<Canopy> canopies,
- OutputCollector<Text,VectorWritable> collector) throws IOException {
+ OutputCollector<Text,VectorWritable> collector,
+ Reporter reporter) throws IOException {
double minDist = Double.MAX_VALUE;
Canopy closest = null;
boolean isCovered = false;
@@ -168,6 +171,7 @@
isCovered = true;
vw.set(point);
collector.collect(new Text(canopy.getIdentifier()), vw);
+ reporter.setStatus("Emit Canopy ID:" +canopy.getIdentifier());
} else if (dist < minDist) {
minDist = dist;
closest = canopy;
@@ -178,6 +182,7 @@
vw.set(point);
if (!isCovered) {
collector.collect(new Text(closest.getIdentifier()), vw);
+ reporter.setStatus("Emit Closest Canopy ID:" + closest.getIdentifier());
}
}
Modified: lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java
URL: http://svn.apache.org/viewvc/lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java?rev=909938&r1=909937&r2=909938&view=diff
==============================================================================
--- lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java (original)
+++ lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java Sun Feb 14 00:19:31 2010
@@ -47,7 +47,7 @@
private static final Logger log = LoggerFactory.getLogger(CanopyDriver.class);
- private CanopyDriver() { }
+ private CanopyDriver() {}
public static void main(String[] args) throws IOException {
DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
@@ -129,10 +129,10 @@
* @param t2
* the T2 distance threshold
*/
- public static void runJob(String input, String output, String measureClassName, double t1, double t2) throws IOException {
- CanopyDriver.log.info("Input: {} Out: {} Measure: {} t1: {} t2: {}", new Object[] {input, output,
- measureClassName, t1,
- t2});
+ public static void runJob(String input, String output,
+ String measureClassName, double t1, double t2) throws IOException {
+ CanopyDriver.log.info("Input: {} Out: {} "
+ + "Measure: {} t1: {} t2: {}", new Object[] {input, output, measureClassName, t1, t2});
Configurable client = new JobClient();
JobConf conf = new JobConf(CanopyDriver.class);
conf.set(CanopyConfigKeys.DISTANCE_MEASURE_KEY, measureClassName);
Modified: lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/ClusterMapper.java
URL: http://svn.apache.org/viewvc/lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/ClusterMapper.java?rev=909938&r1=909937&r2=909938&view=diff
==============================================================================
--- lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/ClusterMapper.java (original)
+++ lucene/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/ClusterMapper.java Sun Feb 14 00:19:31 2010
@@ -45,7 +45,7 @@
VectorWritable point,
OutputCollector<Text,VectorWritable> output,
Reporter reporter) throws IOException {
- canopyClusterer.emitPointToExistingCanopies(point.get(), canopies, output);
+ canopyClusterer.emitPointToExistingCanopies(point.get(), canopies, output, reporter);
}
/**
Modified: lucene/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/canopy/TestCanopyCreation.java
URL: http://svn.apache.org/viewvc/lucene/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/canopy/TestCanopyCreation.java?rev=909938&r1=909937&r2=909938&view=diff
==============================================================================
--- lucene/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/canopy/TestCanopyCreation.java (original)
+++ lucene/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/canopy/TestCanopyCreation.java Sun Feb 14 00:19:31 2010
@@ -593,7 +593,7 @@
List<VectorWritable> points = getPoints(raw);
// map the data
for (VectorWritable point : points) {
- mapper.map(new Text(), point, collector, null);
+ mapper.map(new Text(), point, collector, new DummyReporter());
}
Map<String, List<VectorWritable>> data = collector.getData();