You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mahout.apache.org by dr...@apache.org on 2010/07/23 22:40:51 UTC
svn commit: r967253 - in /mahout/trunk:
core/src/main/java/org/apache/mahout/clustering/meanshift/
examples/src/main/java/org/apache/mahout/text/
utils/src/main/java/org/apache/mahout/clustering/cdbw/
utils/src/main/java/org/apache/mahout/utils/nlp/col...
Author: drew
Date: Fri Jul 23 20:40:51 2010
New Revision: 967253
URL: http://svn.apache.org/viewvc?rev=967253&view=rev
Log:
Many cases where job.setJarByClass(Class) was not being called, possibly related to MAHOUT-167 MAHOUT-427
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java
mahout/trunk/examples/src/main/java/org/apache/mahout/text/WikipediaToSequenceFile.java
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/cdbw/CDbwDriver.java
mahout/trunk/utils/src/main/java/org/apache/mahout/utils/nlp/collocations/llr/CollocDriver.java
mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/common/PartialVectorMerger.java
mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DictionaryVectorizer.java
mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DocumentProcessor.java
mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/tfidf/TFIDFConverter.java
Modified: mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java?rev=967253&r1=967252&r2=967253&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java (original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java Fri Jul 23 20:40:51 2010
@@ -331,6 +331,7 @@ public class MeanShiftCanopyDriver exten
private void createCanopyFromVectorsMR(Path input, Path output) throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
Job job = new Job(conf);
+ job.setJarByClass(MeanShiftCanopyDriver.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(MeanShiftCanopy.class);
job.setMapperClass(MeanShiftCanopyCreatorMapper.class);
Modified: mahout/trunk/examples/src/main/java/org/apache/mahout/text/WikipediaToSequenceFile.java
URL: http://svn.apache.org/viewvc/mahout/trunk/examples/src/main/java/org/apache/mahout/text/WikipediaToSequenceFile.java?rev=967253&r1=967252&r2=967253&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/text/WikipediaToSequenceFile.java (original)
+++ mahout/trunk/examples/src/main/java/org/apache/mahout/text/WikipediaToSequenceFile.java Fri Jul 23 20:40:51 2010
@@ -174,6 +174,7 @@ public final class WikipediaToSequenceFi
job.setInputFormatClass(XmlInputFormat.class);
job.setReducerClass(Reducer.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
+ job.setJarByClass(WikipediaToSequenceFile.class);
/*
* conf.set("mapred.compress.map.output", "true"); conf.set("mapred.map.output.compression.type",
Modified: mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/cdbw/CDbwDriver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/cdbw/CDbwDriver.java?rev=967253&r1=967252&r2=967253&view=diff
==============================================================================
--- mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/cdbw/CDbwDriver.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/cdbw/CDbwDriver.java Fri Jul 23 20:40:51 2010
@@ -182,6 +182,7 @@ public final class CDbwDriver extends Ab
conf.set(STATE_IN_KEY, stateIn.toString());
conf.set(DISTANCE_MEASURE_KEY, distanceMeasureClass);
Job job = new Job(conf);
+ job.setJarByClass(CDbwDriver.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(VectorWritable.class);
job.setMapOutputKeyClass(IntWritable.class);
Modified: mahout/trunk/utils/src/main/java/org/apache/mahout/utils/nlp/collocations/llr/CollocDriver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/utils/nlp/collocations/llr/CollocDriver.java?rev=967253&r1=967252&r2=967253&view=diff
==============================================================================
--- mahout/trunk/utils/src/main/java/org/apache/mahout/utils/nlp/collocations/llr/CollocDriver.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/utils/nlp/collocations/llr/CollocDriver.java Fri Jul 23 20:40:51 2010
@@ -206,9 +206,11 @@ public final class CollocDriver extends
con.setBoolean(EMIT_UNIGRAMS, emitUnigrams);
con.setInt(CollocMapper.MAX_SHINGLE_SIZE, maxNGramSize);
con.setInt(CollocReducer.MIN_SUPPORT, minSupport);
+
Job job = new Job(con);
job.setJobName(CollocDriver.class.getSimpleName() + ".generateCollocations:" + input);
-
+ job.setJarByClass(CollocDriver.class);
+
job.setMapOutputKeyClass(GramKey.class);
job.setMapOutputValueClass(Gram.class);
job.setPartitionerClass(GramKeyPartitioner.class);
@@ -253,7 +255,8 @@ public final class CollocDriver extends
Job job = new Job(conf);
job.setJobName(CollocDriver.class.getSimpleName() + ".computeNGrams: " + output);
-
+ job.setJarByClass(CollocDriver.class);
+
job.setMapOutputKeyClass(Gram.class);
job.setMapOutputValueClass(Gram.class);
Modified: mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/common/PartialVectorMerger.java
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/common/PartialVectorMerger.java?rev=967253&r1=967252&r2=967253&view=diff
==============================================================================
--- mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/common/PartialVectorMerger.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/common/PartialVectorMerger.java Fri Jul 23 20:40:51 2010
@@ -92,7 +92,8 @@ public final class PartialVectorMerger {
Job job = new Job(conf);
job.setJobName("PartialVectorMerger::MergePartialVectors");
-
+ job.setJarByClass(PartialVectorMerger.class);
+
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(VectorWritable.class);
Modified: mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DictionaryVectorizer.java
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DictionaryVectorizer.java?rev=967253&r1=967252&r2=967253&view=diff
==============================================================================
--- mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DictionaryVectorizer.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DictionaryVectorizer.java Fri Jul 23 20:40:51 2010
@@ -272,6 +272,7 @@ public final class DictionaryVectorizer
Job job = new Job(conf);
job.setJobName("DictionaryVectorizer::MakePartialVectors: input-folder: " + input
+ ", dictionary-file: " + dictionaryFilePath.toString());
+ job.setJarByClass(DictionaryVectorizer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(StringTuple.class);
@@ -309,6 +310,7 @@ public final class DictionaryVectorizer
Job job = new Job(conf);
job.setJobName("DictionaryVectorizer::WordCount: input-folder: " + input.toString());
+ job.setJarByClass(DictionaryVectorizer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
Modified: mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DocumentProcessor.java
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DocumentProcessor.java?rev=967253&r1=967252&r2=967253&view=diff
==============================================================================
--- mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DocumentProcessor.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/text/DocumentProcessor.java Fri Jul 23 20:40:51 2010
@@ -80,6 +80,7 @@ public final class DocumentProcessor {
Job job = new Job(conf);
job.setJobName("DocumentProcessor::DocumentTokenizer: input-folder: " + input);
+ job.setJarByClass(DocumentProcessor.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(StringTuple.class);
Modified: mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/tfidf/TFIDFConverter.java
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/tfidf/TFIDFConverter.java?rev=967253&r1=967252&r2=967253&view=diff
==============================================================================
--- mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/tfidf/TFIDFConverter.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/utils/vectors/tfidf/TFIDFConverter.java Fri Jul 23 20:40:51 2010
@@ -319,6 +319,8 @@ public final class TFIDFConverter {
Job job = new Job(conf);
job.setJobName("VectorTfIdf Document Frequency Count running over input: " + input.toString());
+ job.setJarByClass(TFIDFConverter.class);
+
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(LongWritable.class);