mahout-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From s..@apache.org
Subject svn commit: r1587423 - in /mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes: ComplementaryNaiveBayesClassifier.java NaiveBayesModel.java StandardNaiveBayesClassifier.java training/TrainNaiveBayesJob.java
Date Tue, 15 Apr 2014 05:22:32 GMT
Author: ssc
Date: Tue Apr 15 05:22:31 2014
New Revision: 1587423

URL: http://svn.apache.org/r1587423
Log:
MAHOUT-1504 fixed minor style issues

Modified:
    mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/ComplementaryNaiveBayesClassifier.java
    mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/NaiveBayesModel.java
    mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/StandardNaiveBayesClassifier.java
    mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/training/TrainNaiveBayesJob.java

Modified: mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/ComplementaryNaiveBayesClassifier.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/ComplementaryNaiveBayesClassifier.java?rev=1587423&r1=1587422&r2=1587423&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/ComplementaryNaiveBayesClassifier.java
(original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/ComplementaryNaiveBayesClassifier.java
Tue Apr 15 05:22:31 2014
@@ -18,10 +18,7 @@
 package org.apache.mahout.classifier.naivebayes;
 
 
-/**
- * Class implementing the Naive Bayes Classifier Algorithm
- * 
- */
+/** Implementation of the Naive Bayes Classifier Algorithm */
 public class ComplementaryNaiveBayesClassifier extends AbstractNaiveBayesClassifier {
   public ComplementaryNaiveBayesClassifier(NaiveBayesModel model) {
     super(model);
@@ -30,13 +27,13 @@ public class ComplementaryNaiveBayesClas
   @Override
   public double getScoreForLabelFeature(int label, int feature) {
     NaiveBayesModel model = getModel();
-    double weight=computeWeight(model.featureWeight(feature), model.weight(label, feature),
+    double weight = computeWeight(model.featureWeight(feature), model.weight(label, feature),
         model.totalWeightSum(), model.labelWeight(label), model.alphaI(), model.numFeatures());
-    // http://people.csail.mit.edu/jrennie/papers/icml03-nb.pdf - Section 3.2, Weight Magnitude
Errors
-    return weight/model.thetaNormalizer(label);
+    // see http://people.csail.mit.edu/jrennie/papers/icml03-nb.pdf - Section 3.2, Weight
Magnitude Errors
+    return weight / model.thetaNormalizer(label);
   }
 
-  // http://people.csail.mit.edu/jrennie/papers/icml03-nb.pdf - Section 3.1, Skewed Data
bias
+  // see http://people.csail.mit.edu/jrennie/papers/icml03-nb.pdf - Section 3.1, Skewed Data
bias
   public static double computeWeight(double featureWeight, double featureLabelWeight,
       double totalWeight, double labelWeight, double alphaI, double numFeatures) {
     double numerator = featureWeight - featureLabelWeight + alphaI;

Modified: mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/NaiveBayesModel.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/NaiveBayesModel.java?rev=1587423&r1=1587422&r2=1587423&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/NaiveBayesModel.java
(original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/NaiveBayesModel.java
Tue Apr 15 05:22:31 2014
@@ -33,12 +33,11 @@ import org.apache.mahout.math.VectorWrit
 import com.google.common.base.Preconditions;
 import com.google.common.io.Closeables;
 
-/** NaiveBayesModel holds the weight Matrix, the feature and label sums and the weight normalizer
vectors.*/
+/** NaiveBayesModel holds the weight matrix, the feature and label sums and the weight normalizer
vectors.*/
 public class NaiveBayesModel {
 
   private final Vector weightsPerLabel;
   private final Vector perlabelThetaNormalizer;
-  //  private final double minThetaNormalizer;
   private final Vector weightsPerFeature;
   private final Matrix weightsPerLabelAndFeature;
   private final float alphaI;
@@ -57,7 +56,6 @@ public class NaiveBayesModel {
     this.numFeatures = weightsPerFeature.getNumNondefaultElements();
     this.totalWeightSum = weightsPerLabel.zSum();
     this.alphaI = alphaI;
-//    this.minThetaNormalizer = thetaNormalizer.maxValue();
   }
 
   public double labelWeight(int label) {

Modified: mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/StandardNaiveBayesClassifier.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/StandardNaiveBayesClassifier.java?rev=1587423&r1=1587422&r2=1587423&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/StandardNaiveBayesClassifier.java
(original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/StandardNaiveBayesClassifier.java
Tue Apr 15 05:22:31 2014
@@ -18,7 +18,7 @@
 package org.apache.mahout.classifier.naivebayes;
 
 
-/** Class implementing the Naive Bayes Classifier Algorithm */
+/** Implementation of the Naive Bayes Classifier Algorithm */
 public class StandardNaiveBayesClassifier extends AbstractNaiveBayesClassifier { 
  
   public StandardNaiveBayesClassifier(NaiveBayesModel model) {
@@ -28,9 +28,8 @@ public class StandardNaiveBayesClassifie
   @Override
   public double getScoreForLabelFeature(int label, int feature) {
     NaiveBayesModel model = getModel();
-    // Standard Naive Bayes does not use weight normalization
-    // uncomment following line for weight normalized NB
-    // weight=weight/model.thetaNormalizer(label);
+    // Standard Naive Bayes does not use weight normalization, uncomment following line for
weight normalized NB
+    // weight = weight / model.thetaNormalizer(label);
     return computeWeight(model.weight(label, feature), model.labelWeight(label), model.alphaI(),
model.numFeatures());
   }
 

Modified: mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/training/TrainNaiveBayesJob.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/training/TrainNaiveBayesJob.java?rev=1587423&r1=1587422&r2=1587423&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/training/TrainNaiveBayesJob.java
(original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/classifier/naivebayes/training/TrainNaiveBayesJob.java
Tue Apr 15 05:22:31 2014
@@ -43,9 +43,7 @@ import org.apache.mahout.math.VectorWrit
 
 import com.google.common.base.Splitter;
 
-/**
- * This class trains a Naive Bayes Classifier (Parameters for both Naive Bayes and Complementary
Naive Bayes)
- */
+/** Trains a Naive Bayes Classifier (parameters for both Naive Bayes and Complementary Naive
Bayes) */
 public final class TrainNaiveBayesJob extends AbstractJob {
   private static final String TRAIN_COMPLEMENTARY = "trainComplementary";
   private static final String ALPHA_I = "alphaI";
@@ -93,13 +91,12 @@ public final class TrainNaiveBayesJob ex
     }
     long labelSize = createLabelIndex(labPath);
     float alphaI = Float.parseFloat(getOption(ALPHA_I));
-    //boolean trainComplementary = Boolean.parseBoolean(getOption(TRAIN_COMPLEMENTARY));
//always result to false
     boolean trainComplementary = hasOption(TRAIN_COMPLEMENTARY);
 
     HadoopUtil.setSerializations(getConf());
     HadoopUtil.cacheFiles(labPath, getConf());
 
-    //add up all the vectors with the same labels, while mapping the labels into our index
+    // Add up all the vectors with the same labels, while mapping the labels into our index
     Job indexInstances = prepareJob(getInputPath(),
                                     getTempPath(SUMMED_OBSERVATIONS),
                                     SequenceFileInputFormat.class,
@@ -115,7 +112,7 @@ public final class TrainNaiveBayesJob ex
     if (!succeeded) {
       return -1;
     }
-    //sum up all the weights from the previous step, per label and per feature
+    // Sum up all the weights from the previous step, per label and per feature
     Job weightSummer = prepareJob(getTempPath(SUMMED_OBSERVATIONS),
                                   getTempPath(WEIGHTS),
                                   SequenceFileInputFormat.class,
@@ -133,11 +130,10 @@ public final class TrainNaiveBayesJob ex
       return -1;
     }
 
-    //put the per label and per feature vectors into the cache
+    // Put the per label and per feature vectors into the cache
     HadoopUtil.cacheFiles(getTempPath(WEIGHTS), getConf());
 
-    // calculate the per label theta normalizers, write out to LABEL_THETA_NORMALIZER vector
--
-    // Rennie 3.2      
+    // Calculate the per label theta normalizers, write out to LABEL_THETA_NORMALIZER vector
-- Rennie 3.2
     Job thetaSummer = prepareJob(getTempPath(SUMMED_OBSERVATIONS),
                                  getTempPath(THETAS),
                                  SequenceFileInputFormat.class,
@@ -156,10 +152,10 @@ public final class TrainNaiveBayesJob ex
       return -1;
     }
     
-    //put the per label theta normalizers into the cache 
+    // Put the per label theta normalizers into the cache
     HadoopUtil.cacheFiles(getTempPath(THETAS), getConf());
     
-    //validate our model and then write it out to the official output
+    // Validate our model and then write it out to the official output
     getConf().setFloat(ThetaMapper.ALPHA_I, alphaI);
     NaiveBayesModel naiveBayesModel = BayesUtils.readModelFromDir(getTempPath(), getConf());
     naiveBayesModel.validate();



Mime
View raw message