bae 0.0.6-java → 0.0.7-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6f7b557eff0f63a4dfa9007451f932293eb80ece
-  data.tar.gz: 33f009d0119de54ae777e5f76537ca2661dcd047
+  metadata.gz: 71c761f2619746bfc4dd287a5afa5443a7bfe037
+  data.tar.gz: 886257c2c8987fd8e95edbb63105ef87d7960de5
 SHA512:
-  metadata.gz: 741fb65cac66f3f47a536e20618dd4dd75880079616652e57651f139c5ad384ca2e508c84d86bf813176e8b39ef590810a8daa33a0dda56b67ffd490fb7a530d
-  data.tar.gz: bc8e0e209dd1b88995e39cbb5d6d18db1437b519599b71c1f6fef06aa22af770da3f6fe7d45c897682056755a5d97023d3c073b3d9329e74ab6407b157173d66
+  metadata.gz: e02048771022daa4b61097ae500831a671f1a6ec3d8e9e48f235efd7ff9902be31678e503b4bd31b6cd0a0526d61c2868f1af39cb619c8c9fb120517242928cc
+  data.tar.gz: c2c7073db8b7afeea466a5aa9db9f157101a9a8e9b38d87787281c204990eb3c4b3f75b64a9ecb2fd7a8dc5629bd807d101b0ea702c38d735ba52e2595bdc822

data/README.md

@@ -28,6 +28,9 @@ You can refer to ["naivebayes"](https://github.com/id774/naivebayes) gem for mor
 classifier = ::Bae::Classifier.new
 classifier.train("positive", {"aaa" => 0, "bbb" => 1})
 classifier.train("negative", {"ccc" => 2, "ddd" => 3})
+
+classifier.finish_training!
+
 classifier.classify({"aaa" => 1, "bbb" => 1})
 
 #=> {"positive" => 0.8767123287671234, "negative" => 0.12328767123287669}
@@ -39,6 +42,9 @@ classifier = ::Bae::Classifier.new
 classifier.train("positive", "aaa aaa bbb");
 classifier.train("negative", "ccc ccc ddd ddd");
 classifier.train("neutral", "eee eee eee fff fff fff");
+
+classifier.finish_training!
+
 classifier.classify("aaa bbb")
 
 #=> {"positive"=>0.8962655601659751, "negative"=>0.0663900414937759, "neutral"=>0.037344398340248955}

data/lib/bae/classifier.rb

@@ -15,5 +15,9 @@ module Bae
       internal_classifier.classify(::Java::Bae::Document.new(feature))
     end
 
+    def finish_training!
+      internal_classifier.calculateInitialLikelihoods()
+    end
+
   end
 end

data/lib/bae/version.rb

@@ -1,3 +1,3 @@
 module Bae
-  VERSION = "0.0.6"
+  VERSION = "0.0.7"
 end

data/spec/lib/bae/classifier_spec.rb

@@ -7,6 +7,9 @@ describe ::Bae::Classifier do
   it "can classify from ruby to java with a hash document" do
     subject.train("positive", {"aaa" => 0, "bbb" => 1})
     subject.train("negative", {"ccc" => 2, "ddd" => 3})
+
+    subject.finish_training!
+
     results = subject.classify({"aaa" => 1, "bbb" => 1})
 
     expect(results["positive"]).to be_within(0.001).of(0.94117)
@@ -17,6 +20,9 @@ describe ::Bae::Classifier do
     subject.train("positive", "aaa aaa bbb");
     subject.train("negative", "ccc ccc ddd ddd");
     subject.train("neutral", "eee eee eee fff fff fff");
+
+    subject.finish_training!
+
     results = subject.classify("aaa bbb")
 
     expect(results["positive"]).to be_within(0.001).of(0.89626)

data/src/main/java/bae/NaiveBayesClassifier.java

@@ -8,12 +8,16 @@ public class NaiveBayesClassifier {
     private FrequencyTable frequencyTable;
     private Map<String, Long> wordTable;
     private Map<String, Long> instanceCountOf;
+    private Map<String, Double> initialLikelihoodOf;
+    Map<String, Double> classPriorOf;
     private double totalCount = 0;
 
     public NaiveBayesClassifier() {
         this.frequencyTable = new FrequencyTable();
         this.wordTable = new HashMap<>();
         this.instanceCountOf = new HashMap<>();
+        this.initialLikelihoodOf = new HashMap<>();
+        this.classPriorOf = new HashMap<>();
     }
 
     public void train(String label, Document document) {
@@ -37,12 +41,23 @@ public class NaiveBayesClassifier {
         updateIntegerCountBy(this.instanceCountOf, label, 1);
     }
 
-    public Map<String, Double> classify(Document document) {
-        Map<String, Double> classPriorOf = new HashMap<>();
-        Map<String, Double> likelihoodOf = new HashMap<>();
-        Map<String, Double> classPosteriorOf = new HashMap<>();
-        Map<String, Long> frequencyMap = document.getFrequencyMap();
-        double evidence = 0;
+    public void calculateInitialLikelihoods() {
+        // Update likelihood counts
+        for(String label : this.frequencyTable.getLabels()) {
+            // Set initial likelihood
+            initialLikelihoodOf.put(label, 1d);
+
+            // Calculate likelihoods
+            for (String word : this.wordTable.keySet()) {
+                double laplaceWordLikelihood =
+                        (this.frequencyTable.get(label, word) + 1d) /
+                        (this.instanceCountOf.get(label) + this.wordTable.size());
+
+                // Update likelihood
+                double likelihood = initialLikelihoodOf.get(label);
+                initialLikelihoodOf.put(label, likelihood * (1d - laplaceWordLikelihood));
+            }
+        }
 
         // Update the prior
         for(Map.Entry<String, Long> entry : this.instanceCountOf.entrySet()) {
@@ -50,36 +65,39 @@ public class NaiveBayesClassifier {
             double frequency = entry.getValue();
 
             // Update instance count
-            classPriorOf.put(label, (frequency / this.totalCount));
+            this.classPriorOf.put(label, (frequency / this.totalCount));
         }
+    }
+
+    public Map<String, Double> classify(Document document) {
+        Map<String, Double> likelihoodOf = new HashMap<>();
+        Map<String, Double> classPosteriorOf = new HashMap<>();
+        Map<String, Long> featureFrequencyMap = document.getFrequencyMap();
+        double evidence = 0;
 
         // Update likelihood counts
         for(String label : this.frequencyTable.getLabels()) {
             // Set initial likelihood
-            likelihoodOf.put(label, 1d);
+            likelihoodOf.put(label, this.initialLikelihoodOf.get(label));
 
-            // Calculate likelihoods
-            for(String word : wordTable.keySet()) {
+            // Calculate actual likelihoods likelihoods
+            for(String word : featureFrequencyMap.keySet()) {
                 double laplaceWordLikelihood =
                         (this.frequencyTable.get(label, word) + 1d) /
                         (this.instanceCountOf.get(label) + this.wordTable.size());
 
-                // Update likelihood
+                // Update likelihood for words not in features
                 double likelihood = likelihoodOf.get(label);
-                if(frequencyMap.containsKey(word)) {
-                    likelihoodOf.put(label, likelihood * laplaceWordLikelihood);
-                } else {
-                    likelihoodOf.put(label, likelihood * (1d - laplaceWordLikelihood));
+                if(featureFrequencyMap.containsKey(word)) {
+                    likelihoodOf.put(label, (likelihood * laplaceWordLikelihood) / (1d - laplaceWordLikelihood));
                 }
             }
 
             // Default class posterior of label to 1.0
-            if(!classPosteriorOf.containsKey(label)) {
-                classPosteriorOf.put(label, 1d);
-            }
+            classPosteriorOf.put(label, 1d);
 
             // Update class posterior
-            double classPosterior = classPriorOf.get(label) * likelihoodOf.get(label);
+            double classPosterior = this.classPriorOf.get(label) * likelihoodOf.get(label);
             classPosteriorOf.put(label, classPosterior);
             evidence += classPosterior;
         }

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bae
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.7
 platform: java
 authors:
 - Garrett Thornburg
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2015-02-18 00:00:00.000000000 Z
+date: 2015-02-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement