bae 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: ae80b08d7f073815336ca2f4b6d485e63cc64a16
-  data.tar.gz: 318820b928f8d66049ad5f329b69cc6c47a1bee3
+SHA256:
+  metadata.gz: 7422728086a7f0fcebaaf67b5f30fff38646edd2ae4696f92bab4b9ab7ec9668
+  data.tar.gz: d089c5231adfc4932ca7e0e3a48af72b8437ff67b0c6285330ddbe453194dc90
 SHA512:
-  metadata.gz: 9299062efc70e820d4b491e7b7e257f6cba19f49968e55f3e6c05bbee6b6b7af2178bd829ca019238e8e3b9d654b8082c376e91169202f8c41d49c84a0fafb7a
-  data.tar.gz: c8d55c7517dc22c9ab937e73d523132c68f940ebb297f9f8798a9b8d736011fbdbcdf60e1fc8b3a71aa039b33d505765bb2a2a14e36489e686efe98303baa0be
+  metadata.gz: 9ca7153d587cccd93c8b0c5fb501e881600cc59f2ff6ffa257b88fae8579fe5bc410b9146fa0114c56988ba5b1dc2e3fdfa88b89e00478c479bd80a1817f8708
+  data.tar.gz: 7ca71754f35caa12a3d905f63ae517256fd48a04d86def7cab979872777e1c611d146bd49c3c09ade7e38f98c9d84d4ea32e0e49f3bc84736814cdbe2cd37680

data/.gemignore

@@ -0,0 +1 @@
+vendor/

data/bae.gemspec

@@ -13,7 +13,9 @@ Gem::Specification.new do |spec|
   spec.homepage      = "https://github.com/film42/bae"
   spec.license       = "GPL version 3, or LGPL version 3 (Dual License)"
 
-  spec.files         = `git ls-files -z`.split("\x0")
+  gem_files          = `git ls-files -z`.split("\x0")
+  gem_ignored_files  = `git ls-files -i -X .gemignore -z`.split("\x0")
+  spec.files         = gem_files - gem_ignored_files
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ["lib"]

data/build.xml

@@ -1,18 +1,43 @@
-<project>
+<project name="bae">
+  <path id="classpath.test">
+    <pathelement location="vendor/junit-4.12.jar"/>
+    <pathelement location="vendor/hamcrest-core-1.3.jar"/>
+    <pathelement location="out/classes/"/>
+  </path>
 
-    <target name="clean">
-        <delete dir="out/classes"/>
-    </target>
+  <target name="clean">
+    <delete dir="out/classes"/>
+  </target>
 
-    <target name="compile" depends="clean">
-        <mkdir dir="out"/>
-        <mkdir dir="out/classes"/>
-        <javac srcdir="src/main/java" destdir="out/classes" source="1.7" target="1.7" includeantruntime="false" />
-    </target>
+  <target name="compile" depends="clean">
+    <mkdir dir="out"/>
+    <mkdir dir="out/classes"/>
+    <javac srcdir="src/main/java" destdir="out/classes" source="1.7" target="1.7" includeantruntime="false" debug="on"  />
+  </target>
 
-    <target name="jar" depends="compile">
-        <mkdir dir="target"/>
-        <jar destfile="target/bae.jar" basedir="out/classes" excludes="**/*.jar,**/MANIFEST.MF,**/BCKEY.*" />
-    </target>
+  <target name="jar" depends="compile">
+    <mkdir dir="target"/>
+    <jar destfile="target/bae.jar" basedir="out/classes" excludes="**/*.jar,**/MANIFEST.MF,**/BCKEY.*" />
+  </target>
 
+  <target name="test" depends="compile">
+    <mkdir dir="out"/>
+    <mkdir dir="out/test/"/>
+    <mkdir dir="out/test/classes"/>
+    <javac srcdir="src/test/java" debug="on" destdir="out/test/classes" includeantruntime="false">
+      <classpath refid="classpath.test"/>
+    </javac>
+
+    <junit printsummary="on" haltonfailure="yes" fork="true">
+      <classpath>
+        <path refid="classpath.test"/>
+        <pathelement location="out/test/classes"/>
+        <pathelement location="out/classes"/>
+      </classpath>
+      <formatter type="brief" usefile="false" />
+      <batchtest>
+        <fileset dir="src/test/java" includes="**/*Test.java" />
+      </batchtest>
+    </junit>
+  </target>
 </project>

data/lib/bae/classifier.rb

@@ -13,6 +13,8 @@ module Bae
     end
 
     def finish_training!
+      @frequency_table_size = @frequency_table.keys.size
+
       calculate_likelihoods!
       calculate_priors!
     end
@@ -68,7 +70,7 @@ module Bae
       likelihoods = @likelihoods.dup
       posterior = {}
 
-      vocab_size = frequency_table.keys.size
+      vocab_size = @frequency_table_size
 
       label_index.each do |label, index|
         words.map do |word|
@@ -130,7 +132,7 @@ module Bae
     def calculate_likelihoods!
       @likelihoods = label_index.inject({}) do |accumulator, (label, index)|
         initial_likelihood = 1.0
-        vocab_size = frequency_table.keys.size
+        vocab_size = @frequency_table_size
 
         frequency_table.each do |feature, row|
           laplace_word_likelihood = (row[index] + 1.0).to_f / (label_instance_count[label] + vocab_size).to_f

data/lib/bae/version.rb

@@ -1,3 +1,3 @@
 module Bae
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

data/src/test/java/bae/NaiveBayesClassifierTest.java

@@ -18,6 +18,7 @@ public class NaiveBayesClassifierTest {
         n.train("negative", new Document("ccc ccc ddd ddd ddd"));
         n.train("positive", new Document("aaa bbb bbb"));
         n.train("negative", new Document("ccc ccc ccc ddd ddd ddd ddd"));
+        n.calculateInitialLikelihoods();
 
         assertEquals(1, n.getFrequencyTable().get("positive", "aaa"));
         assertEquals(3, n.getFrequencyTable().get("positive", "bbb"));
@@ -33,6 +34,7 @@ public class NaiveBayesClassifierTest {
         n.train("negative", new Document("ccc ccc ddd ddd ddd"));
         n.train("positive", new Document("aaa bbb bbb"));
         n.train("negative", new Document("ccc ccc ccc ddd ddd ddd ddd"));
+        n.calculateInitialLikelihoods();
 
         assertEquals(1, (long)n.getWordTable().get("aaa"));
         assertEquals(1, (long)n.getWordTable().get("bbb"));
@@ -49,6 +51,7 @@ public class NaiveBayesClassifierTest {
         n.train("positive", new Document("aaa bbb bbb"));
         n.train("negative", new Document("ccc ccc ccc ddd ddd ddd ddd"));
         n.train("negative", new Document("ccc ccc ccc ddd ddd"));
+        n.calculateInitialLikelihoods();
 
         assertEquals(2, (long)n.getInstanceCount().get("positive"));
         assertEquals(3, (long)n.getInstanceCount().get("negative"));
@@ -64,6 +67,7 @@ public class NaiveBayesClassifierTest {
 
         n.train("positive", d);
         n.train("negative", new Document("ccc ccc ddd ddd ddd"));
+        n.calculateInitialLikelihoods();
 
         Map<String, Double> results = n.classify(new Document("aaa bbb"));
 
@@ -80,6 +84,7 @@ public class NaiveBayesClassifierTest {
 
         n.train("positive", d);
         n.train("negative", new Document("ccc ccc ddd ddd ddd"));
+        n.calculateInitialLikelihoods();
 
         Map<String, Double> results = n.classify(new Document("ccc ccc ccc ddd ddd ddd"));
 
@@ -90,10 +95,10 @@ public class NaiveBayesClassifierTest {
     @Test
     public void canCorrectlyClassifyPositiveWithThreeLabels() {
         NaiveBayesClassifier n = new NaiveBayesClassifier();
-
         n.train("positive", new Document("aaa aaa bbb"));
         n.train("negative", new Document("ccc ccc ddd ddd"));
         n.train("neutral", new Document("eee eee eee fff fff fff"));
+        n.calculateInitialLikelihoods();
 
         Map<String, Double> results = n.classify(new Document("aaa bbb"));
 
@@ -109,6 +114,7 @@ public class NaiveBayesClassifierTest {
         n.train("positive", new Document("aaa aaa bbb"));
         n.train("negative", new Document("ccc ccc ddd ddd"));
         n.train("neutral", new Document("eee eee eee fff fff fff"));
+        n.calculateInitialLikelihoods();
 
         Map<String, Double> results = n.classify(new Document("ccc ccc ccc ddd ddd"));
 
@@ -124,6 +130,7 @@ public class NaiveBayesClassifierTest {
         n.train("positive", new Document("aaa aaa bbb"));
         n.train("negative", new Document("ccc ccc ddd ddd"));
         n.train("neutral", new Document("eee eee eee fff fff fff"));
+        n.calculateInitialLikelihoods();
 
         Map<String, Double> results = n.classify(new Document("aaa ddd ddd eee eee eee fff"));
 
@@ -131,4 +138,4 @@ public class NaiveBayesClassifierTest {
         assertEquals(0.09756097560975606, results.get("negative"), 0.00001);
         assertEquals(0.7804878048780488, results.get("neutral"), 0.00001);
     }
-}
+}

metadata

@@ -1,52 +1,52 @@
 --- !ruby/object:Gem::Specification
 name: bae
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Garrett Thornburg
-autorequire:
+autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-06-12 00:00:00.000000000 Z
+date: 2019-02-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
+  name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.6'
-  name: bundler
-  prerelease: false
   type: :development
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.6'
 - !ruby/object:Gem::Dependency
+  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  name: rspec
-  prerelease: false
   type: :development
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  name: rake
-  prerelease: false
   type: :development
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -59,6 +59,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".gemignore"
 - ".gitignore"
 - Gemfile
 - LICENSE.txt
@@ -84,7 +85,7 @@ homepage: https://github.com/film42/bae
 licenses:
 - GPL version 3, or LGPL version 3 (Dual License)
 metadata: {}
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -99,9 +100,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project:
-rubygems_version: 2.6.10
-signing_key:
+rubyforge_project: 
+rubygems_version: 2.7.6
+signing_key: 
 specification_version: 4
 summary: Multinomial naive bayes classifier with a kick of java
 test_files: