nlp_backpack 0.0.0

data/spec/nlp_backpack_spec.rb

@@ -0,0 +1,4 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe "NlpBackpack" do
+end

data/spec/pos/brill_tagger_spec.rb

@@ -0,0 +1,24 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+
+include NLPBackpack
+
+describe POS::BrillTagger do
+  before(:all) do
+    @pos = POS::BrillTagger.analyze(text)
+  end
+
+  it "should properly tag 'the fast fox'" do
+    @pos[0][1].should == "DT"
+    @pos[1][1].should == "JJ"
+    @pos[2][1].should == "NN"
+  end
+
+  it "should return a POSData object" do
+    @pos.should be_a(POS::POSArray)
+  end
+
+  def text
+    "This regular expression is read in the following manner: Zero or more adjectives or nouns, followed by an option group of a noun and a preposition, followed again by zero or more adjectives or nouns, followed by a single noun. A sequence of tags matching this pattern ensures that the corresponding words make up a noun phrase.
+    In addition to simply pulling out the phrases, it is common to do some simple post processing to link variants together (For example, unpluralizing plural variants)."
+  end
+end

data/spec/pos/pos_array_spec.rb

@@ -0,0 +1,45 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'nlp_backpack/pos/pos_array'
+
+include NLPBackpack
+
+describe POS::POSArray do
+  before do
+    @pos_a = POS::POSArray.new
+  end
+
+  describe "Appending words" do
+    describe "Using <<" do
+      it "should raise an error if we insert too much data" do
+        lambda do
+          @pos_a << ["hello", :NN, "LOL"]
+        end.should raise_error
+      end
+
+      it "size should be 2" do
+        2.times { @pos_a << word }
+        @pos_a.size.should == 2
+      end
+    end
+
+    describe "Using #append" do
+      it "size should be 2" do
+        2.times { @pos_a.append(*word) }
+        @pos_a.size.should == 2
+      end
+    end
+  end
+
+  describe "to_s" do
+    it "should return properly formed string for ChunkGrammer" do
+      @pos_a << word
+      @pos_a << word
+
+      @pos_a.to_s.should == "hello/NN hello/NN"
+    end
+  end
+
+  def word
+    ["hello", :NN]
+  end
+end

data/spec/spec.opts

@@ -0,0 +1 @@
+--color

data/spec/spec_helper.rb

@@ -0,0 +1,18 @@
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'rubygems'
+require 'nlp_backpack'
+require 'spec'
+require 'spec/autorun'
+
+Spec::Runner.configure do |config|
+
+end
+
+def correct_results
+  [1,1,2,1,1,1,1,1,1,1]
+end
+
+def test_results
+  [1,1,3,1,1,1,1,1,1,1]
+end

data/spec/stop_words_spec.rb

@@ -0,0 +1,15 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+include NLPBackpack
+
+describe StopWords do
+  before(:all) { @stop_words = StopWords.all }
+
+  it "should return z" do
+    @stop_words.last.should == "z"
+  end
+
+  it "should return a" do
+    @stop_words.first.should == "a"
+  end
+end

data/spec/test_saves/naive.nb

@@ -0,0 +1 @@
+o:(NLPBackpack::Classifier::NaiveBayes	:@features_count{:	spam}"	wordf1"badf1f0:ham}"wef1"badf1@:@db_filepath"M/Users/reddavis/Documents/projects/nlp_backpack/spec/test_saves/naive.nb:

data/spec/tokenizers/custom_spec.rb

@@ -0,0 +1,24 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'nlp_backpack/tokenizers/custom'
+
+include NLPBackpack
+
+describe Tokenizer::Custom do
+  describe "split by ands" do
+    it "should return 3" do
+      a = Tokenizer::Custom.tokenize(text, "and")
+      a.size.should == 3
+    end
+  end
+
+  describe "split by any character" do
+    it "should return 3" do
+      a = Tokenizer::Custom.tokenize("and", //)
+      a.size.should == 3
+    end
+  end
+
+  def text
+    "hello and there and this"
+  end
+end

data/spec/tokenizers/line_spec.rb

@@ -0,0 +1,15 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'nlp_backpack/tokenizers/line'
+
+include NLPBackpack
+
+describe Tokenizer::Line do
+  it "should split text by whitespace" do
+    a = Tokenizer::Line.tokenize(text)
+    a.size.should == 3
+  end
+
+  def text
+    "hello\n\nthere this"
+  end
+end

data/spec/tokenizers/space_spec.rb

@@ -0,0 +1,15 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'nlp_backpack/tokenizers/space'
+
+include NLPBackpack
+
+describe Tokenizer::Space do
+  it "should split text by single spaces" do
+    a = Tokenizer::Space.tokenize(text)
+    a.size.should == 4
+  end
+
+  def text
+    "hello  there this"
+  end
+end

data/spec/tokenizers/tab_spec.rb

@@ -0,0 +1,15 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'nlp_backpack/tokenizers/tab'
+
+include NLPBackpack
+
+describe Tokenizer::Tab do
+  it "should split text by single tabs" do
+    a = Tokenizer::Tab.tokenize(text)
+    a.size.should == 4
+  end
+
+  def text
+    "hello\tthere\t\tthis"
+  end
+end

data/spec/tokenizers/whitespace_spec.rb

@@ -0,0 +1,16 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'nlp_backpack/tokenizers/whitespace'
+
+include NLPBackpack
+
+describe Tokenizer::Whitespace do
+  it "should split text by whitespace" do
+    a = Tokenizer::Whitespace.tokenize(text)
+    a.size.should == 3
+    a[0].should == "hello"
+  end
+
+  def text
+    "hello there this"
+  end
+end

data/spec/tokenizers/word_spec.rb

@@ -0,0 +1,15 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+require 'nlp_backpack/tokenizers/word'
+
+include NLPBackpack
+
+describe Tokenizer::Word do
+  it "should split text by words" do
+    a = Tokenizer::Word.tokenize(text)
+    a.size.should == 5
+  end
+
+  def text
+    "hello; there, this. that you're"
+  end
+end

metadata

@@ -0,0 +1,141 @@
+--- !ruby/object:Gem::Specification 
+name: nlp_backpack
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 0
+  version: 0.0.0
+platform: ruby
+authors: 
+- reddavis
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-06-21 00:00:00 +01:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 1
+        - 2
+        - 9
+        version: 1.2.9
+  type: :development
+  version_requirements: *id001
+description: A backpack full of useful toys
+email: reddavis@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/nlp_backpack.rb
+- lib/nlp_backpack/chunker.rb
+- lib/nlp_backpack/chunker/regex_chunker.rb
+- lib/nlp_backpack/chunker/tag_pattern.rb
+- lib/nlp_backpack/classifier.rb
+- lib/nlp_backpack/classifier/base.rb
+- lib/nlp_backpack/classifier/naive_bayes.rb
+- lib/nlp_backpack/evaluation.rb
+- lib/nlp_backpack/evaluation/accuracy.rb
+- lib/nlp_backpack/evaluation/base.rb
+- lib/nlp_backpack/evaluation/confusion_matrix.rb
+- lib/nlp_backpack/frequency_distribution.rb
+- lib/nlp_backpack/pos.rb
+- lib/nlp_backpack/pos/brill_tagger.rb
+- lib/nlp_backpack/pos/brill_tagger/lexicon.txt
+- lib/nlp_backpack/pos/pos_array.rb
+- lib/nlp_backpack/stop_words.rb
+- lib/nlp_backpack/stop_words/stop_words.txt
+- lib/nlp_backpack/tokenizers/custom.rb
+- lib/nlp_backpack/tokenizers/line.rb
+- lib/nlp_backpack/tokenizers/space.rb
+- lib/nlp_backpack/tokenizers/tab.rb
+- lib/nlp_backpack/tokenizers/whitespace.rb
+- lib/nlp_backpack/tokenizers/word.rb
+- nlp_backpack.gemspec
+- spec/chunkers/regex_chunker_spec.rb
+- spec/chunkers/tag_pattern_spec.rb
+- spec/classifiers/naive_bayes_spec.rb
+- spec/evaluation/accuracy_spec.rb
+- spec/evaluation/confusion_matrix_spec.rb
+- spec/frequency_distribution_spec.rb
+- spec/nlp_backpack_spec.rb
+- spec/pos/brill_tagger_spec.rb
+- spec/pos/pos_array_spec.rb
+- spec/spec.opts
+- spec/spec_helper.rb
+- spec/stop_words_spec.rb
+- spec/test_saves/naive.nb
+- spec/tokenizers/custom_spec.rb
+- spec/tokenizers/line_spec.rb
+- spec/tokenizers/space_spec.rb
+- spec/tokenizers/tab_spec.rb
+- spec/tokenizers/whitespace_spec.rb
+- spec/tokenizers/word_spec.rb
+has_rdoc: true
+homepage: http://github.com/reddavis/NLP-Backpack
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.6
+signing_key: 
+specification_version: 3
+summary: A backpack full of useful toys
+test_files: 
+- spec/chunkers/regex_chunker_spec.rb
+- spec/chunkers/tag_pattern_spec.rb
+- spec/classifiers/naive_bayes_spec.rb
+- spec/evaluation/accuracy_spec.rb
+- spec/evaluation/confusion_matrix_spec.rb
+- spec/frequency_distribution_spec.rb
+- spec/nlp_backpack_spec.rb
+- spec/pos/brill_tagger_spec.rb
+- spec/pos/pos_array_spec.rb
+- spec/spec_helper.rb
+- spec/stop_words_spec.rb
+- spec/tokenizers/custom_spec.rb
+- spec/tokenizers/line_spec.rb
+- spec/tokenizers/space_spec.rb
+- spec/tokenizers/tab_spec.rb
+- spec/tokenizers/whitespace_spec.rb
+- spec/tokenizers/word_spec.rb