tf-idf_csv 0.1.0

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,21 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2010 Julian Burgess
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,19 @@
+= tf-idf_csv
+
+This provides a simple executable which will read a CSV in the following format and then produce a CSV of each term's TF-IDF.
+
+For more detail about TF-IDF see http://en.wikipedia.org/wiki/Tf%E2%80%93idf
+
+== Note on Patches/Pull Requests
+ 
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+== Copyright
+
+Copyright (c) 2010 Julian Burgess. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,52 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "tf-idf_csv"
+    gem.summary = %Q{Calculate the TF-IDF for terms in a CSV file}
+    gem.email = "jburgess@ap.org"
+    gem.homepage = "http://github.com/aubergene/tf-idf_csv"
+    gem.authors = ["Julian Burgess"]
+    gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+task :test => :check_dependencies
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "tf-idf_csv #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/bin/tf-idf_csv

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+
+$LOAD_PATH.unshift File.dirname(__FILE__) + '/../lib'
+require 'tf-idf_csv'
+
+tf = TfIdf_CSV.new(ARGV[0])
+
+

data/lib/tf-idf_csv.rb

@@ -0,0 +1,100 @@
+require 'csv'
+require 'set'
+
+# This class expects a CSV input
+# One row per document, 
+# the first cell should be a document identifier
+# each subsequent cell contains one term. 
+# TF-IDF will be returned based on the number of times the term appears in each document, relative to the total number of documents it appears in
+
+class TfIdf_CSV
+
+  DECIMAL_PLACES = 20 # number of decimal places to use in output
+  
+  # n the n-grams of the data http://en.wikipedia.org/wiki/N-gram
+  def initialize(csv_file)
+    @output_csv_file = csv_file.sub(/\.csv$/,'-tf-idf.csv')
+        
+    @tf_idf = {}
+    @total_number_of_docs = 0 
+    @doc_count_per_term = Hash.new(0)
+    @term_freq_per_doc = Hash.new
+    
+    add_csv(csv_file)
+    calculate_tf_idf
+    puts "Finished calculations"
+
+    save_output
+    puts "Finished saving to #{@output_csv_file}"
+  end
+
+  def add_csv(csv_file)
+    begin
+      CSV.foreach(csv_file) do |row|
+        add_doc(row[0], row[1..-1])
+        @total_number_of_docs += 1
+      end
+    rescue Exception
+      puts "Error opening #{csv_file}. Please specify a valid CSV file"
+      Process.exit(1  )
+    end
+  end
+
+  def add_doc(doc, terms)
+    term_counts_doc = Hash.new(0.0)
+
+    # Count the number of times each term appears in this document
+    terms.each do |term|
+      term_counts_doc[term] += 1.0    
+    end
+
+    # Normalize the count to find term frequency. Divide count by total number of terms in document
+    term_counts_doc.each_key do |term|
+      term_counts_doc[term] /= terms.size
+      @doc_count_per_term[term] += 1.0
+    end
+    
+    @term_freq_per_doc[doc] = term_counts_doc    
+  end
+
+  def docs
+    @term_freq_per_doc.keys
+  end
+
+  # produces a hash indexed by term, with each value being a hash indexed by document with a value being the TF-IDF
+  # { "cat" => { "Green Eggs and Ham" => 0.04535, "Dick Wittington" => 0.02343434 }, "Eggs" => { "Green Eggs and Ham" => 0.02764} } }
+  def calculate_tf_idf  
+    @doc_count_per_term.each do |term, count_per_doc|
+      doc_list = {}
+      docs.each do |doc|
+        # if we have a frequency for this term, we can calculate TF-IDF
+        if @term_freq_per_doc[doc].key?(term)
+          doc_list[doc] = @term_freq_per_doc[doc][term] * Math.log10(@total_number_of_docs / count_per_doc) 
+        else
+          doc_list[doc] = nil
+        end
+      end
+      @tf_idf[term] = doc_list    
+    end
+  end
+
+  # Save the results as CSV
+  # Term, Doc1, Doc2, Doc3...
+  # Eggs, 0.04535,,0.02
+  def save_output
+    CSV.open(@output_csv_file,"w") do |f|
+      f << ["term", docs].flatten
+      @tf_idf.each do |term, values|
+        tmp_row = [term]
+        docs.each do |doc|
+          value = values[doc] ? ("%.#{DECIMAL_PLACES}f" % values[doc]) : nil
+          value = nil if value =~ /^0\.0+$/
+          tmp_row << value
+        end
+        f << tmp_row
+      end
+    end
+  end
+ 
+end
+

data/sample-tf-idf.csv

@@ -0,0 +1,46 @@
+term,doc1,doc2
+the,,
+limerick,0.01038034467806831646,
+packs,0.01038034467806831646,
+laughs,0.01038034467806831646,
+anatomical,0.01038034467806831646,
+in,0.01038034467806831646,
+space,0.01038034467806831646,
+that,,
+is,0.01038034467806831646,
+quite,0.01038034467806831646,
+economical,0.01038034467806831646,
+but,,
+good,0.01038034467806831646,
+ones,0.02076068935613663291,
+i've,0.01038034467806831646,
+seen,0.01038034467806831646,
+so,0.02076068935613663291,
+seldom,0.02076068935613663291,
+are,0.02076068935613663291,
+clean,0.02076068935613663291,
+and,,
+comical,0.01038034467806831646,
+there,,0.01003433318879937315
+was,,0.01003433318879937315
+a,,0.01003433318879937315
+young,,0.01003433318879937315
+person,,0.01003433318879937315
+of,,0.02006866637759874630
+smyrna,,0.02006866637759874630
+whose,,0.01003433318879937315
+grandmother,,0.01003433318879937315
+threatened,,0.01003433318879937315
+to,,0.01003433318879937315
+burn,,0.02006866637759874630
+her,,0.01003433318879937315
+she,,0.01003433318879937315
+seized,,0.01003433318879937315
+on,,0.01003433318879937315
+cat,,0.01003433318879937315
+said,,0.01003433318879937315
+'granny,,0.01003433318879937315
+you,,0.01003433318879937315
+incongruous,,0.01003433318879937315
+old,,0.01003433318879937315
+woman,,0.01003433318879937315

data/sample.csv

@@ -0,0 +1,2 @@
+doc1,the,limerick,packs,laughs,anatomical,in,space,that,is,quite,economical,but,the,good,ones,i've,seen,so,seldom,are,clean,and,the,clean,ones,so,seldom,are,comical
+doc2,there,was,a,young,person,of,smyrna,whose,grandmother,threatened,to,burn,her,but,she,seized,on,the,cat,and,said,'granny,burn,that,you,incongruous,old,woman,of,smyrna

data/test/helper.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'tf-idf_csv'
+
+class Test::Unit::TestCase
+end

data/test/test_tf-idf_csv.rb

@@ -0,0 +1,7 @@
+require 'helper'
+
+class TestTfIdfCsv < Test::Unit::TestCase
+  should "probably rename this file and start testing for real" do
+    flunk "hey buddy, you should probably rename this file and start testing for real"
+  end
+end

metadata

@@ -0,0 +1,89 @@
+--- !ruby/object:Gem::Specification 
+name: tf-idf_csv
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Julian Burgess
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-11-02 00:00:00 -04:00
+default_executable: tf-idf_csv
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: thoughtbot-shoulda
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id001
+description: 
+email: jburgess@ap.org
+executables: 
+- tf-idf_csv
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- bin/tf-idf_csv
+- lib/tf-idf_csv.rb
+- sample-tf-idf.csv
+- sample.csv
+- test/helper.rb
+- test/test_tf-idf_csv.rb
+has_rdoc: true
+homepage: http://github.com/aubergene/tf-idf_csv
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Calculate the TF-IDF for terms in a CSV file
+test_files: 
+- test/helper.rb
+- test/test_tf-idf_csv.rb