kfold 0.1 → 0.3

data/.gitignore

@@ -0,0 +1,4 @@
+tmp
+.DS_Store
+nbproject/private
+pkg

data/.idea/encodings.xml

@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Encoding" useUTFGuessing="true" native2AsciiForPropertiesFiles="false" />
+</project>
+

data/.idea/kfold.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="RUBY_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+    <orderEntry type="library" scope="PROVIDED" name="bundler (v1.0.18, ruby-1.9.2-p290) [gem]" level="application" />
+  </component>
+</module>
+

data/.idea/misc.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="DependencyValidationManager">
+    <option name="SKIP_IMPORT_STATEMENTS" value="false" />
+  </component>
+  <component name="ProjectResources">
+    <default-html-doctype>http://www.w3.org/1999/xhtml</default-html-doctype>
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="ruby-1.9.2-p290" project-jdk-type="RUBY_SDK" />
+</project>
+

data/.idea/modules.xml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/kfold.iml" filepath="$PROJECT_DIR$/.idea/kfold.iml" />
+    </modules>
+  </component>
+</project>
+

data/.idea/vcs.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
+

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format documentation

data/CHANGELOG

@@ -1 +1,3 @@
-v0.1. Commands for K-fold splitting and folding
+v0.2. Commands for K-fold training and testing added.
+
+v0.1. Commands for K-fold splitting and folding added.

data/Gemfile

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in sample-gem.gemspec
+gemspec

data/Manifest

@@ -1,7 +1,7 @@
 CHANGELOG
 LICENSE
 Manifest
-README
+README.rdoc
 Rakefile
 bin/kfold
 lib/kfold.rb

data/README.rdoc

@@ -0,0 +1,166 @@
+= kfold
+
+kfold creates K-fold splits from data files and assists in training and testing (useful for cross-validation in supervised machine
+learning)
+
+== Command overview
+
+    help                 Display global or [command] help documentation.		
+    split                Split a data file into K partitions		
+    test                 Apply trained models on a dataset previously split using kfold		
+    train                Train models on a dataset previously split using kfold	
+
+== Example usage
+
+10-fold cross-validation of the standard MaltParser on a treebank named shuffled.c32.conll may be done as follows:
+
+  kfold split -f -i shuffled.c32.conll -d '\n\n' 
+  kfold train -f --base shuffled.c32.conll -- java -jar ~/Tools/malt-1.4.1/malt.jar -c %B.model_%N -i %T -m learn
+  kfold test -f --base shuffled.c32.conll -- java -jar ~/Tools/malt-1.4.1/malt.jar -c %B.model_%N -i %T -o %O -m parse
+  eval07.pl -q -g shuffled.c32.conll -s shuffled.c32.conll.output
+  
+The MaltParser does not like to put its models in a subdirectory, so rather than using the standard model files suggested by kfold (%M), we construct custom non-nested model filenames using %B.model_%N.
+
+== Command details
+
+The following is simply the output of the built-in help commands.
+
+=== Splitting data files
+
+  NAME:
+
+    split
+
+  DESCRIPTION:
+
+    Given the data file INPUT, the partitions are written to files named INPUT.parts/{01..K}
+
+  SYNOPSIS:
+
+    kfold split -i INPUT [options]
+
+  EXAMPLES:
+	
+    # Split the file sample.txt into 4 parts
+    kfold split -k4 sample.txt
+	
+    # Split the double-newline-delimited file sample.conll into 10 parts
+    kfold split -d"\n\n" sample.conll
+	
+  OPTIONS:
+	
+    -i, --input FILE 
+        Data file to split
+	
+    -k, --parts N 
+        The number of partitions desired
+	
+    -d, --delimiter DELIM 
+        String used to separate individual entries (newline per default)
+	
+    -g, --granularity N 
+        Ensure the number of entries in each partition is divisible by N (useful for block-structured data)
+	
+    -f, --overwrite 
+        Remove existing parts prior to executing
+	
+    --fold 
+        Additionally, create K folds of K-1 parts in a another folder
+	
+    --parts-name STRING 
+        Use the given name as suffix for the partitions folder created
+	
+    --folds-name STRING 
+        Use the given name as suffix for the folds folder created
+
+=== Training on the folds
+
+  NAME:
+
+    train
+
+  DESCRIPTION:
+
+    Given training data previously split in K parts and folds, train K models on the K folds
+    
+    Certain keywords in the training command and its arguments are interpolated at runtime:
+
+     * %N  - fold number, e.g. '01'
+     * %F  - fold filename, e.g. 'brown.train/01'
+     * %I  - alias for %F
+     * %M  - model filename, e.g. 'brown.models/01'
+     * %B  - basename (as specified on the command line), e.g. 'brown'
+
+
+  SYNOPSIS:
+
+    kfold train --base NAME [options] -- CMD [--CMD-OPTIONS] [CMD-ARGS]
+
+  EXAMPLES:
+	
+    # Train MaltParser for cross-validation
+    kfold train -f --base shuffled.c32.conll -- java -jar ~/Tools/malt-1.4.1/malt.jar -c %B.model_%N -i %T -m learn
+	
+  OPTIONS:
+	
+    -f, --overwrite 
+        Remove existing models prior to executing
+	
+    --base NAME 
+        Default prefix of training folds and model files
+	
+    --folds-name SUFFIX 
+        Look for folds {01..K} in the folder BASE.SUFFIX
+	
+    --models-name SUFFIX 
+        Yield model names as BASE.SUFFIX/{01..K} as interpolation pattern %M
+
+=== Testing the models on their reciprocal data file parts
+
+  NAME:
+
+    test
+
+  DESCRIPTION:
+
+    Process K parts of a split datafile using K previously trained models.
+    
+    Certain keywords in the testing command and its arguments are interpolated at runtime:
+
+     * %N  - part number, e.g. '01'
+     * %T  - part filename, e.g. 'brown.test/01'
+     * %I  - alias for %T
+     * %O  - output filename, e.g. 'brown.outputs/01'
+     * %M  - model filename, e.g. 'brown.models/01'
+     * %B  - basename (as specified on the command line), e.g. 'brown'
+
+
+  SYNOPSIS:
+
+    kfold test --base NAME [options] -- CMD [--CMD-OPTIONS] [CMD-ARGS]
+
+  EXAMPLES:
+	
+    # Apply trained MaltParser models for cross-validation
+    kfold test -f --base shuffled.c32.conll -- java -jar ~/Tools/malt-1.4.1/malt.jar -c %B.model_%N -i %T -o %O -m parse
+	
+  OPTIONS:
+	
+    -f, --overwrite 
+        Remove existing test output prior to executing
+	
+    --base NAME 
+        Default prefix of model files and test outputs
+	
+    --parts-name SUFFIX 
+        Look for parts {01..K} to be processed in the folder BASE.SUFFIX
+	
+    --models-name SUFFIX 
+        Yield model names as BASE.SUFFIX/{01..K} as interpolation pattern %M
+	
+    --outputs-name SUFFIX 
+        Yield output filenames as BASE.SUFFIX/{01..K} as interpolation pattern %O
+	
+    --output-name SUFFIX 
+        Put the concatenated output of all models in BASE.SUFFIX
+

data/Rakefile

@@ -1,17 +1 @@
-# coding: UTF-8
-require 'rubygems'
-require 'rake'
-require 'echoe'
-
-$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), 'lib'))
-require 'kfold'
-
-Echoe.new('kfold', Kfold::VERSION) do |p|
-  p.description    = "Create k-fold splits from datafiles (useful for cross-validation in supervised machine learning)"
-  p.url            = "http://github.com/crishoj/kfold"
-  p.author         = "Christian Rishøj"
-  p.email          = "christian@rishoj.net"
-  p.ignore_pattern = ["tmp/**/*", "script/*", "nbproject/**/*"]
-  p.runtime_dependencies = ["commander"]
-  p.development_dependencies = []
-end
+require "bundler/gem_tasks"

data/bin/kfold

@@ -1,13 +1,11 @@
 #!/usr/bin/env ruby
-
-require 'rubygems'
 require 'commander/import'
 require 'kfold'
 require 'fileutils'
 
 program :version, Kfold::VERSION
-program :description, 'Do stuff'
- 
+program :description, "Create K-fold splits from data files and assist in training and testing (useful for cross-validation in supervised machine learning)"
+
 def do_directory(dir, overwrite = false)
   if File.exist? dir
     if overwrite
@@ -35,7 +33,7 @@ command :split do |c|
   c.option '--parts-name STRING', String, 'Use the given name as suffix for the partitions folder created'
   c.option '--folds-name STRING', String, 'Use the given name as suffix for the folds folder created'
   c.action do |args, options|
-    options.default :parts => 10, :delimiter => "\n", :granularity => 1, :parts_name => 'parts'
+    options.default :parts => 10, :delimiter => "\n", :granularity => 1, :parts_name => 'test', :folds_name => 'train'
     abort "Failed: Please specify input file using -i INPUT" unless options.input 
     abort "Failed: Input file #{options.input} does not exist" unless File.exist? options.input
     # Interpret newlines, linefeeds and tabs
@@ -87,25 +85,103 @@ end
 
 alias_command :fold, :split, '--fold'
 
-#command :train do |c|
-#  c.syntax = 'kfold train [options]'
-#  c.summary = ''
-#  c.description = ''
-#  c.example 'description', 'command example'
-#  c.option '--some-switch', 'Some switch that does something'
-#  c.action do |args, options|
-#    # Do something or c.when_called Kfold::Commands::Train
-#  end
-#end
-#
-#command :test do |c|
-#  c.syntax = 'kfold test [options]'
-#  c.summary = ''
-#  c.description = ''
-#  c.example 'description', 'command example'
-#  c.option '--some-switch', 'Some switch that does something'
-#  c.action do |args, options|
-#    # Do something or c.when_called Kfold::Commands::Test
-#  end
-#end
+command :train do |c|
+  c.syntax = 'kfold train --base NAME [options] -- CMD [--CMD-OPTIONS] [CMD-ARGS]'
+  c.summary = 'Train models on a dataset previously split using kfold'
+  c.description = <<-end
+Given training data previously split in K parts and folds, train K models on the K folds
+    
+    Certain keywords in the training command and its arguments are interpolated at runtime:
+
+     * %N  - fold number, e.g. '01'
+     * %F  - fold filename, e.g. 'brown.train/01'
+     * %I  - alias for %F
+     * %M  - model filename, e.g. 'brown.models/01'
+     * %B  - basename (as specified on the command line), e.g. 'brown'
+  end
+  c.example 'Train MaltParser for cross-validation', 'kfold train -f --base shuffled.c32.conll -- java -jar ~/Tools/malt-1.4.1/malt.jar -c %B.model_%N -i %T -m learn'
+  c.option '-f', '--overwrite', 'Remove existing models prior to executing'
+  c.option '--base NAME', String, 'Default prefix of training folds and model files'
+  c.option '--folds-name SUFFIX', String, 'Look for folds {01..K} in the folder BASE.SUFFIX'
+  c.option '--models-name SUFFIX', String, 'Yield model names as BASE.SUFFIX/{01..K} as interpolation pattern %M'
+  c.action do |args, options|
+    options.default :folds_name => 'train', :models_name => 'models'
+    raise "Must specify base name using --base" unless options.base
+    folds_dir = "#{options.base}.#{options.folds_name}"
+    models_dir = "#{options.base}.#{options.models_name}"
+    raise "Folds directory not found" unless File.exists?(folds_dir)
+    folds = Dir.glob(File.join(folds_dir, '*')).collect { |file|
+      file if File.basename(file) =~ /^[0-9]+$/
+    }.compact
+    raise "No folds found in #{folds_dir}" if folds.count == 0
+    say "Found #{folds.count} folds in #{folds_dir}"
+    cmds = folds.collect do |fold|
+      num = File.basename(fold)
+      model = File.join(models_dir, num)
+      args.collect { |arg|
+        arg.gsub(/%F/, fold).gsub(/%T/, fold).gsub(/%N/, num).gsub('%M', model).gsub('%B', options.base)
+      }.join(' ')
+    end
+    do_directory(models_dir, options.overwrite) if cmds.first.match(models_dir)
+    cmds.each do |cmd|
+      say "[exec] #{cmd}"
+      system cmd
+    end
+  end
+end
+
+command :test do |c|
+  c.syntax = 'kfold test --base NAME [options] -- CMD [--CMD-OPTIONS] [CMD-ARGS]'
+  c.summary = 'Apply trained models on a dataset previously split using kfold'
+  c.option '-f', '--overwrite', 'Remove existing test output prior to executing'
+  c.option '--base NAME', String, 'Default prefix of model files and test outputs'
+  c.option '--parts-name SUFFIX', String, 'Look for parts {01..K} to be processed in the folder BASE.SUFFIX'
+  c.option '--models-name SUFFIX', String, 'Yield model names as BASE.SUFFIX/{01..K} as interpolation pattern %M'
+  c.option '--outputs-name SUFFIX', String, 'Yield output filenames as BASE.SUFFIX/{01..K} as interpolation pattern %O'
+  c.option '--output-name SUFFIX', String, 'Put the concatenated output of all models in BASE.SUFFIX'
+  c.description = <<-end
+Process K parts of a split datafile using K previously trained models.
+    
+    Certain keywords in the testing command and its arguments are interpolated at runtime:
 
+     * %N  - part number, e.g. '01'
+     * %T  - part filename, e.g. 'brown.test/01'
+     * %I  - alias for %T
+     * %O  - output filename, e.g. 'brown.outputs/01'
+     * %M  - model filename, e.g. 'brown.models/01'
+     * %B  - basename (as specified on the command line), e.g. 'brown'
+  end
+  c.example 'Apply trained MaltParser models for cross-validation', 'kfold test -f --base shuffled.c32.conll -- java -jar ~/Tools/malt-1.4.1/malt.jar -c %B.model_%N -i %T -o %O -m parse'
+  c.action do |args, options|
+    options.default :parts_name => 'test', :models_name => 'models', :outputs_name => 'outputs', :output_name => 'output'
+    raise "Must specify base name using --base" unless options.base
+    parts_dir = "#{options.base}.#{options.parts_name}"
+    models_dir = "#{options.base}.#{options.models_name}"
+    output_dir = "#{options.base}.#{options.outputs_name}"
+    output_file = "#{options.base}.#{options.output_name}"
+    raise "Parts directory not found" unless File.exists?(parts_dir)
+    raise "Model directory not found" unless File.exists?(models_dir)
+    parts = Dir.glob(File.join(parts_dir, '*')).collect { |file|
+      file if File.basename(file) =~ /^[0-9]+$/
+    }.compact
+    raise "No parts found in #{parts_dir}" if parts.count == 0
+    say "Found #{parts.count} parts in #{parts_dir}"
+    outputs = []
+    cmds = parts.collect do |part|
+      num = File.basename(part)
+      model = File.join(models_dir, num)
+      output = File.join(output_dir, num)
+      outputs << output
+      args.collect { |arg|
+        arg.gsub(/%O/, output).gsub(/%I/, part).gsub(/%T/, part).gsub(/%N/, num).gsub('%M', model).gsub('%B', options.base)
+      }.join(' ')
+    end
+    do_directory(output_dir, options.overwrite)
+    cmds.each do |cmd|
+      say "[exec] #{cmd}"
+      system cmd
+    end
+    say "[join] #{outputs.join(' ')} => #{output_file}"
+    system "cat #{outputs.join(' ')} > #{output_file}"
+  end  
+end

data/kfold.gemspec

@@ -1,37 +1,20 @@
-# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "kfold/version"
 
 Gem::Specification.new do |s|
-  s.name = %q{kfold}
-  s.version = "0.1"
+  s.name        = "kfold"
+  s.version     = Kfold::VERSION
+  s.authors     = ["Christian Rishoj"]
+  s.email       = ["christian@rishoj.net"]
+  s.homepage    = "http://github.com/crishoj/kfold"
+  s.summary     = %q{Split your data and process it in parallel}
+  s.description = %q{Create K-fold splits from data files and assist in training and testing (useful for cross-validation in supervised machine learning)}
 
-  s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
-  s.authors = ["Christian Rishøj"]
-  s.cert_chain = ["/Users/crjensen/Documents/Certificates/gem-public_cert.pem"]
-  s.date = %q{2010-12-30}
-  s.default_executable = %q{kfold}
-  s.description = %q{Create k-fold splits from datafiles (useful for cross-validation in supervised machine learning)}
-  s.email = %q{christian@rishoj.net}
-  s.executables = ["kfold"]
-  s.extra_rdoc_files = ["CHANGELOG", "LICENSE", "README", "bin/kfold", "lib/kfold.rb", "lib/kfold/data_file.rb"]
-  s.files = ["CHANGELOG", "LICENSE", "Manifest", "README", "Rakefile", "bin/kfold", "lib/kfold.rb", "lib/kfold/data_file.rb", "spec/helper.rb", "spec/kfold/data_file_spec.rb", "spec/kfold/sample_data_file.conll", "kfold.gemspec"]
-  s.homepage = %q{http://github.com/crishoj/kfold}
-  s.rdoc_options = ["--line-numbers", "--inline-source", "--title", "Kfold", "--main", "README"]
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   s.require_paths = ["lib"]
-  s.rubyforge_project = %q{kfold}
-  s.rubygems_version = %q{1.3.7}
-  s.signing_key = %q{/Users/crjensen/Documents/Certificates/gem-private_key.pem}
-  s.summary = %q{Create k-fold splits from datafiles (useful for cross-validation in supervised machine learning)}
 
-  if s.respond_to? :specification_version then
-    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
-    s.specification_version = 3
-
-    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
-      s.add_runtime_dependency(%q<commander>, [">= 0"])
-    else
-      s.add_dependency(%q<commander>, [">= 0"])
-    end
-  else
-    s.add_dependency(%q<commander>, [">= 0"])
-  end
+  s.add_development_dependency "rspec"
+  s.add_runtime_dependency "commander"
 end

data/lib/kfold.rb

@@ -1,7 +1,5 @@
-
+require 'kfold/version'
 require 'kfold/data_file'
 
 module Kfold
-  VERSION = 0.1
-  
 end

data/lib/kfold/version.rb

@@ -0,0 +1,3 @@
+module Kfold
+  VERSION = "0.3"
+end

data/spec/kfold/data_file_spec.rb

@@ -1,4 +1,4 @@
-
+require 'spec_helper'
 require 'kfold/data_file'
 
 describe Kfold::DataFile do

data/spec/spec_helper.rb

@@ -0,0 +1,9 @@
+require 'rubygems'
+require 'bundler/setup'
+
+require 'kfold' # and any other gems you need
+
+RSpec.configure do |config|
+  # some (optional) config here
+end
+

metadata

@@ -1,118 +1,93 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: kfold
-version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 1
-  version: "0.1"
+version: !ruby/object:Gem::Version
+  version: '0.3'
+  prerelease: 
 platform: ruby
-authors: 
-- "Christian Rish\xC3\xB8j"
+authors:
+- Christian Rishoj
 autorequire: 
 bindir: bin
-cert_chain: 
-- |
-  -----BEGIN CERTIFICATE-----
-  MIIDNjCCAh6gAwIBAgIBADANBgkqhkiG9w0BAQUFADBBMRIwEAYDVQQDDAljaHJp
-  c3RpYW4xFjAUBgoJkiaJk/IsZAEZFgZyaXNob2oxEzARBgoJkiaJk/IsZAEZFgNu
-  ZXQwHhcNMTAxMjMwMTAwMjUzWhcNMTExMjMwMTAwMjUzWjBBMRIwEAYDVQQDDAlj
-  aHJpc3RpYW4xFjAUBgoJkiaJk/IsZAEZFgZyaXNob2oxEzARBgoJkiaJk/IsZAEZ
-  FgNuZXQwggEiMA0GCSqGSIb3DQEBAQUAA4IBDwAwggEKAoIBAQCg2y4Tc0otb09T
-  /UucTm3DbQilOfQwN9QCzjjnPT6071YeyHsEmv4zokUCBSW5n+H/D0tSAQobT6D+
-  APet6eFLGRW0L9MGsi7do5w+GY4B2nr6CGaouJaoj7XvWKqgigZ6YwfI9RAdpVNT
-  UhF5VeUs9KZ8dMgc9YeezrB9yZMNHM9nDKDEH6bK53xH8OeUkaUBhASEYJ07zMj+
-  hioKQQB/BUCAxpc5ElE9dmdJuinHFqD7KmqU7KSp/0wHvvgT5sqzS32xzlovOSxK
-  GDHt9mtVmQiD3fBCfPJhysaRSUyaUA7jEFljgRTxuH1GWLyGE24/c6zVBknLPSC+
-  hFW0Ib3/AgMBAAGjOTA3MAkGA1UdEwQCMAAwHQYDVR0OBBYEFNtKnxiLUpy9a406
-  diOk3lm5ISTEMAsGA1UdDwQEAwIEsDANBgkqhkiG9w0BAQUFAAOCAQEAiMhO6NXU
-  f/uTInOl2fFxIQsakyCXoWE2u7U2NLLW5R5DCYFK/EH+OYsum1Khu+Jt/n5loV7e
-  B4QlCbwlhwztW7sWA/sQQoLQsroZi2kmYwnkYLeqRgUre3E+YpD3S9QAWIFYpkBZ
-  b9mIToqxb0m+WiLCysrg3sfDymrfuNDdtQcVPcJ5W2+Mj6LJJN65bAvqqExVpr63
-  qbn/bmiocEIbQUsPSVuw+FSIiR6be/Ty3QpWQgxXnbHsfHFWPpADuOwTYPLxWqBg
-  4izI+lCFvIjAaa5WjKVW8PV3XIvgr4+/ESIzs1OOVW7ktQNwu7GXt/kR2KQH9FRC
-  VSyVlp5OZP6OoA==
-  -----END CERTIFICATE-----
-
-date: 2010-12-30 00:00:00 +07:00
-default_executable: 
-dependencies: 
-- !ruby/object:Gem::Dependency 
-  name: commander
+cert_chain: []
+date: 2011-10-15 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &70121742826740 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
   prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
+  version_requirements: *70121742826740
+- !ruby/object:Gem::Dependency
+  name: commander
+  requirement: &70121742826200 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :runtime
-  version_requirements: *id001
-description: Create k-fold splits from datafiles (useful for cross-validation in supervised machine learning)
-email: christian@rishoj.net
-executables: 
+  prerelease: false
+  version_requirements: *70121742826200
+description: Create K-fold splits from data files and assist in training and testing
+  (useful for cross-validation in supervised machine learning)
+email:
+- christian@rishoj.net
+executables:
 - kfold
 extensions: []
-
-extra_rdoc_files: 
-- CHANGELOG
-- LICENSE
-- README
-- bin/kfold
-- lib/kfold.rb
-- lib/kfold/data_file.rb
-files: 
+extra_rdoc_files: []
+files:
+- .gitignore
+- .idea/encodings.xml
+- .idea/kfold.iml
+- .idea/misc.xml
+- .idea/modules.xml
+- .idea/vcs.xml
+- .rspec
 - CHANGELOG
+- Gemfile
 - LICENSE
 - Manifest
-- README
+- README.rdoc
 - Rakefile
 - bin/kfold
+- kfold.gemspec
 - lib/kfold.rb
 - lib/kfold/data_file.rb
-- spec/helper.rb
+- lib/kfold/version.rb
 - spec/kfold/data_file_spec.rb
 - spec/kfold/sample_data_file.conll
-- kfold.gemspec
-has_rdoc: true
+- spec/spec_helper.rb
 homepage: http://github.com/crishoj/kfold
 licenses: []
-
 post_install_message: 
-rdoc_options: 
-- --line-numbers
-- --inline-source
-- --title
-- Kfold
-- --main
-- README
-require_paths: 
+rdoc_options: []
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+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 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 1
-      - 2
-      version: "1.2"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
-rubyforge_project: kfold
-rubygems_version: 1.3.7
+rubyforge_project: 
+rubygems_version: 1.8.10
 signing_key: 
 specification_version: 3
-summary: Create k-fold splits from datafiles (useful for cross-validation in supervised machine learning)
-test_files: []
-
+summary: Split your data and process it in parallel
+test_files:
+- spec/kfold/data_file_spec.rb
+- spec/kfold/sample_data_file.conll
+- spec/spec_helper.rb

data/README

@@ -1,3 +0,0 @@
-== kfold
-
-You should document your project here.

data/spec/helper.rb

@@ -1,3 +0,0 @@
-$LOAD_PATH.unshift File.dirname(__FILE__) + '/..'
- 
-require 'spec'

metadata.gz.sig

@@ -1,2 +0,0 @@
-y���ڇ�1�c���<�0�/Ź�)ZA�^�
-�����ࠤ�d�Z�8WZ.~��u��-P}Z����""a��R(_��ڤC���T|�N�`�A�W~(��O� 	�䞾��q�x0��\.��πxM#�����n��f�j��^E�����F��?���!�&�	]�-�,��B��7�(offb;���խaaP�U�'t��D|#�%�]������,��[ڈ.� /�j�#�v81�9��е+%Y�)�d9-/i