kfold 0.1

data/CHANGELOG

@@ -0,0 +1 @@
+v0.1. Commands for K-fold splitting and folding

data/Manifest

@@ -0,0 +1,11 @@
+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

data/README

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

data/Rakefile

@@ -0,0 +1,17 @@
+# 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

data/bin/kfold

@@ -0,0 +1,111 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'commander/import'
+require 'kfold'
+require 'fileutils'
+
+program :version, Kfold::VERSION
+program :description, 'Do stuff'
+ 
+def do_directory(dir, overwrite = false)
+  if File.exist? dir
+    if overwrite
+      say "Removing existing #{dir}"
+      FileUtils.rm_rf(dir)
+    else
+      abort "Failed: Directory #{dir} exists" 
+    end
+  end
+  FileUtils.mkdir dir
+end
+
+command :split do |c|
+  c.syntax = 'kfold split -i INPUT [options]'
+  c.summary = 'Split a data file into K partitions'
+  c.description = 'Given the data file INPUT, the partitions are written to files named INPUT.parts/{01..K}'
+  c.example 'Split the file sample.txt into 4 parts', 'kfold split -k4 sample.txt'
+  c.example 'Split the double-newline-delimited file sample.conll into 10 parts', 'kfold split -d"\n\n" sample.conll'
+  c.option '-i', '--input FILE', String, 'Data file to split'
+  c.option '-k', '--parts N', Integer, 'The number of partitions desired'
+  c.option '-d', '--delimiter DELIM', String, 'String used to separate individual entries (newline per default)'
+  c.option '-g', '--granularity N', Integer, 'Ensure the number of entries in each partition is divisible by N (useful for block-structured data)'
+  c.option '-f', '--overwrite', 'Remove existing parts prior to executing'
+  c.option '--fold', 'Additionally, create K folds of K-1 parts in a another folder'
+  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'
+    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
+    options.delimiter.gsub!('\n', "\n")
+    options.delimiter.gsub!('\r', "\r")
+    options.delimiter.gsub!('\t', "\t")
+    parts_dir = "#{options.input}.#{options.parts_name}"
+    do_directory(parts_dir, options.overwrite)
+    df = Kfold::DataFile.new(options.input, options.delimiter, options.granularity)
+    say "Partitioning breakdown: #{df.breakdown options.parts}"
+    part, part_file, last_part_num = nil
+    part_names = []
+    part_entries = 0
+    df.each_entry_in_parts(options.parts) do |part_num, entry|
+      if part_num != last_part_num
+        if part
+          part.close
+          say "[part] Wrote #{part_entries} entries to #{part_file}"
+        end
+        part_name = part_num.to_s.rjust(options.parts.to_s.size, '0')
+        part_names << part_name
+        part_file = File.join(parts_dir, part_name)
+        part = File.open(part_file, 'w')
+        last_part_num = part_num
+        part_entries = 0
+      end
+      part << entry
+      part_entries += 1
+    end
+    say "[part] Wrote #{part_entries} entries to #{part_file}"
+    part.close
+    if options.fold
+      folds_dir = "#{options.input}.#{options.folds_name}"
+      do_directory(folds_dir, options.overwrite)
+      part_names.each do |fold_name|
+        fold_parts = part_names - [fold_name]
+        fold_file = File.join(folds_dir, fold_name)
+        File.open(fold_file, 'w') do |fold|
+          fold_parts.each do |part|
+            part_file = File.join(parts_dir, part)
+            fold << File.open(part_file).read
+          end
+        end
+        say "[fold] Wrote parts #{fold_parts * ' '} to #{fold_file}"
+      end
+    end
+  end
+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
+

data/kfold.gemspec

@@ -0,0 +1,37 @@
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{kfold}
+  s.version = "0.1"
+
+  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.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
+end

data/lib/kfold.rb

@@ -0,0 +1,7 @@
+
+require 'kfold/data_file'
+
+module Kfold
+  VERSION = 0.1
+  
+end

data/lib/kfold/data_file.rb

@@ -0,0 +1,67 @@
+
+module Kfold
+  class DataFile
+    attr_reader :filename, :delimiter, :granularity  
+
+    def initialize(filename, delimiter = "\n", granularity = 1)
+      @filename, @delimiter, @granularity = filename, delimiter, granularity
+    end
+
+    def num_entries
+      @num_entres ||= count_entries
+    end
+
+    def num_blocks
+      @num_blocks ||= (self.num_entries.to_f/self.granularity.to_f).ceil
+    end
+    
+    def breakdown(parts = 10)
+      blocks_per_part, rest = self.num_blocks.divmod(parts)
+      msg = "#{num_entries} entries into #{parts} parts, #{blocks_per_part} blocks of #{self.granularity} entries per part"
+      if rest > 0
+        msg += " (plus #{rest} extra blocks in last part)"
+      end
+      msg
+    end
+    
+    def each_entry_in_parts(parts = 10) 
+      blocks_per_part, rest = num_blocks.divmod(parts)
+      cur_part = 1
+      cur_block = 1
+      cur_entry = 0
+      block_entries = 0
+      part_entries = 0
+      File.foreach(self.filename, self.delimiter) do |entry| 
+        cur_entry += 1
+        yield cur_part, entry
+        block_entries += 1
+        part_entries += 1
+        if block_entries == self.granularity 
+          # End of this block
+          if cur_block == blocks_per_part and not cur_part == parts
+            # End of this part
+            cur_part += 1
+            cur_block = 1
+          else
+            cur_block += 1
+          end
+          block_entries = 0
+        end
+      end
+    end
+    
+    protected
+    
+    def count_entries
+      num_entries = 0
+      last_empty = false
+      File.foreach(self.filename, self.delimiter) do |entry|
+        last_empty = (entry == '')
+        num_entries += 1 
+      end
+      num_entries -= 1 if last_empty
+      num_entries
+    end
+    
+  end
+end

data/spec/helper.rb

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

data/spec/kfold/data_file_spec.rb

@@ -0,0 +1,65 @@
+
+require 'kfold/data_file'
+
+describe Kfold::DataFile do
+  before(:each) do
+    @sample_file = File.join(File.dirname(__FILE__), 'sample_data_file.conll')
+    @df = Kfold::DataFile.new(@sample_file, "\n\n")
+  end
+
+  it "should contain 11 entries" do
+    @df.num_entries.should == 11
+  end
+
+  it "should yield consecutive part numbers" do
+    next_part_num = nil
+    @df.each_entry_in_parts(@df.num_entries) do |part_num, entry|
+      part_num.should == next_part_num unless next_part_num.nil?
+      next_part_num = part_num + 1
+    end
+  end
+  
+  it "should yield all the entries in the file" do
+    yield_count = 0
+    part_count = 0
+    last_part_num = nil
+    @df.each_entry_in_parts(1) do |part_num, entry|
+      yield_count += 1
+      if (part_num != last_part_num)
+        part_count += 1
+        last_part_num = part_num
+      end
+    end
+    yield_count.should == @df.num_entries
+    part_count.should == 1
+  end
+
+  it "should yield one entry per part if so requested" do
+    yield_count = 0
+    part_count = 0
+    last_part_num = nil
+    @df.each_entry_in_parts(@df.num_entries) do |part_num, entry|
+      yield_count += 1
+      if (part_num != last_part_num)
+        part_count += 1
+        last_part_num = part_num
+      end
+    end
+    yield_count.should == @df.num_entries
+    part_count.should == @df.num_entries
+  end
+
+  it "should yield the number of parts requested" do
+    part_count = 0
+    last_part_num = nil
+    @df.each_entry_in_parts(3) do |part_num, entry|
+      if (part_num != last_part_num)
+        part_count += 1
+        last_part_num = part_num
+      end
+    end
+    part_count.should == 3
+  end
+  
+end
+

data/spec/kfold/sample_data_file.conll

@@ -0,0 +1,108 @@
+1	tashiro	_	NAME	NAMEper	_	2	HD	2	HD
+2	yasuko	_	NAME	NAMEper	_	3	COMP	3	COMP
+3	desu	_	PV	PVfin	u	0	ROOT	0	ROOT
+4	.	_	.	.	_	3	PUNCT	3	PUNCT
+
+1	hayakawa	_	NAME	NAMEper	_	2	HD	2	HD
+2	ryou	_	NAME	NAMEper	_	3	COMP	3	COMP
+3	desu	_	PV	PVfin	u	0	ROOT	0	ROOT
+4	.	_	.	.	_	3	PUNCT	3	PUNCT
+
+1	hayakawa	_	NAME	NAMEper	_	2	COMP	2	COMP
+2	saN	_	P	PNsf	_	6	ADJ	6	ADJ
+3	ima	_	N	Ntmp	_	6	ADJ	6	ADJ
+4	chotto	_	ADV	ADV	_	6	ADJ	6	ADJ
+5	ojikaN	_	N	NN	_	6	SBJ	6	SBJ
+6	yoroshii	_	ADJ	ADJifin	_	7	COMP	7	COMP
+7	desu	_	PV	PVfin	u	0	ROOT	0	ROOT
+8	ka	_	PS	PSE	_	7	MRK	7	MRK
+9	chotto	_	ADV	ADV	_	16	ADJ	16	ADJ
+10	doitsu	_	NAME	NAMEloc	_	11	COMP	11	COMP
+11	no	_	P	Pgen	_	12	ADJ	12	ADJ
+12	shucchou	_	N	VN	_	13	COMP	13	COMP
+13	no	_	P	Pgen	_	14	COMP	14	COMP
+14	koto	_	N	NF	_	15	COMP	15	COMP
+15	de	_	P	P	_	16	ADJ	16	ADJ
+16	gosoudaN	_	N	VN	_	17	COMP	17	COMP
+17	shitai	_	VADJ	VADJi	_	18	COMP	18	COMP
+18	no	_	N	NF	_	19	COMP	19	COMP
+19	desu	_	PV	PVfin	u	20	COMP	20	COMP
+20	ga	_	PS	PSSb	_	0	ROOT	0	ROOT
+21	.	_	.	.	_	20	PUNCT	20	PUNCT
+
+1	hai	_	ITJ	ITJ	_	0	ROOT	0	ROOT
+2	.	_	.	.	_	1	PUNCT	1	PUNCT
+
+1	daijoubu	_	ADJ	ADJ_n	_	2	COMP	2	COMP
+2	desu	_	PV	PVfin	u	3	COMP	3	COMP
+3	ga	_	PS	PSSb	_	0	ROOT	0	ROOT
+4	.	_	.	.	_	3	PUNCT	3	PUNCT
+
+1	de	_	CNJ	CNJ	_	21	ADJ	21	ADJ
+2	dekimashitara	_	V	Vcnd	_	9	ADJ	9	ADJ
+3	koNkai	_	N	Ntmp	_	4	COMP	4	COMP
+4	no	_	P	Pgen	_	5	ADJ	5	ADJ
+5	shucchou	_	N	VN	_	7	SBJ	7	SBJ
+6	juuichigatsu	_	CD	CDdate	_	7	COMP	7	COMP
+7	ni	_	P	P	_	8	COMP	8	COMP
+8	to	_	P	PQ	_	9	COMP	9	COMP
+9	omotte	_	V	Vte	_	10	COMP	10	COMP
+10	iru	_	VAUX	VAUXfin	u	11	COMP	11	COMP
+11	no	_	N	NF	_	12	COMP	12	COMP
+12	desu	_	PV	PVfin	u	13	COMP	13	COMP
+13	ga	_	PS	PSSb	_	21	ADJ	21	ADJ
+14	juuichigatsu	_	CD	CDdate	_	15	COMP	15	COMP
+15	desu	_	PV	PVfin	u	16	COMP	16	COMP
+16	to	_	PS	PSSa	_	21	ADJ	21	ADJ
+17	goyotei	_	N	NN	_	18	COMP	18	COMP
+18	no	_	P	Pgen	_	19	COMP	19	COMP
+19	hou	_	N	NF	_	21	SBJ	21	SBJ
+20	ikaga	_	ADV	ADVwh	_	21	COMP	21	COMP
+21	deshou	_	PV	PVfin	u	0	ROOT	0	ROOT
+22	ka	_	PS	PSE	_	21	MRK	21	MRK
+23	.	_	.	.	_	22	PUNCT	22	PUNCT
+
+1	juuichigatsu	_	CD	CDdate	_	2	COMP	2	COMP
+2	desu	_	PV	PVfin	u	0	ROOT	0	ROOT
+3	ka	_	PS	PSE	_	2	MRK	2	MRK
+4	.	_	.	.	_	3	PUNCT	3	PUNCT
+
+1	juuichigatsu	_	CD	CDdate	_	7	ADJ	7	ADJ
+2	wa	_	P	Pfoc	_	1	MRK	1	MRK
+3	zeNhaN	_	N	Ntmp	_	7	ADJ	7	ADJ
+4	nara	_	P	Pfoc	_	3	MRK	3	MRK
+5	jikaN	_	N	NN	_	6	COMP	6	COMP
+6	ga	_	P	Pnom	_	7	SBJ	7	SBJ
+7	toreru	_	V	Vfin	u	9	COMP	9	COMP
+8	ka	_	PS	PSE	_	7	MRK	7	MRK
+9	to	_	P	PQ	_	10	COMP	10	COMP
+10	omoimasu	_	V	Vfin	u	11	COMP	11	COMP
+11	ga	_	PS	PSSb	_	0	ROOT	0	ROOT
+12	.	_	.	.	_	11	PUNCT	11	PUNCT
+
+1	tsuki	_	N	NN	_	2	COMP	2	COMP
+2	no	_	P	Pgen	_	3	ADJ	3	ADJ
+3	zeNhaN	_	N	Ntmp	_	5	ADJ	5	ADJ
+4	nara	_	P	Pfoc	_	3	MRK	3	MRK
+5	yoroshii	_	ADJ	ADJifin	_	6	COMP	6	COMP
+6	desu	_	PV	PVfin	u	0	ROOT	0	ROOT
+7	ka	_	PS	PSE	_	6	MRK	6	MRK
+8	.	_	.	.	_	7	PUNCT	7	PUNCT
+
+1	hai	_	ITJ	ITJ	_	0	ROOT	0	ROOT
+2	.	_	.	.	_	1	PUNCT	1	PUNCT
+
+1	sou	_	ADV	ADVdem	_	2	COMP	2	COMP
+2	shimasu	_	V	Vfin	u	3	COMP	3	COMP
+3	to	_	PS	PSSa	_	11	ADJ	11	ADJ
+4	kokonoka	_	CD	CDdate	_	5	COMP	5	COMP
+5	no	_	P	Pgen	_	7	ADJ	7	ADJ
+6	getsuyou	_	NT	NT	_	7	COMP	7	COMP
+7	hatsu	_	N	Nsf	_	11	SBJ	11	SBJ
+8	toka	_	P	Pcnj	_	7	MRK	7	MRK
+9	wa	_	P	Pfoc	_	7	MRK	7	MRK
+10	ikaga	_	ADV	ADVwh	_	11	COMP	11	COMP
+11	deshou	_	PV	PVfin	u	0	ROOT	0	ROOT
+12	ka	_	PS	PSE	_	11	MRK	11	MRK
+13	.	_	.	.	_	12	PUNCT	12	PUNCT
+

metadata

@@ -0,0 +1,118 @@
+--- !ruby/object:Gem::Specification 
+name: kfold
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  version: "0.1"
+platform: ruby
+authors: 
+- "Christian Rish\xC3\xB8j"
+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
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        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: 
+- kfold
+extensions: []
+
+extra_rdoc_files: 
+- CHANGELOG
+- LICENSE
+- README
+- bin/kfold
+- lib/kfold.rb
+- lib/kfold/data_file.rb
+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
+has_rdoc: true
+homepage: http://github.com/crishoj/kfold
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --line-numbers
+- --inline-source
+- --title
+- Kfold
+- --main
+- README
+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: 
+      - 1
+      - 2
+      version: "1.2"
+requirements: []
+
+rubyforge_project: kfold
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Create k-fold splits from datafiles (useful for cross-validation in supervised machine learning)
+test_files: []
+

metadata.gz.sig

@@ -0,0 +1,2 @@
+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