davidrichards-data_frame 0.0.17 → 0.0.18

data/VERSION.yml

@@ -1,4 +1,4 @@
 --- 
 :major: 0
 :minor: 0
-:patch: 17
+:patch: 18

data/lib/data_frame.rb

@@ -20,5 +20,6 @@ $:.unshift(File.dirname(__FILE__))
 require 'data_frame/callback_array'
 require 'data_frame/transposable_array'
 require 'data_frame/parameter_capture'
+require 'data_frame/arff'
 require 'data_frame/data_frame'
 require 'data_frame/model'

data/lib/data_frame/arff.rb

@@ -0,0 +1,45 @@
+# Turns a data frame into ARFF-formatted content.
+module ARFF
+
+  # Used in arff, but generally useful.
+  def to_csv(include_header=true)
+    value = include_header ? self.labels.map{|e| e.to_s}.join(',') + "\n" : ''
+    self.items.inject(value) do |list, e|
+      list << e.map {|cell| cell.to_s}.join(',') + "\n"
+    end
+  end
+
+  def to_arff
+    arff_header + to_csv(false)
+  end
+  
+  protected
+    def arff_attributes
+      container = defined?(Dictionary) ? Dictionary.new : Hash.new
+      
+      self.labels.inject(container) do |list, e|
+        list[e] = self.render_column(e).categories
+      end
+    end
+    
+    def arff_formatted_attributes
+      self.labels.inject('') do |str, e|
+        val = "{" + self.render_column(e).categories.map{|x| x.to_s}.join(',') + "}"
+        str << "@attribute #{e} #{val}\n"
+      end
+    end
+    
+    def arff_relation
+      self.name ? self.name.to_underscore_sym.to_s : 'unamed_relation'
+    end
+    
+    def arff_header
+      %[@relation #{arff_relation}
+
+#{arff_formatted_attributes}
+@data   
+]
+    end
+    
+    alias :arff_items :to_csv
+end

data/lib/data_frame/data_frame.rb

@@ -18,13 +18,25 @@ class DataFrame
     # This returns bar where 'foo' was found and 'foo' everywhere else.
     def from_csv(obj, opts={})
       labels, table = infer_csv_contents(obj, opts)
+      name = infer_name_from_contents(obj, opts)
       return nil unless labels and table
       df = new(*labels)
       df.import(table)
+      df.name = name
       df
     end
     
     protected
+    
+      # Only works for names sources, urls and files
+      def infer_name_from_contents(obj, opts={})
+        begin
+          File.split(obj).last.split('.')[0..-2].join('.').titleize
+        rescue
+          nil
+        end
+      end
+      
       def infer_csv_contents(obj, opts={})
         contents = File.read(obj) if File.exist?(obj)
         begin
@@ -45,6 +57,9 @@ class DataFrame
       def default_csv_opts; {:converters => :all}; end
   end
   
+  # Include the methods from arff.rb
+  include ARFF
+  
   # Loads a batch of rows.  Expects an array of arrays, else you don't
   # know what you have. 
   def import(rows)
@@ -64,6 +79,9 @@ class DataFrame
   # The items stored in the frame
   attr_reader :items
   
+  # An optional name, useful for arff files
+  attr_accessor :name
+  
   def initialize(*labels)
     @labels = labels.map {|e| e.to_underscore_sym }
     @items = TransposableArray.new

data/spec/data_frame/arff_spec.rb

@@ -0,0 +1,47 @@
+require File.join(File.dirname(__FILE__), "/../spec_helper")
+
+describe "ARFF" do
+  before do
+    @df = DataFrame.from_csv(File.expand_path(File.join(File.dirname(__FILE__), '..', 'fixtures', 'basic.csv')))
+  end
+  
+  it "should allow a data frame to be expressed as an arff-formatted file" do
+    @df.to_arff.should eql(basic_arff)
+  end
+  
+  it "should add a to_csv method" do
+    @df.to_csv.should eql(%{x,y,month,day,ffmc,dmc,dc,isi,temp,rh,wind,rain,area
+7,5,mar,fri,86.2,26.2,94.3,5.1,8.2,51,6.7,0,0
+7,4,oct,tue,90.6,35.4,669.1,6.7,18,33,0.9,0,0
+})
+  end
+  
+  it "should allow a non-header export for to_csv" do
+    @df.to_csv(false).should eql(%{7,5,mar,fri,86.2,26.2,94.3,5.1,8.2,51,6.7,0,0
+7,4,oct,tue,90.6,35.4,669.1,6.7,18,33,0.9,0,0
+})
+  end
+end
+
+def basic_arff
+  %[@relation basic
+
+@attribute x {7}
+@attribute y {4,5}
+@attribute month {mar,oct}
+@attribute day {fri,tue}
+@attribute ffmc {86.2,90.6}
+@attribute dmc {26.2,35.4}
+@attribute dc {94.3,669.1}
+@attribute isi {5.1,6.7}
+@attribute temp {8.2,18}
+@attribute rh {33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51}
+@attribute wind {0.9,6.7}
+@attribute rain {0}
+@attribute area {0}
+
+@data   
+7,5,mar,fri,86.2,26.2,94.3,5.1,8.2,51,6.7,0,0
+7,4,oct,tue,90.6,35.4,669.1,6.7,18,33,0.9,0,0
+]
+end

data/spec/data_frame/data_frame_spec.rb

@@ -12,6 +12,10 @@ describe DataFrame do
     df.labels.should eql(@labels)
   end
   
+  it "should have an optional name" do
+    @df.name = :some_name
+    @df.name.should eql(:some_name)
+  end
   it "should initialize with an empty items list" do
     @df.items.should be_is_a(TransposableArray)
     @df.items.should be_empty
@@ -91,6 +95,18 @@ describe DataFrame do
       @df.x.should eql([7,7])
       @df.area.should eql([0,0])
     end
+    
+    it "should infer a name when importing from a file" do
+      filename = "/tmp/data_frame_spec.csv"
+      contents = %{X,Y,month,day,FFMC,DMC,DC,ISI,temp,RH,wind,rain,area
+7,5,mar,fri,86.2,26.2,94.3,5.1,8.2,51,6.7,0,0
+7,4,oct,tue,90.6,35.4,669.1,6.7,18,33,0.9,0,0
+}
+      File.open(filename, 'w') {|f| f.write contents}
+      @df = DataFrame.from_csv(filename)
+      @df.name.should eql('Data Frame Spec')
+      `rm -rf #{filename}`
+    end
   end
   
   it "should be able to remove a column" do

data/spec/fixtures/basic.csv

@@ -0,0 +1,3 @@
+X,Y,month,day,FFMC,DMC,DC,ISI,temp,RH,wind,rain,area
+7,5,mar,fri,86.2,26.2,94.3,5.1,8.2,51,6.7,0,0
+7,4,oct,tue,90.6,35.4,669.1,6.7,18,33,0.9,0,0

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: davidrichards-data_frame
 version: !ruby/object:Gem::Version 
-  version: 0.0.17
+  version: 0.0.18
 platform: ruby
 authors: 
 - David Richards
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-08-29 00:00:00 -07:00
+date: 2009-09-13 00:00:00 -07:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -54,6 +54,7 @@ files:
 - README.rdoc
 - VERSION.yml
 - lib/data_frame
+- lib/data_frame/arff.rb
 - lib/data_frame/callback_array.rb
 - lib/data_frame/data_frame.rb
 - lib/data_frame/model.rb
@@ -65,12 +66,15 @@ files:
 - lib/ext/string.rb
 - lib/ext/symbol.rb
 - spec/data_frame
+- spec/data_frame/arff_spec.rb
 - spec/data_frame/callback_array_spec.rb
 - spec/data_frame/data_frame_spec.rb
 - spec/data_frame/model_spec.rb
 - spec/data_frame/parameter_capture_spec.rb
 - spec/data_frame/transposable_array_spec.rb
 - spec/data_frame_spec.rb
+- spec/fixtures
+- spec/fixtures/basic.csv
 - spec/spec_helper.rb
 has_rdoc: true
 homepage: http://github.com/davidrichards/data_frame