davidrichards-data_frame 0.0.18 → 0.0.19

data/spec/data_frame/data_frame_spec.rb

@@ -21,12 +21,6 @@ describe DataFrame do
     @df.items.should be_empty
   end
   
-  it "should be able to add an item" do
-    item = [1,2,3,4]
-    @df.add_item(item)
-    @df.items.should eql([item])
-  end
-
   it "should use just_enumerable_stats" do
     [1,2,3].std.should eql(1)
     lambda{[1,2,3].cor([2,3,5])}.should_not raise_error
@@ -74,12 +68,15 @@ describe DataFrame do
     end
   end
   
-  it "should be able to import more than one row at a time" do
-    @df.import([[2,2,2,2],[3,3,3,3],[4,4,4,4]])
-    @df.row_labels = [:twos, :threes, :fours]
-    @df.twos.should eql([2,2,2,2])
-    @df.threes.should eql([3,3,3,3])
-    @df.fours.should eql([4,4,4,4])
+  it "should be able to initialize from an array" do
+    contents = %{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
+}
+    
+    @labels = [:x, :y, :month, :day, :ffmc, :dmc, :dc, :isi, :temp, :rh, :wind, :rain, :area]
+    @df = DataFrame.new(@labels)
+    @df.import(contents)
+    @df.labels.should eql(@labels)
   end
   
   context "csv" do
@@ -89,7 +86,7 @@ describe DataFrame do
 7,4,oct,tue,90.6,35.4,669.1,6.7,18,33,0.9,0,0
 }
       labels = [:x, :y, :month, :day, :ffmc, :dmc, :dc, :isi, :temp, :rh, :wind, :rain, :area]
-      
+
       @df = DataFrame.from_csv(contents)
       @df.labels.should eql(labels)
       @df.x.should eql([7,7])
@@ -109,22 +106,6 @@ describe DataFrame do
     end
   end
   
-  it "should be able to remove a column" do
-    @df = DataFrame.new :twos, :threes, :fours
-    @df.import([[2,3,4], [2,3,4], [2,3,4], [2,3,4]])
-    @df.drop!(:twos)
-    @df.items.all? {|i| i.should eql([3,4])}
-    @df.labels.should eql([:threes, :fours])
-  end
-  
-  it "should be able to remove more than one column at a time" do
-    @df = DataFrame.new :twos, :threes, :fours
-    @df.import([[2,3,4], [2,3,4], [2,3,4], [2,3,4]])
-    @df.drop!(:twos, :fours)
-    @df.items.all? {|i| i.should eql([3])}
-    @df.labels.should eql([:threes])
-  end
-  
   it "should offer a hash-like structure of columns" do
     @df.add [1,2,3,4]
     @df.add [5, 6, 7, 8]
@@ -156,202 +137,5 @@ describe DataFrame do
     @df.variables.should eql(@labels)
   end
   
-  context "replace!" do
-    before do
-      @df.add [1,2,3,4]
-      @df.add [5, 6, 7, 8]
-      @doubler = lambda{|e| e * 2}
-    end
-
-    it "should only replace columns that actually exist" do
-      lambda{@df.replace!(:not_a_column, &@doubler)}.should raise_error(
-        ArgumentError, /Must provide the name of an existing column./)
-      lambda{@df.replace!(:these, &@doubler)}.should_not raise_error
-    end
-
-    it "should be able to replace a column with a block" do
-      @df.replace!(:these) {|e| e * 2}
-      @df.these.should eql([2,10])
-    end
-    
-    it "should be able to replace a column with an array" do
-      @a = [5,9]
-      @df.replace!(:these, @a)
-      @df.these.should eql(@a)
-    end
-  end
-  
-  context "filter!" do
-    before do
-      @df.add [1,2,3,4]
-      @df.add [5, 6, 7, 8]
-    end
-    
-    it "should be able to filter a data frame with a block using an OpenStruct for each row" do
-      @df.filter!(:open_struct) {|row| row.these == 5}
-      @df.items.should eql([[5, 6, 7, 8]])
-    end
-    
-    it "should be able to filter a data frame with a block using a Hash for each row" do
-      @df.filter!(:hash) {|row| row[:these] == 5}
-      @df.items.should eql([[5, 6, 7, 8]])
-    end
-    
-    S4 = Struct.new(:one, :two, :three, :four)
-    it "should be able to filter a data frame with a block using another class that uses the row as input" do
-      @df.filter!(S4) {|row| row.one == 5}
-      @df.items.should eql([[5, 6, 7, 8]])
-    end
-    
-    it "should be able to filter a data frame with a block using an array for each row" do
-      @df.filter! {|row| row.first == 5}
-      @df.items.should eql([[5, 6, 7, 8]])
-    end
-    
-    it "should be able to do fancy things with the row as the filter" do
-      @df.filter! {|row| row.sum > 10}
-      @df.items.should eql([[5, 6, 7, 8]])
-    end
-    
-    it "should be able to generate a new data frame with filter" do
-      new_df = @df.filter(:open_struct) {|row| row.these == 5}
-      new_df.items.should eql([[5, 6, 7, 8]])
-      @df.items.should eql([[1, 2, 3, 4], [5, 6, 7, 8]])
-    end
-    
-  end
-  
-  context "filter_by_category" do
-    
-    before do
-      @df = DataFrame.new(:weather, :date)
-
-      (1..31).each do |i|
-        @df.add [(i % 3 == 1) ? :fair : :good, Date.parse("07/#{i}/2009")]
-      end
-
-      @d1 = Date.parse("07/15/2009")
-      @d2 = Date.parse("07/31/2009")
-
-    end
-    
-    it "should be able to filter by category" do
-      filtered = @df.filter_by_category(:weather => :good)
-      filtered.weather.uniq.should eql([:good])
-      @df.weather.uniq.should be_include(:fair)
-    end
-    
-    it "should be able to manage ranges for filter values" do
-      filtered = @df.filter_by_category(:date => (@d1..@d2))
-      filtered.date.should_not be_include(Date.parse("07/01/2009"))
-      filtered.date.should_not be_include(Date.parse("07/14/2009"))
-      filtered.date.should be_include(Date.parse("07/15/2009"))
-      filtered.date.should be_include(Date.parse("07/31/2009"))
-      @df.date.should be_include(Date.parse("07/01/2009"))
-    end
-    
-    it "should be able to take an array of values to filter with" do
-      filtered = @df.filter_by_category(:date => [@d1, @d2])
-      filtered.date.should_not be_include(Date.parse("07/01/2009"))
-      filtered.date.should be_include(Date.parse("07/15/2009"))
-      filtered.date.should be_include(Date.parse("07/31/2009"))
-    end
-    
-    it "should have a destructive version" do
-      @df.filter_by_category!(:date => [@d1, @d2])
-      @df.date.should_not be_include(Date.parse("07/01/2009"))
-      @df.date.should be_include(Date.parse("07/15/2009"))
-      @df.date.should be_include(Date.parse("07/31/2009"))
-    end
-    
-  end
-  
-  context "subset_from_columns" do
-    before do
-      @df.add [1,2,3,4]
-      @df.add [5, 6, 7, 8]
-    end
-
-    it "should be able to create a subset of columns" do
-      new_data_frame = @df.subset_from_columns(:these, :labels)
-      new_data_frame.should_not eql(@df)
-      new_data_frame.labels.should eql([:these, :labels])
-      new_data_frame.items.should eql([[1,4],[5,8]])
-      new_data_frame.these.should eql([1,5])
-    end
-  end
-  
-  it "should be able to j_binary_ize! a column, taking its categories and creating a column for each" do
-    df = DataFrame.new(:observations)
-    df.add [:many]
-    df.add [:fine]
-    df.add [:things]
-    df.add [:are]
-    df.add [:available]
-    df.j_binary_ize!(:observations)
-    df.observations_many.should eql([true, false, false, false, false])
-    df.observations_fine.should eql([false, true, false, false, false])
-    df.observations_things.should eql([false, false, true, false, false])
-    df.observations_are.should eql([false, false, false, true, false])
-    df.observations_available.should eql([false, false, false, false, true])
-    df.observations.should eql([:many, :fine, :things, :are, :available])
-  end
-  
-  it "should be able to j_binary_ize! a more normal column" do
-    df = DataFrame.new(:observations)
-    df.import([1,2,3,4,5,4,3,2,1].map{|e| Array(e)})
-    df.observations.add_category(:small) {|e| e <= 3}
-    df.observations.add_category(:large) {|e| e >= 3}
-    df.j_binary_ize!(:observations)
-    df.observations_small.should eql([true, true, true, false, false, false, true, true, true])
-    df.observations_large.should eql([false, false, false, true, true, true, false, false, false])
-  end
   
-  it "should be able to j_binary_ize with non-adjacent sets (sets that allow a value to have more than one category)" do
-    df = DataFrame.new(:observations)
-    df.import([1,2,3,4,5,4,3,2,1].map{|e| Array(e)})
-    df.observations.add_category(:small) {|e| e <= 3}
-    df.observations.add_category(:large) {|e| e >= 3}
-    df.j_binary_ize!(:observations, :allow_overlap => true)
-    df.observations_small.should eql([true, true, true, false, false, false, true, true, true])
-    df.observations_large.should eql([false, false, true, true, true, true, true, false, false])
-  end
-  
-  it "should be able to hold multiple ideas of a columns categories by resetting the category and re-running j_binary_ize" do
-    df = DataFrame.new(:observations)
-    df.import([1,2,3,4,5,4,3,2,1].map{|e| Array(e)})
-    df.observations.add_category(:small) {|e| e <= 3}
-    df.observations.add_category(:large) {|e| e >= 3}
-    df.j_binary_ize!(:observations, :allow_overlap => true)
-    df.observations.set_categories(:odd => lambda{|e| e.odd?}, :even => lambda{|e| e.even?})
-    df.j_binary_ize!(:observations)
-    df.observations_small.should eql([true, true, true, false, false, false, true, true, true])
-    df.observations_large.should eql([false, false, true, true, true, true, true, false, false])
-    df.observations.should eql([1,2,3,4,5,4,3,2,1])
-    df.observations_even.should eql([false, true, false, true, false, true, false, true, false])
-    df.observations_odd.should eql([true, false, true, false, true, false, true, false, true])
-  end
-  
-  context "append!" do
-    
-    before do
-      @df.add [1,2,3,4]
-      @df.add [5, 6, 7, 8]
-    end
-    
-    it "should be able to append an array of values to the data frame" do
-      @df.append!(:new_column, [5,5])
-      @df.new_column.should eql([5,5])
-    end
-    
-    it "should be able to append a default value to the data frame" do
-      @df.append!(:new_column, :value)
-      @df.new_column.should eql([:value, :value])
-    end
-    
-    it "should use nil as the default value" do
-      @df.append!(:new_column)
-      @df.new_column.should eql([nil, nil])
-    end
-  end
 end

data/spec/data_frame/id3_spec.rb

@@ -0,0 +1,22 @@
+require File.join(File.dirname(__FILE__), "/../spec_helper")
+require 'data_frame/id3'
+
+describe "DecisionTree" do
+
+  before do
+    @filename = File.expand_path(File.join(File.dirname(__FILE__), "../fixtures/discrete_training.csv"))
+    @df = DataFrame.from_csv(@filename)
+    @test_data = File.read(@filename)
+  end
+  
+  it "should require the decisiontree gem" do
+    defined?(DecisionTree::ID3Tree).should eql('constant')
+  end
+  
+  it "should be able to create a decision tree from a data frame" do
+    # Come back to this.
+    # @df.create_id3(:purchase)
+    # @df.id3.train
+    # @df.id3.predict(["36 - 55", "masters", "high", "single", 1]).should eql(1)
+  end
+end

data/spec/ext/array_spec.rb

@@ -0,0 +1,13 @@
+require File.join(File.dirname(__FILE__), "/../spec_helper")
+
+describe Array do
+  it "should be able to determine its dimensions" do
+    [1,2,3].dimensions.should eql(1)
+    [[1,2,3], [1,2,3]].dimensions.should eql(2)
+    [[[1,2,3], [1,2,3]], [[1,2,3], [1,2,3], [[1,2,3], [1,2,3]]]].dimensions.should eql(3)
+  end
+  
+  it "should depend on the first element to determine dimensions" do
+    [1, [1,2]].dimensions.should eql(1)
+  end
+end

data/spec/fixtures/discrete_testing.csv

@@ -0,0 +1,4 @@
+36 - 55,masters,high,single,will buy
+18 - 35,high school,low,single,won't buy
+18 - 35,masters,high,single,won't buy
+36 - 55,high school,low,single,will buy

data/spec/fixtures/discrete_training.csv

@@ -0,0 +1,21 @@
+Age,Education,Income,Marital Status,Purchase
+36 - 55,masters,high,single,will buy
+18 - 35,high school,low,single,won't buy
+36 - 55,masters,low,single,will buy
+18 - 35,bachelors,high,single,won't buy
+< 18,high school,low,single,will buy
+18 - 35,bachelors,high,married,won't buy
+36 - 55,bachelors,low,married,won't buy
+> 55,bachelors,high,single,will buy
+36 - 55,masters,low,married,won't buy
+> 55,masters,low,married,will buy
+36 - 55,masters,high,single,will buy
+> 55,masters,high,single,will buy
+< 18,high school,high,single,won't buy
+36 - 55,masters,low,single,will buy
+36 - 55,high school,low,single,will buy
+< 18,high school,low,married,will buy
+18 - 35,bachelors,high,married,won't buy
+> 55,high school,high,married,will buy
+> 55,bachelors,low,single,will buy
+36 - 55,high school,high,married,won't buy

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: davidrichards-data_frame
 version: !ruby/object:Gem::Version 
-  version: 0.0.18
+  version: 0.0.19
 platform: ruby
 authors: 
 - David Richards
@@ -9,8 +9,8 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-09-13 00:00:00 -07:00
-default_executable: 
+date: 2009-09-24 00:00:00 -07:00
+default_executable: plain_frame
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: activesupport
@@ -44,8 +44,8 @@ dependencies:
     version: 
 description: Data Frames with memoized transpose
 email: davidlamontrichards@gmail.com
-executables: []
-
+executables: 
+- plain_frame
 extensions: []
 
 extra_rdoc_files: []
@@ -53,31 +53,58 @@ extra_rdoc_files: []
 files: 
 - README.rdoc
 - VERSION.yml
+- bin/plain_frame
 - lib/data_frame
 - lib/data_frame/arff.rb
 - lib/data_frame/callback_array.rb
+- lib/data_frame/core
+- lib/data_frame/core/column_management.rb
+- lib/data_frame/core/filter.rb
+- lib/data_frame/core/import.rb
+- lib/data_frame/core/pre_process.rb
+- lib/data_frame/core/saving.rb
+- lib/data_frame/core/training.rb
 - lib/data_frame/data_frame.rb
+- lib/data_frame/id3.rb
+- lib/data_frame/kmeans.rb
+- lib/data_frame/labels_from_uci.rb
+- lib/data_frame/mlp.rb
 - lib/data_frame/model.rb
 - lib/data_frame/parameter_capture.rb
+- lib/data_frame/sbn.rb
 - lib/data_frame/transposable_array.rb
 - lib/data_frame.rb
 - lib/ext
+- lib/ext/array.rb
 - lib/ext/open_struct.rb
 - 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/core
+- spec/data_frame/core/column_management_spec.rb
+- spec/data_frame/core/filter_spec.rb
+- spec/data_frame/core/import_spec.rb
+- spec/data_frame/core/pre_process_spec.rb
+- spec/data_frame/core/saving_spec.rb
+- spec/data_frame/core/training_spec.rb
 - spec/data_frame/data_frame_spec.rb
+- spec/data_frame/id3_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/ext
+- spec/ext/array_spec.rb
 - spec/fixtures
 - spec/fixtures/basic.csv
+- spec/fixtures/discrete_testing.csv
+- spec/fixtures/discrete_training.csv
 - spec/spec_helper.rb
 has_rdoc: true
 homepage: http://github.com/davidrichards/data_frame
+licenses: 
 post_install_message: 
 rdoc_options: 
 - --inline-source
@@ -99,7 +126,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.2.0
+rubygems_version: 1.3.5
 signing_key: 
 specification_version: 2
 summary: Data Frames with memoized transpose