daru 0.0.2.2 → 0.0.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6266fb09be80748530baa8b92aface148f47bac6
-  data.tar.gz: 37f2301d6b3fed23b15e11c5608892935befb04e
+  metadata.gz: e425d7fab01db79087549701e3e9e95df2b495d1
+  data.tar.gz: f3b186c9405b1fb14fb7b95a2ecde7a291decbb4
 SHA512:
-  metadata.gz: fa67c4506dea445619c1cf79270c5194cd189da302705b8d0dcad6689b3c3717f08bc11ce15af9670c7245fc746b3ce8feb0e82ea22c69aa06bf8da15003f947
-  data.tar.gz: 17d35384cf2daf28eca33aef370789edf7854da821094207e3eda9732933889ce23a44777e9aa451e62c732048a472d74378affb97e1a193cfe235426d83428e
+  metadata.gz: fd89ad49623169a8caf335746094a38e2613864ec05f059488773285deaff87eaa5a8a68b6f60a2a12e37f5ad29cc800e8cdb7b0fba12eeb3a21b9bb3dbcca69
+  data.tar.gz: 0b1458e1df11590ca858e9350503eef9a29420661ea92d1c73907ee47c33879637260f489bd3451aa9d7774d69e20b639e17ecdfac339c18f710c6ba25955908

data/History.txt

@@ -0,0 +1,17 @@
+== 0.0.1
+* Added classes for DataFrame and Vector alongwith some super-basic functions to get off the ground
+
+== 0.0.2
+* Added iterators for dataframe and vector alongwith printing functions (to_html) to interface properly with iRuby notebook.
+
+== 0.0.2.1
+* Fixed bugs with previous code and more iterators
+
+== 0.0.2.2
+* Added test cases and multiple column access through the [] operator on DataFrames
+
+== 0.0.2.3
+* Added #filter\_rows and #delete_row to DataFrame and changed #row to return a row containing a Hash of column name and value.
+* Vector objects passed into a DataFrame are now duplicated so that any changes dont affect the original vector.
+* Added an optional opts argument to DataFrame.
+* Sending more fields than vectors in DataFrame will cause addition of nil vectors.

data/README.md

@@ -31,12 +31,11 @@ Then switch to MRI, do a normal `bundle install` followed by `rspec` for testing
 
 ## Roadmap
 
-* Print dataframe in same order as fields.
-* Return rows in same order as that of fields.
 * Automate testing for both MRI and JRuby.
 * Enable creation of DataFrame by only specifying an NMatrix/MDArray in initialize. Vector naming happens automatically (alphabetic) or is specified in an Array.
 * Add support for missing values in vectors.
-* Add normal and destructive map iterators.
+* Destructive version #filter\_rows!
+* NMatrix.first should return NMatrix (in vector).
 * Completely test all functionality for NMatrix and MDArray.
 * Basic Data manipulation and analysis operations: 
     - Different kinds of join operations
@@ -51,4 +50,5 @@ Then switch to MRI, do a normal `bundle install` followed by `rspec` for testing
     - Runtime alteration of index.
 * Indexing on DataFrame.
 * Vector arithmetic - elementwise addition, subtraction, multiplication, division.
-* Transpose a dataframe.
+* Transpose a dataframe.
+* Option to express a DataFrame as an NMatrix or MDArray so as to use more efficient storage techniques.

data/lib/daru.rb

@@ -3,4 +3,5 @@ require 'matrix'
 require 'csv'
 
 require 'daru/vector.rb'
-require 'daru/dataframe.rb'
+require 'daru/dataframe.rb'
+require 'daru/monkeys.rb'

data/lib/daru/dataframe.rb

@@ -9,18 +9,25 @@ module Daru
 
     attr_reader :name
 
-    def initialize source, fields=[], name=SecureRandom.uuid
+    def initialize source, fields=[], name=SecureRandom.uuid, opts={}
+      @opts = opts
+      set_default_opts
+
       if source.empty?
         @vectors = fields.inject({}){ |a,x| a[x]=Daru::Vector.new; a}
       else
-        @vectors = source
+        @vectors = source.inject({}) do |acc, h|
+          acc[h[0]] = h[1].dv.dup
+          acc
+        end
       end
 
       @fields = fields.empty? ? source.keys.sort : fields
       @name   = name
- 
+
       check_length
-      set_fields_order if @vectors.keys.sort != @fields.sort
+      set_missing_vectors if @vectors.keys.size < @fields.size
+      set_fields_order    if @vectors.keys.sort != @fields.sort
       set_vector_names
     end
 
@@ -53,20 +60,36 @@ module Daru
       @vectors[name]
     end
 
-    def delete name
+    def delete_vector name
       @vectors.delete name
       @fields.delete name
     end
 
-    # def filter_rows
-      
-    # end
+    alias_method :delete, :delete_vector
 
-    # def filter_columns
-      
-    # end
+    def delete_row index
+      # TODO: Make this work with NMatrix and MDArray
+      raise "Expected index less than size." if index > @size
+
+      @fields.each do |field|
+        @vectors[field].delete index
+      end
+      puts @vectors
+    end
+
+    def filter_rows name=self.name, &block
+      df = DataFrame.new({}, @fields, name)
+
+      self.each_row do |row|
+        keep_row = yield row
+
+        df.insert_row(row.values) if keep_row
+      end
 
-    def [](*name)
+      df
+    end
+
+    def [] *name
       unless name[1]
         return column(name[0])
       end
@@ -81,21 +104,21 @@ module Daru
       DataFrame.new h, req_fields, @name
     end
 
-    def ==(other)
+    def == other
       @name == other.name and @vectors == other.vectors and 
       @size == other.size and @fields  == other.fields 
     end
 
-    def []=(name, vector)
+    def []= name, vector
       insert_vector name, vector
     end
 
     def row index
       raise Exception, "Expected index to be within bounds" if index > @size
 
-      row = []
-      self.each_column do |column|
-        row << column[index]
+      row = {}
+      self.each_vector do |column|
+        row[column.name] = column[index]
       end
 
       row
@@ -105,7 +128,7 @@ module Daru
       !!@vectors[vector]
     end
 
-    def each_row
+    def each_row(&block)
       0.upto(@size-1) do |index|
         yield row(index)
       end
@@ -113,7 +136,7 @@ module Daru
       self
     end
 
-    def each_row_with_index
+    def each_row_with_index(&block)
       0.upto(@size-1) do |index|
         yield row(index), index
       end
@@ -121,7 +144,7 @@ module Daru
       self
     end
 
-    def each_column
+    def each_vector(&block)
       @fields.each do |field|
         yield @vectors[field]
       end
@@ -129,7 +152,7 @@ module Daru
       self
     end
 
-    def each_column_with_name
+    def each_vector_with_name(&block)
       @fields.each do |field|
         yield @vectors[field], field
       end
@@ -152,6 +175,8 @@ module Daru
       @fields.each_with_index do |field, index|
         @vectors[field] << row[index]
       end
+
+      @size += 1
     end
 
     def to_html(threshold=15)
@@ -164,7 +189,7 @@ module Daru
       self.each_row_with_index do |row, index|
         break if index > threshold and index <= @size
         html += '<tr>'
-        row.each{ |val| html.concat('<td>' + val.to_s + '</td>') }
+        row.each_value { |val| html.concat('<td>' + val.to_s + '</td>') }
         html += '</tr>'
         if index == threshold
           html += '<tr>'
@@ -206,17 +231,30 @@ module Daru
       @size = size
     end
 
-    def set_fields_order
-      @fields = @vectors.keys & @fields
-      @fields += @vecorts.keys.sort - @fields
+    def set_fields_order # vectors more than specified fields
+      @fields = @fields & @vectors.keys
+      @fields += @vectors.keys.sort - @fields
     end
 
     # Writes names specified in the hash to the actual name of the vector.
     # Will over-ride any previous name assigned to the vector.
-    def set_vector_names
+    def set_vector_names      
       @fields.each do |name|
         @vectors[name].name = name
       end
     end
+
+    def set_default_opts
+      # Future proofing
+    end
+
+    def set_missing_vectors
+      missing_fields = @fields - @vectors.keys
+
+      missing_fields.each do |field|
+        @vectors[field] = ([nil]*@size).dv
+        @fields << field
+      end
+    end
   end
 end

data/lib/daru/monkeys.rb

@@ -0,0 +1,39 @@
+class Array
+  def daru_vector name=nil
+    Daru::Vector.new self, name
+  end
+
+  alias_method :dv, :daru_vector
+end
+
+class Range
+  def daru_vector name=nil
+    Daru::Vector.new self, name
+  end
+
+  alias_method :dv, :daru_vector
+end
+
+class Hash
+  def daru_vector
+    Daru::Vector.new self.values[0], self.keys[0]
+  end
+
+  alias_method :dv, :daru_vector
+end
+
+class NMatrix
+  def daru_vector name=nil
+    Daru::Vector.new self
+  end
+
+  alias_method :dv, :daru_vector
+end
+
+class MDArray
+  def daru_vector name=nil
+    Daru::Vector.new self, name
+  end
+
+  alias_method :dv, :daru_vector
+end

data/lib/daru/vector.rb

@@ -1,43 +1,3 @@
-class Array
-  def daru_vector
-    Daru::Vector.new self
-  end
-
-  alias_method :dv, :daru_vector
-end
-
-class Range
-  def daru_vector
-    Daru::Vector.new self
-  end
-
-  alias_method :dv, :daru_vector
-end
-
-class Hash
-  def daru_vector
-    Daru::Vector.new self.values[0], self.keys[0]
-  end
-
-  alias_method :dv, :daru_vector
-end
-
-class NMatrix
-  def daru_vector
-    Daru::Vector.new self
-  end
-
-  alias_method :dv, :daru_vector
-end
-
-class MDArray
-  def daru_vector
-    Daru::Vector.new self
-  end
-
-  alias_method :dv, :daru_vector
-end
-
 module Daru
   class Vector
     include Enumerable
@@ -79,11 +39,13 @@ module Daru
     end
 
     def ==(other)
-      other.vector == @vector and other.name == @name
+      other.vector == @vector and other.name == @name and other.size == @size
     end
 
     def <<(element)
       @vector << element
+
+      @size += 1
     end
 
     def to_json
@@ -104,6 +66,12 @@ module Daru
       lim == 1 ? @vector.first : @vector.first(lim)
     end
 
+    def delete index
+      @vector[index] = nil
+      @vector.compact!
+      @size -= 1
+    end
+
     def to_html threshold=15
       html = '<table><tr><th>' + @name.to_s + '</th></tr>>'
 
@@ -117,7 +85,17 @@ module Daru
     end
 
     def dup
-      Daru::Vector.new @vector.dup, @name.dup
+      Daru::Vector.new @vector.dup, @name
+    end
+
+    def daru_vector
+      self
+    end
+
+    alias_method :dv, :daru_vector
+
+    def compact!
+      @vector.compact!
     end
   end
 end

data/lib/version.rb

@@ -1,3 +1,3 @@
 module Daru
-  VERSION = "0.0.2.2"
+  VERSION = "0.0.2.3"
 end

data/spec/mri/dataframe_spec.rb

@@ -1,7 +1,7 @@
 require 'spec_helper.rb'
 
 describe Daru::DataFrame do
-  context "DataFrame from normal array vectors" do
+  context "DataFrame of Array" do
     
     before :each do
       @df = Daru::DataFrame.new({a: Daru::Vector.new(1..3), 
@@ -36,12 +36,12 @@ describe Daru::DataFrame do
     it "returns a row" do
       r = @df.row 0
 
-      expect(r).to eq(['Jesse',1,50])
+      expect(r).to eq({:b_bad=> "Jesse", :a=> 1, :b=> 50})
     end
 
     it "iterates over columns in the specified order" do
       cols = []
-      df = @df.each_column do |col|
+      df = @df.each_vector do |col|
         expect(col.is_a?(Daru::Vector)).to be(true)
         cols << col.name
       end
@@ -56,6 +56,13 @@ describe Daru::DataFrame do
       end
     end
 
+    it "filters rows" do
+      res = @df.filter_rows(@df.name) { |row| row[:b] == 50 }
+
+      expect(res).to eq(Daru::DataFrame.new({a: [1].dv, b: [50].dv, b_bad: ['Jesse'].dv}, 
+        @df.fields, @df.name))
+    end
+
     it "shows column fields" do
       expect(@df.fields).to eq([:b_bad, :a, :b])
     end
@@ -90,9 +97,26 @@ describe Daru::DataFrame do
 
       expect(@df[:a, :b]).to eq(req)
     end
+
+    it "creates DataFrame from Array" do
+      a_df = Daru::DataFrame.new({a: [1,2,3,4], b: [10,11,12,13]})
+
+      expect(a_df.a.is_a? Daru::Vector).to eq(true)
+      expect(a_df.a.vector).to eq([1,2,3,4])
+    end
+  end
+
+  context "Malformed DataFrame from Array" do
+    it "adds extra nil vectors from fields" do
+      df = Daru::DataFrame.new({a: (1..4).dv, b: (50..53).dv}, [:b, :a, :jazzy, :joe])
+
+      expect(df.fields).to eq([:b, :a, :jazzy, :joe])
+      expect(df.jazzy).to eq(([nil]*4).dv(:jazzy))
+      expect(df.joe).to eq(([nil]*4).dv(:joe))
+    end
   end
 
-  context "DataFrame loads from files" do
+  context "DataFrame from files" do
 
     it "loads a DataFrame from CSV" do
       df = Daru::DataFrame.from_csv('spec/fixtures/matrix_test.csv', 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: daru
 version: !ruby/object:Gem::Version
-  version: 0.0.2.2
+  version: 0.0.2.3
 platform: ruby
 authors:
 - Sameer Deshmukh
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-10-11 00:00:00.000000000 Z
+date: 2014-10-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -72,6 +72,7 @@ files:
 - daru.gemspec
 - lib/daru.rb
 - lib/daru/dataframe.rb
+- lib/daru/monkeys.rb
 - lib/daru/vector.rb
 - lib/version.rb
 - spec/fixtures/matrix_test.csv