rails-data-explorer 0.2.3 → 1.0.0

data/lib/{rails-data-explorer → rails_data_explorer}/statistics/rng_power_law.rb

@@ -1,12 +1,23 @@
+# -*- coding: utf-8 -*-
+
 class RailsDataExplorer
   module Statistics
+
+    # Responsibilities:
+    #  * Provide random numeric data, following a power distribution.
+    #
     class RngPowerLaw
 
+      # @param min [Numeric]
+      # @param max [Numeric]
+      # @param pow [Numeric]
+      # @param rng [Proc, optional] a random number generator
       def initialize(min = 1, max = 1000, pow = 2, rng = lambda { Kernel.rand })
         @min, @max, @pow, @rng = min, max, pow, rng
         @max += 1
       end
 
+      # Returns random data following a power distribution.
       def rand
         y = (
           (

data/lib/{rails-data-explorer → rails_data_explorer}/utils/color_scale.rb

@@ -1,5 +1,11 @@
+# -*- coding: utf-8 -*-
+
 class RailsDataExplorer
   module Utils
+
+    # Responsibilities:
+    #  * Map an input value between -1 and 1 to a color on a color scale.
+    #
     class ColorScale
 
       def initialize

data/lib/{rails-data-explorer → rails_data_explorer}/utils/data_binner.rb

@@ -1,13 +1,18 @@
-# Convert quantitative data to categorical data.
-# http://saedsayad.com/binning.htm
-# E.g., ages in years to 5 groups:
-# * < 10
-# * 11 - 20
-# * 21 - 30
-# * 31 - 40
-# * > 40
+# -*- coding: utf-8 -*-
+
 class RailsDataExplorer
   module Utils
+
+    # Responsibilities:
+    #  * Convert quantitative data to categorical data.
+    #
+    # http://saedsayad.com/binning.htm
+    # E.g., ages in years to 5 groups:
+    # * < 10
+    # * 11 - 20
+    # * 21 - 30
+    # * 31 - 40
+    # * > 40
     class DataBinner
 
       # @param[Hash] threshold_specs a hash with a key value pair for each threshold

data/lib/{rails-data-explorer → rails_data_explorer}/utils/data_encoder.rb

@@ -1,2 +1,4 @@
+# -*- coding: utf-8 -*-
+
 # Convert categorical data to quantitative data.
 # http://saedsayad.com/encoding.htm

data/lib/{rails-data-explorer → rails_data_explorer}/utils/data_quantizer.rb

@@ -1,7 +1,12 @@
-# Map a large set of quantitative/temporal/geo input values to a (countable)
-# smaller set – such as rounding values to some unit of precision.
+# -*- coding: utf-8 -*-
+
 class RailsDataExplorer
   module Utils
+
+    # Responsibilities:
+    #  * Map a large set of quantitative/temporal/geo input values to a (countable)
+    #    smaller set – such as rounding values to some unit of precision.
+    #
     class DataQuantizer
 
       attr_accessor :number_of_bins, :delta
@@ -10,7 +15,7 @@ class RailsDataExplorer
         @options = {
           nice: true,
           type: 'midtread', # 'midtread' or 'midrise'
-          number_of_bins: 100, # assuming 800px wide chart, 8px per bin
+          number_of_bins: 100, # assuming 1000px wide chart, 10px per bin
           delta: nil,
         }.merge(options)
         @data_series = data_series

data/lib/{rails-data-explorer → rails_data_explorer}/utils/rde_table.rb

@@ -1,18 +1,21 @@
-# Defines classes to describe tables:
-#     rde_table.rows
-#       rde_row.css_class
-#       rde_row.tag
-#       rde_row.cells
-#         rde_cell.css_class
-#         rde_cell.ruby_formatter
-#         rde_cell.style
-#         rde_cell.tag
-#         rde_cell.title
-#         rde_cell.value
+# -*- coding: utf-8 -*-
 
 class RailsDataExplorer
   module Utils
 
+    # Responsibilities:
+    #  * Provide classes to describe tables:
+    #     rde_table.rows
+    #       rde_row.css_class
+    #       rde_row.tag
+    #       rde_row.cells
+    #         rde_cell.css_class
+    #         rde_cell.ruby_formatter
+    #         rde_cell.style
+    #         rde_cell.tag
+    #         rde_cell.title
+    #         rde_cell.value
+    #
     class RdeTable
 
       attr_accessor :rows

data/lib/{rails-data-explorer → rails_data_explorer}/utils/value_formatter.rb

@@ -1,9 +1,14 @@
-# Add ValueFormat to DataSeries and to individual data points
-# Good resource on significant figures:
-# * http://www.edu.pe.ca/gray/class_pages/krcutcliffe/physics521/sigfigs/sigfigRULES.htm
-# * http://en.wikipedia.org/wiki/Significant_figures
+# -*- coding: utf-8 -*-
+
 class RailsDataExplorer
   module Utils
+
+    # Responsibilities:
+    #  * Format values in data series and individual data
+    #
+    # Good resource on significant figures:
+    # * http://www.edu.pe.ca/gray/class_pages/krcutcliffe/physics521/sigfigs/sigfigRULES.htm
+    # * http://en.wikipedia.org/wiki/Significant_figures
     class ValueFormatter
 
       attr_accessor :d3_format, :ruby_formatter, :significant_figures

data/rails-data-explorer.gemspec

@@ -3,7 +3,7 @@ $:.push File.expand_path('../lib', __FILE__)
 
 Gem::Specification.new do |gem|
   gem.name = 'rails-data-explorer'
-  gem.version = '0.2.3'
+  gem.version = '1.0.0'
   gem.platform = Gem::Platform::RUBY
 
   gem.authors = ['Jo Hund']
@@ -16,15 +16,14 @@ Gem::Specification.new do |gem|
   gem.files = `git ls-files`.split("\n")
   gem.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
 
-  gem.add_dependency 'color'
-  gem.add_dependency 'descriptive-statistics'
-  gem.add_dependency 'distribution'
-  gem.add_dependency 'interpolate'
+  gem.add_dependency 'color', ['~> 1.7.1']
+  gem.add_dependency 'descriptive-statistics', ['~> 2.1.2']
+  gem.add_dependency 'distribution', ['~> 0.7.1']
+  gem.add_dependency 'interpolate', ['~> 0.3.0']
 
   gem.add_development_dependency 'actionview', '>= 3.0.0'
   gem.add_development_dependency 'bundler', ['>= 1.0.0']
   gem.add_development_dependency 'minitest'
   gem.add_development_dependency 'minitest-spec-expect'
   gem.add_development_dependency 'rake', ['>= 0']
-  gem.add_development_dependency 'yui-compressor'
 end

data/spec/rails_data_explorer/chart_spec.rb

@@ -0,0 +1,11 @@
+require_relative '../helper_no_rails'
+
+class RailsDataExplorer
+  describe Chart do
+
+    it 'computes a dom id' do
+      Chart.new.dom_id.must_match /rde-chart-\d/
+    end
+
+  end
+end

data/spec/rails_data_explorer/data_set_spec.rb

@@ -0,0 +1,31 @@
+require_relative '../helper_no_rails'
+
+class RailsDataExplorer
+  describe DataSet do
+
+    let(:data_set) {
+      data_series_attrs = [
+        { name: 'ds1', values: (1..6).to_a },
+        { name: 'ds2', values: ('a'..'f').to_a },
+      ]
+      DataSet.new(data_series_attrs, 'the title')
+    }
+
+    it 'returns #data_series' do
+      data_set.data_series.count.must_equal 2
+    end
+
+    it 'returns #number_of_values' do
+      data_set.number_of_values.must_equal 6
+    end
+
+    it 'returns number of dimensions' do
+      data_set.dimensions_count.must_equal 2
+    end
+
+    it 'returns data data_series_names' do
+      data_set.data_series_names.must_equal ["ds1", "ds2"]
+    end
+
+  end
+end

data/spec/rails_data_explorer/data_type/categorical_spec.rb

@@ -0,0 +1,126 @@
+require_relative '../../helper_no_rails'
+
+class RailsDataExplorer
+  class DataType
+    describe Categorical do
+
+      let(:dt) { Categorical.new }
+      let(:values) { ['a', 'a', 'b', 'c'] }
+
+      describe "#descriptive_statistics" do
+
+        let(:desc_stats) {
+          dt.descriptive_statistics(values)
+        }
+
+        it "computes count for each uniq val" do
+          desc_stats.detect{ |e| 'a_count' == e[:label] }[:value].must_equal 2
+        end
+
+        it "computes percent for each uniq val" do
+          desc_stats.detect{ |e| 'a_percent' == e[:label] }[:value].must_equal 50.0
+        end
+
+        it "computes total count" do
+          desc_stats.detect{ |e| '[Total]_count' == e[:label] }[:value].must_equal 4
+        end
+      end
+
+      describe "#available_chart_types" do
+      end
+
+      describe '#label_sorter' do
+
+        it 'sorts numerical labels with greater and less than signs' do
+          labels = ['3', '< -1', '2', '1', '0', '> 3', '-1']
+          ds = DataSeries.new('_', labels)
+          labels.sort(
+            &Categorical.new.label_sorter(nil, ds, '_')
+          ).must_equal(['< -1', '-1', '0', '1', '2', '3', '> 3'])
+        end
+
+        it 'sorts mixed numerical and non-numerical labels with non-num at the end' do
+          labels = ['3', '2', '[Other]', '1']
+          ds = DataSeries.new('_', labels)
+          labels.sort(
+            &Categorical.new.label_sorter(nil, ds, '_')
+          ).must_equal(['1', '2', '3', '[Other]'])
+        end
+
+        it 'accesses label_val_key if given' do
+          labels = ['2', '1']
+          ds = DataSeries.new('_', labels)
+          labels.map { |e| { x: e } }.sort(
+            &Categorical.new.label_sorter(:x, ds, '_')
+          ).must_equal([{ x: '1' }, { x: '2' }])
+        end
+
+      end
+
+      describe '#limit_distinct_values' do
+
+        let(:vals) {
+          %w[
+            a a a a a a a a a a a a a
+            b b b b
+            c
+            d
+            e e e e e
+            f f f f f f f
+            g
+            h h h h
+          ]
+        }
+
+        it 'reduces large number of observations to smaller number' do
+          Categorical.new.limit_distinct_values(vals, 4).must_equal(
+            %w[
+              a a a a a a a a a a a a a
+              [Other] [Other] [Other] [Other]
+              [Other]
+              [Other]
+              e e e e e
+              f f f f f f f
+              [Other]
+              [Other] [Other] [Other] [Other]
+            ]
+          )
+        end
+
+        it 'allows override for val_for_others' do
+          Categorical.new.limit_distinct_values(
+            vals, 4, 'override'
+          ).must_equal(
+            %w[
+              a a a a a a a a a a a a a
+              override override override override
+              override
+              override
+              e e e e e
+              f f f f f f f
+              override
+              override override override override
+            ]
+          )
+        end
+
+        it 'uses label value as tie breaker on equal frequencies' do
+          Categorical.new.limit_distinct_values(vals, 5).must_equal(
+            %w[
+              a a a a a a a a a a a a a
+              b b b b
+              [Other]
+              [Other]
+              e e e e e
+              f f f f f f f
+              [Other]
+              [Other] [Other] [Other] [Other]
+            ]
+          )
+        end
+
+      end
+
+    end
+  end
+end

data/spec/rails_data_explorer/data_type/quantitative/temporal_spec.rb

@@ -0,0 +1,34 @@
+require_relative '../../../helper_no_rails'
+
+class RailsDataExplorer
+  class DataType
+    class Quantitative
+      describe Temporal do
+
+        let(:dt) { Temporal.new }
+        let(:values) { [DateTime.new(2015, 02, 06), DateTime.new(2015, 02, 07)] }
+
+        describe "#descriptive_statistics" do
+
+          let(:desc_stats) {
+            dt.descriptive_statistics(values)
+          }
+
+          it "computes 'Min'" do
+            desc_stats.detect { |e| 'Min' == e[:label] }[:value].must_equal DateTime.new(2015, 02, 06)
+          end
+
+          it "computes 'Max'" do
+            desc_stats.detect { |e| 'Max' == e[:label] }[:value].must_equal DateTime.new(2015, 02, 07)
+          end
+
+          it "computes 'Count'" do
+            desc_stats.detect { |e| 'Count' == e[:label] }[:value].must_equal 2
+          end
+
+        end
+
+      end
+    end
+  end
+end

data/spec/rails_data_explorer/data_type/quantitative_spec.rb

@@ -0,0 +1,118 @@
+require_relative '../../helper_no_rails'
+
+class RailsDataExplorer
+  class DataType
+    describe Quantitative do
+
+      let(:dt) { Quantitative.new }
+      let(:values) { (1..101).to_a }
+
+      describe "#descriptive_statistics" do
+
+        let(:desc_stats) {
+          dt.descriptive_statistics(values)
+        }
+
+        it "computes 'Min'" do
+          desc_stats.detect { |e| 'Min' == e[:label] }[:value].must_equal 1
+        end
+
+        it "computes '1%ile'" do
+          desc_stats.detect { |e| '1%ile' == e[:label] }[:value].must_equal 3
+        end
+
+        it "computes '5%ile'" do
+          desc_stats.detect { |e| '5%ile' == e[:label] }[:value].must_equal 7
+        end
+
+        it "computes '10%ile'" do
+          desc_stats.detect { |e| '10%ile' == e[:label] }[:value].must_equal 12
+        end
+
+        it "computes '25%ile'" do
+          desc_stats.detect { |e| '25%ile' == e[:label] }[:value].must_equal 27
+        end
+
+        it "computes 'Median'" do
+          desc_stats.detect { |e| 'Median' == e[:label] }[:value].must_equal 51
+        end
+
+        it "computes '75%ile'" do
+          desc_stats.detect { |e| '75%ile' == e[:label] }[:value].must_equal 77
+        end
+
+        it "computes '90%ile'" do
+          desc_stats.detect { |e| '90%ile' == e[:label] }[:value].must_equal 92
+        end
+
+        it "computes '95%ile'" do
+          desc_stats.detect { |e| '95%ile' == e[:label] }[:value].must_equal 97
+        end
+
+        it "computes '99%ile'" do
+          desc_stats.detect { |e| '99%ile' == e[:label] }[:value].must_equal 101
+        end
+
+        it "computes 'Max'" do
+          desc_stats.detect { |e| 'Max' == e[:label] }[:value].must_equal 101
+        end
+
+        it "computes 'Range'" do
+          desc_stats.detect { |e| 'Range' == e[:label] }[:value].must_equal 100
+        end
+
+        it "computes 'Mean'" do
+          desc_stats.detect { |e| 'Mean' == e[:label] }[:value].must_equal 51
+        end
+
+        it "computes 'Mode'" do
+          desc_stats.detect { |e| 'Mode' == e[:label] }[:value].must_equal nil
+        end
+
+        it "computes 'Count'" do
+          desc_stats.detect { |e| 'Count' == e[:label] }[:value].must_equal 101
+        end
+
+        it "computes 'Sum'" do
+          desc_stats.detect { |e| 'Sum' == e[:label] }[:value].must_equal 5151
+        end
+
+        it "computes 'Variance'" do
+          desc_stats.detect { |e| 'Variance' == e[:label] }[:value].must_equal 858.5
+        end
+
+        it "computes 'Std. dev.'" do
+          desc_stats.detect { |e| 'Std. dev.' == e[:label] }[:value].must_equal 29.300170647967224
+        end
+
+        it "computes 'Rel. std. dev.'" do
+          desc_stats.detect { |e| 'Rel. std. dev.' == e[:label] }[:value].must_equal 57.166195047502946
+        end
+
+        it "computes 'Skewness'" do
+          desc_stats.detect { |e| 'Skewness' == e[:label] }[:value].must_equal 0.0
+        end
+
+        it "computes 'Kurtosis'" do
+          desc_stats.detect { |e| 'Kurtosis' == e[:label] }[:value].must_equal 1.781945253348864
+        end
+
+      end
+
+      describe '#axis_scale' do
+
+        it 'determines linear' do
+          ds = DataSeries.new('_', [1, 1_000])
+          Quantitative.new.axis_scale(ds, {}, :vega).must_equal 'linear'
+        end
+
+        it 'determines log' do
+          ds = DataSeries.new('_', [1, 1_000_000])
+          Quantitative.new.axis_scale(ds, {}, :vega).must_equal 'log'
+        end
+
+      end
+
+    end
+  end
+end