normalizer 0.0.0 → 0.0.1

data/README.rdoc

@@ -24,7 +24,22 @@ To find the min/max of your current data:
   data = [[0, 1, 2, 3, 4], [10, 11, 12, 13, 14]]
   Normalizer.find_min_and_max(data)
     #=> [[0, 1, 2, 3, 4], [10, 11, 12, 13, 14]]
+    
+You can also use a buffer on the max/min by setting a buffer in standard deviations:
+  data = [[0, 0, 0, 0, 0], [10, 10, 10, 10, 10]]
+  Normalizer.find_min_and_max(data, :std => 3)
+    #=> [[-21.2132034355964, -21.2132034355964, -21.2132034355964, -21.2132034355964, -21.2132034355964], [31.2132034355964, 31.2132034355964, 31.2132034355964, 31.2132034355964, 31.2132034355964]]
+    
+On a project I'm currently working on I need to know whether data has gone past the max/min amount:
+  a = Normalizer.new(:min => [0], :max => [10])
+  a.normalize([50])
+  a.breaks_boundary?
+    #=> true
+
+= Thanks
+
+David Richards (http://blog.tegugears.com/)
 
 == Copyright
 
-Copyright (c) 2009 reddavis. See LICENSE for details.
+Copyright (c) 2009 Red Davis. See LICENSE for details.

data/VERSION

@@ -1 +1 @@
-0.0.0
+0.0.1

data/lib/normalizer.rb

@@ -4,14 +4,55 @@ class Normalizer
     def find_min_and_max(data, options={})
       @data = data
       @std = options[:std] || 0
+      @cat_data = Array.new(@data[0].size) { Array.new }
+      
+      # Along with finding max and min this also fills @cat_data like so:
+      # [[1,2,3], [1,2,3]] turns into [[1,1], [2,2], [3,3]] so we can calculate
       @max, @min = find_max, find_min
       
       unless @std > 0
+        [@min, @max]
+      else
+        mean = find_mean
+        std = calculate_std(mean)
+        
+        @max.each_with_index do |n, i|
+          @max[i] = n + (std[i] * @std)
+        end
+        
+        @min.each_with_index do |n, i|
+          @min[i] = n - (std[i] * @std)
+        end
+        
         [@min, @max]
       end
     end
     
     private
+    
+    def calculate_std(mean)
+      std = []
+      
+      @cat_data.each do |set|
+        var = 0.0
+        set.each_with_index do |n, index|
+          var += ((n - mean[index]) ** 2)
+        end
+        std << Math.sqrt(var)
+      end
+      
+      std
+    end
+    
+    def find_mean
+      mean = []
+      
+      @cat_data.each do |i|
+        sum = i.inject(0.0) {|sum, n| sum += n}
+        mean << sum / i.size
+      end
+      mean
+    end
         
     def find_max
       @max = []
@@ -36,6 +77,7 @@ class Normalizer
     def find_max_in_set(index)
       max = 0.0
       @data.each do |set|
+        @cat_data[index] << set[index]
         max = set[index] > max ? set[index] : max
       end
       max
@@ -66,10 +108,29 @@ class Normalizer
       normalized[index] = (n.to_f - @min[index]) / @ranges[index]
     end
     
-    normalized
+    @breaks_boundary = normalized.any? {|x| x > 1 || x < 0}
+    
+    round_to_boundaries(normalized)
+  end
+  
+  def breaks_boundary?
+    @breaks_boundary
   end
       
   private
+  
+  # Data shouldn't go over/under the boundary
+  def round_to_boundaries(normalized_data)
+    normalized_data.map do |x|
+      if x > 1
+        1
+      elsif x < 0
+        0
+      else
+        x
+      end
+    end
+  end
     
   def calculate_ranges
     range = []

data/normalizer.gemspec

@@ -1,15 +1,15 @@
 # Generated by jeweler
-# DO NOT EDIT THIS FILE
-# Instead, edit Jeweler::Tasks in Rakefile, and run `rake gemspec`
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
 # -*- encoding: utf-8 -*-
 
 Gem::Specification.new do |s|
   s.name = %q{normalizer}
-  s.version = "0.0.0"
+  s.version = "0.0.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["reddavis"]
-  s.date = %q{2009-10-30}
+  s.date = %q{2009-11-10}
   s.description = %q{Tool for normalizing data}
   s.email = %q{reddavis@gmail.com}
   s.extra_rdoc_files = [
@@ -51,3 +51,4 @@ Gem::Specification.new do |s|
     s.add_dependency(%q<rspec>, [">= 0"])
   end
 end
+

data/spec/normalizer_spec.rb

@@ -1,15 +1,36 @@
 require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 
 describe "Normalizer" do
-    
+   
   describe "Normalization" do
     it "should be 0.5" do
       a = Normalizer.new(:min => [0], :max => [10])
       results = a.normalize([5])
       results[0].should == 0.5
     end
+
+    describe "Going over/under max/min" do
+      before(:all) do
+        @a = Normalizer.new(:min => [0], :max => [10])
+      end
+      
+      it "should return true" do
+        results = @a.normalize([20])
+        @a.breaks_boundary?.should be_true
+      end
+      
+      it "should return false" do
+        results = @a.normalize([2])
+        @a.breaks_boundary?.should be_false
+      end
+      
+      it "should still only return data between 0 and 1" do
+        results = @a.normalize([20])
+        results[0].should == 1
+      end
+    end
   end
-  
+ 
   describe "Finding Max and Min" do
     describe "With 0 Standard deviation" do
       before(:all) do
@@ -24,7 +45,23 @@ describe "Normalizer" do
       it "should return 0,1,2,3,4 for min" do
         @a[0].should == [0, 1, 2, 3, 4]
       end
+    end
+    
+    describe "With 3 Standard deviation" do
+      before(:all) do
+        data = [[0, 0, 0, 0, 0], [10, 10, 10, 10, 10]]
+        @a = Normalizer.find_min_and_max(data, :std => 3)
+      end
+      
+      it "should return std for max" do
+        std = (Math.sqrt(50) * 3) + 10.0
+        @a[1][0].should == std
+      end
       
+      it "should return std for min" do
+        std = 0.0 - (Math.sqrt(50) * 3)
+        @a[0][0].should == std
+      end
     end
   end
   

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: normalizer
 version: !ruby/object:Gem::Version 
-  version: 0.0.0
+  version: 0.0.1
 platform: ruby
 authors: 
 - reddavis
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-10-30 00:00:00 +00:00
+date: 2009-11-10 00:00:00 +00:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency