normalizer 0.0.0 → 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +16 -1
- data/VERSION +1 -1
- data/lib/normalizer.rb +62 -1
- data/normalizer.gemspec +5 -4
- data/spec/normalizer_spec.rb +39 -2
- metadata +2 -2
data/README.rdoc
CHANGED
@@ -24,7 +24,22 @@ To find the min/max of your current data:
|
|
24
24
|
data = [[0, 1, 2, 3, 4], [10, 11, 12, 13, 14]]
|
25
25
|
Normalizer.find_min_and_max(data)
|
26
26
|
#=> [[0, 1, 2, 3, 4], [10, 11, 12, 13, 14]]
|
27
|
+
|
28
|
+
You can also use a buffer on the max/min by setting a buffer in standard deviations:
|
29
|
+
data = [[0, 0, 0, 0, 0], [10, 10, 10, 10, 10]]
|
30
|
+
Normalizer.find_min_and_max(data, :std => 3)
|
31
|
+
#=> [[-21.2132034355964, -21.2132034355964, -21.2132034355964, -21.2132034355964, -21.2132034355964], [31.2132034355964, 31.2132034355964, 31.2132034355964, 31.2132034355964, 31.2132034355964]]
|
32
|
+
|
33
|
+
On a project I'm currently working on I need to know whether data has gone past the max/min amount:
|
34
|
+
a = Normalizer.new(:min => [0], :max => [10])
|
35
|
+
a.normalize([50])
|
36
|
+
a.breaks_boundary?
|
37
|
+
#=> true
|
38
|
+
|
39
|
+
= Thanks
|
40
|
+
|
41
|
+
David Richards (http://blog.tegugears.com/)
|
27
42
|
|
28
43
|
== Copyright
|
29
44
|
|
30
|
-
Copyright (c) 2009
|
45
|
+
Copyright (c) 2009 Red Davis. See LICENSE for details.
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.0.
|
1
|
+
0.0.1
|
data/lib/normalizer.rb
CHANGED
@@ -4,14 +4,55 @@ class Normalizer
|
|
4
4
|
def find_min_and_max(data, options={})
|
5
5
|
@data = data
|
6
6
|
@std = options[:std] || 0
|
7
|
+
@cat_data = Array.new(@data[0].size) { Array.new }
|
8
|
+
|
9
|
+
# Along with finding max and min this also fills @cat_data like so:
|
10
|
+
# [[1,2,3], [1,2,3]] turns into [[1,1], [2,2], [3,3]] so we can calculate
|
7
11
|
@max, @min = find_max, find_min
|
8
12
|
|
9
13
|
unless @std > 0
|
14
|
+
[@min, @max]
|
15
|
+
else
|
16
|
+
mean = find_mean
|
17
|
+
std = calculate_std(mean)
|
18
|
+
|
19
|
+
@max.each_with_index do |n, i|
|
20
|
+
@max[i] = n + (std[i] * @std)
|
21
|
+
end
|
22
|
+
|
23
|
+
@min.each_with_index do |n, i|
|
24
|
+
@min[i] = n - (std[i] * @std)
|
25
|
+
end
|
26
|
+
|
10
27
|
[@min, @max]
|
11
28
|
end
|
12
29
|
end
|
13
30
|
|
14
31
|
private
|
32
|
+
|
33
|
+
def calculate_std(mean)
|
34
|
+
std = []
|
35
|
+
|
36
|
+
@cat_data.each do |set|
|
37
|
+
var = 0.0
|
38
|
+
set.each_with_index do |n, index|
|
39
|
+
var += ((n - mean[index]) ** 2)
|
40
|
+
end
|
41
|
+
std << Math.sqrt(var)
|
42
|
+
end
|
43
|
+
|
44
|
+
std
|
45
|
+
end
|
46
|
+
|
47
|
+
def find_mean
|
48
|
+
mean = []
|
49
|
+
|
50
|
+
@cat_data.each do |i|
|
51
|
+
sum = i.inject(0.0) {|sum, n| sum += n}
|
52
|
+
mean << sum / i.size
|
53
|
+
end
|
54
|
+
mean
|
55
|
+
end
|
15
56
|
|
16
57
|
def find_max
|
17
58
|
@max = []
|
@@ -36,6 +77,7 @@ class Normalizer
|
|
36
77
|
def find_max_in_set(index)
|
37
78
|
max = 0.0
|
38
79
|
@data.each do |set|
|
80
|
+
@cat_data[index] << set[index]
|
39
81
|
max = set[index] > max ? set[index] : max
|
40
82
|
end
|
41
83
|
max
|
@@ -66,10 +108,29 @@ class Normalizer
|
|
66
108
|
normalized[index] = (n.to_f - @min[index]) / @ranges[index]
|
67
109
|
end
|
68
110
|
|
69
|
-
normalized
|
111
|
+
@breaks_boundary = normalized.any? {|x| x > 1 || x < 0}
|
112
|
+
|
113
|
+
round_to_boundaries(normalized)
|
114
|
+
end
|
115
|
+
|
116
|
+
def breaks_boundary?
|
117
|
+
@breaks_boundary
|
70
118
|
end
|
71
119
|
|
72
120
|
private
|
121
|
+
|
122
|
+
# Data shouldn't go over/under the boundary
|
123
|
+
def round_to_boundaries(normalized_data)
|
124
|
+
normalized_data.map do |x|
|
125
|
+
if x > 1
|
126
|
+
1
|
127
|
+
elsif x < 0
|
128
|
+
0
|
129
|
+
else
|
130
|
+
x
|
131
|
+
end
|
132
|
+
end
|
133
|
+
end
|
73
134
|
|
74
135
|
def calculate_ranges
|
75
136
|
range = []
|
data/normalizer.gemspec
CHANGED
@@ -1,15 +1,15 @@
|
|
1
1
|
# Generated by jeweler
|
2
|
-
# DO NOT EDIT THIS FILE
|
3
|
-
# Instead, edit Jeweler::Tasks in Rakefile, and run
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
|
4
4
|
# -*- encoding: utf-8 -*-
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{normalizer}
|
8
|
-
s.version = "0.0.
|
8
|
+
s.version = "0.0.1"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["reddavis"]
|
12
|
-
s.date = %q{2009-10
|
12
|
+
s.date = %q{2009-11-10}
|
13
13
|
s.description = %q{Tool for normalizing data}
|
14
14
|
s.email = %q{reddavis@gmail.com}
|
15
15
|
s.extra_rdoc_files = [
|
@@ -51,3 +51,4 @@ Gem::Specification.new do |s|
|
|
51
51
|
s.add_dependency(%q<rspec>, [">= 0"])
|
52
52
|
end
|
53
53
|
end
|
54
|
+
|
data/spec/normalizer_spec.rb
CHANGED
@@ -1,15 +1,36 @@
|
|
1
1
|
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
2
2
|
|
3
3
|
describe "Normalizer" do
|
4
|
-
|
4
|
+
|
5
5
|
describe "Normalization" do
|
6
6
|
it "should be 0.5" do
|
7
7
|
a = Normalizer.new(:min => [0], :max => [10])
|
8
8
|
results = a.normalize([5])
|
9
9
|
results[0].should == 0.5
|
10
10
|
end
|
11
|
+
|
12
|
+
describe "Going over/under max/min" do
|
13
|
+
before(:all) do
|
14
|
+
@a = Normalizer.new(:min => [0], :max => [10])
|
15
|
+
end
|
16
|
+
|
17
|
+
it "should return true" do
|
18
|
+
results = @a.normalize([20])
|
19
|
+
@a.breaks_boundary?.should be_true
|
20
|
+
end
|
21
|
+
|
22
|
+
it "should return false" do
|
23
|
+
results = @a.normalize([2])
|
24
|
+
@a.breaks_boundary?.should be_false
|
25
|
+
end
|
26
|
+
|
27
|
+
it "should still only return data between 0 and 1" do
|
28
|
+
results = @a.normalize([20])
|
29
|
+
results[0].should == 1
|
30
|
+
end
|
31
|
+
end
|
11
32
|
end
|
12
|
-
|
33
|
+
|
13
34
|
describe "Finding Max and Min" do
|
14
35
|
describe "With 0 Standard deviation" do
|
15
36
|
before(:all) do
|
@@ -24,7 +45,23 @@ describe "Normalizer" do
|
|
24
45
|
it "should return 0,1,2,3,4 for min" do
|
25
46
|
@a[0].should == [0, 1, 2, 3, 4]
|
26
47
|
end
|
48
|
+
end
|
49
|
+
|
50
|
+
describe "With 3 Standard deviation" do
|
51
|
+
before(:all) do
|
52
|
+
data = [[0, 0, 0, 0, 0], [10, 10, 10, 10, 10]]
|
53
|
+
@a = Normalizer.find_min_and_max(data, :std => 3)
|
54
|
+
end
|
55
|
+
|
56
|
+
it "should return std for max" do
|
57
|
+
std = (Math.sqrt(50) * 3) + 10.0
|
58
|
+
@a[1][0].should == std
|
59
|
+
end
|
27
60
|
|
61
|
+
it "should return std for min" do
|
62
|
+
std = 0.0 - (Math.sqrt(50) * 3)
|
63
|
+
@a[0][0].should == std
|
64
|
+
end
|
28
65
|
end
|
29
66
|
end
|
30
67
|
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: normalizer
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- reddavis
|
@@ -9,7 +9,7 @@ autorequire:
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
|
12
|
-
date: 2009-10
|
12
|
+
date: 2009-11-10 00:00:00 +00:00
|
13
13
|
default_executable:
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|