histograffle 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.textile +86 -0
- data/Rakefile +53 -0
- data/VERSION +1 -0
- data/lib/histograffle.rb +114 -0
- data/test/helper.rb +10 -0
- data/test/test_histograffle.rb +7 -0
- metadata +90 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Jostein B.E.
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.textile
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
h1. Histograffle
|
2
|
+
|
3
|
+
h2. A sort of histogram object implemented in pure Ruby. Use it to count the occurrence of each of several things.
|
4
|
+
|
5
|
+
h3. Simple example of its use and abuse
|
6
|
+
|
7
|
+
I am not a matematician, so this is not a mathematical library or explaination.
|
8
|
+
|
9
|
+
Sample use case: We have two lists of words, and want to count the occurrence of each word in the lists, first separately, and then together.
|
10
|
+
|
11
|
+
<pre>
|
12
|
+
<code>
|
13
|
+
require 'rubygems'
|
14
|
+
require 'histograffle'
|
15
|
+
|
16
|
+
include Histograffle
|
17
|
+
|
18
|
+
reported_incidents = %w[rain thunder confusion fun rain rain theft]
|
19
|
+
|
20
|
+
hist_one = Histogram.new
|
21
|
+
|
22
|
+
hist_one.eat(reported_incidents)
|
23
|
+
|
24
|
+
hist_one.ladder.each do |count|
|
25
|
+
puts "#{count}: #{hist_one[count].join(', ')}"
|
26
|
+
end
|
27
|
+
|
28
|
+
hist_two = Histogram.new
|
29
|
+
|
30
|
+
unreported_incidents = %w[monkey pig concert ufo airplane pig pig concert]
|
31
|
+
|
32
|
+
hist_two.eat(unreported_incidents)
|
33
|
+
|
34
|
+
hist_one << hist_two
|
35
|
+
|
36
|
+
</code>
|
37
|
+
</pre>
|
38
|
+
|
39
|
+
h3. API quickref
|
40
|
+
|
41
|
+
|_@Histograffle::Histogram.new([serialized_data])@_|Create new instance.|
|
42
|
+
|_@hist.eat(item_or_array_or_histogram)@_|Add the input. You can add histograms together this way.|
|
43
|
+
|_@hist[n]@_|Return the occurrences of which there are _n_.|
|
44
|
+
|_@hist.distribution[n]@_|Return the occurrences of which there are _n_.|
|
45
|
+
|_@hist.distribution@_|Descending list of occurrence counts.|
|
46
|
+
|_@hist.ladder@_|Ascending list of occurrence counts.|
|
47
|
+
|_@hist.top(n)@_|Return the top n entries as a hash like @{12 => 'a_word', 2 => 'some other word'}@.|
|
48
|
+
|_@hist.flat_top(n)@_|Same as above, return only a list of words with no differentiations.|
|
49
|
+
|_@hist << other_hist@_|Add a histogram to another.|
|
50
|
+
|_@hist == other_hist@_|True when they contain counts of the same entries.|
|
51
|
+
|
52
|
+
There is also @.to_mongo@ and @.from_mongo@ serialization support.
|
53
|
+
|
54
|
+
To get copies of the raw data tables (see below), you use @hist.data@ and @hist.lookup@.
|
55
|
+
|
56
|
+
h3. Implementation
|
57
|
+
|
58
|
+
Each instance stores its data internally, in two hashes, quite simply. The _data_ hash keys occurrences to counts. The _lookup_ hash keys counts to occurrences. Occurrences can be any object.
|
59
|
+
|
60
|
+
!http://davidpsydoc.com/brian/pictures/extremely%20random,%20hamburger%20gets%20arrested.jpg!
|
61
|
+
"Credit":http://davidpsydoc.com/brian/pictures/extremely%20random
|
62
|
+
|
63
|
+
h3. LICENSE
|
64
|
+
|
65
|
+
(MIT License)
|
66
|
+
|
67
|
+
Copyright (c) 2009 Jostein Berre Eliassen
|
68
|
+
|
69
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
70
|
+
a copy of this software and associated documentation files (the
|
71
|
+
'Software'), to deal in the Software without restriction, including
|
72
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
73
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
74
|
+
permit persons to whom the Software is furnished to do so, subject to
|
75
|
+
the following conditions:
|
76
|
+
|
77
|
+
The above copyright notice and this permission notice shall be
|
78
|
+
included in all copies or substantial portions of the Software.
|
79
|
+
|
80
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
81
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
82
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
83
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
84
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
85
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
86
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "histograffle"
|
8
|
+
gem.summary = %Q{Count the occurrence of each of several things.}
|
9
|
+
gem.description = %Q{Count the occurrence of each of several things. Pure and banal Ruby.}
|
10
|
+
gem.email = "find.me@on.github"
|
11
|
+
gem.homepage = "http://github.com/jbe/histograffle"
|
12
|
+
gem.authors = ["Jostein B.E."]
|
13
|
+
gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
|
14
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
15
|
+
end
|
16
|
+
Jeweler::GemcutterTasks.new
|
17
|
+
rescue LoadError
|
18
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
19
|
+
end
|
20
|
+
|
21
|
+
require 'rake/testtask'
|
22
|
+
Rake::TestTask.new(:test) do |test|
|
23
|
+
test.libs << 'lib' << 'test'
|
24
|
+
test.pattern = 'test/**/test_*.rb'
|
25
|
+
test.verbose = true
|
26
|
+
end
|
27
|
+
|
28
|
+
begin
|
29
|
+
require 'rcov/rcovtask'
|
30
|
+
Rcov::RcovTask.new do |test|
|
31
|
+
test.libs << 'test'
|
32
|
+
test.pattern = 'test/**/test_*.rb'
|
33
|
+
test.verbose = true
|
34
|
+
end
|
35
|
+
rescue LoadError
|
36
|
+
task :rcov do
|
37
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
task :test => :check_dependencies
|
42
|
+
|
43
|
+
task :default => :test
|
44
|
+
|
45
|
+
require 'rake/rdoctask'
|
46
|
+
Rake::RDocTask.new do |rdoc|
|
47
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
48
|
+
|
49
|
+
rdoc.rdoc_dir = 'rdoc'
|
50
|
+
rdoc.title = "histograffle #{version}"
|
51
|
+
rdoc.rdoc_files.include('README*')
|
52
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
53
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
data/lib/histograffle.rb
ADDED
@@ -0,0 +1,114 @@
|
|
1
|
+
|
2
|
+
module Histograffle; end
|
3
|
+
|
4
|
+
class Histograffle::Histogram
|
5
|
+
|
6
|
+
def data
|
7
|
+
@data.dup
|
8
|
+
end
|
9
|
+
|
10
|
+
def lookup
|
11
|
+
lu = @lookup.dup
|
12
|
+
lu.each_key do |k|
|
13
|
+
lu[k] = lu[k].dup
|
14
|
+
end
|
15
|
+
lu
|
16
|
+
end
|
17
|
+
|
18
|
+
def initialize(d=[{}, {}])
|
19
|
+
@data = d[0].dup
|
20
|
+
@lookup = d[1].dup
|
21
|
+
@data.default = 0
|
22
|
+
end
|
23
|
+
|
24
|
+
def eat( o, n=1 )
|
25
|
+
if o.is_a? self.class
|
26
|
+
self << o
|
27
|
+
else
|
28
|
+
o = [o] unless o.respond_to? :each
|
29
|
+
o.each do |t|
|
30
|
+
@data[t] += n
|
31
|
+
@lookup[@data[t]] ||= []
|
32
|
+
@lookup[@data[t]] << t
|
33
|
+
@lookup[@data[t]-n].delete(t) if @lookup[@data[t]-n]
|
34
|
+
@lookup.delete(@data[t]-n) if (@lookup[@data[t]-n] || []).empty?
|
35
|
+
end
|
36
|
+
end
|
37
|
+
self
|
38
|
+
end
|
39
|
+
|
40
|
+
def [](n)
|
41
|
+
@lookup[n]
|
42
|
+
end
|
43
|
+
|
44
|
+
def distribution
|
45
|
+
ladder.reverse
|
46
|
+
end
|
47
|
+
|
48
|
+
def ladder
|
49
|
+
@lookup.keys.sort
|
50
|
+
end
|
51
|
+
|
52
|
+
def top( n )
|
53
|
+
result = {}
|
54
|
+
distribution.each do |count|
|
55
|
+
@lookup[count].each do |word|
|
56
|
+
result[count] ||= []
|
57
|
+
result[count] << word
|
58
|
+
return result if (n -= 1) < 1
|
59
|
+
end
|
60
|
+
end
|
61
|
+
result
|
62
|
+
end
|
63
|
+
|
64
|
+
def flat_top( n )
|
65
|
+
result = []
|
66
|
+
ladder.reverse.each do |count|
|
67
|
+
@lookup[count].each do |word|
|
68
|
+
result << word
|
69
|
+
return result if (n -= 1) < 1
|
70
|
+
end
|
71
|
+
end
|
72
|
+
result
|
73
|
+
|
74
|
+
end
|
75
|
+
|
76
|
+
def <<(other)
|
77
|
+
other.data.each{|k,v| eat(k,v) }
|
78
|
+
self
|
79
|
+
end
|
80
|
+
|
81
|
+
def ==(other)
|
82
|
+
return false unless other.is_a?(self.class)
|
83
|
+
[@data, @lookup] == [other.data, other.lookup]
|
84
|
+
end
|
85
|
+
|
86
|
+
def self.to_mongo(v)
|
87
|
+
# puts "to_mongo: " + v.inspect
|
88
|
+
return v if v.nil?
|
89
|
+
return Array.to_mongo(v) if v.is_a?(Array)
|
90
|
+
[v.data, stringify_keys(v.lookup)]
|
91
|
+
end
|
92
|
+
|
93
|
+
def self.from_mongo(v)
|
94
|
+
# puts "from_mongo: " + v.inspect
|
95
|
+
return v if v.nil? || v.is_a?(self)
|
96
|
+
v ? self.new([v[0], intify_keys(v[1])]) : nil
|
97
|
+
end
|
98
|
+
|
99
|
+
private
|
100
|
+
def self.stringify_keys(hsh)
|
101
|
+
r = Hash.new
|
102
|
+
hsh.each do |k,v|
|
103
|
+
r[k.to_s] = v
|
104
|
+
end
|
105
|
+
r
|
106
|
+
end
|
107
|
+
def self.intify_keys(hsh)
|
108
|
+
r = Hash.new
|
109
|
+
hsh.each do |k,v|
|
110
|
+
r[k.to_i] = v
|
111
|
+
end
|
112
|
+
r
|
113
|
+
end
|
114
|
+
end
|
data/test/helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,90 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: histograffle
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 27
|
5
|
+
prerelease: false
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
- 0
|
10
|
+
version: 0.1.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Jostein B.E.
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2010-06-20 00:00:00 +02:00
|
19
|
+
default_executable:
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
name: thoughtbot-shoulda
|
23
|
+
prerelease: false
|
24
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 3
|
30
|
+
segments:
|
31
|
+
- 0
|
32
|
+
version: "0"
|
33
|
+
type: :development
|
34
|
+
version_requirements: *id001
|
35
|
+
description: Count the occurrence of each of several things. Pure and banal Ruby.
|
36
|
+
email: find.me@on.github
|
37
|
+
executables: []
|
38
|
+
|
39
|
+
extensions: []
|
40
|
+
|
41
|
+
extra_rdoc_files:
|
42
|
+
- LICENSE
|
43
|
+
- README.textile
|
44
|
+
files:
|
45
|
+
- .document
|
46
|
+
- .gitignore
|
47
|
+
- LICENSE
|
48
|
+
- README.textile
|
49
|
+
- Rakefile
|
50
|
+
- VERSION
|
51
|
+
- lib/histograffle.rb
|
52
|
+
- test/helper.rb
|
53
|
+
- test/test_histograffle.rb
|
54
|
+
has_rdoc: true
|
55
|
+
homepage: http://github.com/jbe/histograffle
|
56
|
+
licenses: []
|
57
|
+
|
58
|
+
post_install_message:
|
59
|
+
rdoc_options:
|
60
|
+
- --charset=UTF-8
|
61
|
+
require_paths:
|
62
|
+
- lib
|
63
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
64
|
+
none: false
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
hash: 3
|
69
|
+
segments:
|
70
|
+
- 0
|
71
|
+
version: "0"
|
72
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ">="
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
hash: 3
|
78
|
+
segments:
|
79
|
+
- 0
|
80
|
+
version: "0"
|
81
|
+
requirements: []
|
82
|
+
|
83
|
+
rubyforge_project:
|
84
|
+
rubygems_version: 1.3.7
|
85
|
+
signing_key:
|
86
|
+
specification_version: 3
|
87
|
+
summary: Count the occurrence of each of several things.
|
88
|
+
test_files:
|
89
|
+
- test/helper.rb
|
90
|
+
- test/test_histograffle.rb
|