commendo 0.0.1

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.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: ccb7bd9fd0ad412db66aeda26a0048db1d3dc040
4
+ data.tar.gz: 0afcaf6c33e8eed6b27401e3bce8bf67dc59440a
5
+ SHA512:
6
+ metadata.gz: 71d5f32a19e6d7de531dc3e99727caafc400eb0d7f0a3aa326f7c03a4b11ed5962654aea49499a75fc1d49344e156987bf20424d778562b901924fa8af939fde
7
+ data.tar.gz: 12f3145df67a43dd59eb56be2884118becb03c93535e7bb25dffaa4fc0d2a9ddeda6a563ea100c658d752f20567c48099ae8cbd2a8af2cb0dd1e6818780a4e2f
@@ -0,0 +1,18 @@
1
+ *.gem
2
+ *.rbc
3
+ .bundle
4
+ .config
5
+ .yardoc
6
+ .idea
7
+ Gemfile.lock
8
+ InstalledFiles
9
+ _yardoc
10
+ coverage
11
+ doc/
12
+ lib/bundler/man
13
+ pkg
14
+ rdoc
15
+ spec/reports
16
+ test/tmp
17
+ test/version_tmp
18
+ tmp
@@ -0,0 +1,2 @@
1
+ # 0.0.1 / 2014-03-28
2
+ * [FEATURE] Initial Release
data/Gemfile ADDED
@@ -0,0 +1,4 @@
1
+ source 'https://rubygems.org'
2
+
3
+ # Specify your gem's dependencies in commendo.gemspec
4
+ gemspec
@@ -0,0 +1,22 @@
1
+ Copyright (c) 2014 Rob Styles
2
+
3
+ MIT License
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining
6
+ a copy of this software and associated documentation files (the
7
+ "Software"), to deal in the Software without restriction, including
8
+ without limitation the rights to use, copy, modify, merge, publish,
9
+ distribute, sublicense, and/or sell copies of the Software, and to
10
+ permit persons to whom the Software is furnished to do so, subject to
11
+ the following conditions:
12
+
13
+ The above copyright notice and this permission notice shall be
14
+ included in all copies or substantial portions of the Software.
15
+
16
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
17
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
18
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
19
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
20
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
21
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
22
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
@@ -0,0 +1,29 @@
1
+ # Commendo
2
+
3
+ TODO: Write a gem description
4
+
5
+ ## Installation
6
+
7
+ Add this line to your application's Gemfile:
8
+
9
+ gem 'commendo'
10
+
11
+ And then execute:
12
+
13
+ $ bundle
14
+
15
+ Or install it yourself as:
16
+
17
+ $ gem install commendo
18
+
19
+ ## Usage
20
+
21
+ TODO: Write usage instructions here
22
+
23
+ ## Contributing
24
+
25
+ 1. Fork it ( http://github.com/<my-github-username>/commendo/fork )
26
+ 2. Create your feature branch (`git checkout -b my-new-feature`)
27
+ 3. Commit your changes (`git commit -am 'Add some feature'`)
28
+ 4. Push to the branch (`git push origin my-new-feature`)
29
+ 5. Create new Pull Request
@@ -0,0 +1,54 @@
1
+ require 'bundler/gem_tasks'
2
+ require 'rake/testtask'
3
+ require 'redis'
4
+ require 'commendo'
5
+
6
+ task :test do
7
+ $LOAD_PATH.unshift('lib', 'test')
8
+ Dir.glob('./test/**/*_test.rb') { |f| require f }
9
+ end
10
+
11
+ task default: :test
12
+
13
+ def tick i, total = nil
14
+ if i % 100 == 0
15
+ print " #{(i / total.to_f).round(2)} " unless total.nil?
16
+ print '.' if total.nil?
17
+ $stdout.flush
18
+ end
19
+ end
20
+
21
+ task :load_traffic_from_tsv, :filename do |task, args|
22
+
23
+ puts "Loading item views from #{args[:filename]}"
24
+ redis = Redis.new(db: 10, timeout: 30)
25
+ cs = Commendo::ContentSet.new(redis, 'CommendoScale')
26
+ redis.flushdb
27
+ start = Time.now
28
+ views = []
29
+ current_resource = nil
30
+ File.open(args[:filename]) do |f|
31
+ f.each_line.with_index do |tsv, i|
32
+ next if i.zero?
33
+ tick i
34
+ tsv.chomp!
35
+ item_type, item_id, user_id, ip_address = tsv.split(/\t/)
36
+ user_id = user_id != 'NULL' ? user_id : ip_address
37
+ next if user_id == 'NULL'
38
+ resource = "#{item_type.gsub(/:+/, '_')}-#{item_id}"
39
+ if not resource == current_resource
40
+ cs.add(current_resource, *views) unless (views.empty? || views.length > 100)
41
+ current_resource = resource
42
+ views = []
43
+ end
44
+ views << user_id unless views.include? user_id
45
+ end
46
+ end
47
+
48
+ puts 'Processing...'
49
+ cs.calculate_similarity(0.1999999999) { |key|
50
+ puts key
51
+ }
52
+ end
53
+
54
+
@@ -0,0 +1,28 @@
1
+ # coding: utf-8
2
+ lib = File.expand_path('../lib', __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require 'commendo/version'
5
+
6
+ Gem::Specification.new do |spec|
7
+ spec.name = 'commendo'
8
+ spec.version = Commendo::VERSION
9
+ spec.authors = ['Rob Styles']
10
+ spec.email = ['rob.styles@dynamicorange.com']
11
+ spec.summary = 'A Jaccard-similarity recommender using Redis sets'
12
+ spec.description = 'A Jaccard-similarity recommender using Redis sets'
13
+ spec.homepage = ''
14
+ spec.license = 'MIT'
15
+
16
+ spec.files = `git ls-files`.split($/)
17
+ spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
18
+ spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
19
+ spec.require_paths = ['lib']
20
+
21
+ spec.add_dependency 'redis'
22
+
23
+ spec.add_development_dependency 'bundler', '~> 1.5'
24
+ spec.add_development_dependency 'rake'
25
+ spec.add_development_dependency 'mocha'
26
+ spec.add_development_dependency 'yard'
27
+ spec.add_development_dependency 'minitest', '~> 5.0.8'
28
+ end
@@ -0,0 +1,7 @@
1
+ require 'redis'
2
+ require 'commendo/version'
3
+ require 'commendo/content_set'
4
+
5
+ module Commendo
6
+ # Your code goes here...
7
+ end
@@ -0,0 +1,72 @@
1
+ module Commendo
2
+
3
+ class ContentSet
4
+
5
+ attr_accessor :redis, :key_base
6
+
7
+ def initialize(redis, key_base)
8
+ @redis, @key_base = redis, key_base
9
+ end
10
+
11
+ def add_by_group(group, *resources)
12
+ resources.each do |res|
13
+ redis.sadd("#{set_key_base}:#{res}", group)
14
+ end
15
+ end
16
+
17
+ def add(resource, *groups)
18
+ redis.sadd("#{set_key_base}:#{resource}", groups)
19
+ end
20
+
21
+ def calculate_similarity(threshold = 0)
22
+ keys = redis.keys("#{set_key_base}:*")
23
+ keys.each do |outer_key|
24
+ outer_res = outer_key.gsub(/^#{set_key_base}:/, '')
25
+ outer_similarity_key = "#{similar_key_base}:#{outer_res}"
26
+ calculate_similarity_in_redis(outer_key, outer_similarity_key, threshold)
27
+ yield(outer_key) if block_given?
28
+ end
29
+
30
+ end
31
+
32
+ def calculate_similarity_in_redis(set_key, similiarity_key, threshold)
33
+ redis.eval(similarity_lua, [set_key, similiarity_key], [set_key_base, threshold])
34
+ end
35
+
36
+ def similar_to(resource)
37
+ similar = []
38
+ similar_resources = redis.hgetall("#{similar_key_base}:#{resource}")
39
+ similar_resources.each do |resource, similarity|
40
+ similar << {resource: resource, similarity: similarity.to_f}
41
+ end
42
+ similar.sort! do |x, y|
43
+ if y[:similarity] != x[:similarity]
44
+ y[:similarity] <=> x[:similarity]
45
+ else
46
+ y[:resource] <=> x[:resource]
47
+ end
48
+ end
49
+ end
50
+
51
+ private
52
+
53
+ def similarity_lua
54
+ @similarity_lua ||= load_similarity_lua
55
+ end
56
+
57
+ def load_similarity_lua
58
+ file = File.open(File.expand_path('../similarity.lua', __FILE__), "r")
59
+ file.read
60
+ end
61
+
62
+ def set_key_base
63
+ "#{key_base}:sets"
64
+ end
65
+
66
+ def similar_key_base
67
+ "#{key_base}:similar"
68
+ end
69
+
70
+ end
71
+
72
+ end
@@ -0,0 +1,31 @@
1
+ local root_key = KEYS[1]
2
+ local sim_key = KEYS[2]
3
+ local set_key_base = ARGV[1]
4
+ local threshold = tonumber(ARGV[2])
5
+
6
+ redis.log(redis.LOG_NOTICE, 'Running similarity for ' .. root_key)
7
+ local key_matches = redis.call('KEYS', set_key_base .. ':*')
8
+
9
+ redis.call('DEL', sim_key)
10
+ local count = 0
11
+ -- local similar = {}
12
+ for _,key in ipairs(key_matches) do
13
+ if key ~= root_key then
14
+ count = count + 1
15
+ local intersect = table.getn(redis.call('SINTER', root_key, key))
16
+ if intersect > 0 then
17
+ local union = table.getn(redis.call('SUNION', root_key, key))
18
+ local similarity = intersect / union
19
+ if similarity > threshold then
20
+ -- table.insert(similar, key)
21
+ -- table.insert(similar, similarity)
22
+ local resource = key:gsub('%' .. set_key_base .. ':', '')
23
+ redis.call('HSET', sim_key, resource, similarity)
24
+ end
25
+ end
26
+ end
27
+ end
28
+
29
+ -- redis.call('HMSET', sim_key, unpack(similar))
30
+ redis.log(redis.LOG_NOTICE, 'Finished running similarity for ' .. root_key)
31
+ return true
@@ -0,0 +1,3 @@
1
+ module Commendo
2
+ VERSION = '0.0.1'
3
+ end
@@ -0,0 +1,100 @@
1
+ gem 'minitest'
2
+ require 'minitest/autorun'
3
+ require 'minitest/pride'
4
+ require 'minitest/mock'
5
+ require 'mocha/setup'
6
+ require 'commendo'
7
+
8
+ module Commendo
9
+
10
+ class ContentSetTest < Minitest::Test
11
+
12
+ def test_stores_sets_by_resource
13
+ redis = Redis.new(db: 15)
14
+ redis.flushdb
15
+ key_base = 'CommendoTests'
16
+ cs = ContentSet.new(redis, key_base)
17
+ cs.add('resource-1', 'group-1', 'group-2')
18
+ cs.add('resource-2', 'group-1')
19
+ cs.add('resource-3', 'group-1', 'group-2')
20
+ cs.add('resource-4', 'group-2')
21
+ assert redis.sismember("#{key_base}:sets:resource-1", 'group-1')
22
+ assert redis.sismember("#{key_base}:sets:resource-2", 'group-1')
23
+ assert redis.sismember("#{key_base}:sets:resource-3", 'group-1')
24
+ refute redis.sismember("#{key_base}:sets:resource-4", 'group-1')
25
+
26
+ assert redis.sismember("#{key_base}:sets:resource-1", 'group-2')
27
+ refute redis.sismember("#{key_base}:sets:resource-2", 'group-2')
28
+ assert redis.sismember("#{key_base}:sets:resource-3", 'group-2')
29
+ assert redis.sismember("#{key_base}:sets:resource-4", 'group-2')
30
+ end
31
+
32
+ def test_stores_sets_by_group
33
+ redis = Redis.new(db: 15)
34
+ redis.flushdb
35
+ key_base = 'CommendoTests'
36
+ cs = ContentSet.new(redis, key_base)
37
+ cs.add_by_group('group-1', 'resource-1', 'resource-2', 'resource-3')
38
+ cs.add_by_group('group-2', 'resource-1', 'resource-3', 'resource-4')
39
+ assert redis.sismember("#{key_base}:sets:resource-1", 'group-1')
40
+ assert redis.sismember("#{key_base}:sets:resource-2", 'group-1')
41
+ assert redis.sismember("#{key_base}:sets:resource-3", 'group-1')
42
+ refute redis.sismember("#{key_base}:sets:resource-4", 'group-1')
43
+
44
+ assert redis.sismember("#{key_base}:sets:resource-1", 'group-2')
45
+ refute redis.sismember("#{key_base}:sets:resource-2", 'group-2')
46
+ assert redis.sismember("#{key_base}:sets:resource-3", 'group-2')
47
+ assert redis.sismember("#{key_base}:sets:resource-4", 'group-2')
48
+ end
49
+
50
+ def test_calculates_similarity_scores
51
+ redis = Redis.new(db: 15)
52
+ redis.flushdb
53
+ key_base = 'CommendoTests'
54
+ cs = ContentSet.new(redis, key_base)
55
+ (3..23).each do |group|
56
+ (3..23).each do |res|
57
+ cs.add_by_group(group, res) if res % group == 0
58
+ end
59
+ end
60
+ cs.calculate_similarity
61
+ expected = [
62
+ { resource: '9', similarity: 0.5 },
63
+ { resource: '6', similarity: 0.5 },
64
+ { resource: '12', similarity: 0.33333333333333 },
65
+ { resource: '3', similarity: 0.25 },
66
+ { resource: '21', similarity: 0.16666666666667 },
67
+ { resource: '15', similarity: 0.16666666666667 }
68
+ ]
69
+ assert_equal expected, cs.similar_to(18)
70
+ end
71
+
72
+ def test_calculates_with_threshold
73
+ redis = Redis.new(db: 15)
74
+ redis.flushdb
75
+ key_base = 'CommendoTests'
76
+ cs = ContentSet.new(redis, key_base)
77
+ (3..23).each do |group|
78
+ (3..23).each do |res|
79
+ cs.add_by_group(group, res) if res % group == 0
80
+ end
81
+ end
82
+ cs.calculate_similarity(0.4)
83
+ expected = [
84
+ { resource: '9', similarity: 0.5 },
85
+ { resource: '6', similarity: 0.5 },
86
+ ]
87
+ assert_equal expected, cs.similar_to(18)
88
+ end
89
+
90
+ def test_calculate_yields_after_each
91
+ skip
92
+ end
93
+
94
+ def test_calculate_deletes_old_values_first
95
+ skip
96
+ end
97
+
98
+ end
99
+
100
+ end
metadata ADDED
@@ -0,0 +1,142 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: commendo
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ platform: ruby
6
+ authors:
7
+ - Rob Styles
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2014-03-28 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: redis
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - '>='
18
+ - !ruby/object:Gem::Version
19
+ version: '0'
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - '>='
25
+ - !ruby/object:Gem::Version
26
+ version: '0'
27
+ - !ruby/object:Gem::Dependency
28
+ name: bundler
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - ~>
32
+ - !ruby/object:Gem::Version
33
+ version: '1.5'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - ~>
39
+ - !ruby/object:Gem::Version
40
+ version: '1.5'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rake
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - '>='
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - '>='
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: mocha
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - '>='
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - '>='
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: yard
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - '>='
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - '>='
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: minitest
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - ~>
88
+ - !ruby/object:Gem::Version
89
+ version: 5.0.8
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - ~>
95
+ - !ruby/object:Gem::Version
96
+ version: 5.0.8
97
+ description: A Jaccard-similarity recommender using Redis sets
98
+ email:
99
+ - rob.styles@dynamicorange.com
100
+ executables: []
101
+ extensions: []
102
+ extra_rdoc_files: []
103
+ files:
104
+ - .gitignore
105
+ - CHANGELOG.md
106
+ - Gemfile
107
+ - LICENSE.txt
108
+ - README.md
109
+ - Rakefile
110
+ - commendo.gemspec
111
+ - lib/commendo.rb
112
+ - lib/commendo/content_set.rb
113
+ - lib/commendo/similarity.lua
114
+ - lib/commendo/version.rb
115
+ - test/content_set_test.rb
116
+ homepage: ''
117
+ licenses:
118
+ - MIT
119
+ metadata: {}
120
+ post_install_message:
121
+ rdoc_options: []
122
+ require_paths:
123
+ - lib
124
+ required_ruby_version: !ruby/object:Gem::Requirement
125
+ requirements:
126
+ - - '>='
127
+ - !ruby/object:Gem::Version
128
+ version: '0'
129
+ required_rubygems_version: !ruby/object:Gem::Requirement
130
+ requirements:
131
+ - - '>='
132
+ - !ruby/object:Gem::Version
133
+ version: '0'
134
+ requirements: []
135
+ rubyforge_project:
136
+ rubygems_version: 2.2.0
137
+ signing_key:
138
+ specification_version: 4
139
+ summary: A Jaccard-similarity recommender using Redis sets
140
+ test_files:
141
+ - test/content_set_test.rb
142
+ has_rdoc: