data_mining 0.0.3 → 0.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 60ae285b5d026048b81017c733fbbb7dc44742cf
-  data.tar.gz: da11d5c783dcc0926e9ea507b49eb120f509f069
+  metadata.gz: 28e3a1a81909e9619dff89714def02389e68c9da
+  data.tar.gz: 2a2260b0fcc65003fdb037b1f859941c8100710d
 SHA512:
-  metadata.gz: 4067507c2086ed6f3d9ff5a641ff9e62f55f58d4a39d3eb06b85dae1544c57bf000a6c7ba0586a8aa31fd5f8e86274384a613bf680964a1d21d8d7af5b7c5b0a
-  data.tar.gz: 16c4bb014d46c2a209d1ad194797f98f3986455653efc642afa4d3f59e419f5671bac6c2a05620883f9adb57fd409f093991e5bee6f2ada0ac99402dca5bce59
+  metadata.gz: 851076c8ca90e25ff3dcec0d6e02d513e8779dbbad190c386b7252ddc227c9b05bc822b4c5422d5cff7e27681d59b4086ff2ffcae08030327e9ed07d3fdd97a1
+  data.tar.gz: 83ea46cdadee44244b09265333041a239e0e5534df65ee58cd0f1833c01d2b48179df823ec6116e544d9f4a525df5608a7d86ee715d872f841f2b95d6809d8e6

data/lib/data_mining.rb

@@ -3,3 +3,4 @@ end
 
 require 'data_mining/dbscan'
 require 'data_mining/apriori'
+require 'data_mining/page_rank'

data/lib/data_mining/apriori.rb

@@ -1,28 +1,32 @@
 module DataMining
   # Apriori Algorithm for frequent set mining and association rule learning
   class Apriori
+    # Find frequent item sets
+    #
+    # Arguments:
+    #   transactions: (array of arrays, like [[:id, [transactions]] .. ])
+    #   minimum_support: (integer)
     attr_reader :results
 
     def initialize(transactions, minimum_support)
       @transactions = transactions.select(&:flatten!).each(&:shift)
       @min_support  = minimum_support
-      @results      = {}
+      @results      = []
     end
 
     def mine!
       apriori
     end
 
+    def item_sets_size(size)
+      @results[size - 1]
+    end
+
     private
 
     def apriori
-      tmp = starting_set
-      i   = 1
-      while tmp.size > 0
-        @results[i] = tmp
-        i += 1
-        tmp = next_set(tmp)
-      end
+      @results << starting_set
+      @results << next_set(@results.last) until @results.last.empty?
     end
 
     def starting_set
@@ -38,14 +42,14 @@ module DataMining
     def next_set(itemsets)
       itemsets.each_with_object([]) do |set, arr|
         possible_candidates(set, itemsets).each do |candidate|
-          arr.push(candidate) if satisfies_min_sup(candidate)
+          arr << candidate if satisfies_min_sup(candidate)
         end
       end
     end
 
     def possible_candidates(itemset, itemsets)
       itemsets.each_with_object([]) do |set, arr|
-        arr.push(itemset + [set.last]) if set.last > itemset.last
+        arr << (itemset + [set.last]) if set.last > itemset.last
       end.uniq
     end
 

data/lib/data_mining/dbscan.rb

@@ -3,19 +3,8 @@ module DataMining
   class DBScan
     # Find clusters and outliers
     #
-    # Example:
-    #   >> input      = [[:p1, [1,1]], [:p2, [2,1]], [:p3, [10,11]]]
-    #   >> radius     = 3
-    #   >> min_points = 2
-    #   >> dbscan     = DataMining::DBScan.cluster(input, radius, min_points)
-    #   >> dbscan.build!
-    #   >>
-    #   >> dbscan.clusters # gives array of clusters found (:p1, :p2)
-    #   >>
-    #   >> dbscan.outliers # gives array of outliers found (:p3)
-    #
     # Arguments:
-    #   data: (array of arrays, like [[:id, value], [:id2, value2]]
+    #   data: (array of arrays, like [[:id, value], [:id2, value2]])
     #   radius: (integer)
     #   min_points: (integer)
     def initialize(data, radius, min_points)
@@ -29,7 +18,6 @@ module DataMining
 
     def cluster!
       dbscan
-      clusters
     end
 
     def outliers
@@ -78,11 +66,10 @@ module DataMining
       fill_current_cluster(neighborhood) if core_object?(neighborhood)
     end
 
-    # use map instead of each?
     def get_neighborhood(point)
-      neighborhood = []
-      @data.each { |p| neighborhood << p if neighbors?(p, point) }
-      neighborhood
+      @data.each_with_object([]) do |p, neighborhood|
+        neighborhood << p if neighbors?(p, point)
+      end
     end
 
     def core_object?(neighborhood)

data/lib/data_mining/page_rank.rb

@@ -0,0 +1,53 @@
+module DataMining
+  # PageRank Algorithm to measure the importance of nodes in a graph
+  class PageRank
+    attr_reader :graph, :ranks
+    # Measure importance of nodes
+    #
+    # Arguments:
+    #   graph: (array of arrays, like:
+    #     [[:p1, [:p2]], [:p2, [:p1, :p3]], [:p3, [:p2]]]
+    #   damping_factor: (double between 0 and 1)
+    def initialize(graph, damping_factor = 0.85, iterations = 100)
+      @graph      = graph.to_h
+      # { :p1 => [:p2], :p2 => [:p1,:p3], :p3 => [:p2] }
+      @outlinks   = Hash.new { |_, key| @graph[key].size }
+      # { :p1 => 1, :p2 => 2, :p3 => 1 }
+      @inlinks    = Hash.new { |_, key| inlinks(key) }
+      # { :p1 => [:p2], :p2 => [:p1,:p3], :p3 => [:p2] }
+      @ranks      = Hash.new(1.0 / @graph.size)
+      # { :p1 => 1/3, :p2 => 1/3, ... }
+
+      @damper     = damping_factor
+      @iterations = iterations
+    end
+
+    def rank!
+      pagerank
+    end
+
+    private
+
+    def inlinks(key)
+      @graph.select { |_, v| v.include?(key) }.keys
+    end
+
+    def pagerank
+      @iterations.times { @ranks = next_state }
+    end
+
+    def next_state
+      @graph.each_with_object({}) do |(node, _), ranks|
+        ranks[node] = term + @damper * sum_incoming_scores(node)
+      end
+    end
+
+    def sum_incoming_scores(node)
+      @inlinks[node].map { |id| @ranks[id] / @outlinks[id] }.inject(:+).to_f
+    end
+
+    def term
+      @term ||= ((1 - @damper) / @graph.size)
+    end
+  end
+end

metadata

@@ -1,43 +1,57 @@
 --- !ruby/object:Gem::Specification
 name: data_mining
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
 platform: ruby
 authors:
 - Manuel Stuefer
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
 date: 2015-06-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '5.7'
-  type: :development
+  name: minitest
   prerelease: false
+  type: :development
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '5.7'
 - !ruby/object:Gem::Dependency
-  name: minitest-reporters
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '1.0'
-  type: :development
+  name: minitest-reporters
   prerelease: false
+  type: :development
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '1.0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.10'
+  name: simplecov
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.10'
 description: A collection of data mining algorithms
 email: mstuefer@gmail.com
 executables: []
@@ -45,31 +59,32 @@ extensions: []
 extra_rdoc_files: []
 files:
 - lib/data_mining.rb
-- lib/data_mining/apriori.rb
 - lib/data_mining/dbscan.rb
 - lib/data_mining/point.rb
+- lib/data_mining/apriori.rb
+- lib/data_mining/page_rank.rb
 homepage: https://github.com/mstuefer/data_mining
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.6
-signing_key: 
+rubyforge_project:
+rubygems_version: 2.1.9
+signing_key:
 specification_version: 4
 summary: Data-Mining-Algorithms
 test_files: []