data_mining 0.0.2 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 974c994068ee3cf5b01c62f5b406f5ae327d17d3
-  data.tar.gz: e95b21a5a62291a3342b32b2b16db1ba31ae9e99
+  metadata.gz: 60ae285b5d026048b81017c733fbbb7dc44742cf
+  data.tar.gz: da11d5c783dcc0926e9ea507b49eb120f509f069
 SHA512:
-  metadata.gz: e81c069008ec95bcc3598b29437890a497917b33e3a873dacbca64265f98681b5f1f8e2484c7fe893597d09837574a35fc846c049cd68c33e159d17c78b5abd2
-  data.tar.gz: b51412c6449a85a22ca5258d2731847abea52a498202bc12f6e4167c1ad28989f60e634c015e0f19409dde655b026a2dd20b5d3eb492f3b1ddbc9db83d9faeef
+  metadata.gz: 4067507c2086ed6f3d9ff5a641ff9e62f55f58d4a39d3eb06b85dae1544c57bf000a6c7ba0586a8aa31fd5f8e86274384a613bf680964a1d21d8d7af5b7c5b0a
+  data.tar.gz: 16c4bb014d46c2a209d1ad194797f98f3986455653efc642afa4d3f59e419f5671bac6c2a05620883f9adb57fd409f093991e5bee6f2ada0ac99402dca5bce59

data/lib/data_mining.rb

@@ -2,3 +2,4 @@ module DataMining
 end
 
 require 'data_mining/dbscan'
+require 'data_mining/apriori'

data/lib/data_mining/apriori.rb

@@ -0,0 +1,60 @@
+module DataMining
+  # Apriori Algorithm for frequent set mining and association rule learning
+  class Apriori
+    attr_reader :results
+
+    def initialize(transactions, minimum_support)
+      @transactions = transactions.select(&:flatten!).each(&:shift)
+      @min_support  = minimum_support
+      @results      = {}
+    end
+
+    def mine!
+      apriori
+    end
+
+    private
+
+    def apriori
+      tmp = starting_set
+      i   = 1
+      while tmp.size > 0
+        @results[i] = tmp
+        i += 1
+        tmp = next_set(tmp)
+      end
+    end
+
+    def starting_set
+      frequent_items.reject { |_, v| v < @min_support }.keys.sort.map { |i| [i] }
+    end
+
+    def frequent_items
+      @transactions.each_with_object(Hash.new(0)) do |sets, hash|
+        sets.each { |item| hash[item] += 1 }
+      end
+    end
+
+    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)
+        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
+      end.uniq
+    end
+
+    def satisfies_min_sup(candidate)
+      return true if (@transactions.inject(0) do |counter, entry|
+        counter += 1 if (candidate - entry).empty?
+        counter
+      end >= @min_support)
+      false
+    end
+  end
+end

data/lib/data_mining/dbscan.rb

@@ -1,5 +1,5 @@
 module DataMining
-  # Density-Based clustering / Outlier-Detection Algorithu
+  # Density-Based clustering / Outlier-Detection Algorithm
   class DBScan
     # Find clusters and outliers
     #
@@ -18,11 +18,6 @@ module DataMining
     #   data: (array of arrays, like [[:id, value], [:id2, value2]]
     #   radius: (integer)
     #   min_points: (integer)
-
-    def self.cluster(data, radius, min_points)
-      DBScan.new(data, radius, min_points)
-    end
-
     def initialize(data, radius, min_points)
       @data               = data.map { |i, v| DataMining::Point.new(i, v) }
       @radius             = radius
@@ -32,7 +27,7 @@ module DataMining
       @unvisited_points   = @data.shuffle
     end
 
-    def build!
+    def cluster!
       dbscan
       clusters
     end
@@ -109,7 +104,11 @@ module DataMining
     def euclidean_distance(p1, p2)
       p1 = p1.value
       p2 = p2.value
-      Math.sqrt(p1.each_with_index.inject(0) { |sum, (v, i)| sum + ((v - p2[i])**2) })
+      Math.sqrt(
+        p1.each_with_index.inject(0) do |sum, (v, i)|
+          sum + ((v - p2[i])**2)
+        end
+      )
     end
   end
 end

data/lib/data_mining/point.rb

@@ -7,7 +7,7 @@ module DataMining
     #
     # Arguments:
     #   id: (symbol)
-    #   value: (integer)
+    #   value: (array)
 
     def initialize(id, value)
       @id             = id

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: data_mining
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - Manuel Stuefer
@@ -9,7 +9,35 @@ autorequire:
 bindir: bin
 cert_chain: []
 date: 2015-06-23 00:00:00.000000000 Z
-dependencies: []
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.7'
+  type: :development
+  prerelease: false
+  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
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
 description: A collection of data mining algorithms
 email: mstuefer@gmail.com
 executables: []
@@ -17,6 +45,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - lib/data_mining.rb
+- lib/data_mining/apriori.rb
 - lib/data_mining/dbscan.rb
 - lib/data_mining/point.rb
 homepage: https://github.com/mstuefer/data_mining