db_clustering 0.1.4 → 0.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8901dbfe4c461163864eecc8934ca87e7e3485cf
-  data.tar.gz: 200614749469e8548535f9d5b2095e641354b00d
+  metadata.gz: 9aa27e97cd4db7b79c7a6ce30db82436e9553f55
+  data.tar.gz: 61628405866773b9bacaa9f5ac954ba623d48f69
 SHA512:
-  metadata.gz: 90931ba87de5fa19325f4965f166ad62a2650dac55789b7e66e4308b1e6b00bc1331a77e91e5013f0f65492272be1f2966d89bd8e6ebe89343b05858c85145d1
-  data.tar.gz: 5857b3d7f4926a0a7b96f711b93ee3f4ab0fb8442430fb66f279188a359ff2ef691cd67bbd2f7eeaab0f83e46dc9330089a44d3645b8fb7a5e9a3040c91a605f
+  metadata.gz: b126213d40d23b9548e754587da63c27d580358d9b403f96a4628c14820d5513a1af7f3e2679e9871521dc280720ba39466bdd448431bfce4e3f5fb4252fd8db
+  data.tar.gz: c0808f2d68358297e6820b9ecebec10711662c285750ef3419d2a3a60969bc1f6632a8ff108bd0fcf2c4ea522d46a77891b7c3195e36b35f8ade781bd9210ee2

data/README.md

@@ -58,6 +58,27 @@ This gem was developed to work best in Ruby on Rails projects.
    ```
    The `max_distance` is the epsilon parameter and the `min_neighbors` the minPts parameter from the usual DBSCAN algorithm documentation (e.g. Wikipedia). You might want to try different values here first before you decide for the right values for your purpose.
 
+   If you're interested in the progress of the algorithm you can run some code after each iteration of it (for DBSCAN this would mean after clustering a single point with its neighbors). Please note though that the current information at that point may be incomplete so don't use this as a method to receive a portion of the final results, treat it more like a partial result or just use it to indicate progress or do some debugging. For example you could do this:
+
+   ``` ruby
+   last_printed_progress = 0.0
+
+   dbscan.cluster(max_distance: 10, min_neighbors: 5) do |point, current_index, points_count|
+     progress = (current_index + 1) * 100 / points_count.to_f
+
+     if progress > last_printed_progress + 1
+       print "[#{progress.to_i}%]"
+       last_printed_progress = progress
+     end
+
+     if point.cluster
+       print "(#{point.cluster.id}|#{point.cluster.points.count})"
+     else
+       print "(nil|0)"
+     end
+   end
+   ```
+
    Plase also take note that the `max_distance` value is **highly dependent on the type of metric** you decided to go for. For the `AverageDifference` and `EuclideanDistance` metrics it can be an **open-ended positive value**. For the `CosineSimilarity` and `PearsonCorrelation` types it needs to be a value between 0 and 2 where a value of `0` means "100% positive correlation/similarity", a value of `1` means "no correlation/similarity at all" and a value of `2` means "100% negative correlation/similarity". You can use any decimal value in between (e.g. 0.25) as a partly positive/negative correlation.
 
 8. Wait for the calculations to finish and use the results the way you want:

data/VERSION

@@ -1 +1 @@
-0.1.4
+0.1.5

data/db_clustering.gemspec

@@ -2,11 +2,11 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: db_clustering 0.1.4 ruby lib
+# stub: db_clustering 0.1.5 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "db_clustering"
-  s.version = "0.1.4"
+  s.version = "0.1.5"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib"]

data/lib/algorithms/density_based/dbscan.rb

@@ -16,7 +16,7 @@ module DbClustering
         @clusters = []
         cluster = nil
 
-        @datasource.iterate_all_points do |point|
+        @datasource.iterate_all_points do |point, current_index, points_count|
           neighbors = @datasource.neighbors(point: point, distance_metric: @distance_metric, max_distance: max_distance)
 
           if neighbors.count < min_neighbors
@@ -36,7 +36,7 @@ module DbClustering
             end
           end
 
-          yield(point)
+          yield(point, current_index, points_count) if block_given?
         end
       end
 

data/lib/datasource_adapters/active_record.rb

@@ -7,9 +7,13 @@ module DbClustering
       end
 
       def iterate_all_points
+        points_count = @relation.count
+        current_index = 0
+        
         @relation.find_each do |datasource_point|
           point = DbClustering::Models::Point.new(datasource_point)
-          yield(point)
+          yield(point, current_index, points_count)
+          current_index += 1
         end
       end
 

data/lib/datasource_adapters/in_memory.rb

@@ -7,8 +7,9 @@ module DbClustering
       end
 
       def iterate_all_points
-        @array.each do |point|
-          yield(point)
+        points_count = @array.count
+        @array.each.with_index do |point, current_index|
+          yield(point, current_index, points_count)
         end
       end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: db_clustering
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.1.5
 platform: ruby
 authors:
 - Cihat Gündüz