hybridforest 0.10.0 → 0.11.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fd85ad9a8081b634556371599f61557c0490c0694bdc24f8aa8d866d44ba0843
-  data.tar.gz: f58382ac2737bce52c85cdf83e27f3099190a0f52be8c159780033194c183dd8
+  metadata.gz: b32e830c0e55cd23122b879bae7d42407085026f573d5565522ba64fe71a255e
+  data.tar.gz: 55c965cbe81e2f2a2e18ebecd21b1027577249f2aa6de4bb0e57b14ab6409f30
 SHA512:
-  metadata.gz: c6678ba9cf3ccf15970801879a4d66f6ef98c8cf80353fc4ce2e9808f79063c447d19e96be374223403fedc093ac67cdd6599140df391ca68d05c708725ba4fc
-  data.tar.gz: 5c94ea5df0e6305719bf8ae9848a0a36d95d71fa51d7abe7bb09ed3f32720df98616bd3f2892e5c3467b647c9f6ebb7b89486e5cff771dde3141388d026fefe4
+  metadata.gz: 7fd27d1de1bcc9f1776607475bc3e03731c8053dbd309171265d1eeb1abc1498965b62d251f1f731ea708ea3914372cba1843b73be1acedcb90d417e79cc54bf
+  data.tar.gz: 75a6a949ccce8e0369966814fdd9a40944a9163dacb82de7a30fad31d54844e5fdc396ea546dbfcad19258e249a60b452973ee3df4e9fe8f07da71d4e888c274

data/CHANGELOG.md

@@ -34,4 +34,9 @@
 
 ## [0.10.0] - 2021-12-29
 
-- Refactor dataframe extensions
+- Refactor dataframe extensions
+
+## [0.11.0] - 2021-12-29
+
+- Randomize Utils.train_test_split
+- Refactor Utils module

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    hybridforest (0.9.0)
+    hybridforest (0.10.0)
       activesupport (~> 6.1)
       rake (~> 13.0)
       require_all

data/lib/hybridforest/trees/feature_selectors/random_feature_subspace.rb

@@ -6,6 +6,7 @@ module HybridForest
   module Trees
     class RandomFeatureSubspace
       def select_features(all_features)
+        # TODO: Allow the subspace size to be configured.
         n = default_subspace_size(all_features.count)
         indices = Set.new
         until indices.size == n

data/lib/hybridforest/utilities/utils.rb

@@ -12,17 +12,16 @@ module HybridForest
     # of independent features and an array of labels. Returns [+training_set+, +testing_set+, +testing_set_labels+]
     #
     def self.train_test_split(dataset, test_set_size = 0.20)
-      # TODO: Shuffle and stratify samples
+      # TODO: Offer stratify param
       dataset = to_dataframe(dataset)
+      all_rows = (0...dataset.count).to_a
 
       test_set_count = (dataset.count * test_set_size).floor
-      test_set_indices = 0..test_set_count
-      test_set = dataset[test_set_indices]
-      test_set_labels = test_set.class_labels
-      test_set.except!(test_set.label)
+      test_set_rows = rand_uniq_nums(test_set_count, 0...dataset.count)
+      test_set = dataset[test_set_rows]
+      test_set, test_set_labels = test_set.disconnect_labels
 
-      train_set_indices = test_set_count + 1...dataset.count
-      train_set = dataset[train_set_indices]
+      train_set = dataset[all_rows - test_set_rows]
 
       [train_set, test_set, test_set_labels]
     end
@@ -37,20 +36,13 @@ module HybridForest
       dataset = to_dataframe(dataset)
       all_rows = (0...dataset.count).to_a
 
-      train_set = Rover::DataFrame.new
-      train_set_rows = []
-      dataset.count.times do
-        row = all_rows.sample
-        train_set_rows << row
-        train_set.concat(dataset[row])
-      end
+      train_set_rows = rand_nums(dataset.count, 0...dataset.count)
+      train_set = dataset[train_set_rows]
 
       return train_test_split(dataset) if train_set_rows.sort == all_rows
 
-      test_set_rows = all_rows - train_set_rows
-      test_set = dataset[test_set_rows]
-      test_set_labels = test_set.class_labels
-      test_set.except!(test_set.label)
+      test_set = dataset[all_rows - train_set_rows]
+      test_set, test_set_labels = test_set.disconnect_labels
 
       [train_set, test_set, test_set_labels]
     end
@@ -88,16 +80,12 @@ module HybridForest
     def self.random_sample(data:, size:, with_replacement: true)
       raise ArgumentError, "Invalid sample size" if size < 1 || size > data.count
 
-      if with_replacement
-        rows = size.times.collect { rand(0...data.count) }
-        data[rows]
+      rows = if with_replacement
+        rand_nums(size, 0...data.count)
       else
-        rows = Set.new
-        until rows.size == size
-          rows << rand(0...data.count)
-        end
-        data[rows.to_a]
+        rand_uniq_nums(size, 0...data.count)
       end
+      data[rows]
     end
 
     # Outputs a report of common prediction metrics.
@@ -168,6 +156,12 @@ module HybridForest
         def class_labels
           self[label].to_a
         end
+
+        def disconnect_labels
+          labels = class_labels
+          except!(label)
+          [self, labels]
+        end
       end
     end
 
@@ -202,5 +196,23 @@ module HybridForest
     def false_label?(label)
       [false, 0].include? label
     end
+
+    ##
+    # Returns an array of +n+ random numbers in the exclusive +range+.
+    def rand_nums(n, range)
+      n.times.collect { rand(range) }
+    end
+
+    ##
+    # Returns an array of +n+ _unique_ random numbers in the exclusive +range+.
+    def rand_uniq_nums(n, range)
+      raise ArgumentError if n > range.size
+
+      nums = Set.new
+      until nums.size == n
+        nums << rand(range)
+      end
+      nums.to_a
+    end
   end
 end

data/lib/hybridforest/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module HybridForest
-  VERSION = "0.10.0"
+  VERSION = "0.11.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: hybridforest
 version: !ruby/object:Gem::Version
-  version: 0.10.0
+  version: 0.11.0
 platform: ruby
 authors:
 - hi-tech-jazz
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2021-12-29 00:00:00.000000000 Z
+date: 2021-12-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake