hybridforest 0.9.0 → 0.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8d0af8ba6e658989bf55d0b8026822ab0be77020c189ffd056ffac3e7a393700
-  data.tar.gz: 968c29d52088fe4ba28d93fcd3aedf7288d323f3a35ba000efde5b1673c10e2b
+  metadata.gz: aa4457c9f58fde0edfa9fd8af0a4ac5ef23db54892f75a50a8f62ac1f8652631
+  data.tar.gz: a8f0afc4b58d067388f3c5986521609a5ede0816643f73235b8517265c6b72c7
 SHA512:
-  metadata.gz: 2e7076a8cdea280c900f61c98a6f53715a335d7765a6861f028a6956a8c6599cbe233b5d3e867b0d55f9a8889e41067e314ca151b00e4455f55071ac407059f5
-  data.tar.gz: dbf3dc47bfba70ff33e9452cc9232d5079651410a3eb319b29172992141c1602f8c06bba50e7ee9a56c1c8530e9099763834b1a964a86cdc4ec4c89d944237f4
+  metadata.gz: 9261b0cc8fa086e8b91f910f8b852f2369a1eac0e76ee4b01f1db3dddf9bb7f8f9947cbcaca2f81d6db6a9c734ed516a0848f29b7735661ea5be428b8e720392
+  data.tar.gz: 5d8a886b98ca5e735b4173fb51e114d313c28ef480bd8cae32cf339634e49384a44d4fdb53548afb82228bd368960ef002d55bbd1292dd8313706b2458bf543c

data/CHANGELOG.md

@@ -30,4 +30,22 @@
 
 ## [0.9.0] - 2021-12-28
 
-- Update dependencies
+- Update dependencies
+
+## [0.10.0] - 2021-12-29
+
+- Refactor dataframe extensions
+
+## [0.11.0] - 2021-12-29
+
+- Randomize Utils.train_test_split
+- Refactor Utils module
+
+## [0.12.0] - 2022-01-08
+
+- Allow Utils.random_sample to be passed a dataframe or a dataframe convertible object
+- Allow Utils.random_sample's 'size' arg to equal the size of the initial dataframe if the strategy is sampling with replacement
+
+## [0.13.0] - 2022-01-09
+
+- Refactor forest growers

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    hybridforest (0.9.0)
+    hybridforest (0.12.0)
       activesupport (~> 6.1)
       rake (~> 13.0)
       require_all

data/lib/hybridforest/forests/forest_growers/cart_grower.rb

@@ -8,7 +8,7 @@ module HybridForest
         def grow_forest(instances, number_of_trees)
           forest = []
           number_of_trees.times do
-            sample, _, _ = HybridForest::Utils.train_test_bootstrap_split(instances)
+            sample = HybridForest::Utils.random_sample(data: instances, size: instances.size)
             forest << HybridForest::Trees::CARTTree.new.fit(sample)
           end
           forest

data/lib/hybridforest/forests/forest_growers/id3_grower.rb

@@ -8,7 +8,7 @@ module HybridForest
         def grow_forest(instances, number_of_trees)
           forest = []
           number_of_trees.times do
-            sample, _, _ = HybridForest::Utils.train_test_bootstrap_split(instances)
+            sample = HybridForest::Utils.random_sample(data: instances, size: instances.size)
             forest << HybridForest::Trees::ID3Tree.new.fit(sample)
           end
           forest

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
@@ -86,18 +78,18 @@ module HybridForest
     # Draws a random sample of +size+ from +data+.
     #
     def self.random_sample(data:, size:, with_replacement: true)
-      raise ArgumentError, "Invalid sample size" if size < 1 || size > data.count
+      data = to_dataframe(data)
 
-      if with_replacement
-        rows = size.times.collect { rand(0...data.count) }
-        data[rows]
+      if size < 1 || (!with_replacement && size > data.count)
+        raise ArgumentError, "Invalid sample size"
+      end
+
+      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.
@@ -113,7 +105,7 @@ module HybridForest
     #
     def self.accuracy(predicted, actual)
       accurate = predicted.zip(actual).count { |p, a| equal_labels?(p, a) }
-      accurate.to_f / predicted.count.to_f
+      accurate.to_f / predicted.count
     end
 
     # Extensions to simplify common dataframe operations.
@@ -146,11 +138,11 @@ module HybridForest
         end
 
         def feature_count(without_label: true)
-          without_label ? names.count - 1 : names.count
+          without_label ? features.count : names.count
         end
 
         def pure?
-          column_by_index(-1).uniq.size == 1
+          self[label].uniq.size == 1
         end
 
         def features
@@ -158,7 +150,7 @@ module HybridForest
         end
 
         def count_labels
-          column_by_index(-1).tally
+          self[label].tally
         end
 
         def label
@@ -168,6 +160,12 @@ 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 +200,23 @@ 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 = "0.9.0"
+  VERSION = "0.13.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: hybridforest
 version: !ruby/object:Gem::Version
-  version: 0.9.0
+  version: 0.13.0
 platform: ruby
 authors:
 - hi-tech-jazz
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2021-12-28 00:00:00.000000000 Z
+date: 2022-01-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake