ai4r 1.12 → 2.0

data/examples/som/som_data.rb

@@ -1,156 +1,159 @@
+# frozen_string_literal: true
+
 # data is from the iris dataset (http://archive.ics.uci.edu/ml/datasets/Iris)
 # it is the full dataset, removing the last column
-# website provides additional information on the dataset itself (attributes, class distribution, etc)
+# website provides additional information on the dataset itself
+# (attributes, class distribution, etc)
 
 SOM_DATA = [
-        [5.1, 3.5, 1.4, 0.2],
-        [4.9, 3.0, 1.4, 0.2],
-        [4.7, 3.2, 1.3, 0.2],
-        [4.6, 3.1, 1.5, 0.2],
-        [5.0, 3.6, 1.4, 0.2],
-        [5.4, 3.9, 1.7, 0.4],
-        [4.6, 3.4, 1.4, 0.3],
-        [5.0, 3.4, 1.5, 0.2],
-        [4.4, 2.9, 1.4, 0.2],
-        [4.9, 3.1, 1.5, 0.1],
-        [5.4, 3.7, 1.5, 0.2],
-        [4.8, 3.4, 1.6, 0.2],
-        [4.8, 3.0, 1.4, 0.1],
-        [4.3, 3.0, 1.1, 0.1],
-        [5.8, 4.0, 1.2, 0.2],
-        [5.7, 4.4, 1.5, 0.4],
-        [5.4, 3.9, 1.3, 0.4],
-        [5.1, 3.5, 1.4, 0.3],
-        [5.7, 3.8, 1.7, 0.3],
-        [5.1, 3.8, 1.5, 0.3],
-        [5.4, 3.4, 1.7, 0.2],
-        [5.1, 3.7, 1.5, 0.4],
-        [4.6, 3.6, 1.0, 0.2],
-        [5.1, 3.3, 1.7, 0.5],
-        [4.8, 3.4, 1.9, 0.2],
-        [5.0, 3.0, 1.6, 0.2],
-        [5.0, 3.4, 1.6, 0.4],
-        [5.2, 3.5, 1.5, 0.2],
-        [5.2, 3.4, 1.4, 0.2],
-        [4.7, 3.2, 1.6, 0.2],
-        [4.8, 3.1, 1.6, 0.2],
-        [5.4, 3.4, 1.5, 0.4],
-        [5.2, 4.1, 1.5, 0.1],
-        [5.5, 4.2, 1.4, 0.2],
-        [4.9, 3.1, 1.5, 0.1],
-        [5.0, 3.2, 1.2, 0.2],
-        [5.5, 3.5, 1.3, 0.2],
-        [4.9, 3.1, 1.5, 0.1],
-        [4.4, 3.0, 1.3, 0.2],
-        [5.1, 3.4, 1.5, 0.2],
-        [5.0, 3.5, 1.3, 0.3],
-        [4.5, 2.3, 1.3, 0.3],
-        [4.4, 3.2, 1.3, 0.2],
-        [5.0, 3.5, 1.6, 0.6],
-        [5.1, 3.8, 1.9, 0.4],
-        [4.8, 3.0, 1.4, 0.3],
-        [5.1, 3.8, 1.6, 0.2],
-        [4.6, 3.2, 1.4, 0.2],
-        [5.3, 3.7, 1.5, 0.2],
-        [5.0, 3.3, 1.4, 0.2],
-        [7.0, 3.2, 4.7, 1.4],
-        [6.4, 3.2, 4.5, 1.5],
-        [6.9, 3.1, 4.9, 1.5],
-        [5.5, 2.3, 4.0, 1.3],
-        [6.5, 2.8, 4.6, 1.5],
-        [5.7, 2.8, 4.5, 1.3],
-        [6.3, 3.3, 4.7, 1.6],
-        [4.9, 2.4, 3.3, 1.0],
-        [6.6, 2.9, 4.6, 1.3],
-        [5.2, 2.7, 3.9, 1.4],
-        [5.0, 2.0, 3.5, 1.0],
-        [5.9, 3.0, 4.2, 1.5],
-        [6.0, 2.2, 4.0, 1.0],
-        [6.1, 2.9, 4.7, 1.4],
-        [5.6, 2.9, 3.6, 1.3],
-        [6.7, 3.1, 4.4, 1.4],
-        [5.6, 3.0, 4.5, 1.5],
-        [5.8, 2.7, 4.1, 1.0],
-        [6.2, 2.2, 4.5, 1.5],
-        [5.6, 2.5, 3.9, 1.1],
-        [5.9, 3.2, 4.8, 1.8],
-        [6.1, 2.8, 4.0, 1.3],
-        [6.3, 2.5, 4.9, 1.5],
-        [6.1, 2.8, 4.7, 1.2],
-        [6.4, 2.9, 4.3, 1.3],
-        [6.6, 3.0, 4.4, 1.4],
-        [6.8, 2.8, 4.8, 1.4],
-        [6.7, 3.0, 5.0, 1.7],
-        [6.0, 2.9, 4.5, 1.5],
-        [5.7, 2.6, 3.5, 1.0],
-        [5.5, 2.4, 3.8, 1.1],
-        [5.5, 2.4, 3.7, 1.0],
-        [5.8, 2.7, 3.9, 1.2],
-        [6.0, 2.7, 5.1, 1.6],
-        [5.4, 3.0, 4.5, 1.5],
-        [6.0, 3.4, 4.5, 1.6],
-        [6.7, 3.1, 4.7, 1.5],
-        [6.3, 2.3, 4.4, 1.3],
-        [5.6, 3.0, 4.1, 1.3],
-        [5.5, 2.5, 4.0, 1.3],
-        [5.5, 2.6, 4.4, 1.2],
-        [6.1, 3.0, 4.6, 1.4],
-        [5.8, 2.6, 4.0, 1.2],
-        [5.0, 2.3, 3.3, 1.0],
-        [5.6, 2.7, 4.2, 1.3],
-        [5.7, 3.0, 4.2, 1.2],
-        [5.7, 2.9, 4.2, 1.3],
-        [6.2, 2.9, 4.3, 1.3],
-        [5.1, 2.5, 3.0, 1.1],
-        [5.7, 2.8, 4.1, 1.3],
-        [6.3, 3.3, 6.0, 2.5],
-        [5.8, 2.7, 5.1, 1.9],
-        [7.1, 3.0, 5.9, 2.1],
-        [6.3, 2.9, 5.6, 1.8],
-        [6.5, 3.0, 5.8, 2.2],
-        [7.6, 3.0, 6.6, 2.1],
-        [4.9, 2.5, 4.5, 1.7],
-        [7.3, 2.9, 6.3, 1.8],
-        [6.7, 2.5, 5.8, 1.8],
-        [7.2, 3.6, 6.1, 2.5],
-        [6.5, 3.2, 5.1, 2.0],
-        [6.4, 2.7, 5.3, 1.9],
-        [6.8, 3.0, 5.5, 2.1],
-        [5.7, 2.5, 5.0, 2.0],
-        [5.8, 2.8, 5.1, 2.4],
-        [6.4, 3.2, 5.3, 2.3],
-        [6.5, 3.0, 5.5, 1.8],
-        [7.7, 3.8, 6.7, 2.2],
-        [7.7, 2.6, 6.9, 2.3],
-        [6.0, 2.2, 5.0, 1.5],
-        [6.9, 3.2, 5.7, 2.3],
-        [5.6, 2.8, 4.9, 2.0],
-        [7.7, 2.8, 6.7, 2.0],
-        [6.3, 2.7, 4.9, 1.8],
-        [6.7, 3.3, 5.7, 2.1],
-        [7.2, 3.2, 6.0, 1.8],
-        [6.2, 2.8, 4.8, 1.8],
-        [6.1, 3.0, 4.9, 1.8],
-        [6.4, 2.8, 5.6, 2.1],
-        [7.2, 3.0, 5.8, 1.6],
-        [7.4, 2.8, 6.1, 1.9],
-        [7.9, 3.8, 6.4, 2.0],
-        [6.4, 2.8, 5.6, 2.2],
-        [6.3, 2.8, 5.1, 1.5],
-        [6.1, 2.6, 5.6, 1.4],
-        [7.7, 3.0, 6.1, 2.3],
-        [6.3, 3.4, 5.6, 2.4],
-        [6.4, 3.1, 5.5, 1.8],
-        [6.0, 3.0, 4.8, 1.8],
-        [6.9, 3.1, 5.4, 2.1],
-        [6.7, 3.1, 5.6, 2.4],
-        [6.9, 3.1, 5.1, 2.3],
-        [5.8, 2.7, 5.1, 1.9],
-        [6.8, 3.2, 5.9, 2.3],
-        [6.7, 3.3, 5.7, 2.5],
-        [6.7, 3.0, 5.2, 2.3],
-        [6.3, 2.5, 5.0, 1.9],
-        [6.5, 3.0, 5.2, 2.0],
-        [6.2, 3.4, 5.4, 2.3],
-        [5.9, 3.0, 5.1, 1.8],
-]
+  [5.1, 3.5, 1.4, 0.2],
+  [4.9, 3.0, 1.4, 0.2],
+  [4.7, 3.2, 1.3, 0.2],
+  [4.6, 3.1, 1.5, 0.2],
+  [5.0, 3.6, 1.4, 0.2],
+  [5.4, 3.9, 1.7, 0.4],
+  [4.6, 3.4, 1.4, 0.3],
+  [5.0, 3.4, 1.5, 0.2],
+  [4.4, 2.9, 1.4, 0.2],
+  [4.9, 3.1, 1.5, 0.1],
+  [5.4, 3.7, 1.5, 0.2],
+  [4.8, 3.4, 1.6, 0.2],
+  [4.8, 3.0, 1.4, 0.1],
+  [4.3, 3.0, 1.1, 0.1],
+  [5.8, 4.0, 1.2, 0.2],
+  [5.7, 4.4, 1.5, 0.4],
+  [5.4, 3.9, 1.3, 0.4],
+  [5.1, 3.5, 1.4, 0.3],
+  [5.7, 3.8, 1.7, 0.3],
+  [5.1, 3.8, 1.5, 0.3],
+  [5.4, 3.4, 1.7, 0.2],
+  [5.1, 3.7, 1.5, 0.4],
+  [4.6, 3.6, 1.0, 0.2],
+  [5.1, 3.3, 1.7, 0.5],
+  [4.8, 3.4, 1.9, 0.2],
+  [5.0, 3.0, 1.6, 0.2],
+  [5.0, 3.4, 1.6, 0.4],
+  [5.2, 3.5, 1.5, 0.2],
+  [5.2, 3.4, 1.4, 0.2],
+  [4.7, 3.2, 1.6, 0.2],
+  [4.8, 3.1, 1.6, 0.2],
+  [5.4, 3.4, 1.5, 0.4],
+  [5.2, 4.1, 1.5, 0.1],
+  [5.5, 4.2, 1.4, 0.2],
+  [4.9, 3.1, 1.5, 0.1],
+  [5.0, 3.2, 1.2, 0.2],
+  [5.5, 3.5, 1.3, 0.2],
+  [4.9, 3.1, 1.5, 0.1],
+  [4.4, 3.0, 1.3, 0.2],
+  [5.1, 3.4, 1.5, 0.2],
+  [5.0, 3.5, 1.3, 0.3],
+  [4.5, 2.3, 1.3, 0.3],
+  [4.4, 3.2, 1.3, 0.2],
+  [5.0, 3.5, 1.6, 0.6],
+  [5.1, 3.8, 1.9, 0.4],
+  [4.8, 3.0, 1.4, 0.3],
+  [5.1, 3.8, 1.6, 0.2],
+  [4.6, 3.2, 1.4, 0.2],
+  [5.3, 3.7, 1.5, 0.2],
+  [5.0, 3.3, 1.4, 0.2],
+  [7.0, 3.2, 4.7, 1.4],
+  [6.4, 3.2, 4.5, 1.5],
+  [6.9, 3.1, 4.9, 1.5],
+  [5.5, 2.3, 4.0, 1.3],
+  [6.5, 2.8, 4.6, 1.5],
+  [5.7, 2.8, 4.5, 1.3],
+  [6.3, 3.3, 4.7, 1.6],
+  [4.9, 2.4, 3.3, 1.0],
+  [6.6, 2.9, 4.6, 1.3],
+  [5.2, 2.7, 3.9, 1.4],
+  [5.0, 2.0, 3.5, 1.0],
+  [5.9, 3.0, 4.2, 1.5],
+  [6.0, 2.2, 4.0, 1.0],
+  [6.1, 2.9, 4.7, 1.4],
+  [5.6, 2.9, 3.6, 1.3],
+  [6.7, 3.1, 4.4, 1.4],
+  [5.6, 3.0, 4.5, 1.5],
+  [5.8, 2.7, 4.1, 1.0],
+  [6.2, 2.2, 4.5, 1.5],
+  [5.6, 2.5, 3.9, 1.1],
+  [5.9, 3.2, 4.8, 1.8],
+  [6.1, 2.8, 4.0, 1.3],
+  [6.3, 2.5, 4.9, 1.5],
+  [6.1, 2.8, 4.7, 1.2],
+  [6.4, 2.9, 4.3, 1.3],
+  [6.6, 3.0, 4.4, 1.4],
+  [6.8, 2.8, 4.8, 1.4],
+  [6.7, 3.0, 5.0, 1.7],
+  [6.0, 2.9, 4.5, 1.5],
+  [5.7, 2.6, 3.5, 1.0],
+  [5.5, 2.4, 3.8, 1.1],
+  [5.5, 2.4, 3.7, 1.0],
+  [5.8, 2.7, 3.9, 1.2],
+  [6.0, 2.7, 5.1, 1.6],
+  [5.4, 3.0, 4.5, 1.5],
+  [6.0, 3.4, 4.5, 1.6],
+  [6.7, 3.1, 4.7, 1.5],
+  [6.3, 2.3, 4.4, 1.3],
+  [5.6, 3.0, 4.1, 1.3],
+  [5.5, 2.5, 4.0, 1.3],
+  [5.5, 2.6, 4.4, 1.2],
+  [6.1, 3.0, 4.6, 1.4],
+  [5.8, 2.6, 4.0, 1.2],
+  [5.0, 2.3, 3.3, 1.0],
+  [5.6, 2.7, 4.2, 1.3],
+  [5.7, 3.0, 4.2, 1.2],
+  [5.7, 2.9, 4.2, 1.3],
+  [6.2, 2.9, 4.3, 1.3],
+  [5.1, 2.5, 3.0, 1.1],
+  [5.7, 2.8, 4.1, 1.3],
+  [6.3, 3.3, 6.0, 2.5],
+  [5.8, 2.7, 5.1, 1.9],
+  [7.1, 3.0, 5.9, 2.1],
+  [6.3, 2.9, 5.6, 1.8],
+  [6.5, 3.0, 5.8, 2.2],
+  [7.6, 3.0, 6.6, 2.1],
+  [4.9, 2.5, 4.5, 1.7],
+  [7.3, 2.9, 6.3, 1.8],
+  [6.7, 2.5, 5.8, 1.8],
+  [7.2, 3.6, 6.1, 2.5],
+  [6.5, 3.2, 5.1, 2.0],
+  [6.4, 2.7, 5.3, 1.9],
+  [6.8, 3.0, 5.5, 2.1],
+  [5.7, 2.5, 5.0, 2.0],
+  [5.8, 2.8, 5.1, 2.4],
+  [6.4, 3.2, 5.3, 2.3],
+  [6.5, 3.0, 5.5, 1.8],
+  [7.7, 3.8, 6.7, 2.2],
+  [7.7, 2.6, 6.9, 2.3],
+  [6.0, 2.2, 5.0, 1.5],
+  [6.9, 3.2, 5.7, 2.3],
+  [5.6, 2.8, 4.9, 2.0],
+  [7.7, 2.8, 6.7, 2.0],
+  [6.3, 2.7, 4.9, 1.8],
+  [6.7, 3.3, 5.7, 2.1],
+  [7.2, 3.2, 6.0, 1.8],
+  [6.2, 2.8, 4.8, 1.8],
+  [6.1, 3.0, 4.9, 1.8],
+  [6.4, 2.8, 5.6, 2.1],
+  [7.2, 3.0, 5.8, 1.6],
+  [7.4, 2.8, 6.1, 1.9],
+  [7.9, 3.8, 6.4, 2.0],
+  [6.4, 2.8, 5.6, 2.2],
+  [6.3, 2.8, 5.1, 1.5],
+  [6.1, 2.6, 5.6, 1.4],
+  [7.7, 3.0, 6.1, 2.3],
+  [6.3, 3.4, 5.6, 2.4],
+  [6.4, 3.1, 5.5, 1.8],
+  [6.0, 3.0, 4.8, 1.8],
+  [6.9, 3.1, 5.4, 2.1],
+  [6.7, 3.1, 5.6, 2.4],
+  [6.9, 3.1, 5.1, 2.3],
+  [5.8, 2.7, 5.1, 1.9],
+  [6.8, 3.2, 5.9, 2.3],
+  [6.7, 3.3, 5.7, 2.5],
+  [6.7, 3.0, 5.2, 2.3],
+  [6.3, 2.5, 5.0, 1.9],
+  [6.5, 3.0, 5.2, 2.0],
+  [6.2, 3.4, 5.4, 2.3],
+  [5.9, 3.0, 5.1, 1.8]
+].freeze

data/examples/som/som_multi_node_example.rb

@@ -1,22 +1,21 @@
-# this example shows the impact of the size of a som on the global error distance
-require File.dirname(__FILE__) + '/../../lib/ai4r/som/som'
-require File.dirname(__FILE__) + '/som_data'
+# frozen_string_literal: true
+
+# Demonstrates how map size impacts error and uses early stopping.
+require_relative '../../lib/ai4r/som/som'
+require_relative 'som_data'
 require 'benchmark'
 
 10.times do |t|
-  t += 3 # minimum number of nodes
+  nodes = t + 3 # minimum number of nodes
 
-  puts "Nodes: #{t}"
-  som = Ai4r::Som::Som.new 4, 8, Ai4r::Som::TwoPhaseLayer.new(t)
+  puts "Nodes: #{nodes}"
+  som = Ai4r::Som::Som.new 4, 8, 8, Ai4r::Som::TwoPhaseLayer.new(nodes)
   som.initiate_map
 
-  puts "global error distance: #{som.global_error(SOM_DATA)}"
-  puts "\ntraining the som\n"
-
+  puts "Initial error: #{som.global_error(SOM_DATA)}"
   times = Benchmark.measure do
-    som.train SOM_DATA
+    som.train(SOM_DATA, error_threshold: 1000)
   end
-
   puts "Elapsed time for training: #{times}"
-  puts "global error distance: #{som.global_error(SOM_DATA)}\n\n"
-end
+  puts "Final error: #{som.global_error(SOM_DATA)}\n\n"
+end

data/examples/som/som_single_example.rb

@@ -1,24 +1,21 @@
-require File.dirname(__FILE__) + '/../../lib/ai4r/som/som'
-require File.dirname(__FILE__) + '/som_data'
+# frozen_string_literal: true
+
+require_relative '../../lib/ai4r/som/som'
+require_relative 'som_data'
 require 'benchmark'
 
-som = Ai4r::Som::Som.new 4, 8, Ai4r::Som::TwoPhaseLayer.new(10)
+# Train a small SOM and stop early when the global error drops below 1000.
+som = Ai4r::Som::Som.new 4, 8, 8, Ai4r::Som::TwoPhaseLayer.new(10)
 som.initiate_map
 
-som.nodes.each do |node|
-  p node.weights
-end
-
-puts "global error distance: #{som.global_error(SOM_DATA)}"
-puts "\ntraining the som\n"
+puts "Initial global error: #{som.global_error(SOM_DATA)}"
 
+puts "\nTraining the SOM (early stopping threshold = 1000)\n"
 times = Benchmark.measure do
-  som.train SOM_DATA
-end
-
-som.nodes.each do |node|
-  p node.weights
+  som.train(SOM_DATA, error_threshold: 1000) do |error|
+    puts "Epoch #{som.epoch}: error = #{error}"
+  end
 end
 
 puts "Elapsed time for training: #{times}"
-puts "global error distance: #{som.global_error(SOM_DATA)}\n\n"
+puts "Final global error: #{som.global_error(SOM_DATA)}\n"

data/examples/transformer/decode_classifier_example.rb

@@ -0,0 +1,68 @@
+# frozen_string_literal: true
+
+require_relative '../../lib/ai4r/neural_network/transformer'
+require_relative '../../lib/ai4r/classifiers/logistic_regression'
+require_relative '../../lib/ai4r/data/data_set'
+
+# Tiny dataset of greetings (label 0) and farewells (label 1)
+sentences = [
+  %w[hello there],
+  %w[how are you],
+  %w[good morning],
+  %w[nice to meet you],
+  %w[goodbye],
+  %w[see you later],
+  %w[have a nice day],
+  %w[take care]
+]
+labels = [0, 0, 0, 0, 1, 1, 1, 1]
+
+# Build vocabulary
+vocab = {}
+next_id = 0
+sentences.each do |tokens|
+  tokens.each do |t|
+    unless vocab.key?(t)
+      vocab[t] = next_id
+      next_id += 1
+    end
+  end
+end
+
+vocab_size = vocab.length
+max_len = sentences.map(&:length).max
+
+transformer = Ai4r::NeuralNetwork::Transformer.new(
+  vocab_size: vocab_size,
+  max_len: max_len,
+  architecture: :decoder
+)
+embed_dim = transformer.embed_dim
+
+# Encode each sentence and average embeddings
+items = []
+sentences.each_with_index do |tokens, idx|
+  ids = tokens.map { |t| vocab[t] }
+  vecs = transformer.eval(ids)
+  avg = Array.new(embed_dim, 0.0)
+  vecs.each do |v|
+    v.each_index { |i| avg[i] += v[i] }
+  end
+  avg.map! { |v| v / vecs.length }
+  items << (avg + [labels[idx]])
+end
+
+labels_names = (0...embed_dim).map { |i| "x#{i}" } + ['class']
+set = Ai4r::Data::DataSet.new(data_items: items, data_labels: labels_names)
+
+classifier = Ai4r::Classifiers::LogisticRegression.new
+classifier.set_parameters(lr: 0.5, iterations: 500).build(set)
+
+# Classify a short greeting
+sample = %w[hello]
+ids = sample.map { |t| vocab[t] }
+vecs = transformer.eval(ids)
+avg = Array.new(embed_dim, 0.0)
+vecs.each { |v| v.each_index { |i| avg[i] += v[i] } }
+avg.map! { |v| v / vecs.length }
+puts "Prediction: #{classifier.eval(avg)} (0=greeting, 1=farewell)"

data/examples/transformer/deterministic_example.rb

@@ -0,0 +1,10 @@
+require_relative '../../lib/ai4r/neural_network/transformer'
+
+# Demonstrates deterministic initialization using the :seed parameter.
+model_a = Ai4r::NeuralNetwork::Transformer.new(vocab_size: 5, max_len: 3, seed: 42)
+model_b = Ai4r::NeuralNetwork::Transformer.new(vocab_size: 5, max_len: 3, seed: 42)
+
+output_a = model_a.eval([0, 1, 2])
+output_b = model_b.eval([0, 1, 2])
+
+puts "Outputs identical? #{output_a == output_b}"

data/examples/transformer/seq2seq_example.rb

@@ -0,0 +1,16 @@
+require_relative '../../lib/ai4r/neural_network/transformer'
+
+# Simple demo of the seq2seq architecture.
+# The model returns random vectors but shows how
+# to provide encoder and decoder inputs.
+model = Ai4r::NeuralNetwork::Transformer.new(
+  vocab_size: 10,
+  max_len: 5,
+  architecture: :seq2seq
+)
+
+encoder_input = [1, 2, 3]
+decoder_input = [4, 5]
+
+output = model.eval(encoder_input, decoder_input)
+puts "Output length: #{output.length}"

data/lib/ai4r/classifiers/classifier.rb

@@ -1,62 +1,70 @@
+# frozen_string_literal: true
+
 # Author::    Sergio Fierens
 # License::   MPL 1.1
 # Project::   ai4r
-# Url::       http://ai4r.org
+# Url::       https://github.com/SergioFierens/ai4r
 #
-# You can redistribute it and/or modify it under the terms of 
-# the Mozilla Public License version 1.1  as published by the 
+# You can redistribute it and/or modify it under the terms of
+# the Mozilla Public License version 1.1  as published by the
 # Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
- 
-require File.dirname(__FILE__) + '/../data/parameterizable' 
- 
+
+require_relative '../data/parameterizable'
+
 module Ai4r
   module Classifiers
-  
     # This class defines a common API for classifiers.
     # All methods in this class must be implemented in subclasses.
     class Classifier
+      include Ai4r::Data::Parameterizable
 
-      include Ai4r::Data::Parameterizable  
-    
       # Build a new classifier, using data examples found in data_set.
       # The last attribute of each item is considered as the
       # item class.
+      # @param data_set [Object]
+      # @return [Object]
       def build(data_set)
         raise NotImplementedError
       end
-      
+
       # You can evaluate new data, predicting its class.
       # e.g.
       #   classifier.eval(['New York',  '<30', 'F'])  # => 'Y'
+      # @param data [Object]
+      # @return [Object]
       def eval(data)
         raise NotImplementedError
       end
-      
+
       # This method returns the generated rules in ruby code.
       # e.g.
-      #   
+      #
       #   classifier.get_rules
       #     # =>  if age_range=='<30' then marketing_target='Y'
       #           elsif age_range=='[30-50)' and city=='Chicago' then marketing_target='Y'
       #           elsif age_range=='[30-50)' and city=='New York' then marketing_target='N'
       #           elsif age_range=='[50-80]' then marketing_target='N'
       #           elsif age_range=='>80' then marketing_target='Y'
-      #           else raise 'There was not enough information during training to do a proper induction for this data element' end
+      #           else
+      #             raise 'There was not enough information during training to do a '
+      #                   'proper induction for this data element'
+      #           end
       #
-      # It is a nice way to inspect induction results, and also to execute them:  
+      # It is a nice way to inspect induction results, and also to execute them:
       #     age_range = '<30'
       #     city='New York'
       #     marketing_target = nil
-      #     eval classifier.get_rules   
+      #     eval classifier.get_rules
       #     puts marketing_target
       #       # =>  'Y'
       #
       # Note, however, that not all classifiers are able to produce rules.
       # This method is not implemented in such classifiers.
+      # @return [Object]
       def get_rules
         raise NotImplementedError
       end
-      
+      # rubocop:enable Naming/AccessorMethodName
     end
   end
 end

data/lib/ai4r/classifiers/gradient_boosting.rb

@@ -0,0 +1,64 @@
+# frozen_string_literal: true
+
+# Author::    OpenAI ChatGPT
+# License::   MPL 1.1
+# Project::   ai4r
+#
+# Very small gradient boosting implementation for regression using
+# simple linear regression as base learner.
+
+require_relative 'simple_linear_regression'
+require_relative '../data/data_set'
+require_relative '../classifiers/classifier'
+
+module Ai4r
+  module Classifiers
+    # Gradient boosting regressor using simple linear regression base learners.
+    class GradientBoosting < Classifier
+      parameters_info n_estimators: 'Number of boosting iterations. Default 10.',
+                      learning_rate: 'Shrinkage parameter for each learner. Default 0.1.'
+
+      attr_reader :initial_value, :learners
+
+      def initialize
+        super()
+        @n_estimators = 10
+        @learning_rate = 0.1
+      end
+
+      def build(data_set)
+        data_set.check_not_empty
+        @learners = []
+        targets = data_set.data_items.map(&:last)
+        @initial_value = targets.sum.to_f / targets.length
+        predictions = Array.new(targets.length, @initial_value)
+        @n_estimators.times do
+          residuals = targets.zip(predictions).map { |y, f| y - f }
+          items = data_set.data_items.each_with_index.map do |item, idx|
+            item[0...-1] + [residuals[idx]]
+          end
+          ds = Ai4r::Data::DataSet.new(data_items: items, data_labels: data_set.data_labels)
+          learner = SimpleLinearRegression.new.build(ds)
+          @learners << learner
+          pred = items.map { |it| learner.eval(it[0...-1]) }
+          predictions = predictions.zip(pred).map { |f, p| f + (@learning_rate * p) }
+        end
+        self
+      end
+      # rubocop:enable Metrics/AbcSize
+
+      def eval(data)
+        value = @initial_value
+        @learners.each do |learner|
+          value += @learning_rate * learner.eval(data)
+        end
+        value
+      end
+
+      def get_rules
+        'GradientBoosting does not support rule extraction.'
+      end
+      # rubocop:enable Naming/AccessorMethodName
+    end
+  end
+end