Class: Ai4r::Classifiers::RandomForest

Inherits:
Classifier
  • Object
show all
Defined in:
lib/ai4r/classifiers/random_forest.rb

Overview

RandomForest ensemble classifier built from decision trees.

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Data::Parameterizable

#get_parameters, included, #set_parameters

Constructor Details

#initialize ⇒ RandomForest

Returns a new instance of RandomForest.



26
27
28
29
30
31
32
 
# File 'lib/ai4r/classifiers/random_forest.rb', line 26

def initialize
  super()
  @n_trees = 10
  @sample_size = nil
  @feature_fraction = nil
  @random_seed = nil
end

Instance Attribute Details

#features ⇒ Object (readonly)

Returns the value of attribute features.



24
25
26
 
# File 'lib/ai4r/classifiers/random_forest.rb', line 24

def features
  @features
end

#trees ⇒ Object (readonly)

Returns the value of attribute trees.



24
25
26
 
# File 'lib/ai4r/classifiers/random_forest.rb', line 24

def trees
  @trees
end

Instance Method Details

#build(data_set) ⇒ Object 



34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
 
# File 'lib/ai4r/classifiers/random_forest.rb', line 34

def build(data_set)
  data_set.check_not_empty
  rng = @random_seed ? Random.new(@random_seed) : Random.new
  num_attributes = data_set.data_labels.length - 1
  frac = @feature_fraction || (Math.sqrt(num_attributes) / num_attributes)
  feature_count = [1, (num_attributes * frac).round].max
  @sample_size ||= data_set.data_items.length
  @trees = []
  @features = []
  @n_trees.times do
    sampled = Array.new(@sample_size) { data_set.data_items.sample(random: rng) }
    feature_idx = (0...num_attributes).to_a.sample(feature_count, random: rng)
    tree_items = sampled.map do |item|
      values = feature_idx.map { |i| item[i] }
      values + [item.last]
    end
    labels = feature_idx.map { |i| data_set.data_labels[i] } + [data_set.data_labels.last]
    ds = Ai4r::Data::DataSet.new(data_items: tree_items, data_labels: labels)
    @trees << ID3.new.build(ds)
    @features << feature_idx
  end
  self
end

#eval(data) ⇒ Object 



58
59
60
61
62
63
64
65
 
# File 'lib/ai4r/classifiers/random_forest.rb', line 58

def eval(data)
  votes = Votes.new
  @trees.each_with_index do |tree, idx|
    sub_data = @features[idx].map { |i| data[i] }
    votes.increment_category(tree.eval(sub_data))
  end
  votes.get_winner
end

#get_rules ⇒ Object 



67
68
69
 
# File 'lib/ai4r/classifiers/random_forest.rb', line 67

def get_rules
  'RandomForest does not support rule extraction.'
end