Class: Rumale::Ensemble::RandomForestClassifier

Inherits:
Base::Estimator show all
Includes:
Base::Classifier
Defined in:
rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb

Overview

RandomForestClassifier is a class that implements random forest for classification.

Examples:

require 'rumale/ensemble/random_forest_classifier'

estimator =
  Rumale::Ensemble::RandomForestClassifier.new(
    n_estimators: 10, criterion: 'gini', max_depth: 3, max_leaf_nodes: 10, min_samples_leaf: 5, random_seed: 1)
estimator.fit(training_samples, traininig_labels)
results = estimator.predict(testing_samples)

Direct Known Subclasses

ExtraTreesClassifier

Instance Attribute Summary collapse

Attributes inherited from Base::Estimator

#params

Instance Method Summary collapse

Methods included from Base::Classifier

#score

Constructor Details

#initialize(n_estimators: 10, criterion: 'gini', max_depth: nil, max_leaf_nodes: nil, min_samples_leaf: 1, max_features: nil, n_jobs: nil, random_seed: nil) ⇒ RandomForestClassifier

Create a new classifier with random forest.

Parameters:

  • n_estimators (Integer) (defaults to: 10) —

    The numeber of decision trees for contructing random forest.

  • criterion (String) (defaults to: 'gini') —

    The function to evalue spliting point. Supported criteria are ‘gini’ and ‘entropy’.

  • max_depth (Integer) (defaults to: nil) —

    The maximum depth of the tree. If nil is given, decision tree grows without concern for depth.

  • max_leaf_nodes (Integer) (defaults to: nil) —

    The maximum number of leaves on decision tree. If nil is given, number of leaves is not limited.

  • min_samples_leaf (Integer) (defaults to: 1) —

    The minimum number of samples at a leaf node.

  • max_features (Integer) (defaults to: nil) —

    The number of features to consider when searching optimal split point. If nil is given, split process considers ‘Math.sqrt(n_features)’ features.

  • n_jobs (Integer) (defaults to: nil) —

    The number of jobs for running the fit method in parallel. If nil is given, the method does not execute in parallel. If zero or less is given, it becomes equal to the number of processors. This parameter is ignored if the Parallel gem is not loaded.

  • random_seed (Integer) (defaults to: nil) —

    The seed value using to initialize the random generator. It is used to randomly determine the order of features when deciding spliting point.



59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
 
# File 'rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb', line 59

def initialize(n_estimators: 10,
               criterion: 'gini', max_depth: nil, max_leaf_nodes: nil, min_samples_leaf: 1,
               max_features: nil, n_jobs: nil, random_seed: nil)
  super()
  @params = {
    n_estimators: n_estimators,
    criterion: criterion,
    max_depth: max_depth,
    max_leaf_nodes: max_leaf_nodes,
    min_samples_leaf: min_samples_leaf,
    max_features: max_features,
    n_jobs: n_jobs,
    random_seed: random_seed || srand
  }
  @rng = Random.new(@params[:random_seed])
end

Instance Attribute Details

#classes ⇒ Numo::Int32 (readonly)

Return the class labels.

Returns:

  • (Numo::Int32) —

    (size: n_classes)



32
33
34
 
# File 'rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb', line 32

def classes
  @classes
end

#estimators ⇒ Array<DecisionTreeClassifier> (readonly)

Return the set of estimators.

Returns:

  • (Array<DecisionTreeClassifier>) 


28
29
30
 
# File 'rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb', line 28

def estimators
  @estimators
end

#feature_importances ⇒ Numo::DFloat (readonly)

Return the importance for each feature.

Returns:

  • (Numo::DFloat) —

    (size: n_features)



36
37
38
 
# File 'rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb', line 36

def feature_importances
  @feature_importances
end

#rng ⇒ Random (readonly)

Return the random generator for random selection of feature index.

Returns:

  • (Random) 


40
41
42
 
# File 'rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb', line 40

def rng
  @rng
end

Instance Method Details

#apply(x) ⇒ Numo::Int32

Return the index of the leaf that each sample reached.

Parameters:

  • x (Numo::DFloat) —

    (shape: [n_samples, n_features]) The samples to predict the labels.

Returns:

  • (Numo::Int32) —

    (shape: [n_samples, n_estimators]) Leaf index for sample.



154
155
156
157
158
 
# File 'rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb', line 154

def apply(x)
  x = ::Rumale::Validation.check_convert_sample_array(x)

  Numo::Int32[*Array.new(@params[:n_estimators]) { |n| @estimators[n].apply(x) }].transpose.dup
end

#fit(x, y) ⇒ RandomForestClassifier

Fit the model with given training data.

Parameters:

  • x (Numo::DFloat) —

    (shape: [n_samples, n_features]) The training data to be used for fitting the model.

  • y (Numo::Int32) —

    (shape: [n_samples]) The labels to be used for fitting the model.

Returns:



81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
 
# File 'rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb', line 81

def fit(x, y)
  x = ::Rumale::Validation.check_convert_sample_array(x)
  y = ::Rumale::Validation.check_convert_label_array(y)
  ::Rumale::Validation.check_sample_size(x, y)

  # Initialize some variables.
  n_samples, n_features = x.shape
  @params[:max_features] = Math.sqrt(n_features).to_i if @params[:max_features].nil?
  @params[:max_features] = [[1, @params[:max_features]].max, n_features].min # rubocop:disable Style/ComparableClamp
  @classes = Numo::Int32.asarray(y.to_a.uniq.sort)
  sub_rng = @rng.dup
  rngs = Array.new(@params[:n_estimators]) { Random.new(sub_rng.rand(::Rumale::Ensemble::Value::SEED_BASE)) }
  # Construct forest.
  @estimators =
    if enable_parallel?
      parallel_map(@params[:n_estimators]) do |n|
        bootstrap_ids = Array.new(n_samples) { rngs[n].rand(0...n_samples) }
        plant_tree(rngs[n].seed).fit(x[bootstrap_ids, true], y[bootstrap_ids])
      end
    else
      Array.new(@params[:n_estimators]) do |n|
        bootstrap_ids = Array.new(n_samples) { rngs[n].rand(0...n_samples) }
        plant_tree(rngs[n].seed).fit(x[bootstrap_ids, true], y[bootstrap_ids])
      end
    end
  @feature_importances =
    if enable_parallel?
      parallel_map(@params[:n_estimators]) { |n| @estimators[n].feature_importances }.sum
    else
      @estimators.sum(&:feature_importances)
    end
  @feature_importances /= @feature_importances.sum
  self
end

#predict(x) ⇒ Numo::Int32

Predict class labels for samples.

Parameters:

  • x (Numo::DFloat) —

    (shape: [n_samples, n_features]) The samples to predict the labels.

Returns:

  • (Numo::Int32) —

    (shape: [n_samples]) Predicted class label per sample.



120
121
122
123
124
125
126
127
128
129
130
131
132
133
 
# File 'rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb', line 120

def predict(x)
  x = ::Rumale::Validation.check_convert_sample_array(x)

  n_samples = x.shape[0]
  n_estimators = @estimators.size
  predicted = if enable_parallel?
                predict_set = parallel_map(n_estimators) { |n| @estimators[n].predict(x).to_a }.transpose
                parallel_map(n_samples) { |n| predict_set[n].group_by { |v| v }.max_by { |_k, v| v.size }.first }
              else
                predict_set = @estimators.map { |tree| tree.predict(x).to_a }.transpose
                Array.new(n_samples) { |n| predict_set[n].group_by { |v| v }.max_by { |_k, v| v.size }.first }
              end
  Numo::Int32.asarray(predicted)
end

#predict_proba(x) ⇒ Numo::DFloat

Predict probability for samples.

Parameters:

  • x (Numo::DFloat) —

    (shape: [n_samples, n_features]) The samples to predict the probailities.

Returns:

  • (Numo::DFloat) —

    (shape: [n_samples, n_classes]) Predicted probability of each class per sample.



139
140
141
142
143
144
145
146
147
148
 
# File 'rumale-ensemble/lib/rumale/ensemble/random_forest_classifier.rb', line 139

def predict_proba(x)
  x = ::Rumale::Validation.check_convert_sample_array(x)

  n_estimators = @estimators.size
  if enable_parallel?
    parallel_map(n_estimators) { |n| predict_proba_tree(@estimators[n], x) }.sum / n_estimators
  else
    @estimators.sum { |tree| predict_proba_tree(tree, x) } / n_estimators
  end
end