Class: Rumale::Ensemble::RandomForestClassifier

Inherits:
Object
  • Object
show all
Includes:
Base::BaseEstimator, Base::Classifier
Defined in:
lib/rumale/ensemble/random_forest_classifier.rb

Overview

RandomForestClassifier is a class that implements random forest for classification.

Examples:

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 included from Base::BaseEstimator

#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 all 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.



57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 57

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)
  check_params_type_or_nil(Integer, max_depth: max_depth, max_leaf_nodes: max_leaf_nodes,
                                    max_features: max_features, n_jobs: n_jobs, random_seed: random_seed)
  check_params_integer(n_estimators: n_estimators, min_samples_leaf: min_samples_leaf)
  check_params_string(criterion: criterion)
  check_params_positive(n_estimators: n_estimators, max_depth: max_depth,
                        max_leaf_nodes: max_leaf_nodes, min_samples_leaf: min_samples_leaf,
                        max_features: max_features)
  @params = {}
  @params[:n_estimators] = n_estimators
  @params[:criterion] = criterion
  @params[:max_depth] = max_depth
  @params[:max_leaf_nodes] = max_leaf_nodes
  @params[:min_samples_leaf] = min_samples_leaf
  @params[:max_features] = max_features
  @params[:n_jobs] = n_jobs
  @params[:random_seed] = random_seed
  @params[:random_seed] ||= srand
  @estimators = nil
  @classes = nil
  @feature_importances = nil
  @rng = Random.new(@params[:random_seed])
end

Instance Attribute Details

#classes ⇒ Numo::Int32 (readonly)

Return the class labels.

Returns:

  • (Numo::Int32) —

    (size: n_classes)



30
31
32
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 30

def classes
  @classes
end

#estimators ⇒ Array<DecisionTreeClassifier> (readonly)

Return the set of estimators.

Returns:

  • (Array<DecisionTreeClassifier>) 


26
27
28
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 26

def estimators
  @estimators
end

#feature_importances ⇒ Numo::DFloat (readonly)

Return the importance for each feature.

Returns:

  • (Numo::DFloat) —

    (size: n_features)



34
35
36
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 34

def feature_importances
  @feature_importances
end

#rng ⇒ Random (readonly)

Return the random generator for random selection of feature index.

Returns:

  • (Random) 


38
39
40
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 38

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.



160
161
162
163
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 160

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



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
115
116
117
118
119
120
121
122
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 88

def fit(x, y)
  check_sample_array(x)
  check_label_array(y)
  check_sample_label_size(x, y)
  # Initialize some variables.
  n_samples, n_features = x.shape
  @params[:max_features] = Math.sqrt(n_features).to_i unless @params[:max_features].is_a?(Integer)
  @params[:max_features] = [[1, @params[:max_features]].max, n_features].min
  @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::Values.int_max)) }
  # Construct forest.
  @estimators =
    if enable_parallel?
      # :nocov:
      parallel_map(@params[:n_estimators]) do |n|
        bootstrap_ids = Array.new(n_samples) { rngs[n].rand(0...n_samples) }
        plant_tree(rngs[n].rand(Rumale::Values.int_max)).fit(x[bootstrap_ids, true], y[bootstrap_ids])
      end
      # :nocov:
    else
      Array.new(@params[:n_estimators]) do |n|
        bootstrap_ids = Array.new(n_samples) { rngs[n].rand(0...n_samples) }
        plant_tree(rngs[n].rand(Rumale::Values.int_max)).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 }.reduce(&:+)
    else
      @estimators.map(&:feature_importances).reduce(&:+)
    end
  @feature_importances /= @feature_importances.sum
  self
end

#marshal_dump ⇒ Hash

Dump marshal data.

Returns:

  • (Hash) —

    The marshal data about RandomForestClassifier.



167
168
169
170
171
172
173
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 167

def marshal_dump
  { params: @params,
    estimators: @estimators,
    classes: @classes,
    feature_importances: @feature_importances,
    rng: @rng }
end

#marshal_load(obj) ⇒ nil

Load marshal data.

Returns:

  • (nil) 


177
178
179
180
181
182
183
184
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 177

def marshal_load(obj)
  @params = obj[:params]
  @estimators = obj[:estimators]
  @classes = obj[:classes]
  @feature_importances = obj[:feature_importances]
  @rng = obj[:rng]
  nil
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.



128
129
130
131
132
133
134
135
136
137
138
139
140
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 128

def predict(x)
  check_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.



146
147
148
149
150
151
152
153
154
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 146

def predict_proba(x)
  check_sample_array(x)
  n_estimators = @estimators.size
  if enable_parallel?
    parallel_map(n_estimators) { |n| predict_proba_tree(@estimators[n], x) }.reduce(&:+) / n_estimators
  else
    @estimators.map { |tree| predict_proba_tree(tree, x) }.reduce(&:+) / n_estimators
  end
end