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, 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.

  • 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.



53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 53

def initialize(n_estimators: 10,
               criterion: 'gini', max_depth: nil, max_leaf_nodes: nil, min_samples_leaf: 1,
               max_features: nil, random_seed: nil)
  check_params_type_or_nil(Integer, max_depth: max_depth, max_leaf_nodes: max_leaf_nodes,
                                    max_features: max_features, 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[: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.



153
154
155
156
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 153

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:



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
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 83

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)
  @feature_importances = Numo::DFloat.zeros(n_features)
  # Construct forest.
  @estimators = Array.new(@params[:n_estimators]) do
    tree = Tree::DecisionTreeClassifier.new(
      criterion: @params[:criterion], max_depth: @params[:max_depth],
      max_leaf_nodes: @params[:max_leaf_nodes], min_samples_leaf: @params[:min_samples_leaf],
      max_features: @params[:max_features], random_seed: @rng.rand(Rumale::Values.int_max)
    )
    bootstrap_ids = Array.new(n_samples) { @rng.rand(0...n_samples) }
    tree.fit(x[bootstrap_ids, true], y[bootstrap_ids])
    @feature_importances += tree.feature_importances
    tree
  end
  @feature_importances /= @feature_importances.sum
  self
end

#marshal_dump ⇒ Hash

Dump marshal data.

Returns:

  • (Hash) —

    The marshal data about RandomForestClassifier.



160
161
162
163
164
165
166
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 160

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) 


170
171
172
173
174
175
176
177
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 170

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.



113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 113

def predict(x)
  check_sample_array(x)
  n_samples, = x.shape
  n_classes = @classes.size
  classes_arr = @classes.to_a
  ballot_box = Numo::DFloat.zeros(n_samples, n_classes)
  @estimators.each do |tree|
    predicted = tree.predict(x)
    n_samples.times do |n|
      class_id = classes_arr.index(predicted[n])
      ballot_box[n, class_id] += 1.0 unless class_id.nil?
    end
  end
  Numo::Int32[*Array.new(n_samples) { |n| @classes[ballot_box[n, true].max_index] }]
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.



133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
 
# File 'lib/rumale/ensemble/random_forest_classifier.rb', line 133

def predict_proba(x)
  check_sample_array(x)
  n_samples, = x.shape
  n_classes = @classes.size
  classes_arr = @classes.to_a
  ballot_box = Numo::DFloat.zeros(n_samples, n_classes)
  @estimators.each do |tree|
    probs = tree.predict_proba(x)
    tree.classes.size.times do |n|
      class_id = classes_arr.index(tree.classes[n])
      ballot_box[true, class_id] += probs[true, n] unless class_id.nil?
    end
  end
  (ballot_box.transpose / ballot_box.sum(axis: 1)).transpose
end