Class: SVMKit::Ensemble::RandomForestRegressor

Inherits:
Object
  • Object
show all
Includes:
Base::BaseEstimator, Base::Regressor
Defined in:
lib/svmkit/ensemble/random_forest_regressor.rb

Overview

RandomForestRegressor is a class that implements random forest for regression

Examples:

estimator =
  SVMKit::Ensemble::RandomForestRegressor.new(
    n_estimators: 10, criterion: 'mse', max_depth: 3, max_leaf_nodes: 10, min_samples_leaf: 5, random_seed: 1)
estimator.fit(training_samples, traininig_values)
results = estimator.predict(testing_samples)

Instance Attribute Summary collapse

Attributes included from Base::BaseEstimator

#params

Instance Method Summary collapse

Methods included from Base::Regressor

#score

Constructor Details

#initialize(n_estimators: 10, criterion: 'mse', max_depth: nil, max_leaf_nodes: nil, min_samples_leaf: 1, max_features: nil, random_seed: nil) ⇒ RandomForestRegressor

Create a new regressor with random forest.



49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
 
# File 'lib/svmkit/ensemble/random_forest_regressor.rb', line 49

def initialize(n_estimators: 10, criterion: 'mse', 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
  @feature_importances = nil
  @rng = Random.new(@params[:random_seed])
end

Instance Attribute Details

#estimators ⇒ Array<DecisionTreeRegressor> (readonly)

Return the set of estimators.



26
27
28
 
# File 'lib/svmkit/ensemble/random_forest_regressor.rb', line 26

def estimators
  @estimators
end

#feature_importances ⇒ Numo::DFloat (readonly)

Return the importance for each feature.



30
31
32
 
# File 'lib/svmkit/ensemble/random_forest_regressor.rb', line 30

def feature_importances
  @feature_importances
end

#rng ⇒ Random (readonly)

Return the random generator for random selection of feature index.



34
35
36
 
# File 'lib/svmkit/ensemble/random_forest_regressor.rb', line 34

def rng
  @rng
end

Instance Method Details

#apply(x) ⇒ Numo::Int32

Return the index of the leaf that each sample reached.



115
116
117
118
 
# File 'lib/svmkit/ensemble/random_forest_regressor.rb', line 115

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

#fit(x, y) ⇒ RandomForestRegressor

Fit the model with given training data.



77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'lib/svmkit/ensemble/random_forest_regressor.rb', line 77

def fit(x, y)
  check_sample_array(x)
  check_tvalue_array(y)
  check_sample_tvalue_size(x, y)
  # Initialize some variables.
  n_samples, n_features = x.shape
  @params[:max_features] ||= n_features
  @params[:max_features] = [[1, @params[:max_features]].max, Math.sqrt(n_features).to_i].min
  single_target = y.shape[1].nil?
  # Construct forest.
  @estimators = Array.new(@params[:n_estimators]) do |_n|
    tree = Tree::DecisionTreeRegressor.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: @params[:random_seed]
    )
    bootstrap_ids = Array.new(n_samples) { @rng.rand(0...n_samples) }
    tree.fit(x[bootstrap_ids, true], single_target ? y[bootstrap_ids] : y[bootstrap_ids, true])
  end
  # Calculate feature importances.
  @feature_importances = @estimators.map(&:feature_importances).reduce(&:+)
  @feature_importances /= @feature_importances.sum
  self
end

#marshal_dump ⇒ Hash

Dump marshal data.



122
123
124
125
126
127
 
# File 'lib/svmkit/ensemble/random_forest_regressor.rb', line 122

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

#marshal_load(obj) ⇒ nil

Load marshal data.



131
132
133
134
135
136
137
 
# File 'lib/svmkit/ensemble/random_forest_regressor.rb', line 131

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

#predict(x) ⇒ Numo::DFloat

Predict values for samples.



106
107
108
109
 
# File 'lib/svmkit/ensemble/random_forest_regressor.rb', line 106

def predict(x)
  check_sample_array(x)
  @estimators.map { |est| est.predict(x) }.reduce(&:+) / @params[:n_estimators]
end