Class: Rumale::Ensemble::RandomForestRegressor

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

Overview

RandomForestRegressor is a class that implements random forest for regression

Examples:

estimator =
  Rumale::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)

Direct Known Subclasses

ExtraTreesRegressor

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, n_jobs: nil, random_seed: nil) ⇒ RandomForestRegressor

Create a new regressor with random forest.



52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
 
# File 'lib/rumale/ensemble/random_forest_regressor.rb', line 52

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

Instance Attribute Details

#estimators ⇒ Array<DecisionTreeRegressor> (readonly)

Return the set of estimators.



25
26
27
 
# File 'lib/rumale/ensemble/random_forest_regressor.rb', line 25

def estimators
  @estimators
end

#feature_importances ⇒ Numo::DFloat (readonly)

Return the importance for each feature.



29
30
31
 
# File 'lib/rumale/ensemble/random_forest_regressor.rb', line 29

def feature_importances
  @feature_importances
end

#rng ⇒ Random (readonly)

Return the random generator for random selection of feature index.



33
34
35
 
# File 'lib/rumale/ensemble/random_forest_regressor.rb', line 33

def rng
  @rng
end

Instance Method Details

#apply(x) ⇒ Numo::Int32

Return the index of the leaf that each sample reached.



136
137
138
139
 
# File 'lib/rumale/ensemble/random_forest_regressor.rb', line 136

def apply(x)
  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.



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
115
116
117
 
# File 'lib/rumale/ensemble/random_forest_regressor.rb', line 82

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] = Math.sqrt(n_features).to_i unless @params[:max_features].is_a?(Integer)
  @params[:max_features] = [[1, @params[:max_features]].max, n_features].min
  single_target = y.shape[1].nil?
  # Construct forest.
  @estimators =
    if enable_parallel?
      rngs = Array.new(@params[:n_estimators]) { Random.new(@rng.rand(Rumale::Values.int_max)) }
      # :nocov:
      parallel_map(@params[:n_estimators]) do |n|
        bootstrap_ids = Array.new(n_samples) { rngs[n].rand(0...n_samples) }
        tree = plant_tree(rngs[n].rand(Rumale::Values.int_max))
        tree.fit(x[bootstrap_ids, true], single_target ? y[bootstrap_ids] : y[bootstrap_ids, true])
      end
      # :nocov:
    else
      Array.new(@params[:n_estimators]) do
        bootstrap_ids = Array.new(n_samples) { @rng.rand(0...n_samples) }
        tree = plant_tree(@rng.rand(Rumale::Values.int_max))
        tree.fit(x[bootstrap_ids, true], single_target ? y[bootstrap_ids] : y[bootstrap_ids, true])
      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.



143
144
145
146
147
148
 
# File 'lib/rumale/ensemble/random_forest_regressor.rb', line 143

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

#marshal_load(obj) ⇒ nil

Load marshal data.



152
153
154
155
156
157
158
 
# File 'lib/rumale/ensemble/random_forest_regressor.rb', line 152

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.



123
124
125
126
127
128
129
130
 
# File 'lib/rumale/ensemble/random_forest_regressor.rb', line 123

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