Class: Rumale::Ensemble::GradientBoostingRegressor

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

Overview

GradientBoostingRegressor is a class that implements gradient tree boosting for regression. The class use L2 loss for the loss function.

reference

  • J H. Friedman, “Greedy Function Approximation: A Gradient Boosting Machine,” Annals of Statistics, 29 (5), pp. 1189–1232, 2001.

  • J H. Friedman, “Stochastic Gradient Boosting,” Computational Statistics and Data Analysis, 38 (4), pp. 367–378, 2002.

    1. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” Proc. KDD’16, pp. 785–794, 2016.

Examples:

estimator =
  Rumale::Ensemble::GradientBoostingRegressor.new(
    n_estimators: 100, learning_rate: 0.3, reg_lambda: 0.001, 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: 100, learning_rate: 0.1, reg_lambda: 0.0, subsample: 1.0, max_depth: nil, max_leaf_nodes: nil, min_samples_leaf: 1, max_features: nil, random_seed: nil) ⇒ GradientBoostingRegressor

Create a new regressor with gradient tree boosting.



56
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
82
 
# File 'lib/rumale/ensemble/gradient_boosting_regressor.rb', line 56

def initialize(n_estimators: 100, learning_rate: 0.1, reg_lambda: 0.0, subsample: 1.0,
               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_float(learning_rate: learning_rate, reg_lambda: reg_lambda, subsample: subsample)
  check_params_positive(n_estimators: n_estimators,
                        learning_rate: learning_rate, reg_lambda: reg_lambda, subsample: subsample,
                        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[:learning_rate] = learning_rate
  @params[:reg_lambda] = reg_lambda
  @params[:subsample] = subsample
  @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
  @base_predictions = nil
  @feature_importances = nil
  @rng = Random.new(@params[:random_seed])
end

Instance Attribute Details

#estimators ⇒ Array<GradientTreeRegressor> (readonly)

Return the set of estimators.



31
32
33
 
# File 'lib/rumale/ensemble/gradient_boosting_regressor.rb', line 31

def estimators
  @estimators
end

#feature_importances ⇒ Numo::DFloat (readonly)

Return the importance for each feature. The feature importances are calculated based on the numbers of times the feature is used for splitting.



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

def feature_importances
  @feature_importances
end

#rng ⇒ Random (readonly)

Return the random generator for random selection of feature index.



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

def rng
  @rng
end

Instance Method Details

#apply(x) ⇒ Numo::Int32

Return the index of the leaf that each sample reached.



146
147
148
149
150
151
152
153
154
155
 
# File 'lib/rumale/ensemble/gradient_boosting_regressor.rb', line 146

def apply(x)
  check_sample_array(x)
  n_outputs = @estimators.first.is_a?(Array) ? @estimators.size : 1
  leaf_ids = if n_outputs > 1
               Array.new(n_outputs) { |n| @estimators[n].map { |tree| tree.apply(x) } }
             else
               @estimators.map { |tree| tree.apply(x) }
             end
  Numo::Int32[*leaf_ids].transpose
end

#fit(x, y) ⇒ GradientBoostingRegressor

Fit the model with given training data.



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
 
# File 'lib/rumale/ensemble/gradient_boosting_regressor.rb', line 89

def fit(x, y)
  check_sample_array(x)
  check_tvalue_array(y)
  check_sample_tvalue_size(x, y)

  n_features = x.shape[1]
  @params[:max_features] = n_features if @params[:max_features].nil?
  @params[:max_features] = [[1, @params[:max_features]].max, n_features].min

  # train regressor.
  n_outputs = y.shape[1].nil? ? 1 : y.shape[1]
  @base_predictions = n_outputs > 1 ? y.mean(0) : y.mean
  @estimators = if n_outputs > 1
                  Array.new(n_outputs) do |n|
                    partial_fit(x, y[true, n], @base_predictions[n])
                  end
                else
                  partial_fit(x, y, @base_predictions)
                end

  # calculate feature importances.
  @feature_importances = Numo::DFloat.zeros(n_features)
  if n_outputs > 1
    n_outputs.times do |n|
      @estimators[n].each { |tree| @feature_importances += tree.feature_importances }
    end
  else
    @estimators.each { |tree| @feature_importances += tree.feature_importances }
  end

  self
end

#marshal_dump ⇒ Hash

Dump marshal data.



159
160
161
162
163
164
165
 
# File 'lib/rumale/ensemble/gradient_boosting_regressor.rb', line 159

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

#marshal_load(obj) ⇒ nil

Load marshal data.



169
170
171
172
173
174
175
176
 
# File 'lib/rumale/ensemble/gradient_boosting_regressor.rb', line 169

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

#predict(x) ⇒ Numo::DFloat

Predict values for samples.



126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
 
# File 'lib/rumale/ensemble/gradient_boosting_regressor.rb', line 126

def predict(x)
  check_sample_array(x)
  n_samples = x.shape[0]
  n_outputs = @estimators.first.is_a?(Array) ? @estimators.size : 1
  if n_outputs > 1
    predicted = Numo::DFloat.ones(n_samples, n_outputs) * @base_predictions
    n_outputs.times do |n|
      @estimators[n].each { |tree| predicted[true, n] += tree.predict(x) }
    end
  else
    predicted = Numo::DFloat.ones(n_samples) * @base_predictions
    @estimators.each { |tree| predicted += tree.predict(x) }
  end
  predicted
end