Class: SVMKit::Tree::DecisionTreeRegressor

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

Overview

DecisionTreeRegressor is a class that implements decision tree for regression.

Examples:

estimator =
  SVMKit::Tree::DecisionTreeRegressor.new(
    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(criterion: 'mse', max_depth: nil, max_leaf_nodes: nil, min_samples_leaf: 1, max_features: nil, random_seed: nil) ⇒ DecisionTreeRegressor

Create a new regressor with decision tree algorithm.



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/svmkit/tree/decision_tree_regressor.rb', line 52

def initialize(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(min_samples_leaf: min_samples_leaf)
  check_params_string(criterion: criterion)
  check_params_positive(max_depth: max_depth, max_leaf_nodes: max_leaf_nodes,
                        min_samples_leaf: min_samples_leaf, max_features: max_features)
  @params = {}
  @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
  @criterion = :mse
  @criterion = :mae if @params[:criterion] == 'mae'
  @tree = nil
  @feature_importances = nil
  @n_leaves = nil
  @leaf_values = nil
  @rng = Random.new(@params[:random_seed])
end

Instance Attribute Details

#feature_importances ⇒ Numo::DFloat (readonly)

Return the importance for each feature.



26
27
28
 
# File 'lib/svmkit/tree/decision_tree_regressor.rb', line 26

def feature_importances
  @feature_importances
end

#leaf_values ⇒ Numo::DFloat (readonly)

Return the values assigned each leaf.



38
39
40
 
# File 'lib/svmkit/tree/decision_tree_regressor.rb', line 38

def leaf_values
  @leaf_values
end

#rng ⇒ Random (readonly)

Return the random generator for random selection of feature index.



34
35
36
 
# File 'lib/svmkit/tree/decision_tree_regressor.rb', line 34

def rng
  @rng
end

#tree ⇒ Node (readonly)

Return the learned tree.



30
31
32
 
# File 'lib/svmkit/tree/decision_tree_regressor.rb', line 30

def tree
  @tree
end

Instance Method Details

#apply(x) ⇒ Numo::Int32

Return the index of the leaf that each sample reached.



110
111
112
113
 
# File 'lib/svmkit/tree/decision_tree_regressor.rb', line 110

def apply(x)
  check_sample_array(x)
  Numo::Int32[*(Array.new(x.shape[0]) { |n| apply_at_node(@tree, x[n, true]) })]
end

#fit(x, y) ⇒ DecisionTreeRegressor

Fit the model with given training data.



82
83
84
85
86
87
88
89
90
91
92
93
94
95
 
# File 'lib/svmkit/tree/decision_tree_regressor.rb', line 82

def fit(x, y)
  check_sample_array(x)
  check_tvalue_array(y)
  check_sample_tvalue_size(x, y)
  single_target = y.shape[1].nil?
  y = y.expand_dims(1) if single_target
  n_samples, n_features = x.shape
  @params[:max_features] = n_features if @params[:max_features].nil?
  @params[:max_features] = [@params[:max_features], n_features].min
  build_tree(x, y)
  @leaf_values = @leaf_values[true] if single_target
  eval_importance(n_samples, n_features)
  self
end

#marshal_dump ⇒ Hash

Dump marshal data.



117
118
119
120
121
122
123
124
 
# File 'lib/svmkit/tree/decision_tree_regressor.rb', line 117

def marshal_dump
  { params: @params,
    criterion: @criterion,
    tree: @tree,
    feature_importances: @feature_importances,
    leaf_values: @leaf_values,
    rng: @rng }
end

#marshal_load(obj) ⇒ nil

Load marshal data.



128
129
130
131
132
133
134
135
136
 
# File 'lib/svmkit/tree/decision_tree_regressor.rb', line 128

def marshal_load(obj)
  @params = obj[:params]
  @criterion = obj[:criterion]
  @tree = obj[:tree]
  @feature_importances = obj[:feature_importances]
  @leaf_values = obj[:leaf_values]
  @rng = obj[:rng]
  nil
end

#predict(x) ⇒ Numo::DFloat

Predict values for samples.



101
102
103
104
 
# File 'lib/svmkit/tree/decision_tree_regressor.rb', line 101

def predict(x)
  check_sample_array(x)
  @leaf_values.shape[1].nil? ? @leaf_values[apply(x)] : @leaf_values[apply(x), true]
end