rumale 0.8.0

data/lib/rumale/ensemble/ada_boost_regressor.rb

@@ -0,0 +1,178 @@
+# frozen_string_literal: true
+
+require 'rumale/values'
+require 'rumale/base/base_estimator'
+require 'rumale/base/regressor'
+require 'rumale/tree/decision_tree_regressor'
+
+module Rumale
+  module Ensemble
+    # AdaBoostRegressor is a class that implements random forest for regression.
+    # This class uses decision tree for a weak learner.
+    #
+    # @example
+    #   estimator =
+    #     Rumale::Ensemble::AdaBoostRegressor.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)
+    #
+    # *Reference*
+    # - D. L. Shrestha and D. P. Solomatine, "Experiments with AdaBoost.RT, an Improved Boosting Scheme for Regression," Neural Computation 18 (7), pp. 1678--1710, 2006.
+    #
+    class AdaBoostRegressor
+      include Base::BaseEstimator
+      include Base::Regressor
+
+      # Return the set of estimators.
+      # @return [Array<DecisionTreeRegressor>]
+      attr_reader :estimators
+
+      # Return the weight for each weak learner.
+      # @return [Numo::DFloat] (size: n_estimates)
+      attr_reader :estimator_weights
+
+      # Return the importance for each feature.
+      # @return [Numo::DFloat] (size: n_features)
+      attr_reader :feature_importances
+
+      # Return the random generator for random selection of feature index.
+      # @return [Random]
+      attr_reader :rng
+
+      # Create a new regressor with random forest.
+      #
+      # @param n_estimators [Integer] The numeber of decision trees for contructing random forest.
+      # @param threshold [Float] The threshold for delimiting correct and incorrect predictions. That is constrained to [0, 1]
+      # @param exponent [Float] The exponent for the weight of each weak learner.
+      # @param criterion [String] The function to evalue spliting point. Supported criteria are 'gini' and 'entropy'.
+      # @param max_depth [Integer] The maximum depth of the tree.
+      #   If nil is given, decision tree grows without concern for depth.
+      # @param max_leaf_nodes [Integer] The maximum number of leaves on decision tree.
+      #   If nil is given, number of leaves is not limited.
+      # @param min_samples_leaf [Integer] The minimum number of samples at a leaf node.
+      # @param max_features [Integer] The number of features to consider when searching optimal split point.
+      #   If nil is given, split process considers all features.
+      # @param random_seed [Integer] The seed value using to initialize the random generator.
+      #   It is used to randomly determine the order of features when deciding spliting point.
+      def initialize(n_estimators: 10, threshold: 0.2, exponent: 1.0,
+                     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_float(threshold: threshold, exponent: exponent)
+        check_params_string(criterion: criterion)
+        check_params_positive(n_estimators: n_estimators, threshold: threshold, exponent: exponent,
+                              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[:threshold] = threshold
+        @params[:exponent] = exponent
+        @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
+
+      # Fit the model with given training data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
+      # @param y [Numo::DFloat] (shape: [n_samples]) The target values to be used for fitting the model.
+      # @return [AdaBoostRegressor] The learned regressor itself.
+      def fit(x, y) # rubocop:disable Metrics/AbcSize
+        check_sample_array(x)
+        check_tvalue_array(y)
+        check_sample_tvalue_size(x, y)
+        # Check target values
+        raise ArgumentError, 'Expect target value vector to be 1-D arrray' unless y.shape.size == 1
+        # Initialize some variables.
+        n_samples, n_features = x.shape
+        @params[:max_features] = n_features unless @params[:max_features].is_a?(Integer)
+        @params[:max_features] = [[1, @params[:max_features]].max, n_features].min
+        observation_weights = Numo::DFloat.zeros(n_samples) + 1.fdiv(n_samples)
+        @estimators = []
+        @estimator_weights = []
+        @feature_importances = Numo::DFloat.zeros(n_features)
+        # Construct forest.
+        @params[:n_estimators].times do |_t|
+          # Fit weak learner.
+          ids = Rumale::Utils.choice_ids(n_samples, observation_weights, @rng)
+          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: @rng.rand(Rumale::Values.int_max)
+          )
+          tree.fit(x[ids, true], y[ids])
+          p = tree.predict(x)
+          # Calculate errors.
+          abs_err = ((p - y) / y).abs
+          err = observation_weights[abs_err.gt(@params[:threshold])].sum
+          break if err <= 0.0
+          # Calculate weight.
+          beta = err**@params[:exponent]
+          weight = Math.log(1.fdiv(beta))
+          # Store model.
+          @estimators.push(tree)
+          @estimator_weights.push(weight)
+          @feature_importances += weight * tree.feature_importances
+          # Update observation weights.
+          update = Numo::DFloat.ones(n_samples)
+          update[abs_err.le(@params[:threshold])] = beta
+          observation_weights *= update
+          observation_weights = observation_weights.clip(1.0e-15, nil)
+          sum_observation_weights = observation_weights.sum
+          break if sum_observation_weights.zero?
+          observation_weights /= sum_observation_weights
+        end
+        @estimator_weights = Numo::DFloat.asarray(@estimator_weights)
+        @feature_importances /= @estimator_weights.sum
+        self
+      end
+
+      # Predict values for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the values.
+      # @return [Numo::DFloat] (shape: [n_samples, n_outputs]) Predicted value per sample.
+      def predict(x)
+        check_sample_array(x)
+        n_samples, = x.shape
+        predictions = Numo::DFloat.zeros(n_samples)
+        @estimators.size.times do |t|
+          predictions += @estimator_weights[t] * @estimators[t].predict(x)
+        end
+        sum_weight = @estimator_weights.sum
+        predictions / sum_weight
+      end
+
+      # Dump marshal data.
+      # @return [Hash] The marshal data about AdaBoostRegressor.
+      def marshal_dump
+        { params: @params,
+          estimators: @estimators,
+          estimator_weights: @estimator_weights,
+          feature_importances: @feature_importances,
+          rng: @rng }
+      end
+
+      # Load marshal data.
+      # @return [nil]
+      def marshal_load(obj)
+        @params = obj[:params]
+        @estimators = obj[:estimators]
+        @estimator_weights = obj[:estimator_weights]
+        @feature_importances = obj[:feature_importances]
+        @rng = obj[:rng]
+        nil
+      end
+    end
+  end
+end

data/lib/rumale/ensemble/random_forest_classifier.rb

@@ -0,0 +1,180 @@
+# frozen_string_literal: true
+
+require 'rumale/values'
+require 'rumale/base/base_estimator'
+require 'rumale/base/classifier'
+require 'rumale/tree/decision_tree_classifier'
+
+module Rumale
+  # This module consists of the classes that implement ensemble-based methods.
+  module Ensemble
+    # RandomForestClassifier is a class that implements random forest for classification.
+    #
+    # @example
+    #   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)
+    #
+    class RandomForestClassifier
+      include Base::BaseEstimator
+      include Base::Classifier
+
+      # Return the set of estimators.
+      # @return [Array<DecisionTreeClassifier>]
+      attr_reader :estimators
+
+      # Return the class labels.
+      # @return [Numo::Int32] (size: n_classes)
+      attr_reader :classes
+
+      # Return the importance for each feature.
+      # @return [Numo::DFloat] (size: n_features)
+      attr_reader :feature_importances
+
+      # Return the random generator for random selection of feature index.
+      # @return [Random]
+      attr_reader :rng
+
+      # Create a new classifier with random forest.
+      #
+      # @param n_estimators [Integer] The numeber of decision trees for contructing random forest.
+      # @param criterion [String] The function to evalue spliting point. Supported criteria are 'gini' and 'entropy'.
+      # @param max_depth [Integer] The maximum depth of the tree.
+      #   If nil is given, decision tree grows without concern for depth.
+      # @param max_leaf_nodes [Integer] The maximum number of leaves on decision tree.
+      #   If nil is given, number of leaves is not limited.
+      # @param min_samples_leaf [Integer] The minimum number of samples at a leaf node.
+      # @param max_features [Integer] The number of features to consider when searching optimal split point.
+      #   If nil is given, split process considers all features.
+      # @param random_seed [Integer] The seed value using to initialize the random generator.
+      #   It is used to randomly determine the order of features when deciding spliting point.
+      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
+
+      # Fit the model with given training data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
+      # @param y [Numo::Int32] (shape: [n_samples]) The labels to be used for fitting the model.
+      # @return [RandomForestClassifier] The learned classifier itself.
+      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
+
+      # Predict class labels for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the labels.
+      # @return [Numo::Int32] (shape: [n_samples]) Predicted class label per sample.
+      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 probability for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the probailities.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted probability of each class per sample.
+      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
+
+      # Return the index of the leaf that each sample reached.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the labels.
+      # @return [Numo::Int32] (shape: [n_samples, n_estimators]) Leaf index for sample.
+      def apply(x)
+        check_sample_array(x)
+        Numo::Int32[*Array.new(@params[:n_estimators]) { |n| @estimators[n].apply(x) }].transpose
+      end
+
+      # Dump marshal data.
+      # @return [Hash] The marshal data about RandomForestClassifier.
+      def marshal_dump
+        { params: @params,
+          estimators: @estimators,
+          classes: @classes,
+          feature_importances: @feature_importances,
+          rng: @rng }
+      end
+
+      # Load marshal data.
+      # @return [nil]
+      def marshal_load(obj)
+        @params = obj[:params]
+        @estimators = obj[:estimators]
+        @classes = obj[:classes]
+        @feature_importances = obj[:feature_importances]
+        @rng = obj[:rng]
+        nil
+      end
+    end
+  end
+end

data/lib/rumale/ensemble/random_forest_regressor.rb

@@ -0,0 +1,141 @@
+# frozen_string_literal: true
+
+require 'rumale/values'
+require 'rumale/base/base_estimator'
+require 'rumale/base/regressor'
+require 'rumale/tree/decision_tree_regressor'
+
+module Rumale
+  module Ensemble
+    # RandomForestRegressor is a class that implements random forest for regression
+    #
+    # @example
+    #   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)
+    #
+    class RandomForestRegressor
+      include Base::BaseEstimator
+      include Base::Regressor
+
+      # Return the set of estimators.
+      # @return [Array<DecisionTreeRegressor>]
+      attr_reader :estimators
+
+      # Return the importance for each feature.
+      # @return [Numo::DFloat] (size: n_features)
+      attr_reader :feature_importances
+
+      # Return the random generator for random selection of feature index.
+      # @return [Random]
+      attr_reader :rng
+
+      # Create a new regressor with random forest.
+      #
+      # @param n_estimators [Integer] The numeber of decision trees for contructing random forest.
+      # @param criterion [String] The function to evalue spliting point. Supported criteria are 'gini' and 'entropy'.
+      # @param max_depth [Integer] The maximum depth of the tree.
+      #   If nil is given, decision tree grows without concern for depth.
+      # @param max_leaf_nodes [Integer] The maximum number of leaves on decision tree.
+      #   If nil is given, number of leaves is not limited.
+      # @param min_samples_leaf [Integer] The minimum number of samples at a leaf node.
+      # @param max_features [Integer] The number of features to consider when searching optimal split point.
+      #   If nil is given, split process considers all features.
+      # @param random_seed [Integer] The seed value using to initialize the random generator.
+      #   It is used to randomly determine the order of features when deciding spliting point.
+      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
+
+      # Fit the model with given training data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
+      # @param y [Numo::DFloat] (shape: [n_samples, n_outputs]) The target values to be used for fitting the model.
+      # @return [RandomForestRegressor] The learned regressor itself.
+      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
+        @feature_importances = Numo::DFloat.zeros(n_features)
+        single_target = y.shape[1].nil?
+        # Construct forest.
+        @estimators = Array.new(@params[:n_estimators]) do
+          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: @rng.rand(Rumale::Values.int_max)
+          )
+          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])
+          @feature_importances += tree.feature_importances
+          tree
+        end
+        @feature_importances /= @feature_importances.sum
+        self
+      end
+
+      # Predict values for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the values.
+      # @return [Numo::DFloat] (shape: [n_samples, n_outputs]) Predicted value per sample.
+      def predict(x)
+        check_sample_array(x)
+        @estimators.map { |est| est.predict(x) }.reduce(&:+) / @params[:n_estimators]
+      end
+
+      # Return the index of the leaf that each sample reached.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to assign each leaf.
+      # @return [Numo::Int32] (shape: [n_samples, n_estimators]) Leaf index for sample.
+      def apply(x)
+        check_sample_array(x)
+        Numo::Int32[*Array.new(@params[:n_estimators]) { |n| @estimators[n].apply(x) }].transpose
+      end
+
+      # Dump marshal data.
+      # @return [Hash] The marshal data about RandomForestRegressor.
+      def marshal_dump
+        { params: @params,
+          estimators: @estimators,
+          feature_importances: @feature_importances,
+          rng: @rng }
+      end
+
+      # Load marshal data.
+      # @return [nil]
+      def marshal_load(obj)
+        @params = obj[:params]
+        @estimators = obj[:estimators]
+        @feature_importances = obj[:feature_importances]
+        @rng = obj[:rng]
+        nil
+      end
+    end
+  end
+end