rumale-tree 0.29.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0d069a3649ab98c465d12b4e6a3af233ce05326156e74f4ff491436ffab8be5f
-  data.tar.gz: 9e952c4de1af5a0f7e24ce03ffe40cedeeeec722d33282de342913ec2d08d384
+  metadata.gz: fe371a348b02a2b18cb90639fb64af902f76bfa0c2f57bee235cdad12e183584
+  data.tar.gz: a2ffee131bc50ea0f850ac1fcbc5ca29be81d101f6a175a94e4756db4d19dede
 SHA512:
-  metadata.gz: 0ce3edf83049347530912e1d80488ffe42fadd74cf5f69886b62e7bfdee6888a0cdd63adfd417f97cb9ecd7b6b4d10963228fe7293e503d857e7b55d2f1f433b
-  data.tar.gz: 3622373d0692b3429dd704d56dc028a3f785aca16c07b7562e45aefcf278e3b9eb9ab54d2fb4dcc62c141293b71fdb5dee8bcd959313243513a9f7a1479cab5a
+  metadata.gz: 2b73e0d16c2e63b23ea42ed6235aa22b49bf014e9187d1faba3d73642b1c2e1a203c6cfa2791c6e31be0d94f432b68764f00350dbf77e54d2ec1efd04930518e
+  data.tar.gz: d025cbffcadcc38b904f3afe9c17d0dd8e33347345d9aac02a10d052653abb42ee362819f4a50eb267d40ed5610242139fdc5e4e0c2318ef276cbbe3d44dc4da

data/lib/rumale/tree/version.rb

@@ -5,6 +5,6 @@ module Rumale
   # This module consists of the classes that implement tree models.
   module Tree
     # @!visibility private
-    VERSION = '0.29.0'
+    VERSION = '1.0.0'
   end
 end

data/lib/rumale/tree/vr_tree_classifier.rb

@@ -0,0 +1,98 @@
+# frozen_string_literal: true
+
+require 'rumale/tree/decision_tree_classifier'
+
+module Rumale
+  module Tree
+    # VRTreeClassifier is a class that implements Variable-Random (VR) tree for classification.
+    #
+    # @example
+    #   require 'rumale/tree/vr_tree_classifier'
+    #
+    #   estimator =
+    #     Rumale::Tree::VRTreeClassifier.new(
+    #       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)
+    #
+    # *Reference*
+    # - Liu, F. T., Ting, K. M., Yu, Y., and Zhou, Z. H., "Spectrum of Variable-Random Trees," Journal of Artificial Intelligence Research, vol. 32, pp. 355--384, 2008.
+    class VRTreeClassifier < DecisionTreeClassifier
+      # 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 learned tree.
+      # @return [Node]
+      attr_reader :tree
+
+      # Return the random generator for random selection of feature index.
+      # @return [Random]
+      attr_reader :rng
+
+      # Return the labels assigned each leaf.
+      # @return [Numo::Int32] (size: n_leafs)
+      attr_reader :leaf_labels
+
+      # Create a new classifier with variable-random tree algorithm.
+      #
+      # @param criterion [String] The function to evaluate spliting point. Supported criteria are 'gini' and 'entropy'.
+      # @param alpha [Float] The probability of choosing a deterministic or random spliting point.
+      #   If 1.0 is given, the tree is the same as the normal decision tree.
+      # @param max_depth [Integer] The maximum depth of the tree.
+      #   If nil is given, variable-random tree grows without concern for depth.
+      # @param max_leaf_nodes [Integer] The maximum number of leaves on variable-random 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(criterion: 'gini', alpha: 0.5, max_depth: nil, max_leaf_nodes: nil, min_samples_leaf: 1, max_features: nil,
+                     random_seed: nil)
+        super(criterion: criterion, max_depth: max_depth, max_leaf_nodes: max_leaf_nodes, min_samples_leaf: min_samples_leaf,
+              max_features: max_features, random_seed: random_seed)
+        @params[:alpha] = alpha.clamp(0.0, 1.0)
+      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 [VRTreeClassifier] The learned classifier itself.
+
+      # 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.
+
+      # 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.
+
+      private
+
+      def best_split(features, y, whole_impurity)
+        r = -@sub_rng.rand(-1.0...0.0) # generate random number with (0, 1]
+        return super if r <= @params[:alpha]
+
+        fa, fb = features.to_a.uniq.sample(2, random: @sub_rng)
+        fb = fa if fb.nil?
+        threshold = 0.5 * (fa + fb)
+        l_ids = features.le(threshold).where
+        r_ids = features.gt(threshold).where
+        l_impurity = l_ids.empty? ? 0.0 : impurity(y[l_ids])
+        r_impurity = r_ids.empty? ? 0.0 : impurity(y[r_ids])
+        gain = whole_impurity -
+               l_impurity * l_ids.size.fdiv(y.size) -
+               r_impurity * r_ids.size.fdiv(y.size)
+        [l_impurity, r_impurity, threshold, gain]
+      end
+    end
+  end
+end

data/lib/rumale/tree/vr_tree_regressor.rb

@@ -0,0 +1,89 @@
+# frozen_string_literal: true
+
+require 'rumale/tree/decision_tree_regressor'
+
+module Rumale
+  module Tree
+    # VRTreeRegressor is a class that implements Variable-Random (VR) tree for regression.
+    #
+    # @example
+    #   require 'rumale/tree/vr_tree_regressor'
+    #
+    #   estimator =
+    #     Rumale::Tree::VRTreeRegressor.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)
+    #
+    # *Reference*
+    # - Liu, F. T., Ting, K. M., Yu, Y., and Zhou, Z. H., "Spectrum of Variable-Random Trees," Journal of Artificial Intelligence Research, vol. 32, pp. 355--384, 2008.
+    class VRTreeRegressor < DecisionTreeRegressor
+      # Return the importance for each feature.
+      # @return [Numo::DFloat] (size: n_features)
+      attr_reader :feature_importances
+
+      # Return the learned tree.
+      # @return [Node]
+      attr_reader :tree
+
+      # Return the random generator for random selection of feature index.
+      # @return [Random]
+      attr_reader :rng
+
+      # Return the values assigned each leaf.
+      # @return [Numo::DFloat] (shape: [n_leafs, n_outputs])
+      attr_reader :leaf_values
+
+      # Create a new regressor with variable-random tree algorithm.
+      #
+      # @param criterion [String] The function to evaluate spliting point. Supported criteria are 'mae' and 'mse'.
+      # @param alpha [Float] The probability of choosing a deterministic or random spliting point.
+      #   If 1.0 is given, the tree is the same as the normal decision tree.
+      # @param max_depth [Integer] The maximum depth of the tree.
+      #   If nil is given, variable-random tree grows without concern for depth.
+      # @param max_leaf_nodes [Integer] The maximum number of leaves on variable-random 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(criterion: 'mse', alpha: 0.5, max_depth: nil, max_leaf_nodes: nil, min_samples_leaf: 1, max_features: nil,
+                     random_seed: nil)
+        super(criterion: criterion, max_depth: max_depth, max_leaf_nodes: max_leaf_nodes, min_samples_leaf: min_samples_leaf,
+              max_features: max_features, random_seed: random_seed)
+        @params[:alpha] = alpha.clamp(0.0, 1.0)
+      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 taget values to be used for fitting the model.
+      # @return [VRTreeRegressor] The learned regressor itself.
+
+      # 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 values per sample.
+
+      private
+
+      def best_split(features, y, whole_impurity)
+        r = -@sub_rng.rand(-1.0...0.0) # generate random number with (0, 1]
+        return super if r <= @params[:alpha]
+
+        fa, fb = features.to_a.uniq.sample(2, random: @sub_rng)
+        fb = fa if fb.nil?
+        threshold = 0.5 * (fa + fb)
+        l_ids = features.le(threshold).where
+        r_ids = features.gt(threshold).where
+        l_impurity = l_ids.empty? ? 0.0 : impurity(y[l_ids, true])
+        r_impurity = r_ids.empty? ? 0.0 : impurity(y[r_ids, true])
+        gain = whole_impurity -
+               l_impurity * l_ids.size.fdiv(y.shape[0]) -
+               r_impurity * r_ids.size.fdiv(y.shape[0])
+        [l_impurity, r_impurity, threshold, gain]
+      end
+    end
+  end
+end

data/lib/rumale/tree.rb

@@ -9,3 +9,5 @@ require_relative 'tree/decision_tree_regressor'
 require_relative 'tree/extra_tree_classifier'
 require_relative 'tree/extra_tree_regressor'
 require_relative 'tree/gradient_tree_regressor'
+require_relative 'tree/vr_tree_classifier'
+require_relative 'tree/vr_tree_regressor'

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: rumale-tree
 version: !ruby/object:Gem::Version
-  version: 0.29.0
+  version: 1.0.0
 platform: ruby
 authors:
 - yoshoku
-autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-03-30 00:00:00.000000000 Z
+date: 2025-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -30,14 +29,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.29.0
+        version: 1.0.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.29.0
+        version: 1.0.0
 description: Rumale::Tree provides classifier and regression based on decision tree
   algorithms with Rumale interface.
 email:
@@ -61,6 +60,8 @@ files:
 - lib/rumale/tree/gradient_tree_regressor.rb
 - lib/rumale/tree/node.rb
 - lib/rumale/tree/version.rb
+- lib/rumale/tree/vr_tree_classifier.rb
+- lib/rumale/tree/vr_tree_regressor.rb
 homepage: https://github.com/yoshoku/rumale
 licenses:
 - BSD-3-Clause
@@ -70,7 +71,6 @@ metadata:
   changelog_uri: https://github.com/yoshoku/rumale/blob/main/CHANGELOG.md
   documentation_uri: https://yoshoku.github.io/rumale/doc/
   rubygems_mfa_required: 'true'
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -85,8 +85,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.7
-signing_key:
+rubygems_version: 3.6.2
 specification_version: 4
 summary: Rumale::Tree provides classifier and regression based on decision tree algorithms
   with Rumale interface.