rumale 0.23.1 → 0.23.2

data/lib/rumale/clustering/hdbscan.rb

@@ -1,6 +1,5 @@
 # frozen_string_literal: true
 
-require 'ostruct'
 require 'rumale/base/base_estimator'
 require 'rumale/base/cluster_analyzer'
 require 'rumale/pairwise_metric'
@@ -108,7 +107,28 @@ module Rumale
         end
       end
 
-      private_constant :UnionFind
+      # @!visibility private
+      class Node
+        # @!visibility private
+        attr_reader :x, :y, :weight, :n_elements
+
+        # @!visibility private
+        def initialize(x:, y:, weight:, n_elements: 0)
+          @x = x
+          @y = y
+          @weight = weight
+          @n_elements = n_elements
+        end
+
+        # @!visibility private
+        def ==(other)
+          # :nocov:
+          x == other.x && y == other.y && weight == other.weight && n_elements == other.n_elements
+          # :nocov:
+        end
+      end
+
+      private_constant :UnionFind, :Node
 
       def partial_fit(distance_mat)
         mr_distance_mat = mutual_reachability_distances(distance_mat, @params[:min_samples])
@@ -161,30 +181,30 @@ module Rumale
 
           if n_x_elements >= min_cluster_size && n_y_elements >= min_cluster_size
             relabel[edge.x] = next_label
-            res.push(OpenStruct.new(x: relabel[n_id], y: relabel[edge.x], weight: density, n_elements: n_x_elements))
+            res.push(Node.new(x: relabel[n_id], y: relabel[edge.x], weight: density, n_elements: n_x_elements))
             next_label += 1
             relabel[edge.y] = next_label
-            res.push(OpenStruct.new(x: relabel[n_id], y: relabel[edge.y], weight: density, n_elements: n_y_elements))
+            res.push(Node.new(x: relabel[n_id], y: relabel[edge.y], weight: density, n_elements: n_y_elements))
             next_label += 1
           elsif n_x_elements < min_cluster_size && n_y_elements < min_cluster_size
             breadth_first_search_hierarchy(hierarchy, edge.x).each do |sn_id|
-              res.push(OpenStruct.new(x: relabel[n_id], y: sn_id, weight: density, n_elements: 1)) if sn_id < n_points
+              res.push(Node.new(x: relabel[n_id], y: sn_id, weight: density, n_elements: 1)) if sn_id < n_points
               visited[sn_id] = true
             end
             breadth_first_search_hierarchy(hierarchy, edge.y).each do |sn_id|
-              res.push(OpenStruct.new(x: relabel[n_id], y: sn_id, weight: density, n_elements: 1)) if sn_id < n_points
+              res.push(Node.new(x: relabel[n_id], y: sn_id, weight: density, n_elements: 1)) if sn_id < n_points
               visited[sn_id] = true
             end
           elsif n_x_elements < min_cluster_size
             relabel[edge.y] = relabel[n_id]
             breadth_first_search_hierarchy(hierarchy, edge.x).each do |sn_id|
-              res.push(OpenStruct.new(x: relabel[n_id], y: sn_id, weight: density, n_elements: 1)) if sn_id < n_points
+              res.push(Node.new(x: relabel[n_id], y: sn_id, weight: density, n_elements: 1)) if sn_id < n_points
               visited[sn_id] = true
             end
           elsif n_y_elements < min_cluster_size
             relabel[edge.x] = relabel[n_id]
             breadth_first_search_hierarchy(hierarchy, edge.y).each do |sn_id|
-              res.push(OpenStruct.new(x: relabel[n_id], y: sn_id, weight: density, n_elements: 1)) if sn_id < n_points
+              res.push(Node.new(x: relabel[n_id], y: sn_id, weight: density, n_elements: 1)) if sn_id < n_points
               visited[sn_id] = true
             end
           end

data/lib/rumale/clustering/single_linkage.rb

@@ -1,6 +1,5 @@
 # frozen_string_literal: true
 
-require 'ostruct'
 require 'rumale/base/base_estimator'
 require 'rumale/base/cluster_analyzer'
 require 'rumale/pairwise_metric'
@@ -25,7 +24,7 @@ module Rumale
       attr_reader :labels
 
       # Return the hierarchical structure.
-      # @return [Array<OpenStruct>] (shape: [n_samples - 1])
+      # @return [Array<SingleLinkage::Node>] (shape: [n_samples - 1])
       attr_reader :hierarchy
 
       # Create a new cluster analyzer with single linkage algorithm.
@@ -104,7 +103,26 @@ module Rumale
         end
       end
 
-      private_constant :UnionFind
+      # @!visibility private
+      class Node
+        # @!visibility private
+        attr_reader :x, :y, :weight, :n_elements
+
+        # @!visibility private
+        def initialize(x:, y:, weight:, n_elements: 0)
+          @x = x
+          @y = y
+          @weight = weight
+          @n_elements = n_elements
+        end
+
+        # @!visibility private
+        def ==(other)
+          x == other.x && y == other.y && weight == other.weight && n_elements == other.n_elements
+        end
+      end
+
+      private_constant :UnionFind, :Node
 
       def partial_fit(distance_mat)
         mst = minimum_spanning_tree(distance_mat)
@@ -125,7 +143,7 @@ module Rumale
           curr_weights = Numo::DFloat.minimum(curr_weights[target], complete_graph[curr_node, curr_labels])
           next_node = curr_labels[curr_weights.min_index]
           weight = curr_weights.min
-          OpenStruct.new(x: curr_node, y: next_node, weight: weight)
+          Node.new(x: curr_node, y: next_node, weight: weight)
         end
         mst.sort! { |a, b| a.weight <=> b.weight }
       end
@@ -140,7 +158,7 @@ module Rumale
           x_root, y_root = [y_root, x_root] unless x_root < y_root
           weight = mst[n].weight
           n_samples = uf.union(x_root, y_root)
-          OpenStruct.new(x: x_root, y: y_root, weight: weight, n_elements: n_samples)
+          Node.new(x: x_root, y: y_root, weight: weight, n_elements: n_samples)
         end
       end
 

data/lib/rumale/evaluation_measure/roc_auc.rb

@@ -118,8 +118,7 @@ module Rumale
         desc_y_true = Numo::Int32.cast(bin_y_true[desc_pred_ids])
         desc_y_score = y_score[desc_pred_ids]
 
-        dist_value_ids = desc_y_score.diff.ne(0).where
-        threshold_ids = dist_value_ids.append(desc_y_true.size - 1)
+        threshold_ids = Numo::Int32.cast(desc_y_score.diff.ne(0).where.to_a.append(desc_y_true.size - 1))
 
         true_pos = desc_y_true.cumsum[threshold_ids]
         false_pos = 1 + threshold_ids - true_pos

data/lib/rumale/nearest_neighbors/vp_tree.rb

@@ -10,6 +10,8 @@ module Rumale
     # This implementation, unlike the paper, does not perform random sampling with vantage point selection.
     # This class is used internally for k-nearest neighbor estimators.
     #
+    # @deprecated This class will be removed in ver. 0.24.0. The author recommends to use the annoy-rb gem instead.
+    #
     # *Reference*
     # - Yianilos, P N., "Data Structures and Algorithms for Nearest Neighbor Search in General Metric Spaces," Proc. SODA'93, pp. 311--321, 1993.
     class VPTree

data/lib/rumale/version.rb

@@ -3,5 +3,5 @@
 # Rumale is a machine learning library in Ruby.
 module Rumale
   # The version of Rumale you are using.
-  VERSION = '0.23.1'
+  VERSION = '0.23.2'
 end

data/lib/rumale.rb

@@ -2,136 +2,135 @@
 
 require 'numo/narray'
 
-require 'rumale/rumaleext'
-
-require 'rumale/version'
-require 'rumale/validation'
-require 'rumale/values'
-require 'rumale/utils'
-require 'rumale/pairwise_metric'
-require 'rumale/dataset'
-require 'rumale/probabilistic_output'
-require 'rumale/base/base_estimator'
-require 'rumale/base/classifier'
-require 'rumale/base/regressor'
-require 'rumale/base/cluster_analyzer'
-require 'rumale/base/transformer'
-require 'rumale/base/splitter'
-require 'rumale/base/evaluator'
-require 'rumale/pipeline/pipeline'
-require 'rumale/pipeline/feature_union'
-require 'rumale/kernel_approximation/rbf'
-require 'rumale/kernel_approximation/nystroem'
-require 'rumale/linear_model/base_sgd'
-require 'rumale/linear_model/svc'
-require 'rumale/linear_model/svr'
-require 'rumale/linear_model/logistic_regression'
-require 'rumale/linear_model/linear_regression'
-require 'rumale/linear_model/ridge'
-require 'rumale/linear_model/lasso'
-require 'rumale/linear_model/elastic_net'
-require 'rumale/linear_model/nnls'
-require 'rumale/kernel_machine/kernel_svc'
-require 'rumale/kernel_machine/kernel_pca'
-require 'rumale/kernel_machine/kernel_fda'
-require 'rumale/kernel_machine/kernel_ridge'
-require 'rumale/kernel_machine/kernel_ridge_classifier'
-require 'rumale/multiclass/one_vs_rest_classifier'
-require 'rumale/nearest_neighbors/vp_tree'
-require 'rumale/nearest_neighbors/k_neighbors_classifier'
-require 'rumale/nearest_neighbors/k_neighbors_regressor'
-require 'rumale/naive_bayes/base_naive_bayes'
-require 'rumale/naive_bayes/bernoulli_nb'
-require 'rumale/naive_bayes/complement_nb'
-require 'rumale/naive_bayes/gaussian_nb'
-require 'rumale/naive_bayes/multinomial_nb'
-require 'rumale/naive_bayes/negation_nb'
-require 'rumale/tree/node'
-require 'rumale/tree/base_decision_tree'
-require 'rumale/tree/decision_tree_classifier'
-require 'rumale/tree/decision_tree_regressor'
-require 'rumale/tree/extra_tree_classifier'
-require 'rumale/tree/extra_tree_regressor'
-require 'rumale/tree/gradient_tree_regressor'
-require 'rumale/ensemble/ada_boost_classifier'
-require 'rumale/ensemble/ada_boost_regressor'
-require 'rumale/ensemble/gradient_boosting_classifier'
-require 'rumale/ensemble/gradient_boosting_regressor'
-require 'rumale/ensemble/random_forest_classifier'
-require 'rumale/ensemble/random_forest_regressor'
-require 'rumale/ensemble/extra_trees_classifier'
-require 'rumale/ensemble/extra_trees_regressor'
-require 'rumale/ensemble/stacking_classifier'
-require 'rumale/ensemble/stacking_regressor'
-require 'rumale/ensemble/voting_classifier'
-require 'rumale/ensemble/voting_regressor'
-require 'rumale/clustering/k_means'
-require 'rumale/clustering/mini_batch_k_means'
-require 'rumale/clustering/k_medoids'
-require 'rumale/clustering/gaussian_mixture'
-require 'rumale/clustering/dbscan'
-require 'rumale/clustering/hdbscan'
-require 'rumale/clustering/snn'
-require 'rumale/clustering/power_iteration'
-require 'rumale/clustering/spectral_clustering'
-require 'rumale/clustering/single_linkage'
-require 'rumale/decomposition/pca'
-require 'rumale/decomposition/nmf'
-require 'rumale/decomposition/factor_analysis'
-require 'rumale/decomposition/fast_ica'
-require 'rumale/manifold/tsne'
-require 'rumale/manifold/mds'
-require 'rumale/metric_learning/fisher_discriminant_analysis'
-require 'rumale/metric_learning/neighbourhood_component_analysis'
-require 'rumale/metric_learning/mlkr'
-require 'rumale/neural_network/adam'
-require 'rumale/neural_network/base_mlp'
-require 'rumale/neural_network/mlp_regressor'
-require 'rumale/neural_network/mlp_classifier'
-require 'rumale/feature_extraction/hash_vectorizer'
-require 'rumale/feature_extraction/feature_hasher'
-require 'rumale/feature_extraction/tfidf_transformer'
-require 'rumale/preprocessing/l2_normalizer'
-require 'rumale/preprocessing/l1_normalizer'
-require 'rumale/preprocessing/max_normalizer'
-require 'rumale/preprocessing/min_max_scaler'
-require 'rumale/preprocessing/max_abs_scaler'
-require 'rumale/preprocessing/standard_scaler'
-require 'rumale/preprocessing/bin_discretizer'
-require 'rumale/preprocessing/label_binarizer'
-require 'rumale/preprocessing/label_encoder'
-require 'rumale/preprocessing/one_hot_encoder'
-require 'rumale/preprocessing/ordinal_encoder'
-require 'rumale/preprocessing/binarizer'
-require 'rumale/preprocessing/polynomial_features'
-require 'rumale/preprocessing/kernel_calculator'
-require 'rumale/model_selection/k_fold'
-require 'rumale/model_selection/group_k_fold'
-require 'rumale/model_selection/stratified_k_fold'
-require 'rumale/model_selection/shuffle_split'
-require 'rumale/model_selection/group_shuffle_split'
-require 'rumale/model_selection/stratified_shuffle_split'
-require 'rumale/model_selection/time_series_split'
-require 'rumale/model_selection/cross_validation'
-require 'rumale/model_selection/grid_search_cv'
-require 'rumale/model_selection/function'
-require 'rumale/evaluation_measure/accuracy'
-require 'rumale/evaluation_measure/precision'
-require 'rumale/evaluation_measure/recall'
-require 'rumale/evaluation_measure/f_score'
-require 'rumale/evaluation_measure/roc_auc'
-require 'rumale/evaluation_measure/log_loss'
-require 'rumale/evaluation_measure/r2_score'
-require 'rumale/evaluation_measure/explained_variance_score'
-require 'rumale/evaluation_measure/mean_squared_error'
-require 'rumale/evaluation_measure/mean_squared_log_error'
-require 'rumale/evaluation_measure/mean_absolute_error'
-require 'rumale/evaluation_measure/median_absolute_error'
-require 'rumale/evaluation_measure/adjusted_rand_score'
-require 'rumale/evaluation_measure/purity'
-require 'rumale/evaluation_measure/mutual_information'
-require 'rumale/evaluation_measure/normalized_mutual_information'
-require 'rumale/evaluation_measure/silhouette_score'
-require 'rumale/evaluation_measure/davies_bouldin_score'
-require 'rumale/evaluation_measure/calinski_harabasz_score'
-require 'rumale/evaluation_measure/function'
+require_relative 'rumale/version'
+require_relative 'rumale/rumaleext'
+require_relative 'rumale/validation'
+require_relative 'rumale/values'
+require_relative 'rumale/utils'
+require_relative 'rumale/pairwise_metric'
+require_relative 'rumale/dataset'
+require_relative 'rumale/probabilistic_output'
+require_relative 'rumale/base/base_estimator'
+require_relative 'rumale/base/classifier'
+require_relative 'rumale/base/regressor'
+require_relative 'rumale/base/cluster_analyzer'
+require_relative 'rumale/base/transformer'
+require_relative 'rumale/base/splitter'
+require_relative 'rumale/base/evaluator'
+require_relative 'rumale/pipeline/pipeline'
+require_relative 'rumale/pipeline/feature_union'
+require_relative 'rumale/kernel_approximation/rbf'
+require_relative 'rumale/kernel_approximation/nystroem'
+require_relative 'rumale/linear_model/base_sgd'
+require_relative 'rumale/linear_model/svc'
+require_relative 'rumale/linear_model/svr'
+require_relative 'rumale/linear_model/logistic_regression'
+require_relative 'rumale/linear_model/linear_regression'
+require_relative 'rumale/linear_model/ridge'
+require_relative 'rumale/linear_model/lasso'
+require_relative 'rumale/linear_model/elastic_net'
+require_relative 'rumale/linear_model/nnls'
+require_relative 'rumale/kernel_machine/kernel_svc'
+require_relative 'rumale/kernel_machine/kernel_pca'
+require_relative 'rumale/kernel_machine/kernel_fda'
+require_relative 'rumale/kernel_machine/kernel_ridge'
+require_relative 'rumale/kernel_machine/kernel_ridge_classifier'
+require_relative 'rumale/multiclass/one_vs_rest_classifier'
+require_relative 'rumale/nearest_neighbors/vp_tree'
+require_relative 'rumale/nearest_neighbors/k_neighbors_classifier'
+require_relative 'rumale/nearest_neighbors/k_neighbors_regressor'
+require_relative 'rumale/naive_bayes/base_naive_bayes'
+require_relative 'rumale/naive_bayes/bernoulli_nb'
+require_relative 'rumale/naive_bayes/complement_nb'
+require_relative 'rumale/naive_bayes/gaussian_nb'
+require_relative 'rumale/naive_bayes/multinomial_nb'
+require_relative 'rumale/naive_bayes/negation_nb'
+require_relative 'rumale/tree/node'
+require_relative 'rumale/tree/base_decision_tree'
+require_relative 'rumale/tree/decision_tree_classifier'
+require_relative 'rumale/tree/decision_tree_regressor'
+require_relative 'rumale/tree/extra_tree_classifier'
+require_relative 'rumale/tree/extra_tree_regressor'
+require_relative 'rumale/tree/gradient_tree_regressor'
+require_relative 'rumale/ensemble/ada_boost_classifier'
+require_relative 'rumale/ensemble/ada_boost_regressor'
+require_relative 'rumale/ensemble/gradient_boosting_classifier'
+require_relative 'rumale/ensemble/gradient_boosting_regressor'
+require_relative 'rumale/ensemble/random_forest_classifier'
+require_relative 'rumale/ensemble/random_forest_regressor'
+require_relative 'rumale/ensemble/extra_trees_classifier'
+require_relative 'rumale/ensemble/extra_trees_regressor'
+require_relative 'rumale/ensemble/stacking_classifier'
+require_relative 'rumale/ensemble/stacking_regressor'
+require_relative 'rumale/ensemble/voting_classifier'
+require_relative 'rumale/ensemble/voting_regressor'
+require_relative 'rumale/clustering/k_means'
+require_relative 'rumale/clustering/mini_batch_k_means'
+require_relative 'rumale/clustering/k_medoids'
+require_relative 'rumale/clustering/gaussian_mixture'
+require_relative 'rumale/clustering/dbscan'
+require_relative 'rumale/clustering/hdbscan'
+require_relative 'rumale/clustering/snn'
+require_relative 'rumale/clustering/power_iteration'
+require_relative 'rumale/clustering/spectral_clustering'
+require_relative 'rumale/clustering/single_linkage'
+require_relative 'rumale/decomposition/pca'
+require_relative 'rumale/decomposition/nmf'
+require_relative 'rumale/decomposition/factor_analysis'
+require_relative 'rumale/decomposition/fast_ica'
+require_relative 'rumale/manifold/tsne'
+require_relative 'rumale/manifold/mds'
+require_relative 'rumale/metric_learning/fisher_discriminant_analysis'
+require_relative 'rumale/metric_learning/neighbourhood_component_analysis'
+require_relative 'rumale/metric_learning/mlkr'
+require_relative 'rumale/neural_network/adam'
+require_relative 'rumale/neural_network/base_mlp'
+require_relative 'rumale/neural_network/mlp_regressor'
+require_relative 'rumale/neural_network/mlp_classifier'
+require_relative 'rumale/feature_extraction/hash_vectorizer'
+require_relative 'rumale/feature_extraction/feature_hasher'
+require_relative 'rumale/feature_extraction/tfidf_transformer'
+require_relative 'rumale/preprocessing/l2_normalizer'
+require_relative 'rumale/preprocessing/l1_normalizer'
+require_relative 'rumale/preprocessing/max_normalizer'
+require_relative 'rumale/preprocessing/min_max_scaler'
+require_relative 'rumale/preprocessing/max_abs_scaler'
+require_relative 'rumale/preprocessing/standard_scaler'
+require_relative 'rumale/preprocessing/bin_discretizer'
+require_relative 'rumale/preprocessing/label_binarizer'
+require_relative 'rumale/preprocessing/label_encoder'
+require_relative 'rumale/preprocessing/one_hot_encoder'
+require_relative 'rumale/preprocessing/ordinal_encoder'
+require_relative 'rumale/preprocessing/binarizer'
+require_relative 'rumale/preprocessing/polynomial_features'
+require_relative 'rumale/preprocessing/kernel_calculator'
+require_relative 'rumale/model_selection/k_fold'
+require_relative 'rumale/model_selection/group_k_fold'
+require_relative 'rumale/model_selection/stratified_k_fold'
+require_relative 'rumale/model_selection/shuffle_split'
+require_relative 'rumale/model_selection/group_shuffle_split'
+require_relative 'rumale/model_selection/stratified_shuffle_split'
+require_relative 'rumale/model_selection/time_series_split'
+require_relative 'rumale/model_selection/cross_validation'
+require_relative 'rumale/model_selection/grid_search_cv'
+require_relative 'rumale/model_selection/function'
+require_relative 'rumale/evaluation_measure/accuracy'
+require_relative 'rumale/evaluation_measure/precision'
+require_relative 'rumale/evaluation_measure/recall'
+require_relative 'rumale/evaluation_measure/f_score'
+require_relative 'rumale/evaluation_measure/roc_auc'
+require_relative 'rumale/evaluation_measure/log_loss'
+require_relative 'rumale/evaluation_measure/r2_score'
+require_relative 'rumale/evaluation_measure/explained_variance_score'
+require_relative 'rumale/evaluation_measure/mean_squared_error'
+require_relative 'rumale/evaluation_measure/mean_squared_log_error'
+require_relative 'rumale/evaluation_measure/mean_absolute_error'
+require_relative 'rumale/evaluation_measure/median_absolute_error'
+require_relative 'rumale/evaluation_measure/adjusted_rand_score'
+require_relative 'rumale/evaluation_measure/purity'
+require_relative 'rumale/evaluation_measure/mutual_information'
+require_relative 'rumale/evaluation_measure/normalized_mutual_information'
+require_relative 'rumale/evaluation_measure/silhouette_score'
+require_relative 'rumale/evaluation_measure/davies_bouldin_score'
+require_relative 'rumale/evaluation_measure/calinski_harabasz_score'
+require_relative 'rumale/evaluation_measure/function'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rumale
 version: !ruby/object:Gem::Version
-  version: 0.23.1
+  version: 0.23.2
 platform: ruby
 authors:
 - yoshoku
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2021-06-27 00:00:00.000000000 Z
+date: 2022-05-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -57,24 +57,13 @@ extensions:
 - ext/rumale/extconf.rb
 extra_rdoc_files: []
 files:
-- ".clang-format"
-- ".coveralls.yml"
-- ".github/workflows/build.yml"
-- ".github/workflows/coverage.yml"
-- ".gitignore"
-- ".rspec"
-- ".rubocop.yml"
 - CHANGELOG.md
 - CODE_OF_CONDUCT.md
-- Gemfile
 - LICENSE.txt
 - README.md
-- Rakefile
 - ext/rumale/extconf.rb
 - ext/rumale/rumaleext.c
 - ext/rumale/rumaleext.h
-- ext/rumale/tree.c
-- ext/rumale/tree.h
 - lib/rumale.rb
 - lib/rumale/base/base_estimator.rb
 - lib/rumale/base/classifier.rb
@@ -208,7 +197,6 @@ files:
 - lib/rumale/validation.rb
 - lib/rumale/values.rb
 - lib/rumale/version.rb
-- rumale.gemspec
 homepage: https://github.com/yoshoku/rumale
 licenses:
 - BSD-2-Clause
@@ -218,7 +206,8 @@ metadata:
   source_code_uri: https://github.com/yoshoku/rumale
   documentation_uri: https://yoshoku.github.io/rumale/doc/
   bug_tracker_uri: https://github.com/yoshoku/rumale/issues
-post_install_message: 
+  rubygems_mfa_required: 'true'
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -233,8 +222,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.6
-signing_key: 
+rubygems_version: 3.2.33
+signing_key:
 specification_version: 4
 summary: Rumale is a machine learning library in Ruby. Rumale provides machine learning
   algorithms with interfaces similar to Scikit-Learn in Python.