rumale 0.19.3 → 0.21.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dc3413c05ad7c365117adc4abbc304ff1851fa9a3ff69fef3c69e730d9a2b834
-  data.tar.gz: 8895cce8b350c4e245aabb5e3e4c4036655fa8d24a72f6481e0d2f8c9869fa54
+  metadata.gz: fd5ca16629a5258be9e577771dc8c6b42dbfdf3a60a4c43d4ee170cc17b72bea
+  data.tar.gz: 70b26bcf0b39bb8e716b9bbb4aba100c496152b1c4e71879105046440c7d8758
 SHA512:
-  metadata.gz: fe10c975f286a4c9ac155d29310d61d1f180cbcc909ec7bdba3925973b6b9857635befc9bf4938cf28a6ef50c8011894b7b15768735f6200c27ce912907e5fb1
-  data.tar.gz: 327cce25145c1ca3f5623f84b4163560bdbee8245009c3d8e1c3318f61dec94b58a7395ebc3538e7b04a9702af08b077e7f426c54f7c5d4fd3b0fcf11c4744cf
+  metadata.gz: 645a6bda6e3601534c69f5ecfbd840c1d6c1ed7a5a3b8bd57995621a03d970cd02e9749a8a70be5af2678c029a26a5e6e1c32376a4514a64e96d6a9b4b12aa3e
+  data.tar.gz: 5904c64da9cc30cf0c288dfbeb3051bca3333e588e153cf19619c169d713e93edcb95e6902134e58c823d621ebad9e6a56310123c110b6d810033f5f96a40fbb

data/.rubocop.yml

@@ -3,6 +3,7 @@ require:
   - rubocop-rspec
 
 AllCops:
+  NewCops: enable
   TargetRubyVersion: 2.5
   DisplayCopNames: true
   DisplayStyleGuide: true
@@ -15,34 +16,16 @@ AllCops:
 Style/Documentation:
   Enabled: false
 
-Style/HashEachMethods:
-  Enabled: true
-
-Style/HashTransformKeys:
-  Enabled: true
-
-Style/HashTransformValues:
-  Enabled: true
-
-Lint/DeprecatedOpenSSLConstant:
-  Enabled: true
-
-Lint/DuplicateElsifCondition:
-  Enabled: true
-
-Lint/MixedRegexpCaptureTypes:
-  Enabled: true
-
-Lint/RaiseException:
-  Enabled: true
-
-Lint/StructNewOverride:
-  Enabled: true
-
 Layout/LineLength:
   Max: 145
   IgnoredPatterns: ['(\A|\s)#']
 
+Lint/ConstantDefinitionInBlock:
+  Enabled: false
+
+Lint/MissingSuper:
+  Enabled: false
+
 Metrics/ModuleLength:
   Max: 200
 
@@ -78,87 +61,21 @@ Naming/MethodParameterName:
 Naming/ConstantName:
   Enabled: false
 
-Style/AccessorGrouping:
-  Enabled: true
-
-Style/ArrayCoercion:
-  Enabled: true
-
-Style/BisectedAttrAccessor:
-  Enabled: true
-
-Style/CaseLikeIf:
-  Enabled: true
-
-Style/ExponentialNotation:
-  Enabled: true
-
 Style/FormatStringToken:
   Enabled: false
 
-Style/HashAsLastArrayItem:
-  Enabled: true
-
-Style/HashLikeCase:
-  Enabled: true
-
 Style/NumericLiterals:
   Enabled: false
 
-Style/RedundantAssignment:
-  Enabled: true
-
-Style/RedundantFetchBlock:
-  Enabled: true
-
-Style/RedundantFileExtensionInRequire:
-  Enabled: true
-
-Style/RedundantRegexpCharacterClass:
-  Enabled: true
-
-Style/RedundantRegexpEscape:
-  Enabled: true
-
-Style/SlicingWithRange:
-  Enabled: true
-
-Layout/EmptyLineAfterGuardClause:
-  Enabled: true
-
-Layout/EmptyLinesAroundAttributeAccessor:
-  Enabled: true
-
-Layout/SpaceAroundMethodCallOperator:
-  Enabled: true
-
-Performance/AncestorsInclude:
-  Enabled: true
-
-Performance/BigDecimalWithNumericArgument:
-  Enabled: true
-
-Performance/RedundantSortBlock:
-  Enabled: true
-
-Performance/RedundantStringChars:
-  Enabled: true
-
-Performance/ReverseFirst:
-  Enabled: true
-
-Performance/SortReverse:
-  Enabled: true
-
-Performance/Squeeze:
-  Enabled: true
-
-Performance/StringInclude:
-  Enabled: true
+Style/StringConcatenation:
+  Enabled: false
 
 RSpec/MultipleExpectations:
   Enabled: false
 
+RSpec/MultipleMemoizedHelpers:
+  Max: 25
+
 RSpec/NestedGroups:
   Max: 4
 
@@ -170,3 +87,6 @@ RSpec/InstanceVariable:
 
 RSpec/LeakyConstantDeclaration:
   Enabled: false
+
+Performance/Sum:
+  Enabled: false

data/CHANGELOG.md

@@ -1,3 +1,29 @@
+# 0.21.0
+## Breaking change
+- Change the default value of max_iter argument on LinearModel estimators to 1000.
+
+# 0.20.3
+- Fix to use automatic solver of PCA in NeighbourhoodComponentAnalysis.
+- Refactor some codes with Rubocop.
+- Update README.
+
+# 0.20.2
+- Add cross-validator class for time-series data.
+  - [TimeSeriesSplit](https://yoshoku.github.io/rumale/doc/Rumale/ModelSelection/TimeSeriesSplit.html)
+
+# 0.20.1
+- Add cross-validator classes that split data according group labels.
+  - [GroupKFold](https://yoshoku.github.io/rumale/doc/Rumale/ModelSelection/GroupKFold.html)
+  - [GroupShuffleSplit](https://yoshoku.github.io/rumale/doc/Rumale/ModelSelection/GroupShuffleSplit.html)
+- Fix fraction treating of the number of samples on shuffle split cross-validator classes.
+  - [ShuffleSplit](https://yoshoku.github.io/rumale/doc/Rumale/ModelSelection/ShuffleSplit.html)
+  - [StratifiedShuffleSplit](https://yoshoku.github.io/rumale/doc/Rumale/ModelSelection/StratifiedShuffleSplit.html)
+- Refactor some codes with Rubocop.
+
+# 0.20.0
+## Breaking changes
+- Delete deprecated estimators such as PolynomialModel, Optimizer, and BaseLinearModel.
+
 # 0.19.3
 - Add preprocessing class for [Binarizer](https://yoshoku.github.io/rumale/doc/Rumale/Preprocessing/Binarizer.html)
 - Add preprocessing class for [MaxNormalizer](https://yoshoku.github.io/rumale/doc/Rumale/Preprocessing/MaxNormalizer.html)
@@ -13,6 +39,7 @@
 - Fix some typos.
 
 # 0.19.0
+## Breaking changes
 - Change mmh3 and mopti gem to non-runtime dependent library.
   - The mmh3 gem is used in [FeatureHasher](https://yoshoku.github.io/rumale/doc/Rumale/FeatureExtraction/FeatureHasher.html).
   You only need to require mmh3 gem when using FeatureHasher.

data/Gemfile

@@ -11,3 +11,6 @@ gem 'parallel', '>= 1.17.0'
 gem 'rake', '~> 12.0'
 gem 'rake-compiler', '~> 1.0'
 gem 'rspec', '~> 3.0'
+gem 'rubocop', '~> 0.91'
+gem 'rubocop-performance', '~> 1.8'
+gem 'rubocop-rspec', '~> 1.43'

data/README.md

@@ -228,6 +228,10 @@ When -1 is given to n_jobs parameter, all processors are used.
 estimator = Rumale::Ensemble::RandomForestClassifier.new(n_jobs: -1, random_seed: 1)
 ```
 
+## Novelties
+
+* [Rumale SHOP](https://suzuri.jp/yoshoku)
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/rumale.

data/lib/rumale.rb

@@ -18,17 +18,10 @@ require 'rumale/base/cluster_analyzer'
 require 'rumale/base/transformer'
 require 'rumale/base/splitter'
 require 'rumale/base/evaluator'
-require 'rumale/optimizer/sgd'
-require 'rumale/optimizer/ada_grad'
-require 'rumale/optimizer/rmsprop'
-require 'rumale/optimizer/adam'
-require 'rumale/optimizer/nadam'
-require 'rumale/optimizer/yellow_fin'
 require 'rumale/pipeline/pipeline'
 require 'rumale/pipeline/feature_union'
 require 'rumale/kernel_approximation/rbf'
 require 'rumale/kernel_approximation/nystroem'
-require 'rumale/linear_model/base_linear_model'
 require 'rumale/linear_model/base_sgd'
 require 'rumale/linear_model/svc'
 require 'rumale/linear_model/svr'
@@ -41,9 +34,6 @@ 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/polynomial_model/base_factorization_machine'
-require 'rumale/polynomial_model/factorization_machine_classifier'
-require 'rumale/polynomial_model/factorization_machine_regressor'
 require 'rumale/multiclass/one_vs_rest_classifier'
 require 'rumale/nearest_neighbors/vp_tree'
 require 'rumale/nearest_neighbors/k_neighbors_classifier'
@@ -108,9 +98,12 @@ require 'rumale/preprocessing/ordinal_encoder'
 require 'rumale/preprocessing/binarizer'
 require 'rumale/preprocessing/polynomial_features'
 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'

data/lib/rumale/clustering/hdbscan.rb

@@ -136,7 +136,7 @@ module Rumale
         res
       end
 
-      # rubocop:disable Metrics/AbcSize, Metrics/MethodLength, Metrics/PerceivedComplexity
+      # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/MethodLength, Metrics/PerceivedComplexity
       def condense_tree(hierarchy, min_cluster_size)
         n_edges = hierarchy.size
         root = 2 * n_edges
@@ -265,7 +265,7 @@ module Rumale
         end
         res
       end
-      # rubocop:enable Metrics/AbcSize, Metrics/MethodLength, Metrics/PerceivedComplexity
+      # rubocop:enable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/MethodLength, Metrics/PerceivedComplexity
     end
   end
 end

data/lib/rumale/clustering/snn.rb

@@ -51,7 +51,7 @@ module Rumale
       # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to be used for cluster analysis.
       #   If the metric is 'precomputed', x must be a square distance matrix (shape: [n_samples, n_samples]).
       # @return [Numo::Int32] (shape: [n_samples]) Predicted cluster label per sample.
-      def fit_predict(x)
+      def fit_predict(x) # rubocop:disable Lint/UselessMethodDefinition
         super
       end
 

data/lib/rumale/dataset.rb

@@ -225,7 +225,7 @@ module Rumale
         line = dump_label(label, label_type.to_s)
         ftvec.to_a.each_with_index do |val, n|
           idx = n + (zero_based == false ? 1 : 0)
-          line += format(" %d:#{value_type}", idx, val) if val != 0.0
+          line += format(" %d:#{value_type}", idx, val) if val != 0
         end
         line
       end

data/lib/rumale/decomposition/nmf.rb

@@ -77,7 +77,7 @@ module Rumale
       # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data.
       def transform(x)
         x = check_convert_sample_array(x)
-        partial_fit(x, false)
+        partial_fit(x, update_comps: false)
       end
 
       # Inverse transform the given transformed data with the learned model.
@@ -91,7 +91,7 @@ module Rumale
 
       private
 
-      def partial_fit(x, update_comps = true)
+      def partial_fit(x, update_comps: true)
         # initialize some variables.
         n_samples, n_features = x.shape
         scale = Math.sqrt(x.mean / @params[:n_components])

data/lib/rumale/ensemble/random_forest_classifier.rb

@@ -85,7 +85,7 @@ module Rumale
       # @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)
+      def fit(x, y) # rubocop:disable Metrics/AbcSize
         x = check_convert_sample_array(x)
         y = check_convert_label_array(y)
         check_sample_label_size(x, y)

data/lib/rumale/ensemble/random_forest_regressor.rb

@@ -79,7 +79,7 @@ module Rumale
       # @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)
+      def fit(x, y) # rubocop:disable Metrics/AbcSize
         x = check_convert_sample_array(x)
         y = check_convert_tvalue_array(y)
         check_sample_tvalue_size(x, y)

data/lib/rumale/evaluation_measure/roc_auc.rb

@@ -75,9 +75,12 @@ module Rumale
         false_pos, true_pos, thresholds = binary_roc_curve(y_true, y_score, pos_label)
 
         if true_pos.size.zero? || false_pos[0] != 0 || true_pos[0] != 0
+          # NOTE: Numo::NArray#insert is not a destructive method.
+          # rubocop:disable Style/RedundantSelfAssignment
           true_pos = true_pos.insert(0, 0)
           false_pos = false_pos.insert(0, 0)
           thresholds = thresholds.insert(0, thresholds[0] + 1)
+          # rubocop:enable Style/RedundantSelfAssignment
         end
 
         tpr = true_pos / true_pos[-1].to_f

data/lib/rumale/feature_extraction/feature_hasher.rb

@@ -67,7 +67,7 @@ module Rumale
       def transform(x)
         raise 'FeatureHasher#transform requires Mmh3 but that is not loaded.' unless enable_mmh3?
 
-        x = [x] unless x.is_a?(Array)
+        x = [x] unless x.is_a?(Array) # rubocop:disable Style/ArrayCoercion
         n_samples = x.size
 
         z = Numo::DFloat.zeros(n_samples, n_features)

data/lib/rumale/feature_extraction/hash_vectorizer.rb

@@ -99,7 +99,7 @@ module Rumale
       # @param x [Array<Hash>] (shape: [n_samples]) The array of hash consisting of feature names and values.
       # @return [Numo::DFloat] (shape: [n_samples, n_features]) The encoded sample array.
       def transform(x)
-        x = [x] unless x.is_a?(Array)
+        x = [x] unless x.is_a?(Array) # rubocop:disable Style/ArrayCoercion
         n_samples = x.size
         n_features = @vocabulary.size
         z = Numo::DFloat.zeros(n_samples, n_features)

data/lib/rumale/linear_model/base_sgd.rb

@@ -171,7 +171,7 @@ module Rumale
         @params[:fit_bias] = true
         @params[:reg_param] = 0.0
         @params[:l1_ratio] = 0.0
-        @params[:max_iter] = 200
+        @params[:max_iter] = 1000
         @params[:batch_size] = 50
         @params[:tol] = 0.0001
         @params[:verbose] = false

data/lib/rumale/linear_model/elastic_net.rb

@@ -10,7 +10,7 @@ module Rumale
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::ElasticNet.new(reg_param: 0.1, l1_ratio: 0.5, max_iter: 200, batch_size: 50, random_seed: 1)
+    #     Rumale::LinearModel::ElasticNet.new(reg_param: 0.1, l1_ratio: 0.5, max_iter: 1000, batch_size: 50, random_seed: 1)
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -59,7 +59,7 @@ module Rumale
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      reg_param: 1.0, l1_ratio: 0.5, fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,
                              reg_param: reg_param, l1_ratio: l1_ratio, bias_scale: bias_scale,

data/lib/rumale/linear_model/lasso.rb

@@ -10,7 +10,7 @@ module Rumale
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::Lasso.new(reg_param: 0.1, max_iter: 500, batch_size: 20, random_seed: 1)
+    #     Rumale::LinearModel::Lasso.new(reg_param: 0.1, max_iter: 1000, batch_size: 20, random_seed: 1)
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -55,7 +55,7 @@ module Rumale
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      reg_param: 1.0, fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,
                              reg_param: reg_param, bias_scale: bias_scale,

data/lib/rumale/linear_model/linear_regression.rb

@@ -10,7 +10,7 @@ module Rumale
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::LinearRegression.new(max_iter: 500, batch_size: 20, random_seed: 1)
+    #     Rumale::LinearModel::LinearRegression.new(max_iter: 1000, batch_size: 20, random_seed: 1)
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -68,7 +68,7 @@ module Rumale
       #   If solver = 'svd', this parameter is ignored.
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
-                     fit_bias: true, bias_scale: 1.0, max_iter: 200, batch_size: 50, tol: 1e-4,
+                     fit_bias: true, bias_scale: 1.0, max_iter: 1000, batch_size: 50, tol: 1e-4,
                      solver: 'auto',
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,

data/lib/rumale/linear_model/logistic_regression.rb

@@ -15,7 +15,7 @@ module Rumale
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::LogisticRegression.new(reg_param: 1.0, max_iter: 200, batch_size: 50, random_seed: 1)
+    #     Rumale::LinearModel::LogisticRegression.new(reg_param: 1.0, max_iter: 1000, batch_size: 50, random_seed: 1)
     #   estimator.fit(training_samples, traininig_labels)
     #   results = estimator.predict(testing_samples)
     #
@@ -72,7 +72,7 @@ module Rumale
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      penalty: 'l2', reg_param: 1.0, l1_ratio: 0.5,
                      fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,
                              reg_param: reg_param, l1_ratio: l1_ratio, bias_scale: bias_scale,