rumale 0.18.5 → 0.19.2

data/lib/rumale/probabilistic_output.rb

@@ -12,8 +12,8 @@ module Rumale
   #   probs = 1 / (Numo::NMath.exp(params[0] * df + params[1]) + 1)
   #
   # *Reference*
-  # 1. J C. Platt, "Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods," Adv. Large Margin Classifiers, pp. 61--74, 2000.
-  # 1. H-T Lin, C-J Lin, and R C.Weng, "A Note on Platt's Probabilistic Outputs for Support Vector Machines," J. Machine Learning, Vol. 63 (3), pp. 267--276, 2007.
+  # - Platt, J C., "Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods," Adv. Large Margin Classifiers, pp. 61--74, 2000.
+  # - Lin, H-T., Lin, C-J., and Weng, R C., "A Note on Platt's Probabilistic Outputs for Support Vector Machines," J. Machine Learning, Vol. 63 (3), pp. 267--276, 2007.
   module ProbabilisticOutput
     class << self
       # Fit the probabilistic model for binary SVM outputs.
@@ -47,6 +47,7 @@ module Rumale
           hess_mat = hessian_matrix(probs, df, sigma)
           break if grad_vec.abs.lt(1e-5).count == 2
           break if (old_grad_vec - grad_vec).abs.sum < 1e-5
+
           old_grad_vec = grad_vec
           # Calculate Newton directions.
           dirs_vec = directions(grad_vec, hess_mat)
@@ -58,6 +59,7 @@ module Rumale
             new_beta = beta + stepsize * dirs_vec[1]
             new_err = error_function(target_probs, df, new_alpha, new_beta)
             next unless new_err < err + 0.0001 * stepsize * grad_dir
+
             alpha = new_alpha
             beta = new_beta
             err = new_err

data/lib/rumale/tree/base_decision_tree.rb

@@ -53,6 +53,7 @@ module Rumale
         return node.leaf_id if node.leaf
         return apply_at_node(node.left, sample) if node.right.nil?
         return apply_at_node(node.right, sample) if node.left.nil?
+
         if sample[node.feature_id] <= node.threshold
           apply_at_node(node.left, sample)
         else
@@ -138,6 +139,7 @@ module Rumale
       def eval_importance_at_node(node)
         return nil if node.leaf
         return nil if node.left.nil? || node.right.nil?
+
         gain = node.n_samples * node.impurity -
                node.left.n_samples * node.left.impurity -
                node.right.n_samples * node.right.impurity

data/lib/rumale/tree/decision_tree_classifier.rb

@@ -110,6 +110,7 @@ module Rumale
         return node.probs if node.leaf
         return predict_proba_at_node(node.left, sample) if node.right.nil?
         return predict_proba_at_node(node.right, sample) if node.left.nil?
+
         if sample[node.feature_id] <= node.threshold
           predict_proba_at_node(node.left, sample)
         else

data/lib/rumale/tree/extra_tree_classifier.rb

@@ -14,7 +14,7 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - P. Geurts, D. Ernst, and L. Wehenkel, "Extremely randomized trees," Machine Learning, vol. 63 (1), pp. 3--42, 2006.
+    # - Geurts, P., Ernst, D., and Wehenkel, L., "Extremely randomized trees," Machine Learning, vol. 63 (1), pp. 3--42, 2006.
     class ExtraTreeClassifier < DecisionTreeClassifier
       # Return the class labels.
       # @return [Numo::Int32] (size: n_classes)

data/lib/rumale/tree/extra_tree_regressor.rb

@@ -14,7 +14,7 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - P. Geurts, D. Ernst, and L. Wehenkel, "Extremely randomized trees," Machine Learning, vol. 63 (1), pp. 3--42, 2006.
+    # - Geurts, P., Ernst, D., and Wehenkel, L., "Extremely randomized trees," Machine Learning, vol. 63 (1), pp. 3--42, 2006.
     class ExtraTreeRegressor < DecisionTreeRegressor
       # Return the importance for each feature.
       # @return [Numo::DFloat] (size: n_features)

data/lib/rumale/tree/gradient_tree_regressor.rb

@@ -10,11 +10,10 @@ module Rumale
     # GradientTreeRegressor is a class that implements decision tree for regression with exact gredy algorithm.
     # This class is used internally for estimators with gradient tree boosting.
     #
-    # *reference*
-    # - J H. Friedman, "Greedy Function Approximation: A Gradient Boosting Machine," Annals of Statistics, 29 (5), pp. 1189--1232, 2001.
-    # - J H. Friedman, "Stochastic Gradient Boosting," Computational Statistics and Data Analysis, 38 (4), pp. 367--378, 2002.
-    # - T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System,"  Proc. KDD'16, pp. 785--794, 2016.
-    #
+    # *Reference*
+    # - Friedman, J H., "Greedy Function Approximation: A Gradient Boosting Machine," Annals of Statistics, 29 (5), pp. 1189--1232, 2001.
+    # - Friedman, J H., "Stochastic Gradient Boosting," Computational Statistics and Data Analysis, 38 (4), pp. 367--378, 2002.
+    # - Chen, T., and Guestrin, C., "XGBoost: A Scalable Tree Boosting System,"  Proc. KDD'16, pp. 785--794, 2016.
     class GradientTreeRegressor
       include Base::BaseEstimator
       include Base::Regressor
@@ -124,6 +123,7 @@ module Rumale
         return node.leaf_id if node.leaf
         return apply_at_node(node.left, sample) if node.right.nil?
         return apply_at_node(node.right, sample) if node.left.nil?
+
         if sample[node.feature_id] <= node.threshold
           apply_at_node(node.left, sample)
         else

data/lib/rumale/utils.rb

@@ -13,6 +13,7 @@ module Rumale
         chosen = 0
         probs.each_with_index do |p, idx|
           break (chosen = idx) if target <= p
+
           target -= p
         end
         chosen

data/lib/rumale/validation.rb

@@ -9,6 +9,7 @@ module Rumale
     def check_convert_sample_array(x)
       x = Numo::DFloat.cast(x) unless x.is_a?(Numo::DFloat)
       raise ArgumentError, 'Expect sample matrix to be 2-D array' unless x.ndim == 2
+
       x
     end
 
@@ -16,6 +17,7 @@ module Rumale
     def check_convert_label_array(y)
       y = Numo::Int32.cast(y) unless y.is_a?(Numo::Int32)
       raise ArgumentError, 'Expect label vector to be 1-D arrray' unless y.ndim == 1
+
       y
     end
 
@@ -29,6 +31,7 @@ module Rumale
     def check_sample_array(x)
       raise TypeError, 'Expect class of sample matrix to be Numo::DFloat' unless x.is_a?(Numo::DFloat)
       raise ArgumentError, 'Expect sample matrix to be 2-D array' unless x.ndim == 2
+
       nil
     end
 
@@ -36,24 +39,28 @@ module Rumale
     def check_label_array(y)
       raise TypeError, 'Expect class of label vector to be Numo::Int32' unless y.is_a?(Numo::Int32)
       raise ArgumentError, 'Expect label vector to be 1-D arrray' unless y.ndim == 1
+
       nil
     end
 
     # @!visibility private
     def check_tvalue_array(y)
       raise TypeError, 'Expect class of target value vector to be Numo::DFloat' unless y.is_a?(Numo::DFloat)
+
       nil
     end
 
     # @!visibility private
     def check_sample_label_size(x, y)
       raise ArgumentError, 'Expect to have the same number of samples for sample matrix and label vector' unless x.shape[0] == y.shape[0]
+
       nil
     end
 
     # @!visibility private
     def check_sample_tvalue_size(x, y)
       raise ArgumentError, 'Expect to have the same number of samples for sample matrix and target value vector' unless x.shape[0] == y.shape[0]
+
       nil
     end
 

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 = '0.18.5'
+  VERSION = '0.19.2'
 end

data/rumale.gemspec

@@ -16,7 +16,7 @@ Gem::Specification.new do |spec|
     Rumale is a machine learning library in Ruby.
     Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python.
     Rumale supports Support Vector Machine,
-    Logistic Regression, Ridge, Lasso, Factorization Machine,
+    Logistic Regression, Ridge, Lasso,
     Multi-layer Perceptron,
     Naive Bayes, Decision Tree, Gradient Tree Boosting, Random Forest,
     K-Means, Gaussian Mixture Model, DBSCAN, Spectral Clustering,
@@ -44,17 +44,5 @@ Gem::Specification.new do |spec|
     'bug_tracker_uri' => 'https://github.com/yoshoku/rumale/issues'
   }
 
-  spec.required_ruby_version = '>= 2.3'
-
   spec.add_runtime_dependency 'numo-narray', '>= 0.9.1'
-  spec.add_runtime_dependency 'mopti', '~> 0.1'
-  spec.add_runtime_dependency 'mmh3', '~> 0.1'
-
-  spec.add_development_dependency 'bundler', '~> 2.0'
-  spec.add_development_dependency 'coveralls', '~> 0.8'
-  spec.add_development_dependency 'numo-linalg', '>= 0.1.4'
-  spec.add_development_dependency 'parallel', '>= 1.17.0'
-  spec.add_development_dependency 'rake', '~> 12.0'
-  spec.add_development_dependency 'rake-compiler', '~> 1.0'
-  spec.add_development_dependency 'rspec', '~> 3.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rumale
 version: !ruby/object:Gem::Version
-  version: 0.18.5
+  version: 0.19.2
 platform: ruby
 authors:
 - yoshoku
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-04-18 00:00:00.000000000 Z
+date: 2020-06-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -24,137 +24,11 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 0.9.1
-- !ruby/object:Gem::Dependency
-  name: mopti
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.1'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.1'
-- !ruby/object:Gem::Dependency
-  name: mmh3
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.1'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.1'
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.0'
-- !ruby/object:Gem::Dependency
-  name: coveralls
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.8'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.8'
-- !ruby/object:Gem::Dependency
-  name: numo-linalg
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 0.1.4
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 0.1.4
-- !ruby/object:Gem::Dependency
-  name: parallel
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.17.0
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.17.0
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '12.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '12.0'
-- !ruby/object:Gem::Dependency
-  name: rake-compiler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
-- !ruby/object:Gem::Dependency
-  name: rspec
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.0'
 description: |
   Rumale is a machine learning library in Ruby.
   Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python.
   Rumale supports Support Vector Machine,
-  Logistic Regression, Ridge, Lasso, Factorization Machine,
+  Logistic Regression, Ridge, Lasso,
   Multi-layer Perceptron,
   Naive Bayes, Decision Tree, Gradient Tree Boosting, Random Forest,
   K-Means, Gaussian Mixture Model, DBSCAN, Spectral Clustering,
@@ -198,6 +72,7 @@ files:
 - lib/rumale/clustering/hdbscan.rb
 - lib/rumale/clustering/k_means.rb
 - lib/rumale/clustering/k_medoids.rb
+- lib/rumale/clustering/mini_batch_k_means.rb
 - lib/rumale/clustering/power_iteration.rb
 - lib/rumale/clustering/single_linkage.rb
 - lib/rumale/clustering/snn.rb
@@ -238,6 +113,7 @@ files:
 - lib/rumale/evaluation_measure/silhouette_score.rb
 - lib/rumale/feature_extraction/feature_hasher.rb
 - lib/rumale/feature_extraction/hash_vectorizer.rb
+- lib/rumale/feature_extraction/tfidf_transformer.rb
 - lib/rumale/kernel_approximation/nystroem.rb
 - lib/rumale/kernel_approximation/rbf.rb
 - lib/rumale/kernel_machine/kernel_fda.rb
@@ -291,6 +167,7 @@ files:
 - lib/rumale/polynomial_model/factorization_machine_classifier.rb
 - lib/rumale/polynomial_model/factorization_machine_regressor.rb
 - lib/rumale/preprocessing/bin_discretizer.rb
+- lib/rumale/preprocessing/l1_normalizer.rb
 - lib/rumale/preprocessing/l2_normalizer.rb
 - lib/rumale/preprocessing/label_binarizer.rb
 - lib/rumale/preprocessing/label_encoder.rb
@@ -322,7 +199,7 @@ 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: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -330,7 +207,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.3'
+      version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
@@ -338,7 +215,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubygems_version: 3.1.2
-signing_key: 
+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.