rumale 0.18.6 → 0.19.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 40d5504cf4463721f53a4202ed99ec3f015c571fbadf3a4a4c7e0ac6eb00c7a7
-  data.tar.gz: fae3bebad1e88aa166d9279e5f5a2de4ebbad5f79fd416fef68d33d4f66ba2c6
+  metadata.gz: dc3413c05ad7c365117adc4abbc304ff1851fa9a3ff69fef3c69e730d9a2b834
+  data.tar.gz: 8895cce8b350c4e245aabb5e3e4c4036655fa8d24a72f6481e0d2f8c9869fa54
 SHA512:
-  metadata.gz: b9d32bc9bd5c5f37d27b06fcaa554c28f9a209debaaac4024c1c2a1f6fb367484ce760168f62a2d9e1ee24d9372ad9cccd1d36e7280f202734e5330105a995fa
-  data.tar.gz: c18470cb533df4f6315324942afc98b5c52f4b7f6246078f459987a3407b79ae60a42599f40bc6236d5adba3dc85799a091e0d7ae5e9a1a3fd9fc626206cbef2
+  metadata.gz: fe10c975f286a4c9ac155d29310d61d1f180cbcc909ec7bdba3925973b6b9857635befc9bf4938cf28a6ef50c8011894b7b15768735f6200c27ce912907e5fb1
+  data.tar.gz: 327cce25145c1ca3f5623f84b4163560bdbee8245009c3d8e1c3318f61dec94b58a7395ebc3538e7b04a9702af08b077e7f426c54f7c5d4fd3b0fcf11c4744cf

data/.rubocop.yml

@@ -3,7 +3,7 @@ require:
   - rubocop-rspec
 
 AllCops:
-  TargetRubyVersion: 2.3
+  TargetRubyVersion: 2.5
   DisplayCopNames: true
   DisplayStyleGuide: true
   Exclude:
@@ -24,6 +24,15 @@ Style/HashTransformKeys:
 Style/HashTransformValues:
   Enabled: true
 
+Lint/DeprecatedOpenSSLConstant:
+  Enabled: true
+
+Lint/DuplicateElsifCondition:
+  Enabled: true
+
+Lint/MixedRegexpCaptureTypes:
+  Enabled: true
+
 Lint/RaiseException:
   Enabled: true
 
@@ -34,7 +43,6 @@ Layout/LineLength:
   Max: 145
   IgnoredPatterns: ['(\A|\s)#']
 
-
 Metrics/ModuleLength:
   Max: 200
 
@@ -70,14 +78,83 @@ 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: false
+  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
 
 RSpec/MultipleExpectations:
   Enabled: false

data/CHANGELOG.md

@@ -1,3 +1,48 @@
+# 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)
+- Refactor some codes with Rubocop.
+
+# 0.19.2
+- Fix L2Normalizer to avoid zero divide.
+- Add preprocssing class for [L1Normalizer](https://yoshoku.github.io/rumale/doc/Rumale/Preprocessing/L1Normalizer.html).
+- Add transformer class for [TfidfTransformer](https://yoshoku.github.io/rumale/doc/Rumale/FeatureExtraction/TfidfTransformer.html).
+
+# 0.19.1
+- Add cluster analysis class for [mini-batch K-Means](https://yoshoku.github.io/rumale/doc/Rumale/Clustering/MiniBatchKMeans.html).
+- Fix some typos.
+
+# 0.19.0
+- 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.
+    ```ruby
+    require 'mmh3'
+    require 'rumale'
+
+    encoder = Rumale::FeatureExtraction::FeatureHasher.new
+    ```
+  - The mopti gem is used in [NeighbourhoodComponentAnalysis](https://yoshoku.github.io/rumale/doc/Rumale/MetricLearning/NeighbourhoodComponentAnalysis.html).
+  You only need to require mopti gem when using NeighbourhoodComponentAnalysis.
+    ```ruby
+    require 'mopti'
+    require 'rumale'
+
+    transformer = Rumale::MetricLearning::NeighbourhoodComponentAnalysis.new
+    ```
+- Change the default value of solver parameter on [PCA](https://yoshoku.github.io/rumale/doc/Rumale/Decomposition/PCA.html) to 'auto'.
+If Numo::Linalg is loaded, 'evd' is selected for the solver, otherwise 'fpt' is selected.
+- Deprecate [PolynomialModel](https://yoshoku.github.io/rumale/doc/Rumale/PolynomialModel.html), [Optimizer](https://yoshoku.github.io/rumale/doc/Rumale/Optimizer.html), and the estimators contained in them. They will be deleted in version 0.20.0.
+  - Many machine learning libraries do not contain factorization machine algorithms, they are provided by another compatible library.
+  In addition, there are no plans to implement estimators in PolynomialModel.
+  Thus, the author decided to deprecate PolynomialModel.
+  - Currently, the Optimizer classes are only used by PolynomialModel estimators.
+  Therefore, they have been deprecated together with PolynomialModel.
+
+# 0.18.7
+- Fix to convert target_name to string array in [classification_report method](https://yoshoku.github.io/rumale/doc/Rumale/EvaluationMeasure.html#classification_report-class_method).
+- Refactor some codes with Rubocop.
+
 # 0.18.6
 - Fix some configuration files.
 - Update API documentation.

data/Gemfile

@@ -4,6 +4,8 @@ source 'https://rubygems.org'
 gemspec
 
 gem 'coveralls', '~> 0.8'
+gem 'mmh3', '>= 1.0'
+gem 'mopti', '>= 0.1.0'
 gem 'numo-linalg', '>= 0.1.4'
 gem 'parallel', '>= 1.17.0'
 gem 'rake', '~> 12.0'

data/README.md

@@ -11,7 +11,7 @@
 Rumale (**Ru**by **ma**chine **le**arning) 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,
@@ -42,39 +42,7 @@ Or install it yourself as:
 
 ## Usage
 
-### Example 1. XOR data
-First, let's classify simple xor data.
-
-```ruby
-require 'rumale'
-
-# Prepare XOR data.
-samples = [[0, 0], [0, 1], [1, 0], [1, 1]]
-labels = [0, 1, 1, 0]
-
-# Train classifier with nearest neighbor rule.
-estimator = Rumale::NearestNeighbors::KNeighborsClassifier.new(n_neighbors: 1)
-estimator.fit(samples, labels)
-
-# Predict labels.
-p labels
-p estimator.predict(samples)
-```
-
-Execution of the above script result in the following.
-
-```ruby
-[0, 1, 1, 0]
-Numo::Int32#shape=[4]
-[0, 1, 1, 0]
-```
-
-The basic usage of Rumale is to first train the model with the fit method
-and then estimate with the predict method.
-In addition, Rumale recommends using arrays such as feature vectors and labels with
-[Numo::NArray](https://github.com/ruby-numo/numo-narray).
-
-### Example 2. Pendigits dataset classification
+### Example 1. Pendigits dataset classification
 
 Rumale provides function loading libsvm format dataset file.
 We start by downloading the pendigits dataset from LIBSVM Data web site.
@@ -137,7 +105,7 @@ $ ruby test.rb
 Accuracy: 98.7%
 ```
 
-### Example 3. Cross-validation
+### Example 2. Cross-validation
 
 ```ruby
 require 'rumale'
@@ -168,7 +136,7 @@ $ ruby cross_validation.rb
 5-CV mean log-loss: 0.355
 ```
 
-### Example 4. Pipeline
+### Example 3. Pipeline
 
 ```ruby
 require 'rumale'
@@ -203,6 +171,7 @@ $ ruby pipeline.rb
 ## Speed up
 
 ### Numo::Linalg
+Rumale uses [Numo::NArray](https://github.com/ruby-numo/numo-narray) for typed arrays.
 Loading the [Numo::Linalg](https://github.com/ruby-numo/numo-linalg) allows to perform matrix product of Numo::NArray using BLAS libraries.
 For example, using the [OpenBLAS](https://github.com/xianyi/OpenBLAS) speeds up many estimators in Rumale.
 

data/lib/rumale.rb

@@ -70,6 +70,7 @@ require 'rumale/ensemble/random_forest_regressor'
 require 'rumale/ensemble/extra_trees_classifier'
 require 'rumale/ensemble/extra_trees_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'
@@ -92,7 +93,10 @@ 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'
@@ -101,6 +105,7 @@ 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/model_selection/k_fold'
 require 'rumale/model_selection/stratified_k_fold'

data/lib/rumale/base/base_estimator.rb

@@ -25,6 +25,7 @@ module Rumale
 
       def enable_parallel?
         return false if @params[:n_jobs].nil?
+
         if defined?(Parallel).nil?
           warn('If you want to use parallel option, you should install and load Parallel in advance.')
           return false
@@ -34,6 +35,7 @@ module Rumale
 
       def n_processes
         return 1 unless enable_parallel?
+
         @params[:n_jobs] <= 0 ? Parallel.processor_count : @params[:n_jobs]
       end
 

data/lib/rumale/clustering/dbscan.rb

@@ -54,6 +54,7 @@ module Rumale
       def fit(x, _y = nil)
         x = check_convert_sample_array(x)
         raise ArgumentError, 'Expect the input distance matrix to be square.' if @params[:metric] == 'precomputed' && x.shape[0] != x.shape[1]
+
         partial_fit(x)
         self
       end
@@ -66,6 +67,7 @@ module Rumale
       def fit_predict(x)
         x = check_convert_sample_array(x)
         raise ArgumentError, 'Expect the input distance matrix to be square.' if @params[:metric] == 'precomputed' && x.shape[0] != x.shape[1]
+
         partial_fit(x)
         labels
       end
@@ -80,6 +82,7 @@ module Rumale
         @labels = Numo::Int32.zeros(n_samples) - 2
         n_samples.times do |query_id|
           next if @labels[query_id] >= -1
+
           cluster_id += 1 if expand_cluster(metric_mat, query_id, cluster_id)
         end
         @core_sample_ids = Numo::Int32[*@core_sample_ids.flatten]
@@ -102,6 +105,7 @@ module Rumale
           while (m = target_ids.shift)
             neighbor_ids = region_query(metric_mat[m, true])
             next if neighbor_ids.size < @params[:min_samples]
+
             neighbor_ids.each do |n|
               target_ids.push(n) if @labels[n] < -1
               @labels[n] = cluster_id if @labels[n] <= -1

data/lib/rumale/clustering/gaussian_mixture.rb

@@ -86,6 +86,7 @@ module Rumale
           new_memberships = calc_memberships(x, @weights, @means, @covariances, @params[:covariance_type])
           error = (memberships - new_memberships).abs.max
           break if error <= @params[:tol]
+
           memberships = new_memberships.dup
         end
         self
@@ -209,6 +210,7 @@ module Rumale
 
       def check_enable_linalg(method_name)
         return unless @params[:covariance_type] == 'full' && !enable_linalg?
+
         raise "GaussianMixture##{method_name} requires Numo::Linalg when covariance_type is 'full' but that is not loaded."
       end
     end

data/lib/rumale/clustering/hdbscan.rb

@@ -55,6 +55,7 @@ module Rumale
       def fit(x, _y = nil)
         x = check_convert_sample_array(x)
         raise ArgumentError, 'Expect the input distance matrix to be square.' if @params[:metric] == 'precomputed' && x.shape[0] != x.shape[1]
+
         fit_predict(x)
         self
       end
@@ -67,6 +68,7 @@ module Rumale
       def fit_predict(x)
         x = check_convert_sample_array(x)
         raise ArgumentError, 'Expect the input distance matrix to be square.' if @params[:metric] == 'precomputed' && x.shape[0] != x.shape[1]
+
         distance_mat = @params[:metric] == 'precomputed' ? x : Rumale::PairwiseMetric.euclidean_distance(x)
         @labels = partial_fit(distance_mat)
       end
@@ -230,7 +232,7 @@ module Rumale
       end
 
       def flatten(tree, stabilities)
-        node_ids = stabilities.keys.sort { |a, b| b <=> a }.slice(0, stabilities.size - 1)
+        node_ids = stabilities.keys.sort.reverse.slice(0, stabilities.size - 1)
 
         cluster_tree = tree.select { |edge| edge.n_elements > 1 }
         is_cluster = node_ids.each_with_object({}) { |n_id, h| h[n_id] = true }

data/lib/rumale/clustering/k_means.rb

@@ -103,9 +103,10 @@ module Rumale
         # random initialize
         n_samples = x.shape[0]
         sub_rng = @rng.dup
-        rand_id = [*0...n_samples].sample(@params[:n_clusters], random: sub_rng)
+        rand_id = Array(0...n_samples).sample(@params[:n_clusters], random: sub_rng)
         @cluster_centers = x[rand_id, true].dup
         return unless @params[:init] == 'k-means++'
+
         # k-means++ initialize
         (1...@params[:n_clusters]).each do |n|
           distance_matrix = PairwiseMetric.euclidean_distance(x, @cluster_centers[0...n, true])

data/lib/rumale/clustering/k_medoids.rb

@@ -64,6 +64,7 @@ module Rumale
       def fit(x, _not_used = nil)
         x = check_convert_sample_array(x)
         raise ArgumentError, 'Expect the input distance matrix to be square.' if @params[:metric] == 'precomputed' && x.shape[0] != x.shape[1]
+
         # initialize some varibales.
         distance_mat = @params[:metric] == 'precomputed' ? x : Rumale::PairwiseMetric.euclidean_distance(x)
         init_cluster_centers(distance_mat)
@@ -76,6 +77,7 @@ module Rumale
           end
           new_error = distance_mat[true, @medoid_ids].mean
           break if (error - new_error).abs <= @params[:tol]
+
           error = new_error
         end
         @cluster_centers = x[@medoid_ids, true].dup if @params[:metric] == 'euclidean'
@@ -93,6 +95,7 @@ module Rumale
         if @params[:metric] == 'precomputed' && distance_mat.shape[1] != @medoid_ids.size
           raise ArgumentError, 'Expect the size input matrix to be n_samples-by-n_clusters.'
         end
+
         assign_cluster(distance_mat)
       end
 
@@ -121,8 +124,9 @@ module Rumale
         # random initialize
         n_samples = distance_mat.shape[0]
         sub_rng = @rng.dup
-        @medoid_ids = Numo::Int32.asarray([*0...n_samples].sample(@params[:n_clusters], random: sub_rng))
+        @medoid_ids = Numo::Int32.asarray(Array(0...n_samples).sample(@params[:n_clusters], random: sub_rng))
         return unless @params[:init] == 'k-means++'
+
         # k-means++ initialize
         (1...@params[:n_clusters]).each do |n|
           distances = distance_mat[true, @medoid_ids[0...n]]

data/lib/rumale/clustering/mini_batch_k_means.rb

@@ -0,0 +1,139 @@
+# frozen_string_literal: true
+
+require 'rumale/base/base_estimator'
+require 'rumale/base/cluster_analyzer'
+require 'rumale/pairwise_metric'
+
+module Rumale
+  module Clustering
+    # MniBatchKMeans is a class that implements K-Means cluster analysis
+    # with mini-batch stochastic gradient descent (SGD).
+    #
+    # @example
+    #   analyzer = Rumale::Clustering::MiniBatchKMeans.new(n_clusters: 10, max_iter: 50, batch_size: 50, random_seed: 1)
+    #   cluster_labels = analyzer.fit_predict(samples)
+    #
+    # *Reference*
+    # - Sculley, D., "Web-scale k-means clustering," Proc. WWW'10, pp. 1177--1178, 2010.
+    class MiniBatchKMeans
+      include Base::BaseEstimator
+      include Base::ClusterAnalyzer
+
+      # Return the centroids.
+      # @return [Numo::DFloat] (shape: [n_clusters, n_features])
+      attr_reader :cluster_centers
+
+      # Return the random generator.
+      # @return [Random]
+      attr_reader :rng
+
+      # Create a new cluster analyzer with K-Means method with mini-batch SGD.
+      #
+      # @param n_clusters [Integer] The number of clusters.
+      # @param init [String] The initialization method for centroids ('random' or 'k-means++').
+      # @param max_iter [Integer] The maximum number of iterations.
+      # @param batch_size [Integer] The size of the mini batches.
+      # @param tol [Float] The tolerance of termination criterion.
+      # @param random_seed [Integer] The seed value using to initialize the random generator.
+      def initialize(n_clusters: 8, init: 'k-means++', max_iter: 100, batch_size: 100, tol: 1.0e-4, random_seed: nil)
+        check_params_numeric(n_clusters: n_clusters, max_iter: max_iter, batch_size: batch_size, tol: tol)
+        check_params_string(init: init)
+        check_params_numeric_or_nil(random_seed: random_seed)
+        check_params_positive(n_clusters: n_clusters, max_iter: max_iter)
+        @params = {}
+        @params[:n_clusters] = n_clusters
+        @params[:init] = init == 'random' ? 'random' : 'k-means++'
+        @params[:max_iter] = max_iter
+        @params[:batch_size] = batch_size
+        @params[:tol] = tol
+        @params[:random_seed] = random_seed
+        @params[:random_seed] ||= srand
+        @cluster_centers = nil
+        @rng = Random.new(@params[:random_seed])
+      end
+
+      # Analysis clusters with given training data.
+      #
+      # @overload fit(x) -> MiniBatchKMeans
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for cluster analysis.
+      # @return [KMeans] The learned cluster analyzer itself.
+      def fit(x, _y = nil)
+        x = check_convert_sample_array(x)
+        # initialization.
+        n_samples = x.shape[0]
+        update_counter = Numo::Int32.zeros(@params[:n_clusters])
+        sub_rng = @rng.dup
+        init_cluster_centers(x, sub_rng)
+        # optimization with mini-batch sgd.
+        @params[:max_iter].times do |_t|
+          sample_ids = Array(0...n_samples).shuffle(random: sub_rng)
+          old_centers = @cluster_centers.dup
+          until (subset_ids = sample_ids.shift(@params[:batch_size])).empty?
+            # sub sampling
+            sub_x = x[subset_ids, true]
+            # assign nearest centroids
+            cluster_labels = assign_cluster(sub_x)
+            # update centroids
+            @params[:n_clusters].times do |c|
+              assigned_bits = cluster_labels.eq(c)
+              next unless assigned_bits.count.positive?
+
+              update_counter[c] += 1
+              learning_rate = 1.fdiv(update_counter[c])
+              update = sub_x[assigned_bits.where, true].mean(axis: 0)
+              @cluster_centers[c, true] = (1 - learning_rate) * @cluster_centers[c, true] + learning_rate * update
+            end
+          end
+          error = Numo::NMath.sqrt(((old_centers - @cluster_centers)**2).sum(axis: 1)).mean
+          break if error <= @params[:tol]
+        end
+        self
+      end
+
+      # Predict cluster labels for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the cluster label.
+      # @return [Numo::Int32] (shape: [n_samples]) Predicted cluster label per sample.
+      def predict(x)
+        x = check_convert_sample_array(x)
+        assign_cluster(x)
+      end
+
+      # Analysis clusters and assign samples to clusters.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for cluster analysis.
+      # @return [Numo::Int32] (shape: [n_samples]) Predicted cluster label per sample.
+      def fit_predict(x)
+        x = check_convert_sample_array(x)
+        fit(x)
+        predict(x)
+      end
+
+      private
+
+      def assign_cluster(x)
+        distance_matrix = PairwiseMetric.euclidean_distance(x, @cluster_centers)
+        distance_matrix.min_index(axis: 1) - Numo::Int32[*0.step(distance_matrix.size - 1, @cluster_centers.shape[0])]
+      end
+
+      def init_cluster_centers(x, sub_rng)
+        # random initialize
+        n_samples = x.shape[0]
+        rand_id = Array(0...n_samples).sample(@params[:n_clusters], random: sub_rng)
+        @cluster_centers = x[rand_id, true].dup
+        return unless @params[:init] == 'k-means++'
+
+        # k-means++ initialize
+        (1...@params[:n_clusters]).each do |n|
+          distance_matrix = PairwiseMetric.euclidean_distance(x, @cluster_centers[0...n, true])
+          min_distances = distance_matrix.flatten[distance_matrix.min_index(axis: 1)]
+          probs = min_distances**2 / (min_distances**2).sum
+          cum_probs = probs.cumsum
+          selected_id = cum_probs.gt(sub_rng.rand).where.to_a.first
+          @cluster_centers[n, true] = x[selected_id, true].dup
+        end
+      end
+    end
+  end
+end