rumale 0.19.0 → 0.20.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1cd1cdc16e6c72743d064db7d254c74eb98ca33e97cfdf9e8a76cc1fbe5dd29b
-  data.tar.gz: 2077cae2629f2c403cc0afc415dc4b4151a2eac2ab7a3230402bf761bb653829
+  metadata.gz: 0f361026cd2922a2d36846a817eee855bf0c000156ed6c756bca29d2e42d67a2
+  data.tar.gz: 016fa40aa2546824cacbc32353263cbfc9427f0ceabb7e703f99854914bb9a2e
 SHA512:
-  metadata.gz: 2bbcdce6d0a31c95500a81a7d4a55407786068fac65ce1e5ede1bc3f56d97b2ec93fd9ca1dc52fc1a24782dba469099b25d0398a5993716da011851f18f8179c
-  data.tar.gz: cc9fc19ea73dfa76e8ede18df7cb57f931cccdea2c546f414746ed681afbd272e3866913c75534bbdce6b275d057baa2c793b4046c8e46f697e30d5b87dba066
+  metadata.gz: 7a53a958db7ec8b56236018505370b9908ae81a9afc9d7c8ff0b16d83971539c1ad729b5ab350eb49ae9b90ada43a8912ed2404a37eef97a4d34dad90b1d3e9f
+  data.tar.gz: 2f2b3d48625c7120464179bc7759c01ba7de85cb0d54720665eaf1e4822f24c1870474ebc24a47cff123e44a8626b0e0fac6a7e81216c057286071770ea5ba79

data/.rubocop.yml

@@ -3,6 +3,7 @@ require:
   - rubocop-rspec
 
 AllCops:
+  NewCops: enable
   TargetRubyVersion: 2.5
   DisplayCopNames: true
   DisplayStyleGuide: true
@@ -15,25 +16,12 @@ AllCops:
 Style/Documentation:
   Enabled: false
 
-Style/HashEachMethods:
-  Enabled: true
-
-Style/HashTransformKeys:
-  Enabled: true
-
-Style/HashTransformValues:
-  Enabled: true
-
-Lint/RaiseException:
-  Enabled: true
-
-Lint/StructNewOverride:
-  Enabled: true
-
 Layout/LineLength:
   Max: 145
   IgnoredPatterns: ['(\A|\s)#']
 
+Lint/MissingSuper:
+  Enabled: false
 
 Metrics/ModuleLength:
   Max: 200
@@ -70,26 +58,14 @@ Naming/MethodParameterName:
 Naming/ConstantName:
   Enabled: false
 
-Style/ExponentialNotation:
-  Enabled: true
-
 Style/FormatStringToken:
   Enabled: false
 
 Style/NumericLiterals:
   Enabled: false
 
-Style/SlicingWithRange:
-  Enabled: true
-
-Layout/EmptyLineAfterGuardClause:
-  Enabled: true
-
-Layout/EmptyLinesAroundAttributeAccessor:
-  Enabled: true
-
-Layout/SpaceAroundMethodCallOperator:
-  Enabled: true
+Style/StringConcatenation:
+  Enabled: false
 
 RSpec/MultipleExpectations:
   Enabled: false

data/CHANGELOG.md

@@ -1,4 +1,32 @@
+# 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)
+- 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
+## 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/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'
@@ -70,6 +60,7 @@ 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 +83,10 @@ 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'
@@ -101,10 +95,13 @@ 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/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/cross_validation'
 require 'rumale/model_selection/grid_search_cv'

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
@@ -232,7 +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 }
@@ -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/k_means.rb

@@ -103,7 +103,7 @@ 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++'
 

data/lib/rumale/clustering/k_medoids.rb

@@ -124,7 +124,7 @@ 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

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

data/lib/rumale/dataset.rb

@@ -81,7 +81,7 @@ module Rumale
         y = Numo::Int32.hstack([Numo::Int32.zeros(n_samples_out), Numo::Int32.ones(n_samples_in)])
         # shuffle data indices.
         if shuffle
-          rand_ids = [*0...n_samples].shuffle(random: rng.dup)
+          rand_ids = Array(0...n_samples).shuffle(random: rng.dup)
           x = x[rand_ids, true].dup
           y = y[rand_ids].dup
         end
@@ -118,7 +118,7 @@ module Rumale
         y = Numo::Int32.hstack([Numo::Int32.zeros(n_samples_out), Numo::Int32.ones(n_samples_in)])
         # shuffle data indices.
         if shuffle
-          rand_ids = [*0...n_samples].shuffle(random: rng.dup)
+          rand_ids = Array(0...n_samples).shuffle(random: rng.dup)
           x = x[rand_ids, true].dup
           y = y[rand_ids].dup
         end
@@ -173,7 +173,7 @@ module Rumale
         end
         # shuffle data.
         if shuffle
-          rand_ids = [*0...n_samples].shuffle(random: rng.dup)
+          rand_ids = Array(0...n_samples).shuffle(random: rng.dup)
           x = x[rand_ids, true].dup
           y = y[rand_ids].dup
         end
@@ -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/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)