rumale 0.19.1 → 0.20.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f49170105721cfebcae9f1a424e9a858650d78225541a8cb63b0ad4c70734988
-  data.tar.gz: ecc35086328eee1066252e75b8cd638256039e93beebc0bce5714493fe72570b
+  metadata.gz: 5d8c93acbf38fbd07e5df224010abbdd4269a6ce3bbf8112a0eba652a606785d
+  data.tar.gz: e7cb00a802420854835c92f011425f3054bfcc1052bf7b3664da1f95834ef435
 SHA512:
-  metadata.gz: 68f432bb34ff6c8e467a91d7c7e3aa07e816c2dd8807defc9e4e82e7a720c925062dbd27c8a7ec3294ecef2d71041baead2510edaf03a1eee210dc811eede22d
-  data.tar.gz: 5854eacc12de6c3cdcdbab0f9b4e73fc64d1be0533732348da6b4d6dcb0be9f115e2415501b05148fd021fa844ac0c25adc1bb858432a02ca6fe19d30a3538c7
+  metadata.gz: f95fdd89b84dad02e516ee0479b1cddfb101cb96de897b6e7fa3fba546272a243cff5cfe954cb51942ec1ab23cf3028b183db86b52fab00a35d15be7eee5bf92
+  data.tar.gz: e5f6235e88dd47b9002a2154cabd2c1e64afb6cbb5b0745b411c7e5559351e925c9db8ec332724e301b83215662b3582e79a9e997f0338846514b234dabf1fc3

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

@@ -1,8 +1,36 @@
+# 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)
+- 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'
@@ -93,7 +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'
@@ -102,11 +95,15 @@ 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/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
@@ -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

@@ -67,7 +67,7 @@ module Rumale
         init_cluster_centers(x, sub_rng)
         # optimization with mini-batch sgd.
         @params[:max_iter].times do |_t|
-          sample_ids = [*0...n_samples].shuffle(random: sub_rng)
+          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
@@ -120,7 +120,7 @@ module Rumale
       def init_cluster_centers(x, sub_rng)
         # random initialize
         n_samples = x.shape[0]
-        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/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)

data/lib/rumale/feature_extraction/tfidf_transformer.rb

@@ -0,0 +1,113 @@
+# frozen_string_literal: true
+
+require 'rumale/base/base_estimator'
+require 'rumale/base/transformer'
+require 'rumale/preprocessing/l1_normalizer'
+require 'rumale/preprocessing/l2_normalizer'
+
+module Rumale
+  module FeatureExtraction
+    # Transform sample matrix with term frequecy (tf) to a normalized tf-idf (inverse document frequency) reprensentation.
+    #
+    # @example
+    #   encoder = Rumale::FeatureExtraction::HashVectorizer.new
+    #   x = encoder.fit_transform([
+    #     { foo: 1, bar: 2 },
+    #     { foo: 3, baz: 1 }
+    #   ])
+    #
+    #   # > pp x
+    #   # Numo::DFloat#shape=[2,3]
+    #   # [[2, 0, 1],
+    #   #  [0, 1, 3]]
+    #
+    #   transformer = Rumale::FeatureExtraction::TfidfTransformer.new
+    #   x_tfidf = transformer.fit_transform(x)
+    #
+    #   # > pp x_tfidf
+    #   # Numo::DFloat#shape=[2,3]
+    #   # [[0.959056, 0, 0.283217],
+    #   #  [0, 0.491506, 0.870874]]
+    #
+    # *Reference*
+    # - Manning, C D., Raghavan, P., and Schutze, H., "Introduction to Information Retrieval," Cambridge University Press., 2008.
+    class TfidfTransformer
+      include Base::BaseEstimator
+      include Base::Transformer
+
+      # Return the vector consists of inverse document frequency.
+      # @return [Numo::DFloat] (shape: [n_features])
+      attr_reader :idf
+
+      # Create a new transfomer for converting tf vectors to tf-idf vectors.
+      #
+      # @param norm [String] The normalization method to be used ('l1', 'l2' and 'none').
+      # @param use_idf [Boolean] The flag indicating whether to use inverse document frequency weighting.
+      # @param smooth_idf [Boolean] The flag indicating whether to apply idf smoothing by log((n_samples + 1) / (df + 1)) + 1.
+      # @param sublinear_tf [Boolean] The flag indicating whether to perform subliner tf scaling by 1 + log(tf).
+      def initialize(norm: 'l2', use_idf: true, smooth_idf: false, sublinear_tf: false)
+        check_params_string(norm: norm)
+        check_params_boolean(use_idf: use_idf, smooth_idf: smooth_idf, sublinear_tf: sublinear_tf)
+        @params = {}
+        @params[:norm] = norm
+        @params[:use_idf] = use_idf
+        @params[:smooth_idf] = smooth_idf
+        @params[:sublinear_tf] = sublinear_tf
+        @idf = nil
+      end
+
+      # Calculate the inverse document frequency for weighting.
+      #
+      # @overload fit(x) -> TfidfTransformer
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate the idf values.
+      # @return [TfidfTransformer]
+      def fit(x, _y = nil)
+        return self unless @params[:use_idf]
+
+        x = check_convert_sample_array(x)
+
+        n_samples = x.shape[0]
+        df = x.class.cast(x.gt(0.0).count(0))
+
+        if @params[:smooth_idf]
+          df += 1
+          n_samples += 1
+        end
+
+        @idf = Numo::NMath.log(n_samples / df) + 1
+
+        self
+      end
+
+      # Calculate the idf values, and then transfrom samples to the tf-idf representation.
+      #
+      # @overload fit_transform(x) -> Numo::DFloat
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate idf and be transformed to tf-idf representation.
+      # @return [Numo::DFloat] The transformed samples.
+      def fit_transform(x, _y = nil)
+        fit(x).transform(x)
+      end
+
+      # Perform transforming the given samples to the tf-idf representation.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to be transformed.
+      # @return [Numo::DFloat] The transformed samples.
+      def transform(x)
+        x = check_convert_sample_array(x)
+        z = x.dup
+
+        z[z.ne(0)] = Numo::NMath.log(z[z.ne(0)]) + 1 if @params[:sublinear_tf]
+        z *= @idf if @params[:use_idf]
+        case @params[:norm]
+        when 'l2'
+          z = Rumale::Preprocessing::L2Normalizer.new.fit_transform(z)
+        when 'l1'
+          z = Rumale::Preprocessing::L1Normalizer.new.fit_transform(z)
+        end
+        z
+      end
+    end
+  end
+end

data/lib/rumale/kernel_approximation/nystroem.rb

@@ -69,7 +69,7 @@ module Rumale
         n_components = [1, [@params[:n_components], n_samples].min].max
 
         # random sampling.
-        @component_indices = Numo::Int32.cast([*0...n_samples].shuffle(random: sub_rng)[0...n_components])
+        @component_indices = Numo::Int32.cast(Array(0...n_samples).shuffle(random: sub_rng)[0...n_components])
         @components = x[@component_indices, true]
 
         # calculate normalizing factor.