rumale 0.18.5 → 0.19.2

data/lib/rumale/evaluation_measure/silhouette_score.rb

@@ -12,7 +12,7 @@ module Rumale
     #   puts evaluator.score(x, predicted)
     #
     # *Reference*
-    # - P J. Rousseuw, "Silhouettes: A graphical aid to the interpretation and validation of cluster analysis," Journal of Computational and Applied Mathematics, Vol. 20, pp. 53--65, 1987.
+    # - Rousseuw, P J., "Silhouettes: A graphical aid to the interpretation and validation of cluster analysis," Journal of Computational and Applied Mathematics, Vol. 20, pp. 53--65, 1987.
     class SilhouetteScore
       include Base::Evaluator
 
@@ -47,6 +47,7 @@ module Rumale
           cls_pos = y.eq(labels[n])
           sz_cluster = cls_pos.count
           next unless sz_cluster > 1
+
           cls_dist_mat = dist_mat[cls_pos, cls_pos].dup
           cls_dist_mat[cls_dist_mat.diag_indices] = 0.0
           intra_dists[cls_pos] = cls_dist_mat.sum(0) / (sz_cluster - 1)
@@ -57,6 +58,7 @@ module Rumale
           cls_pos = y.eq(labels[m])
           n_clusters.times do |n|
             next if m == n
+
             not_cls_pos = y.eq(labels[n])
             inter_dists[cls_pos] = Numo::DFloat.minimum(
               inter_dists[cls_pos], dist_mat[cls_pos, not_cls_pos].mean(1)

data/lib/rumale/feature_extraction/feature_hasher.rb

@@ -1,6 +1,5 @@
 # frozen_string_literal: true
 
-require 'mmh3'
 require 'rumale/base/base_estimator'
 require 'rumale/base/transformer'
 
@@ -11,11 +10,15 @@ module Rumale
     # This encoder employs signed 32-bit Murmurhash3 as the hash function.
     #
     # @example
+    #   require 'mmh3'
+    #   require 'rumale'
+    #
     #   encoder = Rumale::FeatureExtraction::FeatureHasher.new(n_features: 10)
     #   x = encoder.transform([
     #     { dog: 1, cat: 2, elephant: 4 },
     #     { dog: 2, run: 5 }
     #   ])
+    #
     #   # > pp x
     #   # Numo::DFloat#shape=[2,10]
     #   # [[0, 0, -4, -1, 0, 0, 0, 0, 0, 2],
@@ -62,6 +65,8 @@ 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)
+        raise 'FeatureHasher#transform requires Mmh3 but that is not loaded.' unless enable_mmh3?
+
         x = [x] unless x.is_a?(Array)
         n_samples = x.size
 
@@ -85,6 +90,14 @@ module Rumale
 
       private
 
+      def enable_mmh3?
+        if defined?(Mmh3).nil?
+          warn('FeatureHasher#transform requires Mmh3 but that is not loaded. You should intall and load mmh3 gem in advance.')
+          return false
+        end
+        true
+      end
+
       def n_features
         @params[:n_features]
       end

data/lib/rumale/feature_extraction/hash_vectorizer.rb

@@ -71,6 +71,7 @@ module Rumale
           f.each do |k, v|
             k = "#{k}#{separator}#{v}".to_sym if v.is_a?(String)
             next if @vocabulary.key?(k)
+
             @feature_names.push(k)
             @vocabulary[k] = @vocabulary.size
           end

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

@@ -16,7 +16,7 @@ module Rumale
     #   new_testing_samples = transformer.transform(testing_samples)
     #
     # *Reference*
-    # 1. T. Yang, Y. Li, M. Mahdavi, R. Jin, and Z-H. Zhou, "Nystrom Method vs Random Fourier Features: A Theoretical and Empirical Comparison," Advances in NIPS'12, Vol. 1, pp. 476--484, 2012.
+    # - Yang, T., Li, Y., Mahdavi, M., Jin, R., and Zhou, Z-H., "Nystrom Method vs Random Fourier Features: A Theoretical and Empirical Comparison," Advances in NIPS'12, Vol. 1, pp. 476--484, 2012.
     class Nystroem
       include Base::BaseEstimator
       include Base::Transformer

data/lib/rumale/kernel_approximation/rbf.rb

@@ -15,7 +15,7 @@ module Rumale
     #   new_testing_samples = transformer.transform(testing_samples)
     #
     # *Refernce*:
-    # 1. A. Rahimi and B. Recht, "Random Features for Large-Scale Kernel Machines," Proc. NIPS'07, pp.1177--1184, 2007.
+    # - Rahimi, A., and Recht, B., "Random Features for Large-Scale Kernel Machines," Proc. NIPS'07, pp.1177--1184, 2007.
     class RBF
       include Base::BaseEstimator
       include Base::Transformer

data/lib/rumale/kernel_machine/kernel_fda.rb

@@ -18,7 +18,7 @@ module Rumale
     #   mapped_test_samples = kfda.transform(kernel_mat_test)
     #
     # *Reference*
-    # - Baudat, G. and Anouar, F., "Generalized Discriminant Analysis using a Kernel Approach," Neural Computation, vol. 12, pp. 2385--2404, 2000.
+    # - Baudat, G., and Anouar, F., "Generalized Discriminant Analysis using a Kernel Approach," Neural Computation, vol. 12, pp. 2385--2404, 2000.
     class KernelFDA
       include Base::BaseEstimator
       include Base::Transformer

data/lib/rumale/kernel_machine/kernel_pca.rb

@@ -18,7 +18,7 @@ module Rumale
     #   mapped_test_samples = kpca.transform(kernel_mat_test)
     #
     # *Reference*
-    # - B. Scholkopf, A. Smola, and K-R. Muller, "Nonlinear Component Analysis as a Kernel Eigenvalue Problem," Neural Computation, Vol. 10 (5), pp. 1299--1319, 1998.
+    # - Scholkopf, B., Smola, A., and Muller, K-R., "Nonlinear Component Analysis as a Kernel Eigenvalue Problem," Neural Computation, Vol. 10 (5), pp. 1299--1319, 1998.
     class KernelPCA
       include Base::BaseEstimator
       include Base::Transformer

data/lib/rumale/kernel_machine/kernel_ridge.rb

@@ -30,6 +30,7 @@ module Rumale
       def initialize(reg_param: 1.0)
         raise TypeError, 'Expect class of reg_param to be Float or Numo::DFloat' unless reg_param.is_a?(Float) || reg_param.is_a?(Numo::DFloat)
         raise ArgumentError, 'Expect reg_param array to be 1-D arrray' if reg_param.is_a?(Numo::DFloat) && reg_param.shape.size != 1
+
         @params = {}
         @params[:reg_param] = reg_param
         @weight_vec = nil
@@ -55,6 +56,7 @@ module Rumale
           @weight_vec = Numo::Linalg.solve(reg_kernel_mat, y, driver: 'sym')
         else
           raise ArgumentError, 'Expect y and reg_param to have the same number of elements.' unless y.shape[1] == @params[:reg_param].shape[0]
+
           n_outputs = y.shape[1]
           @weight_vec = Numo::DFloat.zeros(n_samples, n_outputs)
           n_outputs.times do |n|

data/lib/rumale/kernel_machine/kernel_svc.rb

@@ -24,7 +24,7 @@ module Rumale
     #   results = estimator.predict(testing_kernel_matrix)
     #
     # *Reference*
-    # 1. S. Shalev-Shwartz, Y. Singer, N. Srebro, and A. Cotter, "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Mathematical Programming, vol. 127 (1), pp. 3--30, 2011.
+    # - Shalev-Shwartz, S., Singer, Y., Srebro, N., and Cotter, A., "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Mathematical Programming, vol. 127 (1), pp. 3--30, 2011.
     class KernelSVC
       include Base::BaseEstimator
       include Base::Classifier

data/lib/rumale/linear_model/base_linear_model.rb

@@ -8,6 +8,7 @@ module Rumale
     # @note
     #   In version 0.17.0, a new linear model abstract class called BaseSGD is introduced.
     #   BaseLienarModel is deprecated and will be removed in the future.
+    # @deprecated Use BaseSGD class instead. This class will be deleted in version 0.20.0.
     #
     # BaseLinearModel is an abstract class for implementation of linear estimator
     # with mini-batch stochastic gradient descent optimization.
@@ -68,6 +69,7 @@ module Rumale
           # Update weight.
           loss_gradient = calc_loss_gradient(sub_samples, sub_targets, weight)
           next if loss_gradient.ne(0.0).count.zero?
+
           weight = calc_new_weight(optimizer, sub_samples, weight, loss_gradient)
         end
         split_weight(weight)

data/lib/rumale/linear_model/elastic_net.rb

@@ -15,9 +15,9 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - S. Shalev-Shwartz and Y. Singer, "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Proc. ICML'07, pp. 807--814, 2007.
-    # - Y. Tsuruoka, J. Tsujii, and S. Ananiadou, "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
-    # - L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
+    # - Shalev-Shwartz, S., and Singer, Y., "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Proc. ICML'07, pp. 807--814, 2007.
+    # - Tsuruoka, Y., Tsujii, J., and Ananiadou, S., "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
+    # - Bottou, L., "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
     class ElasticNet < BaseSGD
       include Base::Regressor
 

data/lib/rumale/linear_model/lasso.rb

@@ -15,9 +15,9 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - S. Shalev-Shwartz and Y. Singer, "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Proc. ICML'07, pp. 807--814, 2007.
-    # - Y. Tsuruoka, J. Tsujii, and S. Ananiadou, "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
-    # - L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
+    # - Shalev-Shwartz, S., and Singer, Y., "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Proc. ICML'07, pp. 807--814, 2007.
+    # - Tsuruoka, Y., Tsujii, J., and Ananiadou, S., "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
+    # - Bottou, L., "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
     class Lasso < BaseSGD
       include Base::Regressor
 

data/lib/rumale/linear_model/linear_regression.rb

@@ -21,7 +21,7 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
+    # - Bottou, L., "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
     class LinearRegression < BaseSGD
       include Base::Regressor
 
@@ -162,6 +162,7 @@ module Rumale
       def load_linalg?
         return false if defined?(Numo::Linalg).nil?
         return false if Numo::Linalg::VERSION < '0.1.4'
+
         true
       end
     end

data/lib/rumale/linear_model/logistic_regression.rb

@@ -20,9 +20,9 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - S. Shalev-Shwartz, Y. Singer, N. Srebro, and A. Cotter, "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Mathematical Programming, vol. 127 (1), pp. 3--30, 2011.
-    # - Y. Tsuruoka, J. Tsujii, and S. Ananiadou, "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
-    # - L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
+    # - Shalev-Shwartz, S., Singer, Y., Srebro, N., and Cotter, A., "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Mathematical Programming, vol. 127 (1), pp. 3--30, 2011.
+    # - Tsuruoka, Y., Tsujii, J., and Ananiadou, S., "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
+    # - Bottou, L., "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
     class LogisticRegression < BaseSGD
       include Base::Classifier
 

data/lib/rumale/linear_model/ridge.rb

@@ -21,7 +21,7 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
+    # - Bottou, L., "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
     class Ridge < BaseSGD
       include Base::Regressor
 
@@ -164,6 +164,7 @@ module Rumale
       def load_linalg?
         return false if defined?(Numo::Linalg).nil?
         return false if Numo::Linalg::VERSION < '0.1.4'
+
         true
       end
     end

data/lib/rumale/linear_model/svc.rb

@@ -22,9 +22,9 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - S. Shalev-Shwartz and Y. Singer, "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Proc. ICML'07, pp. 807--814, 2007.
-    # - Y. Tsuruoka, J. Tsujii, and S. Ananiadou, "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
-    # - L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
+    # - Shalev-Shwartz, S., and Singer, Y., "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Proc. ICML'07, pp. 807--814, 2007.
+    # - Tsuruoka, Y., Tsujii, J., and Ananiadou, S., "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
+    # - Bottou, L., "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
     class SVC < BaseSGD
       include Base::Classifier
 

data/lib/rumale/linear_model/svr.rb

@@ -19,9 +19,9 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - S. Shalev-Shwartz and Y. Singer, "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Proc. ICML'07, pp. 807--814, 2007.
-    # - Y. Tsuruoka, J. Tsujii, and S. Ananiadou, "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
-    # - L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
+    # - Shalev-Shwartz, S., and Singer, Y., "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Proc. ICML'07, pp. 807--814, 2007.
+    # - Tsuruoka, Y., Tsujii, J., and Ananiadou, S., "Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty," Proc. ACL'09, pp. 477--485, 2009.
+    # - Bottou, L., "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
     class SVR < BaseSGD
       include Base::Regressor
 

data/lib/rumale/manifold/mds.rb

@@ -16,7 +16,7 @@ module Rumale
     #   representations = mds.fit_transform(samples)
     #
     # *Reference*
-    # - P J. F. Groenen and M. van de Velden, "Multidimensional Scaling by Majorization: A Review," J. of Statistical Software, Vol. 73 (8), 2016.
+    # - Groenen, P J. F.  and van de Velden, M., "Multidimensional Scaling by Majorization: A Review," J. of Statistical Software, Vol. 73 (8), 2016.
     class MDS
       include Base::BaseEstimator
       include Base::Transformer
@@ -83,6 +83,7 @@ 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.
         n_samples = x.shape[0]
         hi_distance_mat = @params[:metric] == 'precomputed' ? x : Rumale::PairwiseMetric.euclidean_distance(x)
@@ -142,6 +143,7 @@ module Rumale
       def terminate?(old_stress, new_stress)
         return false if @params[:tol].nil?
         return false if old_stress.nil?
+
         (old_stress - new_stress).abs <= @params[:tol]
       end
 

data/lib/rumale/manifold/tsne.rb

@@ -19,8 +19,8 @@ module Rumale
     #   representations = tsne.fit_transform(samples)
     #
     # *Reference*
-    # - L. van der Maaten and G. Hinton, "Visualizing data using t-SNE," J. of Machine Learning Research, vol. 9, pp. 2579--2605, 2008.
-    # - Z. Yang, I. King, Z. Xu, and E. Oja, "Heavy-Tailed Symmetric Stochastic Neighbor Embedding," Proc. NIPS'09, pp. 2169--2177, 2009.
+    # - van der Maaten, L., and Hinton, G., "Visualizing data using t-SNE," J. of Machine Learning Research, vol. 9, pp. 2579--2605, 2008.
+    # - Yang, Z., King, I., Xu, Z., and Oja, E., "Heavy-Tailed Symmetric Stochastic Neighbor Embedding," Proc. NIPS'09, pp. 2169--2177, 2009.
     class TSNE
       include Base::BaseEstimator
       include Base::Transformer
@@ -89,6 +89,7 @@ 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.
         @n_iter = 0
         distance_mat = @params[:metric] == 'precomputed' ? x**2 : Rumale::PairwiseMetric.squared_error(x)
@@ -99,6 +100,7 @@ module Rumale
         one_vec = Numo::DFloat.ones(x.shape[0]).expand_dims(1)
         @params[:max_iter].times do |t|
           break if terminate?(hi_prob_mat, lo_prob_mat)
+
           a = hi_prob_mat * lo_prob_mat
           b = lo_prob_mat * lo_prob_mat
           y = (b.dot(one_vec) * y + (a - b).dot(y)) / a.dot(one_vec)
@@ -170,6 +172,7 @@ module Rumale
           entropy, probs = gaussian_distributed_probability_vector(sample_id, distance_vec, beta)
           diff_entropy = entropy - init_entropy
           break if diff_entropy.abs <= 1e-5
+
           if diff_entropy.positive?
             betamin = beta
             if betamax == Float::MAX
@@ -211,6 +214,7 @@ module Rumale
 
       def terminate?(p, q)
         return false if @params[:tol].nil?
+
         cost(p, q) <= @params[:tol]
       end
     end

data/lib/rumale/metric_learning/neighbourhood_component_analysis.rb

@@ -2,13 +2,15 @@
 
 require 'rumale/base/base_estimator'
 require 'rumale/base/transformer'
-require 'mopti/scaled_conjugate_gradient'
 
 module Rumale
   module MetricLearning
     # NeighbourhoodComponentAnalysis is a class that implements Neighbourhood Component Analysis.
     #
     # @example
+    #   require 'mopti'
+    #   require 'rumale'
+    #
     #   transformer = Rumale::MetricLearning::NeighbourhoodComponentAnalysis.new
     #   transformer.fit(training_samples, traininig_labels)
     #   low_samples = transformer.transform(testing_samples)
@@ -63,6 +65,8 @@ module Rumale
       # @param y [Numo::Int32] (shape: [n_samples]) The labels to be used for fitting the model.
       # @return [NeighbourhoodComponentAnalysis] The learned classifier itself.
       def fit(x, y)
+        raise 'NeighbourhoodComponentAnalysis#fit requires Mopti but that is not loaded.' unless enable_mopti?
+
         x = check_convert_sample_array(x)
         y = check_convert_label_array(y)
         check_sample_label_size(x, y)
@@ -98,6 +102,14 @@ module Rumale
 
       private
 
+      def enable_mopti?
+        if defined?(Mopti).nil?
+          warn('NeighbourhoodComponentAnalysis#fit requires Mopti but that is not loaded. You should intall and load mopti gem in advance.')
+          return false
+        end
+        true
+      end
+
       def init_components(x, n_features, n_components)
         if @params[:init] == 'pca'
           pca = Rumale::Decomposition::PCA.new(n_components: n_components, solver: 'evd')
@@ -126,6 +138,7 @@ module Rumale
           res = prm
           puts "[NeighbourhoodComponentAnalysis] The value of objective function after #{res[:n_iter]} epochs: #{x.shape[0] - res[:fnc]}" if @params[:verbose]
           break if (fold - res[:fnc]).abs <= @params[:tol] && (dold - res[:jcb]).abs <= @params[:tol]
+
           fold = res[:fnc]
           dold = res[:jcb]
         end