rumale 0.18.5 → 0.19.2

data/lib/rumale/clustering/power_iteration.rb

@@ -13,7 +13,7 @@ module Rumale
     #   cluster_labels = analyzer.fit_predict(samples)
     #
     # *Reference*
-    # - F. Lin and W W. Cohen, "Power Iteration Clustering," Proc. ICML'10, pp. 655--662, 2010.
+    # - Lin, F., and Cohen, W W., "Power Iteration Clustering," Proc. ICML'10, pp. 655--662, 2010.
     class PowerIteration
       include Base::BaseEstimator
       include Base::ClusterAnalyzer
@@ -71,6 +71,7 @@ module Rumale
       def fit(x, _y = nil)
         x = check_convert_sample_array(x)
         raise ArgumentError, 'Expect the input affinity matrix to be square.' if @params[:affinity] == 'precomputed' && x.shape[0] != x.shape[1]
+
         fit_predict(x)
         self
       end
@@ -107,6 +108,7 @@ module Rumale
           new_embedded_line /= new_embedded_line.abs.sum
           new_error = (new_embedded_line - embedded_line).abs
           break if (new_error - error).abs.max <= tol
+
           embedded_line = new_embedded_line
           error = new_error
         end

data/lib/rumale/clustering/single_linkage.rb

@@ -15,7 +15,7 @@ module Rumale
     #   cluster_labels = analyzer.fit_predict(samples)
     #
     # *Reference*
-    # - D. Mullner, "Modern hierarchical, agglomerative clustering algorithms," arXiv:1109.2378, 2011.
+    # - Mullner, D., "Modern hierarchical, agglomerative clustering algorithms," arXiv:1109.2378, 2011.
     class SingleLinkage
       include Base::BaseEstimator
       include Base::ClusterAnalyzer
@@ -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]
+
         fit_predict(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]
+
         distance_mat = @params[:metric] == 'precomputed' ? x : Rumale::PairwiseMetric.euclidean_distance(x)
         @labels = partial_fit(distance_mat)
       end

data/lib/rumale/clustering/snn.rb

@@ -13,8 +13,8 @@ module Rumale
     #   cluster_labels = analyzer.fit_predict(samples)
     #
     # *Reference*
-    # - L. Ertoz, M. Steinbach, and V. Kumar, "Finding Clusters of Different Sizes, Shapes, and Densities in Noisy, High Dimensional Data," Proc. SDM'03, pp. 47--58, 2003.
-    # - M E. Houle, H-P. Kriegel, P. Kroger, E. Schubert, and A. Zimek, "Can Shared-Neighbor Distances Defeat the Curse of Dimensionality?," Proc. SSDBM'10, pp. 482--500, 2010.
+    # - Ertoz, L., Steinbach, M., and Kumar, V., "Finding Clusters of Different Sizes, Shapes, and Densities in Noisy, High Dimensional Data," Proc. SDM'03, pp. 47--58, 2003.
+    # - Houle, M E., Kriegel, H-P., Kroger, P., Schubert, E., and Zimek, A., "Can Shared-Neighbor Distances Defeat the Curse of Dimensionality?," Proc. SSDBM'10, pp. 482--500, 2010.
     class SNN < DBSCAN
       # Create a new cluster analyzer with Shared Neareset Neighbor method.
       #

data/lib/rumale/clustering/spectral_clustering.rb

@@ -16,8 +16,8 @@ module Rumale
     #   cluster_labels = analyzer.fit_predict(samples)
     #
     # *Reference*
-    # - A Y. Ng, M I. Jordan, and Y. Weiss, "On Spectral Clustering: Analyssi and an algorithm," Proc. NIPS'01, pp. 849--856, 2001.
-    # - U von Luxburg, "A tutorial on spectral clustering," Statistics and Computing, Vol. 17 (4), pp. 395--416, 2007.
+    # - Ng, A Y., Jordan, M I., and Weiss, Y., "On Spectral Clustering: Analyssi and an algorithm," Proc. NIPS'01, pp. 849--856, 2001.
+    # - von Luxburg, U., "A tutorial on spectral clustering," Statistics and Computing, Vol. 17 (4), pp. 395--416, 2007.
     class SpectralClustering
       include Base::BaseEstimator
       include Base::ClusterAnalyzer

data/lib/rumale/dataset.rb

@@ -65,6 +65,7 @@ module Rumale
         Rumale::Validation.check_params_numeric_or_nil(noise: noise, random_seed: random_seed)
         raise ArgumentError, 'The number of samples must be more than 2.' if n_samples <= 1
         raise RangeError, 'The interval of factor is (0, 1).' if factor <= 0 || factor >= 1
+
         # initialize some variables.
         rs = random_seed
         rs ||= srand
@@ -101,6 +102,7 @@ module Rumale
         Rumale::Validation.check_params_boolean(shuffle: shuffle)
         Rumale::Validation.check_params_numeric_or_nil(noise: noise, random_seed: random_seed)
         raise ArgumentError, 'The number of samples must be more than 2.' if n_samples <= 1
+
         # initialize some variables.
         rs = random_seed
         rs ||= srand

data/lib/rumale/decomposition/factor_analysis.rb

@@ -14,7 +14,7 @@ module Rumale
     #   representaion = decomposer.fit_transform(samples)
     #
     # *Reference*
-    # - D. Barber, "Bayesian Reasoning and Machine Learning," Cambridge University Press, 2012.
+    # - Barber, D., "Bayesian Reasoning and Machine Learning," Cambridge University Press, 2012.
     class FactorAnalysis
       include Base::BaseEstimator
       include Base::Transformer
@@ -90,9 +90,11 @@ module Rumale
           @components = (sqrt_noise_variance.diag.dot(u) * scaler).transpose.dup
           @noise_variance = Numo::DFloat.maximum(sample_vars - @components.transpose.dot(@components).diagonal, 1e-12)
           next if @params[:tol].nil?
+
           new_loglike = log_likelihood(cov_mat, @components, @noise_variance)
           @loglike.push(new_loglike)
           break if (old_loglike - new_loglike).abs <= @params[:tol]
+
           old_loglike = new_loglike
         end
 

data/lib/rumale/decomposition/fast_ica.rb

@@ -14,8 +14,8 @@ module Rumale
     #   source_data = transformer.fit_transform(observed_data)
     #
     # *Reference*
-    # - A. Hyvarinen "Fast and Robust Fixed-Point Algorithms for Independent Component Analysis," IEEE Trans. Neural Networks, Vol. 10 (3), pp. 626--634, 1999.
-    # - A. Hyvarinen and E. Oja, "Independent Component Analysis: Algorithms and Applications," Neural Networks, Vol. 13 (4-5), pp. 411--430, 2000.
+    # - Hyvarinen, A., "Fast and Robust Fixed-Point Algorithms for Independent Component Analysis," IEEE Trans. Neural Networks, Vol. 10 (3), pp. 626--634, 1999.
+    # - Hyvarinen, A., and Oja, E., "Independent Component Analysis: Algorithms and Applications," Neural Networks, Vol. 13 (4-5), pp. 411--430, 2000.
     class FastICA
       include Base::BaseEstimator
       include Base::Transformer

data/lib/rumale/decomposition/nmf.rb

@@ -13,7 +13,7 @@ module Rumale
     #   representaion = decomposer.fit_transform(samples)
     #
     # *Reference*
-    # - W. Xu, X. Liu, and Y.Gong, "Document Clustering Based On Non-negative Matrix Factorization," Proc. SIGIR' 03 , pp. 267--273, 2003.
+    # - Xu, W., Liu, X., and Gong, Y., "Document Clustering Based On Non-negative Matrix Factorization," Proc. SIGIR' 03 , pp. 267--273, 2003.
     class NMF
       include Base::BaseEstimator
       include Base::Transformer

data/lib/rumale/decomposition/pca.rb

@@ -9,7 +9,7 @@ module Rumale
     # PCA is a class that implements Principal Component Analysis.
     #
     # @example
-    #   decomposer = Rumale::Decomposition::PCA.new(n_components: 2)
+    #   decomposer = Rumale::Decomposition::PCA.new(n_components: 2, solver: 'fpt')
     #   representaion = decomposer.fit_transform(samples)
     #
     #   # If Numo::Linalg is installed, you can specify 'evd' for the solver option.
@@ -17,8 +17,13 @@ module Rumale
     #   decomposer = Rumale::Decomposition::PCA.new(n_components: 2, solver: 'evd')
     #   representaion = decomposer.fit_transform(samples)
     #
+    #   # If Numo::Linalg is loaded and the solver option is not given,
+    #   # the solver option is choosen 'evd' automatically.
+    #   decomposer = Rumale::Decomposition::PCA.new(n_components: 2)
+    #   representaion = decomposer.fit_transform(samples)
+    #
     # *Reference*
-    # - A. Sharma and K K. Paliwal, "Fast principal component analysis using fixed-point algorithm," Pattern Recognition Letters, 28, pp. 1151--1155, 2007.
+    # - Sharma, A., and Paliwal, K K., "Fast principal component analysis using fixed-point algorithm," Pattern Recognition Letters, 28, pp. 1151--1155, 2007.
     class PCA
       include Base::BaseEstimator
       include Base::Transformer
@@ -38,18 +43,24 @@ module Rumale
       # Create a new transformer with PCA.
       #
       # @param n_components [Integer] The number of principal components.
-      # @param solver [String] The algorithm for the optimization ('fpt' or 'evd').
-      #   'fpt' uses the fixed-point algorithm. 'evd' performs eigen value decomposition of the covariance matrix of samples.
+      # @param solver [String] The algorithm for the optimization ('auto', 'fpt' or 'evd').
+      #   'auto' chooses the 'evd' solver if Numo::Linalg is loaded. Otherwise, it chooses the 'fpt' solver.
+      #   'fpt' uses the fixed-point algorithm.
+      #   'evd' performs eigen value decomposition of the covariance matrix of samples.
       # @param max_iter [Integer] The maximum number of iterations. If solver = 'evd', this parameter is ignored.
       # @param tol [Float] The tolerance of termination criterion. If solver = 'evd', this parameter is ignored.
       # @param random_seed [Integer] The seed value using to initialize the random generator.
-      def initialize(n_components: 2, solver: 'fpt', max_iter: 100, tol: 1.0e-4, random_seed: nil)
+      def initialize(n_components: 2, solver: 'auto', max_iter: 100, tol: 1.0e-4, random_seed: nil)
         check_params_numeric(n_components: n_components, max_iter: max_iter, tol: tol)
         check_params_string(solver: solver)
         check_params_numeric_or_nil(random_seed: random_seed)
         check_params_positive(n_components: n_components, max_iter: max_iter, tol: tol)
         @params = {}
-        @params[:solver] = solver != 'evd' ? 'fpt' : 'evd'
+        @params[:solver] = if solver == 'auto'
+                             load_linalg? ? 'evd' : 'fpt'
+                           else
+                             solver != 'evd' ? 'fpt' : 'evd'
+                           end
         @params[:n_components] = n_components
         @params[:max_iter] = max_iter
         @params[:tol] = tol
@@ -87,6 +98,7 @@ module Rumale
             @params[:max_iter].times do
               updated = orthogonalize(covariance_mat.dot(comp_vec))
               break if (updated.dot(comp_vec) - 1).abs < @params[:tol]
+
               comp_vec = updated
             end
             @components = @components.nil? ? comp_vec : Numo::NArray.vstack([@components, comp_vec])
@@ -127,6 +139,13 @@ module Rumale
 
       private
 
+      def load_linalg?
+        return false if defined?(Numo::Linalg).nil?
+        return false if Numo::Linalg::VERSION < '0.1.4'
+
+        true
+      end
+
       def orthogonalize(pcvec)
         unless @components.nil?
           delta = @components.dot(pcvec) * @components.transpose

data/lib/rumale/ensemble/ada_boost_classifier.rb

@@ -19,7 +19,7 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - J. Zhu, S. Rosset, H. Zou, and T.Hashie, "Multi-class AdaBoost," Technical Report No. 430, Department of Statistics, University of Michigan, 2005.
+    # - Zhu, J., Rosset, S., Zou, H., and Hashie, T., "Multi-class AdaBoost," Technical Report No. 430, Department of Statistics, University of Michigan, 2005.
     class AdaBoostClassifier
       include Base::BaseEstimator
       include Base::Classifier
@@ -105,6 +105,7 @@ module Rumale
           # Fit classfier.
           ids = Rumale::Utils.choice_ids(n_samples, observation_weights, sub_rng)
           break if y[ids].to_a.uniq.size != n_classes
+
           tree = Tree::DecisionTreeClassifier.new(
             criterion: @params[:criterion], max_depth: @params[:max_depth],
             max_leaf_nodes: @params[:max_leaf_nodes], min_samples_leaf: @params[:min_samples_leaf],
@@ -120,12 +121,14 @@ module Rumale
           @estimators.push(tree)
           @feature_importances += tree.feature_importances
           break if error.zero?
+
           # Update observation weights.
           log_proba = Numo::NMath.log(proba)
           observation_weights *= Numo::NMath.exp(-1.0 * (n_classes - 1).fdiv(n_classes) * (y_codes * log_proba).sum(1))
           observation_weights = observation_weights.clip(1.0e-15, nil)
           sum_observation_weights = observation_weights.sum
           break if sum_observation_weights.zero?
+
           observation_weights /= sum_observation_weights
         end
         @feature_importances /= @feature_importances.sum

data/lib/rumale/ensemble/ada_boost_regressor.rb

@@ -18,8 +18,7 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - D. L. Shrestha and D. P. Solomatine, "Experiments with AdaBoost.RT, an Improved Boosting Scheme for Regression," Neural Computation 18 (7), pp. 1678--1710, 2006.
-    #
+    # - Shrestha, D. L., and Solomatine, D. P., "Experiments with AdaBoost.RT, an Improved Boosting Scheme for Regression," Neural Computation 18 (7), pp. 1678--1710, 2006.
     class AdaBoostRegressor
       include Base::BaseEstimator
       include Base::Regressor
@@ -94,6 +93,7 @@ module Rumale
         check_sample_tvalue_size(x, y)
         # Check target values
         raise ArgumentError, 'Expect target value vector to be 1-D arrray' unless y.shape.size == 1
+
         # Initialize some variables.
         n_samples, n_features = x.shape
         @params[:max_features] = n_features unless @params[:max_features].is_a?(Integer)
@@ -118,6 +118,7 @@ module Rumale
           abs_err = ((p - y) / y).abs
           err = observation_weights[abs_err.gt(@params[:threshold])].sum
           break if err <= 0.0
+
           # Calculate weight.
           beta = err**@params[:exponent]
           weight = Math.log(1.fdiv(beta))
@@ -132,6 +133,7 @@ module Rumale
           observation_weights = observation_weights.clip(1.0e-15, nil)
           sum_observation_weights = observation_weights.sum
           break if sum_observation_weights.zero?
+
           observation_weights /= sum_observation_weights
         end
         @estimator_weights = Numo::DFloat.asarray(@estimator_weights)

data/lib/rumale/ensemble/extra_trees_classifier.rb

@@ -18,7 +18,7 @@ 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 ExtraTreesClassifier < RandomForestClassifier
       # Return the set of estimators.
       # @return [Array<ExtraTreeClassifier>]

data/lib/rumale/ensemble/extra_trees_regressor.rb

@@ -18,7 +18,7 @@ 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 ExtraTreesRegressor < RandomForestRegressor
       # Return the set of estimators.
       # @return [Array<ExtraTreeRegressor>]

data/lib/rumale/ensemble/gradient_boosting_classifier.rb

@@ -18,10 +18,10 @@ module Rumale
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
-    # *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 GradientBoostingClassifier
       include Base::BaseEstimator

data/lib/rumale/ensemble/gradient_boosting_regressor.rb

@@ -17,10 +17,10 @@ module Rumale
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
-    # *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 GradientBoostingRegressor
       include Base::BaseEstimator

data/lib/rumale/evaluation_measure/adjusted_rand_score.rb

@@ -11,7 +11,7 @@ module Rumale
     #   puts evaluator.score(ground_truth, predicted)
     #
     # *Reference*
-    # - N X. Vinh, J. Epps, and J. Bailey, "Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance", J. Machine Learnig Research, Vol. 11, pp.2837--2854, 2010.
+    # - Vinh, N X., Epps, J., and Bailey, J., "Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance", J. Machine Learnig Research, Vol. 11, pp.2837--2854, 2010.
     class AdjustedRandScore
       include Base::Evaluator
 

data/lib/rumale/evaluation_measure/calinski_harabasz_score.rb

@@ -11,7 +11,7 @@ module Rumale
     #   puts evaluator.score(x, predicted)
     #
     # *Reference*
-    # - T. Calinski and J. Harabsz, "A dendrite method for cluster analysis," Communication in Statistics, Vol. 3 (1), pp. 1--27, 1972.
+    # - Calinski, T., and Harabsz, J., "A dendrite method for cluster analysis," Communication in Statistics, Vol. 3 (1), pp. 1--27, 1972.
     class CalinskiHarabaszScore
       include Base::Evaluator
 

data/lib/rumale/evaluation_measure/davies_bouldin_score.rb

@@ -12,7 +12,7 @@ module Rumale
     #   puts evaluator.score(x, predicted)
     #
     # *Reference*
-    # - D L. Davies and D W. Bouldin, "A Cluster Separation Measure," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. PAMI-1, No. 2, pp. 224--227, 1979.
+    # - Davies, D L., and Bouldin, D W., "A Cluster Separation Measure," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. PAMI-1, No. 2, pp. 224--227, 1979.
     class DaviesBouldinScore
       include Base::Evaluator
 

data/lib/rumale/evaluation_measure/function.rb

@@ -86,7 +86,8 @@ module Rumale
       weighted_recall = (Numo::DFloat.cast(recalls) * weights).sum
       weighted_fscore = (Numo::DFloat.cast(fscores) * weights).sum
       # output reults.
-      target_name ||= classes.map(&:to_s)
+      target_name ||= classes
+      target_name.map!(&:to_s)
       if output_hash
         res = {}
         target_name.each_with_index do |label, n|

data/lib/rumale/evaluation_measure/mutual_information.rb

@@ -11,7 +11,7 @@ module Rumale
     #   puts evaluator.score(ground_truth, predicted)
     #
     # *Reference*
-    # - N X. Vinh, J. Epps, and J. Bailey, "Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance," J. Machine Learning Research, vol. 11, pp. 2837--1854, 2010.
+    # - Vinh, N X., Epps, J., and Bailey, J., "Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance," J. Machine Learning Research, vol. 11, pp. 2837--1854, 2010.
     class MutualInformation
       include Base::Evaluator
 

data/lib/rumale/evaluation_measure/normalized_mutual_information.rb

@@ -12,8 +12,8 @@ module Rumale
     #   puts evaluator.score(ground_truth, predicted)
     #
     # *Reference*
-    # - C D. Manning, P. Raghavan, and H. Schutze, "Introduction to Information Retrieval," Cambridge University Press., 2008.
-    # - N X. Vinh, J. Epps, and J. Bailey, "Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance," J. Machine Learning Research, vol. 11, pp. 2837--1854, 2010.
+    # - Manning, C D., Raghavan, P., and Schutze, H., "Introduction to Information Retrieval," Cambridge University Press., 2008.
+    # - Vinh, N X., Epps, J., and Bailey, J., "Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance," J. Machine Learning Research, vol. 11, pp. 2837--1854, 2010.
     class NormalizedMutualInformation
       include Base::Evaluator
 
@@ -28,8 +28,10 @@ module Rumale
         # calculate entropies.
         class_entropy = entropy(y_true)
         return 0.0 if class_entropy.zero?
+
         cluster_entropy = entropy(y_pred)
         return 0.0 if cluster_entropy.zero?
+
         # calculate mutual information.
         mi = MutualInformation.new
         mi.score(y_true, y_pred) / Math.sqrt(class_entropy * cluster_entropy)

data/lib/rumale/evaluation_measure/precision_recall.rb

@@ -14,6 +14,7 @@ module Rumale
         y_true.sort.to_a.uniq.map do |label|
           target_positions = y_pred.eq(label)
           next 0.0 if y_pred[target_positions].empty?
+
           n_true_positives = Numo::Int32.cast(y_true[target_positions].eq(y_pred[target_positions])).sum.to_f
           n_false_positives = Numo::Int32.cast(y_true[target_positions].ne(y_pred[target_positions])).sum.to_f
           n_true_positives / (n_true_positives + n_false_positives)
@@ -25,6 +26,7 @@ module Rumale
         y_true.sort.to_a.uniq.map do |label|
           target_positions = y_true.eq(label)
           next 0.0 if y_pred[target_positions].empty?
+
           n_true_positives = Numo::Int32.cast(y_true[target_positions].eq(y_pred[target_positions])).sum.to_f
           n_false_negatives = Numo::Int32.cast(y_true[target_positions].ne(y_pred[target_positions])).sum.to_f
           n_true_positives / (n_true_positives + n_false_negatives)
@@ -35,6 +37,7 @@ module Rumale
       def f_score_each_class(y_true, y_pred)
         precision_each_class(y_true, y_pred).zip(recall_each_class(y_true, y_pred)).map do |p, r|
           next 0.0 if p.zero? && r.zero?
+
           (2.0 * p * r) / (p + r)
         end
       end
@@ -44,6 +47,7 @@ module Rumale
         evaluated_values = y_true.sort.to_a.uniq.map do |label|
           target_positions = y_pred.eq(label)
           next [0.0, 0.0] if y_pred[target_positions].empty?
+
           n_true_positives = Numo::Int32.cast(y_true[target_positions].eq(y_pred[target_positions])).sum.to_f
           n_false_positives = Numo::Int32.cast(y_true[target_positions].ne(y_pred[target_positions])).sum.to_f
           [n_true_positives, n_true_positives + n_false_positives]
@@ -57,6 +61,7 @@ module Rumale
         evaluated_values = y_true.sort.to_a.uniq.map do |label|
           target_positions = y_true.eq(label)
           next 0.0 if y_pred[target_positions].empty?
+
           n_true_positives = Numo::Int32.cast(y_true[target_positions].eq(y_pred[target_positions])).sum.to_f
           n_false_negatives = Numo::Int32.cast(y_true[target_positions].ne(y_pred[target_positions])).sum.to_f
           [n_true_positives, n_true_positives + n_false_negatives]

data/lib/rumale/evaluation_measure/purity.rb

@@ -11,7 +11,7 @@ module Rumale
     #   puts evaluator.score(ground_truth, predicted)
     #
     # *Reference*
-    # - C D. Manning, P. Raghavan, and H. Schutze, "Introduction to Information Retrieval," Cambridge University Press., 2008.
+    # - Manning, C D., Raghavan, P., and Schutze, H., "Introduction to Information Retrieval," Cambridge University Press., 2008.
     class Purity
       include Base::Evaluator
 

data/lib/rumale/evaluation_measure/roc_auc.rb

@@ -64,6 +64,7 @@ module Rumale
         y_score = Numo::DFloat.cast(y_score) unless y_score.is_a?(Numo::DFloat)
         raise ArgumentError, 'Expect y_true to be 1-D arrray.' unless y_true.shape[1].nil?
         raise ArgumentError, 'Expect y_score to be 1-D arrray.' unless y_score.shape[1].nil?
+
         labels = y_true.to_a.uniq
         if pos_label.nil?
           raise ArgumentError, 'y_true must be binary labels or pos_label must be specified if y_true is multi-label' unless labels.size == 2
@@ -96,8 +97,10 @@ module Rumale
         y = Numo::NArray.asarray(y) unless y.is_a?(Numo::NArray)
         raise ArgumentError, 'Expect x to be 1-D arrray.' unless x.shape[1].nil?
         raise ArgumentError, 'Expect y to be 1-D arrray.' unless y.shape[1].nil?
+
         n_samples = [x.shape[0], y.shape[0]].min
         raise ArgumentError, 'At least two points are required to calculate area under curve.' if n_samples < 2
+
         (0...n_samples).to_a.each_cons(2).map { |i, j| 0.5 * (x[i] - x[j]).abs * (y[i] + y[j]) }.reduce(&:+)
       end