🚨 Fix Rubocop pointed out

lib/rumale/base/base_estimator.rb

@@ -25,6 +25,7 @@ def enable_linalg?
 
       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 @@ def enable_parallel?
 
       def n_processes
         return 1 unless enable_parallel?
+
         @params[:n_jobs] <= 0 ? Parallel.processor_count : @params[:n_jobs]
       end
 

lib/rumale/clustering/dbscan.rb

@@ -54,6 +54,7 @@ def initialize(eps: 0.5, min_samples: 5, metric: 'euclidean')
       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 @@ def fit(x, _y = nil)
       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 @@ def partial_fit(x)
         @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 @@ def expand_cluster(metric_mat, query_id, cluster_id)
           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

lib/rumale/clustering/gaussian_mixture.rb

@@ -86,6 +86,7 @@ def fit(x, _y = nil)
           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 @@ def calc_inv_sqrt_det_covariance(covar, covar_type)
 
       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

lib/rumale/clustering/hdbscan.rb

@@ -55,6 +55,7 @@ def initialize(min_samples: 10, min_cluster_size: nil, metric: 'euclidean')
       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 @@ def fit(x, _y = nil)
       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

lib/rumale/clustering/k_means.rb

@@ -106,6 +106,7 @@ def init_cluster_centers(x)
         rand_id = [*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])

lib/rumale/clustering/k_medoids.rb

@@ -64,6 +64,7 @@ def initialize(n_clusters: 8, metric: 'euclidean', init: 'k-means++', max_iter:
       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 @@ def fit(x, _not_used = nil)
           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 @@ def predict(x)
         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
 
@@ -123,6 +126,7 @@ def init_cluster_centers(distance_mat)
         sub_rng = @rng.dup
         @medoid_ids = Numo::Int32.asarray([*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]]

lib/rumale/clustering/power_iteration.rb

@@ -71,6 +71,7 @@ def initialize(n_clusters: 8, affinity: 'rbf', gamma: nil, init: 'k-means++', ma
       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 @@ def embedded_space(affinity_mat, max_iter, tol)
           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

lib/rumale/clustering/single_linkage.rb

@@ -54,6 +54,7 @@ def initialize(n_clusters: 2, metric: 'euclidean')
       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 @@ def fit(x, _y = nil)
       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

lib/rumale/dataset.rb

@@ -65,6 +65,7 @@ def make_circles(n_samples, shuffle: true, noise: nil, factor: 0.8, random_seed:
         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 @@ def make_moons(n_samples, shuffle: true, noise: nil, random_seed: nil)
         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

lib/rumale/decomposition/factor_analysis.rb

@@ -90,9 +90,11 @@ def fit(x, _y = nil)
           @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
 

lib/rumale/decomposition/pca.rb

@@ -87,6 +87,7 @@ def fit(x, _y = nil)
             @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])

lib/rumale/ensemble/ada_boost_classifier.rb

@@ -105,6 +105,7 @@ def fit(x, y) # rubocop:disable Metrics/AbcSize
           # 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 @@ def fit(x, y) # rubocop:disable Metrics/AbcSize
           @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

lib/rumale/ensemble/ada_boost_regressor.rb

@@ -93,6 +93,7 @@ def fit(x, y) # rubocop:disable Metrics/AbcSize
         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)
@@ -117,6 +118,7 @@ def fit(x, y) # rubocop:disable Metrics/AbcSize
           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))
@@ -131,6 +133,7 @@ def fit(x, y) # rubocop:disable Metrics/AbcSize
           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)

lib/rumale/evaluation_measure/normalized_mutual_information.rb

@@ -28,8 +28,10 @@ def score(y_true, y_pred)
         # 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)

lib/rumale/evaluation_measure/precision_recall.rb

@@ -14,6 +14,7 @@ def precision_each_class(y_true, y_pred)
         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 @@ def recall_each_class(y_true, y_pred)
         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 @@ def recall_each_class(y_true, y_pred)
       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 @@ def micro_average_precision(y_true, y_pred)
         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 @@ def micro_average_recall(y_true, y_pred)
         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]

lib/rumale/evaluation_measure/roc_auc.rb

@@ -64,6 +64,7 @@ def roc_curve(y_true, y_score, pos_label = nil)
         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 @@ def auc(x, y)
         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
 

lib/rumale/evaluation_measure/silhouette_score.rb

@@ -47,6 +47,7 @@ def score(x, y)
           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 @@ def score(x, y)
           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)

lib/rumale/feature_extraction/hash_vectorizer.rb

@@ -71,6 +71,7 @@ def fit(x, _y = nil)
           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

lib/rumale/kernel_machine/kernel_ridge.rb

@@ -30,6 +30,7 @@ class KernelRidge
       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 @@ def fit(x, y)
           @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|

lib/rumale/linear_model/base_linear_model.rb

@@ -68,6 +68,7 @@ def partial_fit(x, y)
           # 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)

lib/rumale/linear_model/linear_regression.rb

@@ -162,6 +162,7 @@ def fit_bias?
       def load_linalg?
         return false if defined?(Numo::Linalg).nil?
         return false if Numo::Linalg::VERSION < '0.1.4'
+
         true
       end
     end

lib/rumale/linear_model/ridge.rb

@@ -164,6 +164,7 @@ def fit_sgd(x, y)
       def load_linalg?
         return false if defined?(Numo::Linalg).nil?
         return false if Numo::Linalg::VERSION < '0.1.4'
+
         true
       end
     end

lib/rumale/manifold/mds.rb

@@ -83,6 +83,7 @@ def initialize(n_components: 2, metric: 'euclidean', init: 'random',
       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 @@ def init_embedding(x)
       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