rumale 0.18.1 → 0.18.2

data/lib/rumale/naive_bayes/bernoulli_nb.rb

@@ -0,0 +1,82 @@
+# frozen_string_literal: true
+
+require 'rumale/naive_bayes/base_naive_bayes'
+
+module Rumale
+  module NaiveBayes
+    # BernoulliNB is a class that implements Bernoulli Naive Bayes classifier.
+    #
+    # @example
+    #   estimator = Rumale::NaiveBayes::BernoulliNB.new(smoothing_param: 1.0, bin_threshold: 0.0)
+    #   estimator.fit(training_samples, training_labels)
+    #   results = estimator.predict(testing_samples)
+    #
+    # *Reference*
+    # - C D. Manning, P. Raghavan, and H. Schutze, "Introduction to Information Retrieval," Cambridge University Press., 2008.
+    class BernoulliNB < BaseNaiveBayes
+      # Return the class labels.
+      # @return [Numo::Int32] (size: n_classes)
+      attr_reader :classes
+
+      # Return the prior probabilities of the classes.
+      # @return [Numo::DFloat] (shape: [n_classes])
+      attr_reader :class_priors
+
+      # Return the conditional probabilities for features of each class.
+      # @return [Numo::DFloat] (shape: [n_classes, n_features])
+      attr_reader :feature_probs
+
+      # Create a new classifier with Bernoulli Naive Bayes.
+      #
+      # @param smoothing_param [Float] The Laplace smoothing parameter.
+      # @param bin_threshold [Float] The threshold for binarizing of features.
+      def initialize(smoothing_param: 1.0, bin_threshold: 0.0)
+        check_params_numeric(smoothing_param: smoothing_param, bin_threshold: bin_threshold)
+        check_params_positive(smoothing_param: smoothing_param)
+        @params = {}
+        @params[:smoothing_param] = smoothing_param
+        @params[:bin_threshold] = bin_threshold
+      end
+
+      # Fit the model with given training data.
+      #
+      # @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 categorical variables (e.g. labels)
+      #   to be used for fitting the model.
+      # @return [BernoulliNB] The learned classifier itself.
+      def fit(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_label_array(y)
+        check_sample_label_size(x, y)
+        n_samples, = x.shape
+        bin_x = Numo::DFloat[*x.gt(@params[:bin_threshold])]
+        @classes = Numo::Int32[*y.to_a.uniq.sort]
+        n_samples_each_class = Numo::DFloat[*@classes.to_a.map { |l| y.eq(l).count.to_f }]
+        @class_priors = n_samples_each_class / n_samples
+        count_features = Numo::DFloat[*@classes.to_a.map { |l| bin_x[y.eq(l).where, true].sum(0) }]
+        count_features += @params[:smoothing_param]
+        n_samples_each_class += 2.0 * @params[:smoothing_param]
+        n_classes = @classes.size
+        @feature_probs = count_features / n_samples_each_class.reshape(n_classes, 1)
+        self
+      end
+
+      # Calculate confidence scores for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to compute the scores.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Confidence scores per sample for each class.
+      def decision_function(x)
+        x = check_convert_sample_array(x)
+        n_classes = @classes.size
+        bin_x = Numo::DFloat[*x.gt(@params[:bin_threshold])]
+        not_bin_x = Numo::DFloat[*x.le(@params[:bin_threshold])]
+        log_likelihoods = Array.new(n_classes) do |l|
+          Math.log(@class_priors[l]) + (
+            (Numo::DFloat[*bin_x] * Numo::NMath.log(@feature_probs[l, true])).sum(1)
+            (Numo::DFloat[*not_bin_x] * Numo::NMath.log(1.0 - @feature_probs[l, true])).sum(1))
+        end
+        Numo::DFloat[*log_likelihoods].transpose
+      end
+    end
+  end
+end

data/lib/rumale/naive_bayes/complement_nb.rb

@@ -0,0 +1,85 @@
+# frozen_string_literal: true
+
+require 'rumale/naive_bayes/base_naive_bayes'
+
+module Rumale
+  module NaiveBayes
+    # ComplementNB is a class that implements Complement Naive Bayes classifier.
+    #
+    # @example
+    #   estimator = Rumale::NaiveBayes::ComplementNB.new(smoothing_param: 1.0)
+    #   estimator.fit(training_samples, training_labels)
+    #   results = estimator.predict(testing_samples)
+    #
+    # *Reference*
+    # - Rennie, J. D. M., Shih, L., Teevan, J., and Karger, D. R., "Tackling the Poor Assumptions of Naive Bayes Text Classifiers," ICML' 03, pp. 616--623, 2013.
+    class ComplementNB < BaseNaiveBayes
+      # Return the class labels.
+      # @return [Numo::Int32] (size: n_classes)
+      attr_reader :classes
+
+      # Return the prior probabilities of the classes.
+      # @return [Numo::DFloat] (shape: [n_classes])
+      attr_reader :class_priors
+
+      # Return the conditional probabilities for features of each class.
+      # @return [Numo::DFloat] (shape: [n_classes, n_features])
+      attr_reader :feature_probs
+
+      # Create a new classifier with Complement Naive Bayes.
+      #
+      # @param smoothing_param [Float] The smoothing parameter.
+      # @param norm [Boolean] The flag indicating whether to normlize the weight vectors.
+      def initialize(smoothing_param: 1.0, norm: false)
+        check_params_numeric(smoothing_param: smoothing_param)
+        check_params_positive(smoothing_param: smoothing_param)
+        check_params_boolean(norm: norm)
+        @params = {}
+        @params[:smoothing_param] = smoothing_param
+        @params[:norm] = norm
+      end
+
+      # Fit the model with given training data.
+      #
+      # @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 categorical variables (e.g. labels)
+      #   to be used for fitting the model.
+      # @return [ComplementNB] The learned classifier itself.
+      def fit(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_label_array(y)
+        check_sample_label_size(x, y)
+        n_samples, = x.shape
+        @classes = Numo::Int32[*y.to_a.uniq.sort]
+        @class_priors = Numo::DFloat[*@classes.to_a.map { |l| y.eq(l).count.fdiv(n_samples) }]
+        @class_log_probs = Numo::NMath.log(@class_priors)
+        compl_features = Numo::DFloat[*@classes.to_a.map { |l| x[y.ne(l).where, true].sum(0) }]
+        compl_features += @params[:smoothing_param]
+        n_classes = @classes.size
+        @feature_probs = compl_features / compl_features.sum(1).reshape(n_classes, 1)
+        feature_log_probs = Numo::NMath.log(@feature_probs)
+        @weights = if normalize?
+                     feature_log_probs / feature_log_probs.sum(1).reshape(n_classes, 1)
+                   else
+                     -feature_log_probs
+                   end
+        self
+      end
+
+      # Calculate confidence scores for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to compute the scores.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Confidence scores per sample for each class.
+      def decision_function(x)
+        x = check_convert_sample_array(x)
+        @class_log_probs + x.dot(@weights.transpose)
+      end
+
+      private
+
+      def normalize?
+        @params[:norm] == true
+      end
+    end
+  end
+end

data/lib/rumale/naive_bayes/gaussian_nb.rb

@@ -0,0 +1,69 @@
+# frozen_string_literal: true
+
+require 'rumale/naive_bayes/base_naive_bayes'
+
+module Rumale
+  module NaiveBayes
+    # GaussianNB is a class that implements Gaussian Naive Bayes classifier.
+    #
+    # @example
+    #   estimator = Rumale::NaiveBayes::GaussianNB.new
+    #   estimator.fit(training_samples, training_labels)
+    #   results = estimator.predict(testing_samples)
+    class GaussianNB < BaseNaiveBayes
+      # Return the class labels.
+      # @return [Numo::Int32] (size: n_classes)
+      attr_reader :classes
+
+      # Return the prior probabilities of the classes.
+      # @return [Numo::DFloat] (shape: [n_classes])
+      attr_reader :class_priors
+
+      # Return the mean vectors of the classes.
+      # @return [Numo::DFloat] (shape: [n_classes, n_features])
+      attr_reader :means
+
+      # Return the variance vectors of the classes.
+      # @return [Numo::DFloat] (shape: [n_classes, n_features])
+      attr_reader :variances
+
+      # Create a new classifier with Gaussian Naive Bayes.
+      def initialize
+        @params = {}
+      end
+
+      # Fit the model with given training data.
+      #
+      # @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 categorical variables (e.g. labels)
+      #   to be used for fitting the model.
+      # @return [GaussianNB] The learned classifier itself.
+      def fit(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_label_array(y)
+        check_sample_label_size(x, y)
+        n_samples, = x.shape
+        @classes = Numo::Int32[*y.to_a.uniq.sort]
+        @class_priors = Numo::DFloat[*@classes.to_a.map { |l| y.eq(l).count / n_samples.to_f }]
+        @means = Numo::DFloat[*@classes.to_a.map { |l| x[y.eq(l).where, true].mean(0) }]
+        @variances = Numo::DFloat[*@classes.to_a.map { |l| x[y.eq(l).where, true].var(0) }]
+        self
+      end
+
+      # Calculate confidence scores for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to compute the scores.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Confidence scores per sample for each class.
+      def decision_function(x)
+        x = check_convert_sample_array(x)
+        n_classes = @classes.size
+        log_likelihoods = Array.new(n_classes) do |l|
+          Math.log(@class_priors[l]) - 0.5 * (
+            Numo::NMath.log(2.0 * Math::PI * @variances[l, true]) +
+            ((x - @means[l, true])**2 / @variances[l, true])).sum(1)
+        end
+        Numo::DFloat[*log_likelihoods].transpose
+      end
+    end
+  end
+end

data/lib/rumale/naive_bayes/multinomial_nb.rb

@@ -0,0 +1,74 @@
+# frozen_string_literal: true
+
+require 'rumale/naive_bayes/base_naive_bayes'
+
+module Rumale
+  module NaiveBayes
+    # MultinomialNB is a class that implements Multinomial Naive Bayes classifier.
+    #
+    # @example
+    #   estimator = Rumale::NaiveBayes::MultinomialNB.new(smoothing_param: 1.0)
+    #   estimator.fit(training_samples, training_labels)
+    #   results = estimator.predict(testing_samples)
+    #
+    # *Reference*
+    # - C D. Manning, P. Raghavan, and H. Schutze, "Introduction to Information Retrieval," Cambridge University Press., 2008.
+    class MultinomialNB < BaseNaiveBayes
+      # Return the class labels.
+      # @return [Numo::Int32] (size: n_classes)
+      attr_reader :classes
+
+      # Return the prior probabilities of the classes.
+      # @return [Numo::DFloat] (shape: [n_classes])
+      attr_reader :class_priors
+
+      # Return the conditional probabilities for features of each class.
+      # @return [Numo::DFloat] (shape: [n_classes, n_features])
+      attr_reader :feature_probs
+
+      # Create a new classifier with Multinomial Naive Bayes.
+      #
+      # @param smoothing_param [Float] The Laplace smoothing parameter.
+      def initialize(smoothing_param: 1.0)
+        check_params_numeric(smoothing_param: smoothing_param)
+        check_params_positive(smoothing_param: smoothing_param)
+        @params = {}
+        @params[:smoothing_param] = smoothing_param
+      end
+
+      # Fit the model with given training data.
+      #
+      # @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 categorical variables (e.g. labels)
+      #   to be used for fitting the model.
+      # @return [MultinomialNB] The learned classifier itself.
+      def fit(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_label_array(y)
+        check_sample_label_size(x, y)
+        n_samples, = x.shape
+        @classes = Numo::Int32[*y.to_a.uniq.sort]
+        @class_priors = Numo::DFloat[*@classes.to_a.map { |l| y.eq(l).count / n_samples.to_f }]
+        count_features = Numo::DFloat[*@classes.to_a.map { |l| x[y.eq(l).where, true].sum(0) }]
+        count_features += @params[:smoothing_param]
+        n_classes = @classes.size
+        @feature_probs = count_features / count_features.sum(1).reshape(n_classes, 1)
+        self
+      end
+
+      # Calculate confidence scores for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to compute the scores.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Confidence scores per sample for each class.
+      def decision_function(x)
+        x = check_convert_sample_array(x)
+        n_classes = @classes.size
+        bin_x = x.gt(0)
+        log_likelihoods = Array.new(n_classes) do |l|
+          Math.log(@class_priors[l]) + (Numo::DFloat[*bin_x] * Numo::NMath.log(@feature_probs[l, true])).sum(1)
+        end
+        Numo::DFloat[*log_likelihoods].transpose
+      end
+    end
+  end
+end

data/lib/rumale/naive_bayes/negation_nb.rb

@@ -0,0 +1,71 @@
+# frozen_string_literal: true
+
+require 'rumale/naive_bayes/base_naive_bayes'
+
+module Rumale
+  module NaiveBayes
+    # NegationNB is a class that implements Negation Naive Bayes classifier.
+    #
+    # @example
+    #   estimator = Rumale::NaiveBayes::NegationNB.new(smoothing_param: 1.0)
+    #   estimator.fit(training_samples, training_labels)
+    #   results = estimator.predict(testing_samples)
+    #
+    # *Reference*
+    # - Komiya, K., Sato, N., Fujimoto, K., and Kotani, Y., "Negation Naive Bayes for Categorization of Product Pages on the Web," RANLP' 11, pp. 586--592, 2011.
+    class NegationNB < BaseNaiveBayes
+      # Return the class labels.
+      # @return [Numo::Int32] (size: n_classes)
+      attr_reader :classes
+
+      # Return the prior probabilities of the classes.
+      # @return [Numo::DFloat] (shape: [n_classes])
+      attr_reader :class_priors
+
+      # Return the conditional probabilities for features of each class.
+      # @return [Numo::DFloat] (shape: [n_classes, n_features])
+      attr_reader :feature_probs
+
+      # Create a new classifier with Complement Naive Bayes.
+      #
+      # @param smoothing_param [Float] The smoothing parameter.
+      def initialize(smoothing_param: 1.0)
+        check_params_numeric(smoothing_param: smoothing_param)
+        check_params_positive(smoothing_param: smoothing_param)
+        @params = {}
+        @params[:smoothing_param] = smoothing_param
+      end
+
+      # Fit the model with given training data.
+      #
+      # @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 categorical variables (e.g. labels)
+      #   to be used for fitting the model.
+      # @return [ComplementNB] The learned classifier itself.
+      def fit(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_label_array(y)
+        check_sample_label_size(x, y)
+        n_samples, = x.shape
+        @classes = Numo::Int32[*y.to_a.uniq.sort]
+        @class_priors = Numo::DFloat[*@classes.to_a.map { |l| y.eq(l).count.fdiv(n_samples) }]
+        @class_log_probs = Numo::NMath.log(1 / (1 - @class_priors))
+        compl_features = Numo::DFloat[*@classes.to_a.map { |l| x[y.ne(l).where, true].sum(0) }]
+        compl_features += @params[:smoothing_param]
+        n_classes = @classes.size
+        @feature_probs = compl_features / compl_features.sum(1).reshape(n_classes, 1)
+        @weights = Numo::NMath.log(@feature_probs)
+        self
+      end
+
+      # Calculate confidence scores for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to compute the scores.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Confidence scores per sample for each class.
+      def decision_function(x)
+        x = check_convert_sample_array(x)
+        @class_log_probs - x.dot(@weights.transpose)
+      end
+    end
+  end
+end

data/lib/rumale/nearest_neighbors/k_neighbors_classifier.rb

@@ -127,25 +127,6 @@ module Rumale
         n_samples = x.shape[0]
         Numo::Int32.asarray(Array.new(n_samples) { |n| @classes[decision_values[n, true].max_index] })
       end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about KNeighborsClassifier.
-      def marshal_dump
-        { params: @params,
-          prototypes: @prototypes,
-          labels: @labels,
-          classes: @classes }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @prototypes = obj[:prototypes]
-        @labels = obj[:labels]
-        @classes = obj[:classes]
-        nil
-      end
     end
   end
 end

data/lib/rumale/nearest_neighbors/k_neighbors_regressor.rb

@@ -101,23 +101,6 @@ module Rumale
         end
         Numo::DFloat[*predicted_values]
       end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about KNeighborsRegressor.
-      def marshal_dump
-        { params: @params,
-          prototypes: @prototypes,
-          values: @values }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @prototypes = obj[:prototypes]
-        @values = obj[:values]
-        nil
-      end
     end
   end
 end

data/lib/rumale/neural_network/adam.rb

@@ -50,25 +50,6 @@ module Rumale
 
           weight - @params[:learning_rate] * nm_fst_moment / (nm_sec_moment**0.5 + 1e-8)
         end
-
-        # Dump marshal data.
-        # @return [Hash] The marshal data.
-        # def marshal_dump
-        #  { params: @params,
-        #    fst_moment: @fst_moment,
-        #    sec_moment: @sec_moment,
-        #    iter: @iter }
-        # end
-
-        # Load marshal data.
-        # @return [nil]
-        # def marshal_load(obj)
-        #  @params = obj[:params]
-        #  @fst_moment = obj[:fst_moment]
-        #  @sec_moment = obj[:sec_moment]
-        #  @iter = obj[:iter]
-        #  nil
-        # end
       end
     end
   end