svmkit 0.7.3 → 0.8.1

data/lib/svmkit/evaluation_measure/precision_recall.rb

@@ -1,91 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/base/evaluator'
-
-module SVMKit
-  # This module consists of the classes for model evaluation.
-  module EvaluationMeasure
-    # @!visibility private
-    module PrecisionRecall
-      module_function
-
-      # @!visibility private
-      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)
-        end
-      end
-
-      # @!visibility private
-      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)
-        end
-      end
-
-      # @!visibility private
-      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
-
-      # @!visibility private
-      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]
-        end
-        res = evaluated_values.transpose.map { |v| v.inject(:+) }
-        res.first / res.last
-      end
-
-      # @!visibility private
-      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]
-        end
-        res = evaluated_values.transpose.map { |v| v.inject(:+) }
-        res.first / res.last
-      end
-
-      # @!visibility private
-      def micro_average_f_score(y_true, y_pred)
-        p = micro_average_precision(y_true, y_pred)
-        r = micro_average_recall(y_true, y_pred)
-        (2.0 * p * r) / (p + r)
-      end
-
-      # @!visibility private
-      def macro_average_precision(y_true, y_pred)
-        precision_each_class(y_true, y_pred).inject(:+) / y_true.to_a.uniq.size
-      end
-
-      # @!visibility private
-      def macro_average_recall(y_true, y_pred)
-        recall_each_class(y_true, y_pred).inject(:+) / y_true.to_a.uniq.size
-      end
-
-      # @!visibility private
-      def macro_average_f_score(y_true, y_pred)
-        f_score_each_class(y_true, y_pred).inject(:+) / y_true.to_a.uniq.size
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/purity.rb

@@ -1,41 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/evaluator'
-
-module SVMKit
-  module EvaluationMeasure
-    # Purity is a class that calculates the purity of cluatering results.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::Purity.new
-    #   puts evaluator.score(ground_truth, predicted)
-    #
-    # *Reference*
-    # - C D. Manning, P. Raghavan, and H. Schutze, "Introduction to Information Retrieval," Cambridge University Press., 2008.
-    class Purity
-      include Base::Evaluator
-
-      # Calculate purity
-      #
-      # @param y_true [Numo::Int32] (shape: [n_samples]) Ground truth labels.
-      # @param y_pred [Numo::Int32] (shape: [n_samples]) Predicted cluster labels.
-      # @return [Float] Purity
-      def score(y_true, y_pred)
-        SVMKit::Validation.check_label_array(y_true)
-        SVMKit::Validation.check_label_array(y_pred)
-        # initiazlie some variables.
-        purity = 0
-        n_samples = y_pred.size
-        class_ids = y_true.to_a.uniq
-        cluster_ids = y_pred.to_a.uniq
-        # calculate purity.
-        cluster_ids.each do |k|
-          pr_sample_ids = y_pred.eq(k).where.to_a
-          purity += class_ids.map { |j| (pr_sample_ids & y_true.eq(j).where.to_a).size }.max
-        end
-        purity.fdiv(n_samples)
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/r2_score.rb

@@ -1,44 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/evaluator'
-require 'svmkit/evaluation_measure/precision_recall'
-
-module SVMKit
-  module EvaluationMeasure
-    # R2Score is a class that calculates the coefficient of determination for the predicted values.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::R2Score.new
-    #   puts evaluator.score(ground_truth, predicted)
-    class R2Score
-      include Base::Evaluator
-
-      # Create a new evaluation measure calculater for coefficient of determination.
-      def initialize; end
-
-      # Calculate the coefficient of determination.
-      #
-      # @param y_true [Numo::DFloat] (shape: [n_samples, n_outputs]) Ground truth target values.
-      # @param y_pred [Numo::DFloat] (shape: [n_samples, n_outputs]) Estimated taget values.
-      # @return [Float] Coefficient of determination
-      def score(y_true, y_pred)
-        SVMKit::Validation.check_tvalue_array(y_true)
-        SVMKit::Validation.check_tvalue_array(y_pred)
-        raise ArgumentError, 'Expect to have the same size both y_true and y_pred.' unless y_true.shape == y_pred.shape
-
-        n_samples, n_outputs = y_true.shape
-        numerator = ((y_true - y_pred)**2).sum(0)
-        yt_mean = y_true.sum(0) / n_samples
-        denominator = ((y_true - yt_mean)**2).sum(0)
-        if n_outputs.nil?
-          denominator.zero? ? 0.0 : 1.0 - numerator / denominator
-        else
-          scores = 1 - numerator / denominator
-          scores[denominator.eq(0)] = 0.0
-          scores.sum / scores.size
-        end
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/recall.rb

@@ -1,51 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/evaluator'
-require 'svmkit/evaluation_measure/precision_recall'
-
-module SVMKit
-  # This module consists of the classes for model evaluation.
-  module EvaluationMeasure
-    # Recall is a class that calculates the recall of the predicted labels.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::Recall.new
-    #   puts evaluator.score(ground_truth, predicted)
-    class Recall
-      include Base::Evaluator
-      include EvaluationMeasure::PrecisionRecall
-
-      # Return the average type for calculation of recall.
-      # @return [String] ('binary', 'micro', 'macro')
-      attr_reader :average
-
-      # Create a new evaluation measure calculater for recall score.
-      #
-      # @param average [String] The average type ('binary', 'micro', 'macro')
-      def initialize(average: 'binary')
-        SVMKit::Validation.check_params_string(average: average)
-        @average = average
-      end
-
-      # Calculate average recall
-      #
-      # @param y_true [Numo::Int32] (shape: [n_samples]) Ground truth labels.
-      # @param y_pred [Numo::Int32] (shape: [n_samples]) Predicted labels.
-      # @return [Float] Average recall
-      def score(y_true, y_pred)
-        SVMKit::Validation.check_label_array(y_true)
-        SVMKit::Validation.check_label_array(y_pred)
-
-        case @average
-        when 'binary'
-          recall_each_class(y_true, y_pred).last
-        when 'micro'
-          micro_average_recall(y_true, y_pred)
-        when 'macro'
-          macro_average_recall(y_true, y_pred)
-        end
-      end
-    end
-  end
-end

data/lib/svmkit/kernel_approximation/rbf.rb

@@ -1,136 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/base_estimator'
-require 'svmkit/base/transformer'
-
-module SVMKit
-  # Module for kernel approximation algorithms.
-  module KernelApproximation
-    # Class for RBF kernel feature mapping.
-    #
-    # @example
-    #   transformer = SVMKit::KernelApproximation::RBF.new(gamma: 1.0, n_coponents: 128, random_seed: 1)
-    #   new_training_samples = transformer.fit_transform(training_samples)
-    #   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.
-    class RBF
-      include Base::BaseEstimator
-      include Base::Transformer
-
-      # Return the random matrix for transformation.
-      # @return [Numo::DFloat] (shape: [n_features, n_components])
-      attr_reader :random_mat
-
-      # Return the random vector for transformation.
-      # @return [Numo::DFloat] (shape: [n_components])
-      attr_reader :random_vec
-
-      # Return the random generator for transformation.
-      # @return [Random]
-      attr_reader :rng
-
-      # Create a new transformer for mapping to RBF kernel feature space.
-      #
-      # @param gamma [Float] The parameter of RBF kernel: exp(-gamma * x^2).
-      # @param n_components [Integer] The number of dimensions of the RBF kernel feature space.
-      # @param random_seed [Integer] The seed value using to initialize the random generator.
-      def initialize(gamma: 1.0, n_components: 128, random_seed: nil)
-        SVMKit::Validation.check_params_float(gamma: gamma)
-        SVMKit::Validation.check_params_integer(n_components: n_components)
-        SVMKit::Validation.check_params_type_or_nil(Integer, random_seed: random_seed)
-        SVMKit::Validation.check_params_positive(gamma: gamma, n_components: n_components)
-        @params = {}
-        @params[:gamma] = gamma
-        @params[:n_components] = n_components
-        @params[:random_seed] = random_seed
-        @params[:random_seed] ||= srand
-        @random_mat = nil
-        @random_vec = nil
-        @rng = Random.new(@params[:random_seed])
-      end
-
-      # Fit the model with given training data.
-      #
-      # @overload fit(x) -> RBF
-      #
-      # @param x [Numo::NArray] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
-      #   This method uses only the number of features of the data.
-      # @return [RBF] The learned transformer itself.
-      def fit(x, _y = nil)
-        SVMKit::Validation.check_sample_array(x)
-
-        n_features = x.shape[1]
-        @params[:n_components] = 2 * n_features if @params[:n_components] <= 0
-        @random_mat = rand_normal([n_features, @params[:n_components]]) * (2.0 * @params[:gamma])**0.5
-        n_half_components = @params[:n_components] / 2
-        @random_vec = Numo::DFloat.zeros(@params[:n_components] - n_half_components).concatenate(
-          Numo::DFloat.ones(n_half_components) * (0.5 * Math::PI)
-        )
-        self
-      end
-
-      # Fit the model with training data, and then transform them with the learned model.
-      #
-      # @overload fit_transform(x) -> Numo::DFloat
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
-      # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data
-      def fit_transform(x, _y = nil)
-        SVMKit::Validation.check_sample_array(x)
-
-        fit(x).transform(x)
-      end
-
-      # Transform the given data with the learned model.
-      #
-      # @overload transform(x) -> Numo::DFloat
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The data to be transformed with the learned model.
-      # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data.
-      def transform(x)
-        SVMKit::Validation.check_sample_array(x)
-
-        n_samples, = x.shape
-        projection = x.dot(@random_mat) + @random_vec.tile(n_samples, 1)
-        Numo::NMath.sin(projection) * ((2.0 / @params[:n_components])**0.5)
-      end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about RBF.
-      def marshal_dump
-        { params: @params,
-          random_mat: @random_mat,
-          random_vec: @random_vec,
-          rng: @rng }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @random_mat = obj[:random_mat]
-        @random_vec = obj[:random_vec]
-        @rng = obj[:rng]
-        nil
-      end
-
-      private
-
-      # Generate the uniform random matrix with the given shape.
-      def rand_uniform(shape)
-        rnd_vals = Array.new(shape.inject(:*)) { @rng.rand }
-        Numo::DFloat.asarray(rnd_vals).reshape(shape[0], shape[1])
-      end
-
-      # Generate the normal random matrix with the given shape, mean, and standard deviation.
-      def rand_normal(shape, mu = 0.0, sigma = 1.0)
-        a = rand_uniform(shape)
-        b = rand_uniform(shape)
-        (Numo::NMath.sqrt(Numo::NMath.log(a) * -2.0) * Numo::NMath.sin(b * 2.0 * Math::PI)) * sigma + mu
-      end
-    end
-  end
-end

data/lib/svmkit/kernel_machine/kernel_svc.rb

@@ -1,194 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/base_estimator'
-require 'svmkit/base/classifier'
-require 'svmkit/probabilistic_output'
-
-module SVMKit
-  # This module consists of the classes that implement kernel method-based estimator.
-  module KernelMachine
-    # KernelSVC is a class that implements (Nonlinear) Kernel Support Vector Classifier
-    # with stochastic gradient descent (SGD) optimization.
-    # For multiclass classification problem, it uses one-vs-the-rest strategy.
-    #
-    # @example
-    #   training_kernel_matrix = SVMKit::PairwiseMetric::rbf_kernel(training_samples)
-    #   estimator =
-    #     SVMKit::KernelMachine::KernelSVC.new(reg_param: 1.0, max_iter: 1000, random_seed: 1)
-    #   estimator.fit(training_kernel_matrix, traininig_labels)
-    #   testing_kernel_matrix = SVMKit::PairwiseMetric::rbf_kernel(testing_samples, training_samples)
-    #   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.
-    class KernelSVC
-      include Base::BaseEstimator
-      include Base::Classifier
-
-      # Return the weight vector for Kernel SVC.
-      # @return [Numo::DFloat] (shape: [n_classes, n_trainig_sample])
-      attr_reader :weight_vec
-
-      # Return the class labels.
-      # @return [Numo::Int32] (shape: [n_classes])
-      attr_reader :classes
-
-      # Return the random generator for performing random sampling.
-      # @return [Random]
-      attr_reader :rng
-
-      # Create a new classifier with Kernel Support Vector Machine by the SGD optimization.
-      #
-      # @param reg_param [Float] The regularization parameter.
-      # @param max_iter [Integer] The maximum number of iterations.
-      # @param probability [Boolean] The flag indicating whether to perform probability estimation.
-      # @param random_seed [Integer] The seed value using to initialize the random generator.
-      def initialize(reg_param: 1.0, max_iter: 1000, probability: false, random_seed: nil)
-        SVMKit::Validation.check_params_float(reg_param: reg_param)
-        SVMKit::Validation.check_params_integer(max_iter: max_iter)
-        SVMKit::Validation.check_params_boolean(probability: probability)
-        SVMKit::Validation.check_params_type_or_nil(Integer, random_seed: random_seed)
-        SVMKit::Validation.check_params_positive(reg_param: reg_param, max_iter: max_iter)
-        @params = {}
-        @params[:reg_param] = reg_param
-        @params[:max_iter] = max_iter
-        @params[:probability] = probability
-        @params[:random_seed] = random_seed
-        @params[:random_seed] ||= srand
-        @weight_vec = nil
-        @prob_param = nil
-        @classes = nil
-        @rng = Random.new(@params[:random_seed])
-      end
-
-      # Fit the model with given training data.
-      #
-      # @param x [Numo::DFloat] (shape: [n_training_samples, n_training_samples])
-      #   The kernel matrix of the training data to be used for fitting the model.
-      # @param y [Numo::Int32] (shape: [n_training_samples]) The labels to be used for fitting the model.
-      # @return [KernelSVC] The learned classifier itself.
-      def fit(x, y)
-        SVMKit::Validation.check_sample_array(x)
-        SVMKit::Validation.check_label_array(y)
-        SVMKit::Validation.check_sample_label_size(x, y)
-
-        @classes = Numo::Int32[*y.to_a.uniq.sort]
-        n_classes = @classes.size
-        _n_samples, n_features = x.shape
-
-        if n_classes > 2
-          @weight_vec = Numo::DFloat.zeros(n_classes, n_features)
-          @prob_param = Numo::DFloat.zeros(n_classes, 2)
-          n_classes.times do |n|
-            bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
-            @weight_vec[n, true] = binary_fit(x, bin_y)
-            @prob_param[n, true] = if @params[:probability]
-                                     SVMKit::ProbabilisticOutput.fit_sigmoid(x.dot(@weight_vec[n, true].transpose), bin_y)
-                                   else
-                                     Numo::DFloat[1, 0]
-                                   end
-          end
-        else
-          negative_label = y.to_a.uniq.min
-          bin_y = Numo::Int32.cast(y.ne(negative_label)) * 2 - 1
-          @weight_vec = binary_fit(x, bin_y)
-          @prob_param = if @params[:probability]
-                          SVMKit::ProbabilisticOutput.fit_sigmoid(x.dot(@weight_vec.transpose), bin_y)
-                        else
-                          Numo::DFloat[1, 0]
-                        end
-        end
-
-        self
-      end
-
-      # Calculate confidence scores for samples.
-      #
-      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
-      #     The kernel matrix between testing samples and training samples to compute the scores.
-      # @return [Numo::DFloat] (shape: [n_testing_samples, n_classes]) Confidence score per sample.
-      def decision_function(x)
-        SVMKit::Validation.check_sample_array(x)
-
-        x.dot(@weight_vec.transpose)
-      end
-
-      # Predict class labels for samples.
-      #
-      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
-      #     The kernel matrix between testing samples and training samples to predict the labels.
-      # @return [Numo::Int32] (shape: [n_testing_samples]) Predicted class label per sample.
-      def predict(x)
-        SVMKit::Validation.check_sample_array(x)
-
-        return Numo::Int32.cast(decision_function(x).ge(0.0)) * 2 - 1 if @classes.size <= 2
-
-        n_samples, = x.shape
-        decision_values = decision_function(x)
-        Numo::Int32.asarray(Array.new(n_samples) { |n| @classes[decision_values[n, true].max_index] })
-      end
-
-      # Predict probability for samples.
-      #
-      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
-      #     The kernel matrix between testing samples and training samples to predict the labels.
-      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted probability of each class per sample.
-      def predict_proba(x)
-        SVMKit::Validation.check_sample_array(x)
-
-        if @classes.size > 2
-          probs = 1.0 / (Numo::NMath.exp(@prob_param[true, 0] * decision_function(x) + @prob_param[true, 1]) + 1.0)
-          return (probs.transpose / probs.sum(axis: 1)).transpose
-        end
-
-        n_samples, = x.shape
-        probs = Numo::DFloat.zeros(n_samples, 2)
-        probs[true, 1] = 1.0 / (Numo::NMath.exp(@prob_param[0] * decision_function(x) + @prob_param[1]) + 1.0)
-        probs[true, 0] = 1.0 - probs[true, 1]
-        probs
-      end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about KernelSVC.
-      def marshal_dump
-        { params: @params,
-          weight_vec: @weight_vec,
-          prob_param: @prob_param,
-          classes: @classes,
-          rng: @rng }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @weight_vec = obj[:weight_vec]
-        @prob_param = obj[:prob_param]
-        @classes = obj[:classes]
-        @rng = obj[:rng]
-        nil
-      end
-
-      private
-
-      def binary_fit(x, bin_y)
-        # Initialize some variables.
-        n_training_samples = x.shape[0]
-        rand_ids = []
-        weight_vec = Numo::DFloat.zeros(n_training_samples)
-        # Start optimization.
-        @params[:max_iter].times do |t|
-          # random sampling
-          rand_ids = [*0...n_training_samples].shuffle(random: @rng) if rand_ids.empty?
-          target_id = rand_ids.shift
-          # update the weight vector
-          func = (weight_vec * bin_y).dot(x[target_id, true].transpose).to_f
-          func *= bin_y[target_id] / (@params[:reg_param] * (t + 1))
-          weight_vec[target_id] += 1.0 if func < 1.0
-        end
-        weight_vec * bin_y
-      end
-    end
-  end
-end