svmkit 0.7.3 → 0.8.1

data/lib/svmkit/linear_model/lasso.rb

@@ -1,138 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/linear_model/sgd_linear_estimator'
-require 'svmkit/base/regressor'
-
-module SVMKit
-  module LinearModel
-    # Lasso is a class that implements Lasso Regression
-    # with stochastic gradient descent (SGD) optimization.
-    #
-    # @example
-    #   estimator =
-    #     SVMKit::LinearModel::Lasso.new(reg_param: 0.1, max_iter: 1000, batch_size: 20, random_seed: 1)
-    #   estimator.fit(training_samples, traininig_values)
-    #   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.
-    # - L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proc. COMPSTAT'10, pp. 177--186, 2010.
-    class Lasso < SGDLinearEstimator
-      include Base::Regressor
-      include Validation
-
-      # Return the weight vector.
-      # @return [Numo::DFloat] (shape: [n_outputs, n_features])
-      attr_reader :weight_vec
-
-      # Return the bias term (a.k.a. intercept).
-      # @return [Numo::DFloat] (shape: [n_outputs])
-      attr_reader :bias_term
-
-      # Return the random generator for random sampling.
-      # @return [Random]
-      attr_reader :rng
-
-      # Create a new Lasso regressor.
-      #
-      # @param reg_param [Float] The regularization parameter.
-      # @param fit_bias [Boolean] The flag indicating whether to fit the bias term.
-      # @param bias_scale [Float] The scale of the bias term.
-      # @param max_iter [Integer] The maximum number of iterations.
-      # @param batch_size [Integer] The size of the mini batches.
-      # @param optimizer [Optimizer] The optimizer to calculate adaptive learning rate.
-      #   If nil is given, Nadam is used.
-      # @param random_seed [Integer] The seed value using to initialize the random generator.
-      def initialize(reg_param: 1.0, fit_bias: false, bias_scale: 1.0, max_iter: 1000, batch_size: 10, optimizer: nil, random_seed: nil)
-        check_params_float(reg_param: reg_param, bias_scale: bias_scale)
-        check_params_integer(max_iter: max_iter, batch_size: batch_size)
-        check_params_boolean(fit_bias: fit_bias)
-        check_params_type_or_nil(Integer, random_seed: random_seed)
-        check_params_positive(reg_param: reg_param, max_iter: max_iter, batch_size: batch_size)
-        super
-      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, n_outputs]) The target values to be used for fitting the model.
-      # @return [Lasso] The learned regressor itself.
-      def fit(x, y)
-        check_sample_array(x)
-        check_tvalue_array(y)
-        check_sample_tvalue_size(x, y)
-
-        n_outputs = y.shape[1].nil? ? 1 : y.shape[1]
-        n_features = x.shape[1]
-
-        if n_outputs > 1
-          @weight_vec = Numo::DFloat.zeros(n_outputs, n_features)
-          @bias_term = Numo::DFloat.zeros(n_outputs)
-          n_outputs.times { |n| @weight_vec[n, true], @bias_term[n] = partial_fit(x, y[true, n]) }
-        else
-          @weight_vec, @bias_term = partial_fit(x, y)
-        end
-
-        self
-      end
-
-      # Predict values for samples.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the values.
-      # @return [Numo::DFloat] (shape: [n_samples, n_outputs]) Predicted values per sample.
-      def predict(x)
-        check_sample_array(x)
-        x.dot(@weight_vec.transpose) + @bias_term
-      end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about Lasso.
-      def marshal_dump
-        { params: @params,
-          weight_vec: @weight_vec,
-          bias_term: @bias_term,
-          rng: @rng }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @weight_vec = obj[:weight_vec]
-        @bias_term = obj[:bias_term]
-        @rng = obj[:rng]
-        nil
-      end
-
-      private
-
-      def partial_fit(x, y)
-        n_features = @params[:fit_bias] ? x.shape[1] + 1 : x.shape[1]
-        @left_weight = Numo::DFloat.zeros(n_features)
-        @right_weight = Numo::DFloat.zeros(n_features)
-        @left_optimizer = @params[:optimizer].dup
-        @right_optimizer = @params[:optimizer].dup
-        super
-      end
-
-      def calc_loss_gradient(x, y, weight)
-        2.0 * (x.dot(weight) - y)
-      end
-
-      def calc_new_weight(_optimizer, x, _weight, loss_gradient)
-        @left_weight = round_weight(@left_optimizer.call(@left_weight, calc_weight_gradient(loss_gradient, x)))
-        @right_weight = round_weight(@right_optimizer.call(@right_weight, calc_weight_gradient(-loss_gradient, x)))
-        @left_weight - @right_weight
-      end
-
-      def calc_weight_gradient(loss_gradient, data)
-        ((@params[:reg_param] + loss_gradient).expand_dims(1) * data).mean(0)
-      end
-
-      def round_weight(weight)
-        0.5 * (weight + weight.abs)
-      end
-    end
-  end
-end

data/lib/svmkit/linear_model/linear_regression.rb

@@ -1,112 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/linear_model/sgd_linear_estimator'
-require 'svmkit/base/regressor'
-
-module SVMKit
-  module LinearModel
-    # LinearRegression is a class that implements ordinary least square linear regression
-    # with mini-batch stochastic gradient descent optimization.
-    #
-    # @example
-    #   estimator =
-    #     SVMKit::LinearModel::LinearRegression.new(max_iter: 1000, batch_size: 20, random_seed: 1)
-    #   estimator.fit(training_samples, traininig_values)
-    #   results = estimator.predict(testing_samples)
-    #
-    class LinearRegression < SGDLinearEstimator
-      include Base::Regressor
-      include Validation
-
-      # Return the weight vector.
-      # @return [Numo::DFloat] (shape: [n_outputs, n_features])
-      attr_reader :weight_vec
-
-      # Return the bias term (a.k.a. intercept).
-      # @return [Numo::DFloat] (shape: [n_outputs])
-      attr_reader :bias_term
-
-      # Return the random generator for random sampling.
-      # @return [Random]
-      attr_reader :rng
-
-      # Create a new ordinary least square linear regressor.
-      #
-      # @param fit_bias [Boolean] The flag indicating whether to fit the bias term.
-      # @param bias_scale [Float] The scale of the bias term.
-      # @param max_iter [Integer] The maximum number of iterations.
-      # @param batch_size [Integer] The size of the mini batches.
-      # @param optimizer [Optimizer] The optimizer to calculate adaptive learning rate.
-      #   If nil is given, Nadam is used.
-      # @param random_seed [Integer] The seed value using to initialize the random generator.
-      def initialize(fit_bias: false, bias_scale: 1.0, max_iter: 1000, batch_size: 10, optimizer: nil, random_seed: nil)
-        check_params_float(bias_scale: bias_scale)
-        check_params_integer(max_iter: max_iter, batch_size: batch_size)
-        check_params_boolean(fit_bias: fit_bias)
-        check_params_type_or_nil(Integer, random_seed: random_seed)
-        check_params_positive(max_iter: max_iter, batch_size: batch_size)
-        super(reg_param: 0.0, fit_bias: fit_bias, bias_scale: bias_scale,
-              max_iter: max_iter, batch_size: batch_size, optimizer: optimizer, random_seed: random_seed)
-      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, n_outputs]) The target values to be used for fitting the model.
-      # @return [LinearRegression] The learned regressor itself.
-      def fit(x, y)
-        check_sample_array(x)
-        check_tvalue_array(y)
-        check_sample_tvalue_size(x, y)
-
-        n_outputs = y.shape[1].nil? ? 1 : y.shape[1]
-        n_features = x.shape[1]
-
-        if n_outputs > 1
-          @weight_vec = Numo::DFloat.zeros(n_outputs, n_features)
-          @bias_term = Numo::DFloat.zeros(n_outputs)
-          n_outputs.times { |n| @weight_vec[n, true], @bias_term[n] = partial_fit(x, y[true, n]) }
-        else
-          @weight_vec, @bias_term = partial_fit(x, y)
-        end
-
-        self
-      end
-
-      # Predict values for samples.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the values.
-      # @return [Numo::DFloat] (shape: [n_samples, n_outputs]) Predicted values per sample.
-      def predict(x)
-        check_sample_array(x)
-        x.dot(@weight_vec.transpose) + @bias_term
-      end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about LinearRegression.
-      def marshal_dump
-        { params: @params,
-          weight_vec: @weight_vec,
-          bias_term: @bias_term,
-          rng: @rng }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @weight_vec = obj[:weight_vec]
-        @bias_term = obj[:bias_term]
-        @rng = obj[:rng]
-        nil
-      end
-
-      private
-
-      def calc_loss_gradient(x, y, weight)
-        2.0 * (x.dot(weight) - y)
-      end
-    end
-  end
-end

data/lib/svmkit/linear_model/logistic_regression.rb

@@ -1,161 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/linear_model/sgd_linear_estimator'
-require 'svmkit/base/classifier'
-
-module SVMKit
-  module LinearModel
-    # LogisticRegression is a class that implements Logistic Regression
-    # with mini-batch stochastic gradient descent optimization.
-    # For multiclass classification problem, it uses one-vs-the-rest strategy.
-    #
-    # @example
-    #   estimator =
-    #     SVMKit::LinearModel::LogisticRegression.new(reg_param: 1.0, max_iter: 1000, batch_size: 20, random_seed: 1)
-    #   estimator.fit(training_samples, traininig_labels)
-    #   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.
-    class LogisticRegression < SGDLinearEstimator
-      include Base::Classifier
-      include Validation
-
-      # Return the weight vector for Logistic Regression.
-      # @return [Numo::DFloat] (shape: [n_classes, n_features])
-      attr_reader :weight_vec
-
-      # Return the bias term (a.k.a. intercept) for Logistic Regression.
-      # @return [Numo::DFloat] (shape: [n_classes])
-      attr_reader :bias_term
-
-      # 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 Logisitc Regression by the SGD optimization.
-      #
-      # @param reg_param [Float] The regularization parameter.
-      # @param fit_bias [Boolean] The flag indicating whether to fit the bias term.
-      # @param bias_scale [Float] The scale of the bias term.
-      #   If fit_bias is true, the feature vector v becoms [v; bias_scale].
-      # @param max_iter [Integer] The maximum number of iterations.
-      # @param batch_size [Integer] The size of the mini batches.
-      # @param optimizer [Optimizer] The optimizer to calculate adaptive learning rate.
-      #   If nil is given, Nadam is used.
-      # @param random_seed [Integer] The seed value using to initialize the random generator.
-      def initialize(reg_param: 1.0, fit_bias: false, bias_scale: 1.0,
-                     max_iter: 1000, batch_size: 20, optimizer: nil, random_seed: nil)
-        check_params_float(reg_param: reg_param, bias_scale: bias_scale)
-        check_params_integer(max_iter: max_iter, batch_size: batch_size)
-        check_params_boolean(fit_bias: fit_bias)
-        check_params_type_or_nil(Integer, random_seed: random_seed)
-        check_params_positive(reg_param: reg_param, bias_scale: bias_scale, max_iter: max_iter, batch_size: batch_size)
-        super
-        @classes = nil
-      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 labels to be used for fitting the model.
-      # @return [LogisticRegression] The learned classifier itself.
-      def fit(x, y)
-        check_sample_array(x)
-        check_label_array(y)
-        check_sample_label_size(x, y)
-
-        @classes = Numo::Int32[*y.to_a.uniq.sort]
-        n_classes = @classes.size
-        n_features = x.shape[1]
-
-        if n_classes > 2
-          @weight_vec = Numo::DFloat.zeros(n_classes, n_features)
-          @bias_term = Numo::DFloat.zeros(n_classes)
-          n_classes.times do |n|
-            bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
-            @weight_vec[n, true], @bias_term[n] = partial_fit(x, bin_y)
-          end
-        else
-          negative_label = y.to_a.uniq.min
-          bin_y = Numo::Int32.cast(y.ne(negative_label)) * 2 - 1
-          @weight_vec, @bias_term = partial_fit(x, bin_y)
-        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 score per sample.
-      def decision_function(x)
-        check_sample_array(x)
-        x.dot(@weight_vec.transpose) + @bias_term
-      end
-
-      # Predict class labels for samples.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the labels.
-      # @return [Numo::Int32] (shape: [n_samples]) Predicted class label per sample.
-      def predict(x)
-        check_sample_array(x)
-
-        return Numo::Int32.cast(predict_proba(x)[true, 1].ge(0.5)) * 2 - 1 if @classes.size <= 2
-
-        n_samples, = x.shape
-        decision_values = predict_proba(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_samples, n_features]) The samples to predict the probailities.
-      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted probability of each class per sample.
-      def predict_proba(x)
-        check_sample_array(x)
-
-        proba = 1.0 / (Numo::NMath.exp(-decision_function(x)) + 1.0)
-        return (proba.transpose / proba.sum(axis: 1)).transpose if @classes.size > 2
-
-        n_samples, = x.shape
-        probs = Numo::DFloat.zeros(n_samples, 2)
-        probs[true, 1] = proba
-        probs[true, 0] = 1.0 - proba
-        probs
-      end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about LogisticRegression.
-      def marshal_dump
-        { params: @params,
-          weight_vec: @weight_vec,
-          bias_term: @bias_term,
-          classes: @classes,
-          rng: @rng }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @weight_vec = obj[:weight_vec]
-        @bias_term = obj[:bias_term]
-        @classes = obj[:classes]
-        @rng = obj[:rng]
-        nil
-      end
-
-      private
-
-      def calc_loss_gradient(x, y, weight)
-        y / (Numo::NMath.exp(-y * x.dot(weight)) + 1.0) - y
-      end
-    end
-  end
-end

data/lib/svmkit/linear_model/ridge.rb

@@ -1,112 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/linear_model/sgd_linear_estimator'
-require 'svmkit/base/regressor'
-
-module SVMKit
-  module LinearModel
-    # Ridge is a class that implements Ridge Regression
-    # with mini-batch stochastic gradient descent optimization.
-    #
-    # @example
-    #   estimator =
-    #     SVMKit::LinearModel::Ridge.new(reg_param: 0.1, max_iter: 1000, batch_size: 20, random_seed: 1)
-    #   estimator.fit(training_samples, traininig_values)
-    #   results = estimator.predict(testing_samples)
-    #
-    class Ridge < SGDLinearEstimator
-      include Base::Regressor
-      include Validation
-
-      # Return the weight vector.
-      # @return [Numo::DFloat] (shape: [n_outputs, n_features])
-      attr_reader :weight_vec
-
-      # Return the bias term (a.k.a. intercept).
-      # @return [Numo::DFloat] (shape: [n_outputs])
-      attr_reader :bias_term
-
-      # Return the random generator for random sampling.
-      # @return [Random]
-      attr_reader :rng
-
-      # Create a new Ridge regressor.
-      #
-      # @param reg_param [Float] The regularization parameter.
-      # @param fit_bias [Boolean] The flag indicating whether to fit the bias term.
-      # @param bias_scale [Float] The scale of the bias term.
-      # @param max_iter [Integer] The maximum number of iterations.
-      # @param batch_size [Integer] The size of the mini batches.
-      # @param optimizer [Optimizer] The optimizer to calculate adaptive learning rate.
-      #   If nil is given, Nadam is used.
-      # @param random_seed [Integer] The seed value using to initialize the random generator.
-      def initialize(reg_param: 1.0, fit_bias: false, bias_scale: 1.0, max_iter: 1000, batch_size: 10, optimizer: nil, random_seed: nil)
-        check_params_float(reg_param: reg_param, bias_scale: bias_scale)
-        check_params_integer(max_iter: max_iter, batch_size: batch_size)
-        check_params_boolean(fit_bias: fit_bias)
-        check_params_type_or_nil(Integer, random_seed: random_seed)
-        check_params_positive(reg_param: reg_param, max_iter: max_iter, batch_size: batch_size)
-        super
-      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, n_outputs]) The target values to be used for fitting the model.
-      # @return [Ridge] The learned regressor itself.
-      def fit(x, y)
-        check_sample_array(x)
-        check_tvalue_array(y)
-        check_sample_tvalue_size(x, y)
-
-        n_outputs = y.shape[1].nil? ? 1 : y.shape[1]
-        n_features = x.shape[1]
-
-        if n_outputs > 1
-          @weight_vec = Numo::DFloat.zeros(n_outputs, n_features)
-          @bias_term = Numo::DFloat.zeros(n_outputs)
-          n_outputs.times { |n| @weight_vec[n, true], @bias_term[n] = partial_fit(x, y[true, n]) }
-        else
-          @weight_vec, @bias_term = partial_fit(x, y)
-        end
-
-        self
-      end
-
-      # Predict values for samples.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the values.
-      # @return [Numo::DFloat] (shape: [n_samples, n_outputs]) Predicted values per sample.
-      def predict(x)
-        check_sample_array(x)
-        x.dot(@weight_vec.transpose) + @bias_term
-      end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about Ridge.
-      def marshal_dump
-        { params: @params,
-          weight_vec: @weight_vec,
-          bias_term: @bias_term,
-          rng: @rng }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @weight_vec = obj[:weight_vec]
-        @bias_term = obj[:bias_term]
-        @rng = obj[:rng]
-        nil
-      end
-
-      private
-
-      def calc_loss_gradient(x, y, weight)
-        2.0 * (x.dot(weight) - y)
-      end
-    end
-  end
-end