svmkit 0.7.3 → 0.8.1

data/lib/svmkit/pipeline/pipeline.rb

@@ -1,197 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/base_estimator'
-
-module SVMKit
-  # Module implements utilities of pipeline that cosists of a chain of transfomers and estimators.
-  module Pipeline
-    # Pipeline is a class that implements the function to perform the transformers and estimators sequencially.
-    #
-    # @example
-    #   rbf = SVMKit::KernelApproximation::RBF.new(gamma: 1.0, n_coponents: 128, random_seed: 1)
-    #   svc = SVMKit::LinearModel::SVC.new(reg_param: 1.0, fit_bias: true, max_iter: 5000, random_seed: 1)
-    #   pipeline = SVMKit::Pipeline::Pipeline.new(steps: { trs: rbf, est: svc })
-    #   pipeline.fit(training_samples, traininig_labels)
-    #   results = pipeline.predict(testing_samples)
-    #
-    class Pipeline
-      include Base::BaseEstimator
-      include Validation
-
-      # Return the steps.
-      # @return [Hash]
-      attr_reader :steps
-
-      # Create a new pipeline.
-      #
-      # @param steps [Hash] List of transformers and estimators. The order of transforms follows the insertion order of hash keys.
-      #   The last entry is considered an estimator.
-      def initialize(steps:)
-        check_params_type(Hash, steps: steps)
-        validate_steps(steps)
-        @params = {}
-        @steps = steps
-      end
-
-      # Fit the model with given training data.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be transformed and used for fitting the model.
-      # @param y [Numo::NArray] (shape: [n_samples, n_outputs]) The target values or labels to be used for fitting the model.
-      # @return [Pipeline] The learned pipeline itself.
-      def fit(x, y)
-        check_sample_array(x)
-        trans_x = apply_transforms(x, y, fit: true)
-        last_estimator.fit(trans_x, y) unless last_estimator.nil?
-        self
-      end
-
-      # Call the fit_predict method of last estimator after applying all transforms.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be transformed and used for fitting the model.
-      # @param y [Numo::NArray] (shape: [n_samples, n_outputs], default: nil) The target values or labels to be used for fitting the model.
-      # @return [Numo::NArray] The predicted results by last estimator.
-      def fit_predict(x, y = nil)
-        check_sample_array(x)
-        trans_x = apply_transforms(x, y, fit: true)
-        last_estimator.fit_predict(trans_x)
-      end
-
-      # Call the fit_transform method of last estimator after applying all transforms.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be transformed and used for fitting the model.
-      # @param y [Numo::NArray] (shape: [n_samples, n_outputs], default: nil) The target values or labels to be used for fitting the model.
-      # @return [Numo::NArray] The predicted results by last estimator.
-      def fit_transform(x, y = nil)
-        check_sample_array(x)
-        trans_x = apply_transforms(x, y, fit: true)
-        last_estimator.fit_transform(trans_x, y)
-      end
-
-      # Call the decision_function method of last estimator after applying all transforms.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to compute the scores.
-      # @return [Numo::DFloat] (shape: [n_samples]) Confidence score per sample.
-      def decision_function(x)
-        check_sample_array(x)
-        trans_x = apply_transforms(x)
-        last_estimator.decision_function(trans_x)
-      end
-
-      # Call the predict method of last estimator after applying all transforms.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to obtain prediction result.
-      # @return [Numo::NArray] The predicted results by last estimator.
-      def predict(x)
-        check_sample_array(x)
-        trans_x = apply_transforms(x)
-        last_estimator.predict(trans_x)
-      end
-
-      # Call the predict_log_proba method of last estimator after applying all transforms.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the log-probailities.
-      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted log-probability of each class per sample.
-      def predict_log_proba(x)
-        check_sample_array(x)
-        trans_x = apply_transforms(x)
-        last_estimator.predict_log_proba(trans_x)
-      end
-
-      # Call the predict_proba method of last estimator after applying all transforms.
-      #
-      # @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)
-        trans_x = apply_transforms(x)
-        last_estimator.predict_proba(trans_x)
-      end
-
-      # Call the transform method of last estimator after applying all transforms.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to be transformed.
-      # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed samples.
-      def transform(x)
-        check_sample_array(x)
-        trans_x = apply_transforms(x)
-        last_estimator.nil? ? trans_x : last_estimator.transform(trans_x)
-      end
-
-      # Call the inverse_transform method in reverse order.
-      #
-      # @param z [Numo::DFloat] (shape: [n_samples, n_components]) The transformed samples to be restored into original space.
-      # @return [Numo::DFloat] (shape: [n_samples, n_featuress]) The restored samples.
-      def inverse_transform(z)
-        check_sample_array(z)
-        itrans_z = z
-        @steps.keys.reverse_each do |name|
-          transformer = @steps[name]
-          next if transformer.nil?
-          itrans_z = transformer.inverse_transform(itrans_z)
-        end
-        itrans_z
-      end
-
-      # Call the score method of last estimator after applying all transforms.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) Testing data.
-      # @param y [Numo::NArray] (shape: [n_samples, n_outputs]) True target values or labels for testing data.
-      # @return [Float] The score of last estimator
-      def score(x, y)
-        check_sample_array(x)
-        trans_x = apply_transforms(x)
-        last_estimator.score(trans_x, y)
-      end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about Pipeline.
-      def marshal_dump
-        { params: @params,
-          steps: @steps }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @steps = obj[:steps]
-        nil
-      end
-
-      private
-
-      def validate_steps(steps)
-        steps.keys[0...-1].each do |name|
-          transformer = steps[name]
-          next if transformer.nil? || %i[fit transform].all? { |m| transformer.class.method_defined?(m) }
-          raise TypeError,
-                'Class of intermediate step in pipeline should be implemented fit and transform methods: ' \
-                "#{name} => #{transformer.class}"
-        end
-
-        estimator = steps[steps.keys.last]
-        unless estimator.nil? || estimator.class.method_defined?(:fit)
-          raise TypeError,
-                'Class of last step in pipeline should be implemented fit method: ' \
-                "#{steps.keys.last} => #{estimator.class}"
-        end
-      end
-
-      def apply_transforms(x, y = nil, fit: false)
-        trans_x = x
-        @steps.keys[0...-1].each do |name|
-          transformer = @steps[name]
-          next if transformer.nil?
-          transformer.fit(trans_x, y) if fit
-          trans_x = transformer.transform(trans_x)
-        end
-        trans_x
-      end
-
-      def last_estimator
-        @steps[@steps.keys.last]
-      end
-    end
-  end
-end

data/lib/svmkit/polynomial_model/factorization_machine_classifier.rb

@@ -1,262 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/base_estimator'
-require 'svmkit/base/classifier'
-require 'svmkit/optimizer/nadam'
-
-module SVMKit
-  # This module consists of the classes that implement polynomial models.
-  module PolynomialModel
-    # FactorizationMachineClassifier is a class that implements Factorization Machine
-    # with stochastic gradient descent (SGD) optimization.
-    # For multiclass classification problem, it uses one-vs-the-rest strategy.
-    #
-    # @example
-    #   estimator =
-    #     SVMKit::PolynomialModel::FactorizationMachineClassifier.new(
-    #      n_factors: 10, loss: 'hinge', reg_param_linear: 0.001, reg_param_factor: 0.001,
-    #      max_iter: 5000, batch_size: 50, random_seed: 1)
-    #   estimator.fit(training_samples, traininig_labels)
-    #   results = estimator.predict(testing_samples)
-    #
-    # *Reference*
-    # - S. Rendle, "Factorization Machines with libFM," ACM TIST, vol. 3 (3), pp. 57:1--57:22, 2012.
-    # - S. Rendle, "Factorization Machines," Proc. ICDM'10, pp. 995--1000, 2010.
-    class FactorizationMachineClassifier
-      include Base::BaseEstimator
-      include Base::Classifier
-      include Validation
-
-      # Return the factor matrix for Factorization Machine.
-      # @return [Numo::DFloat] (shape: [n_classes, n_factors, n_features])
-      attr_reader :factor_mat
-
-      # Return the weight vector for Factorization Machine.
-      # @return [Numo::DFloat] (shape: [n_classes, n_features])
-      attr_reader :weight_vec
-
-      # Return the bias term for Factoriazation Machine.
-      # @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 random sampling.
-      # @return [Random]
-      attr_reader :rng
-
-      # Create a new classifier with Factorization Machine.
-      #
-      # @param n_factors [Integer] The maximum number of iterations.
-      # @param loss [String] The loss function ('hinge' or 'logistic').
-      # @param reg_param_linear [Float] The regularization parameter for linear model.
-      # @param reg_param_factor [Float] The regularization parameter for factor matrix.
-      # @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(n_factors: 2, loss: 'hinge', reg_param_linear: 1.0, reg_param_factor: 1.0,
-                     max_iter: 1000, batch_size: 10, optimizer: nil, random_seed: nil)
-        check_params_float(reg_param_linear: reg_param_linear, reg_param_factor: reg_param_factor)
-        check_params_integer(n_factors: n_factors, max_iter: max_iter, batch_size: batch_size)
-        check_params_string(loss: loss)
-        check_params_type_or_nil(Integer, random_seed: random_seed)
-        check_params_positive(n_factors: n_factors,
-                              reg_param_linear: reg_param_linear, reg_param_factor: reg_param_factor,
-                              max_iter: max_iter, batch_size: batch_size)
-        @params = {}
-        @params[:n_factors] = n_factors
-        @params[:loss] = loss
-        @params[:reg_param_linear] = reg_param_linear
-        @params[:reg_param_factor] = reg_param_factor
-        @params[:max_iter] = max_iter
-        @params[:batch_size] = batch_size
-        @params[:optimizer] = optimizer
-        @params[:optimizer] ||= Optimizer::Nadam.new
-        @params[:random_seed] = random_seed
-        @params[:random_seed] ||= srand
-        @factor_mat = nil
-        @weight_vec = nil
-        @bias_term = nil
-        @classes = nil
-        @rng = Random.new(@params[: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]) The labels to be used for fitting the model.
-      # @return [FactorizationMachineClassifier] 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_samples, n_features = x.shape
-
-        if n_classes > 2
-          @factor_mat = Numo::DFloat.zeros(n_classes, @params[:n_factors], n_features)
-          @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
-            @factor_mat[n, true, true], @weight_vec[n, true], @bias_term[n] = binary_fit(x, bin_y)
-          end
-        else
-          negative_label = y.to_a.uniq.min
-          bin_y = Numo::Int32.cast(y.ne(negative_label)) * 2 - 1
-          @factor_mat, @weight_vec, @bias_term = binary_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]) Confidence score per sample.
-      def decision_function(x)
-        check_sample_array(x)
-        linear_term = @bias_term + x.dot(@weight_vec.transpose)
-        factor_term = if @classes.size <= 2
-                        0.5 * (@factor_mat.dot(x.transpose)**2 - (@factor_mat**2).dot(x.transpose**2)).sum(0)
-                      else
-                        0.5 * (@factor_mat.dot(x.transpose)**2 - (@factor_mat**2).dot(x.transpose**2)).sum(1).transpose
-                      end
-        linear_term + factor_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(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_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 FactorizationMachineClassifier.
-      def marshal_dump
-        { params: @params,
-          factor_mat: @factor_mat,
-          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]
-        @factor_mat = obj[:factor_mat]
-        @weight_vec = obj[:weight_vec]
-        @bias_term = obj[:bias_term]
-        @classes = obj[:classes]
-        @rng = obj[:rng]
-        nil
-      end
-
-      private
-
-      def binary_fit(x, y)
-        # Initialize some variables.
-        n_samples, n_features = x.shape
-        rand_ids = [*0...n_samples].shuffle(random: @rng)
-        weight_vec = Numo::DFloat.zeros(n_features + 1)
-        factor_mat = Numo::DFloat.zeros(@params[:n_factors], n_features)
-        weight_optimizer = @params[:optimizer].dup
-        factor_optimizers = Array.new(@params[:n_factors]) { @params[:optimizer].dup }
-        # Start optimization.
-        @params[:max_iter].times do |_t|
-          # Random sampling.
-          subset_ids = rand_ids.shift(@params[:batch_size])
-          rand_ids.concat(subset_ids)
-          data = x[subset_ids, true]
-          ex_data = expand_feature(data)
-          label = y[subset_ids]
-          # Calculate gradients for loss function.
-          loss_grad = loss_gradient(data, ex_data, label, factor_mat, weight_vec)
-          next if loss_grad.ne(0.0).count.zero?
-          # Update each parameter.
-          weight_vec = weight_optimizer.call(weight_vec, weight_gradient(loss_grad, ex_data, weight_vec))
-          @params[:n_factors].times do |n|
-            factor_mat[n, true] = factor_optimizers[n].call(factor_mat[n, true],
-                                                            factor_gradient(loss_grad, data, factor_mat[n, true]))
-          end
-        end
-        [factor_mat, *split_weight_vec_bias(weight_vec)]
-      end
-
-      def bin_decision_function(x, ex_x, factor, weight)
-        ex_x.dot(weight) + 0.5 * (factor.dot(x.transpose)**2 - (factor**2).dot(x.transpose**2)).sum(0)
-      end
-
-      def hinge_loss_gradient(x, ex_x, y, factor, weight)
-        evaluated = y * bin_decision_function(x, ex_x, factor, weight)
-        gradient = Numo::DFloat.zeros(evaluated.size)
-        gradient[evaluated < 1.0] = -y[evaluated < 1.0]
-        gradient
-      end
-
-      def logistic_loss_gradient(x, ex_x, y, factor, weight)
-        evaluated = y * bin_decision_function(x, ex_x, factor, weight)
-        sigmoid_func = 1.0 / (Numo::NMath.exp(-evaluated) + 1.0)
-        (sigmoid_func - 1.0) * y
-      end
-
-      def loss_gradient(x, ex_x, y, factor, weight)
-        if @params[:loss] == 'hinge'
-          hinge_loss_gradient(x, ex_x, y, factor, weight)
-        else
-          logistic_loss_gradient(x, ex_x, y, factor, weight)
-        end
-      end
-
-      def weight_gradient(loss_grad, data, weight)
-        (loss_grad.expand_dims(1) * data).mean(0) + @params[:reg_param_linear] * weight
-      end
-
-      def factor_gradient(loss_grad, data, factor)
-        (loss_grad.expand_dims(1) * (data * data.dot(factor).expand_dims(1) - factor * (data**2))).mean(0) + @params[:reg_param_factor] * factor
-      end
-
-      def expand_feature(x)
-        Numo::NArray.hstack([x, Numo::DFloat.ones([x.shape[0], 1])])
-      end
-
-      def split_weight_vec_bias(weight_vec)
-        weights = weight_vec[0...-1].dup
-        bias = weight_vec[-1]
-        [weights, bias]
-      end
-    end
-  end
-end