svmkit 0.7.3 → 0.8.1

data/lib/svmkit/ensemble/random_forest_regressor.rb

@@ -1,143 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/values'
-require 'svmkit/base/base_estimator'
-require 'svmkit/base/regressor'
-require 'svmkit/tree/decision_tree_regressor'
-
-module SVMKit
-  module Ensemble
-    # RandomForestRegressor is a class that implements random forest for regression
-    #
-    # @example
-    #   estimator =
-    #     SVMKit::Ensemble::RandomForestRegressor.new(
-    #       n_estimators: 10, criterion: 'mse', max_depth: 3, max_leaf_nodes: 10, min_samples_leaf: 5, random_seed: 1)
-    #   estimator.fit(training_samples, traininig_values)
-    #   results = estimator.predict(testing_samples)
-    #
-    class RandomForestRegressor
-      include Base::BaseEstimator
-      include Base::Regressor
-      include Validation
-
-      # Return the set of estimators.
-      # @return [Array<DecisionTreeRegressor>]
-      attr_reader :estimators
-
-      # Return the importance for each feature.
-      # @return [Numo::DFloat] (size: n_features)
-      attr_reader :feature_importances
-
-      # Return the random generator for random selection of feature index.
-      # @return [Random]
-      attr_reader :rng
-
-      # Create a new regressor with random forest.
-      #
-      # @param n_estimators [Integer] The numeber of decision trees for contructing random forest.
-      # @param criterion [String] The function to evalue spliting point. Supported criteria are 'gini' and 'entropy'.
-      # @param max_depth [Integer] The maximum depth of the tree.
-      #   If nil is given, decision tree grows without concern for depth.
-      # @param max_leaf_nodes [Integer] The maximum number of leaves on decision tree.
-      #   If nil is given, number of leaves is not limited.
-      # @param min_samples_leaf [Integer] The minimum number of samples at a leaf node.
-      # @param max_features [Integer] The number of features to consider when searching optimal split point.
-      #   If nil is given, split process considers all features.
-      # @param random_seed [Integer] The seed value using to initialize the random generator.
-      #   It is used to randomly determine the order of features when deciding spliting point.
-      def initialize(n_estimators: 10,
-                     criterion: 'mse', max_depth: nil, max_leaf_nodes: nil, min_samples_leaf: 1,
-                     max_features: nil, random_seed: nil)
-        check_params_type_or_nil(Integer, max_depth: max_depth, max_leaf_nodes: max_leaf_nodes,
-                                          max_features: max_features, random_seed: random_seed)
-        check_params_integer(n_estimators: n_estimators, min_samples_leaf: min_samples_leaf)
-        check_params_string(criterion: criterion)
-        check_params_positive(n_estimators: n_estimators, max_depth: max_depth,
-                              max_leaf_nodes: max_leaf_nodes, min_samples_leaf: min_samples_leaf,
-                              max_features: max_features)
-        @params = {}
-        @params[:n_estimators] = n_estimators
-        @params[:criterion] = criterion
-        @params[:max_depth] = max_depth
-        @params[:max_leaf_nodes] = max_leaf_nodes
-        @params[:min_samples_leaf] = min_samples_leaf
-        @params[:max_features] = max_features
-        @params[:random_seed] = random_seed
-        @params[:random_seed] ||= srand
-        @estimators = nil
-        @feature_importances = 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::DFloat] (shape: [n_samples, n_outputs]) The target values to be used for fitting the model.
-      # @return [RandomForestRegressor] The learned regressor itself.
-      def fit(x, y)
-        check_sample_array(x)
-        check_tvalue_array(y)
-        check_sample_tvalue_size(x, y)
-        # Initialize some variables.
-        n_samples, n_features = x.shape
-        @params[:max_features] = Math.sqrt(n_features).to_i unless @params[:max_features].is_a?(Integer)
-        @params[:max_features] = [[1, @params[:max_features]].max, n_features].min
-        @feature_importances = Numo::DFloat.zeros(n_features)
-        single_target = y.shape[1].nil?
-        # Construct forest.
-        @estimators = Array.new(@params[:n_estimators]) do
-          tree = Tree::DecisionTreeRegressor.new(
-            criterion: @params[:criterion], max_depth: @params[:max_depth],
-            max_leaf_nodes: @params[:max_leaf_nodes], min_samples_leaf: @params[:min_samples_leaf],
-            max_features: @params[:max_features], random_seed: @rng.rand(SVMKit::Values.int_max)
-          )
-          bootstrap_ids = Array.new(n_samples) { @rng.rand(0...n_samples) }
-          tree.fit(x[bootstrap_ids, true], single_target ? y[bootstrap_ids] : y[bootstrap_ids, true])
-          @feature_importances += tree.feature_importances
-          tree
-        end
-        @feature_importances /= @feature_importances.sum
-        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 value per sample.
-      def predict(x)
-        check_sample_array(x)
-        @estimators.map { |est| est.predict(x) }.reduce(&:+) / @params[:n_estimators]
-      end
-
-      # Return the index of the leaf that each sample reached.
-      #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to assign each leaf.
-      # @return [Numo::Int32] (shape: [n_samples, n_estimators]) Leaf index for sample.
-      def apply(x)
-        SVMKit::Validation.check_sample_array(x)
-        Numo::Int32[*Array.new(@params[:n_estimators]) { |n| @estimators[n].apply(x) }].transpose
-      end
-
-      # Dump marshal data.
-      # @return [Hash] The marshal data about RandomForestRegressor.
-      def marshal_dump
-        { params: @params,
-          estimators: @estimators,
-          feature_importances: @feature_importances,
-          rng: @rng }
-      end
-
-      # Load marshal data.
-      # @return [nil]
-      def marshal_load(obj)
-        @params = obj[:params]
-        @estimators = obj[:estimators]
-        @feature_importances = obj[:feature_importances]
-        @rng = obj[:rng]
-        nil
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/accuracy.rb

@@ -1,30 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/evaluator'
-
-module SVMKit
-  # This module consists of the classes for model evaluation.
-  module EvaluationMeasure
-    # Accuracy is a class that calculates the accuracy of classifier from the predicted labels.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::Accuracy.new
-    #   puts evaluator.score(ground_truth, predicted)
-    class Accuracy
-      include Base::Evaluator
-
-      # Calculate mean accuracy.
-      #
-      # @param y_true [Numo::Int32] (shape: [n_samples]) Ground truth labels.
-      # @param y_pred [Numo::Int32] (shape: [n_samples]) Predicted labels.
-      # @return [Float] Mean accuracy
-      def score(y_true, y_pred)
-        SVMKit::Validation.check_label_array(y_true)
-        SVMKit::Validation.check_label_array(y_pred)
-
-        (y_true.to_a.map.with_index { |label, n| label == y_pred[n] ? 1 : 0 }).inject(:+) / y_true.size.to_f
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/f_score.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
-    # FScore is a class that calculates the F1-score of the predicted labels.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::FScore.new
-    #   puts evaluator.score(ground_truth, predicted)
-    class FScore
-      include Base::Evaluator
-      include EvaluationMeasure::PrecisionRecall
-
-      # Return the average type for calculation of F1-score.
-      # @return [String] ('binary', 'micro', 'macro')
-      attr_reader :average
-
-      # Create a new evaluation measure calculater for F1-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 F1-score
-      #
-      # @param y_true [Numo::Int32] (shape: [n_samples]) Ground truth labels.
-      # @param y_pred [Numo::Int32] (shape: [n_samples]) Predicted labels.
-      # @return [Float] Average F1-score
-      def score(y_true, y_pred)
-        SVMKit::Validation.check_label_array(y_true)
-        SVMKit::Validation.check_label_array(y_pred)
-
-        case @average
-        when 'binary'
-          f_score_each_class(y_true, y_pred).last
-        when 'micro'
-          micro_average_f_score(y_true, y_pred)
-        when 'macro'
-          macro_average_f_score(y_true, y_pred)
-        end
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/log_loss.rb

@@ -1,46 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/evaluator'
-require 'svmkit/preprocessing/one_hot_encoder'
-
-module SVMKit
-  module EvaluationMeasure
-    # LogLoss is a class that calculates the logarithmic loss of predicted class probability.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::LogLoss.new
-    #   puts evaluator.score(ground_truth, predicted)
-    class LogLoss
-      include Base::Evaluator
-
-      # Calculate mean logarithmic loss.
-      # If both y_true and y_pred are array (both shapes are [n_samples]), this method calculates
-      # mean logarithmic loss for binary classification.
-      #
-      # @param y_true [Numo::Int32] (shape: [n_samples]) Ground truth labels.
-      # @param y_pred [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted class probability.
-      # @param eps [Float] A small value close to zero to avoid outputting infinity in logarithmic calcuation.
-      # @return [Float] mean logarithmic loss
-      def score(y_true, y_pred, eps = 1e-15)
-        SVMKit::Validation.check_params_type(Numo::Int32, y_true: y_true)
-        SVMKit::Validation.check_params_type(Numo::DFloat, y_pred: y_pred)
-
-        n_samples, n_classes = y_pred.shape
-        clipped_p = y_pred.clip(eps, 1 - eps)
-
-        log_loss = if n_classes.nil?
-                     negative_label = y_true.to_a.uniq.min
-                     bin_y_true = Numo::DFloat.cast(y_true.ne(negative_label))
-                     -(bin_y_true * Numo::NMath.log(clipped_p) + (1 - bin_y_true) * Numo::NMath.log(1 - clipped_p))
-                   else
-                     encoder = SVMKit::Preprocessing::OneHotEncoder.new
-                     encoded_y_true = encoder.fit_transform(y_true)
-                     clipped_p /= clipped_p.sum(1).expand_dims(1)
-                     -(encoded_y_true * Numo::NMath.log(clipped_p)).sum(1)
-                   end
-        log_loss.sum / n_samples
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/mean_absolute_error.rb

@@ -1,30 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/evaluator'
-
-module SVMKit
-  module EvaluationMeasure
-    # MeanAbsoluteError is a class that calculates the mean absolute error.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::MeanAbsoluteError.new
-    #   puts evaluator.score(ground_truth, predicted)
-    class MeanAbsoluteError
-      include Base::Evaluator
-
-      # Calculate mean absolute error.
-      #
-      # @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 target values.
-      # @return [Float] Mean absolute error
-      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
-
-        (y_true - y_pred).abs.mean
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/mean_squared_error.rb

@@ -1,30 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/evaluator'
-
-module SVMKit
-  module EvaluationMeasure
-    # MeanSquaredError is a class that calculates the mean squared error.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::MeanSquaredError.new
-    #   puts evaluator.score(ground_truth, predicted)
-    class MeanSquaredError
-      include Base::Evaluator
-
-      # Calculate mean squared error.
-      #
-      # @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 target values.
-      # @return [Float] Mean squared error
-      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
-
-        ((y_true - y_pred)**2).mean
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/normalized_mutual_information.rb

@@ -1,63 +0,0 @@
-# frozen_string_literal: true
-
-require 'svmkit/validation'
-require 'svmkit/base/evaluator'
-
-module SVMKit
-  module EvaluationMeasure
-    # NormalizedMutualInformation is a class that calculates the normalized mutual information of cluatering results.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::NormalizedMutualInformation.new
-    #   puts evaluator.score(ground_truth, predicted)
-    #
-    # *Reference*
-    # - C D. Manning, P. Raghavan, and H. Schutze, "Introduction to Information Retrieval," Cambridge University Press., 2008.
-    # - N X. Vinh, J. Epps, and J. Bailey, "Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance," J. Machine Learning Research, vol. 11, pp. 2837--1854, 2010.
-    class NormalizedMutualInformation
-      include Base::Evaluator
-
-      # Calculate noramlzied mutual information
-      #
-      # @param y_true [Numo::Int32] (shape: [n_samples]) Ground truth labels.
-      # @param y_pred [Numo::Int32] (shape: [n_samples]) Predicted cluster labels.
-      # @return [Float] Normalized mutual information
-      def score(y_true, y_pred)
-        SVMKit::Validation.check_label_array(y_true)
-        SVMKit::Validation.check_label_array(y_pred)
-        # initiazlie some variables.
-        mutual_information = 0.0
-        n_samples = y_pred.size
-        class_ids = y_true.to_a.uniq
-        cluster_ids = y_pred.to_a.uniq
-        # calculate entropy.
-        class_entropy = -1.0 * class_ids.map do |k|
-          ratio = y_true.eq(k).count.fdiv(n_samples)
-          ratio * Math.log(ratio)
-        end.reduce(:+)
-        return 0.0 if class_entropy.zero?
-        cluster_entropy = -1.0 * cluster_ids.map do |k|
-          ratio = y_pred.eq(k).count.fdiv(n_samples)
-          ratio * Math.log(ratio)
-        end.reduce(:+)
-        return 0.0 if cluster_entropy.zero?
-        # calculate mutual information.
-        cluster_ids.map do |k|
-          pr_sample_ids = y_pred.eq(k).where.to_a
-          n_pr_samples = pr_sample_ids.size
-          class_ids.map do |j|
-            tr_sample_ids = y_true.eq(j).where.to_a
-            n_tr_samples = tr_sample_ids.size
-            n_intr_samples = (pr_sample_ids & tr_sample_ids).size
-            if n_intr_samples > 0
-              mutual_information +=
-                n_intr_samples.fdiv(n_samples) * Math.log((n_samples * n_intr_samples).fdiv(n_pr_samples * n_tr_samples))
-            end
-          end
-        end
-        # return normalized mutual information.
-        mutual_information / Math.sqrt(class_entropy * cluster_entropy)
-      end
-    end
-  end
-end

data/lib/svmkit/evaluation_measure/precision.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
-    # Precision is a class that calculates the preicision of the predicted labels.
-    #
-    # @example
-    #   evaluator = SVMKit::EvaluationMeasure::Precision.new
-    #   puts evaluator.score(ground_truth, predicted)
-    class Precision
-      include Base::Evaluator
-      include EvaluationMeasure::PrecisionRecall
-
-      # Return the average type for calculation of precision.
-      # @return [String] ('binary', 'micro', 'macro')
-      attr_reader :average
-
-      # Create a new evaluation measure calculater for precision 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 precision.
-      #
-      # @param y_true [Numo::Int32] (shape: [n_samples]) Ground truth labels.
-      # @param y_pred [Numo::Int32] (shape: [n_samples]) Predicted labels.
-      # @return [Float] Average precision
-      def score(y_true, y_pred)
-        SVMKit::Validation.check_label_array(y_true)
-        SVMKit::Validation.check_label_array(y_pred)
-
-        case @average
-        when 'binary'
-          precision_each_class(y_true, y_pred).last
-        when 'micro'
-          micro_average_precision(y_true, y_pred)
-        when 'macro'
-          macro_average_precision(y_true, y_pred)
-        end
-      end
-    end
-  end
-end