svmkit 0.2.3 → 0.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6271a50754a13199f7c3c12c6f1b9e2a0a2075d5
-  data.tar.gz: ecdc84a2987f22d49ad1b8435397862771f96f37
+  metadata.gz: 22a165e3fa579d5a5d0dbd9095d208dd09d5fbd0
+  data.tar.gz: c3f7fa2f4fe115dc821ec5050cf7c1f0fdd75a36
 SHA512:
-  metadata.gz: 9974eb62cd19ebca32ca92cafbcbf2e34a978d41c0aa9bb0765c001d56963189aa43f71806fa5a2492a4b3e50bcd939a018aa784198f5aef08e2159682682dd2
-  data.tar.gz: eee0f089449a71f79576165aa083c41fe1d9812fcc251c31c2a5c7cf06e6dfd4293dddd6685fa6285c8d89a3744bb3a72bd9db6f36b7cbc586b7a71800c1fb78
+  metadata.gz: 4002a03944871f2fd9cf305fd64b02d4a1899b291167289d2f78112f977c54b33fc60041b2d2c506d755fb938e4d226002b1d6dc41ea74ad28d0e215adc0ee2b
+  data.tar.gz: 59dc53541aee6832ea66b826cc5f92e1329adba108aa2683ddba9105d8ac28fba7fae483ce1d2c092c60d83e9d3b3adfb574bf11401ad74f24435f237d262871

data/.rubocop.yml

@@ -9,6 +9,7 @@ Metrics/AbcSize:
 
 Metrics/LineLength:
   Max: 120
+  IgnoredPatterns: ['(\A|\s)#']
 
 Metrics/ModuleLength:
   Max: 200

data/HISTORY.md

@@ -1,3 +1,8 @@
+# 0.2.4
+- Added class for Factorization Machine classifier.
+- Added classes for evaluation measures.
+- Fixed the method for prediction of class probability in Logistic Regression.
+
 # 0.2.3
 - Added class for cross validation.
 - Added specs for base modules.

data/README.md

@@ -4,9 +4,11 @@
 [![Gem Version](https://badge.fury.io/rb/svmkit.svg)](https://badge.fury.io/rb/svmkit)
 [![BSD 2-Clause License](https://img.shields.io/badge/License-BSD%202--Clause-orange.svg)](https://github.com/yoshoku/SVMKit/blob/master/LICENSE.txt)
 
-SVMKit is a library for machine learninig in Ruby.
-SVMKit implements machine learning algorithms with an interface similar to Scikit-Learn in Python.
-However, since SVMKit is an experimental library, there are few machine learning algorithms implemented.
+SVMKit is a machine learninig library in Ruby.
+SVMKit implements machine learning algorithms with interfaces similar to Scikit-Learn in Python.
+Since the development of SVMKit has just getting started,
+the methods implemented in SVMKit are only Linear / Kernel SVC,
+Logistic Regression, Factorization Machine, K-nearest neighbor classifier, and cross-validation.
 
 ## Installation
 

data/lib/svmkit/base/evaluator.rb

@@ -0,0 +1,12 @@
+
+module SVMKit
+  module Base
+    # Module for all evaluation measures in SVMKit.
+    module Evaluator
+      # An abstract method for evaluation of model.
+      def score
+        raise NotImplementedError, "#{__method__} has to be implemented in #{self.class}."
+      end
+    end
+  end
+end

data/lib/svmkit/evaluation_measure/accuracy.rb

@@ -0,0 +1,24 @@
+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
+
+      # Claculate 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)
+        (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

@@ -0,0 +1,44 @@
+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')
+        @average = average
+      end
+
+      # Claculate 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)
+        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/precision.rb

@@ -0,0 +1,44 @@
+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')
+        @average = average
+      end
+
+      # Claculate 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)
+        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

data/lib/svmkit/evaluation_measure/precision_recall.rb

@@ -0,0 +1,89 @@
+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/recall.rb

@@ -0,0 +1,44 @@
+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')
+        @average = average
+      end
+
+      # Claculate 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)
+        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/linear_model/logistic_regression.rb

@@ -127,9 +127,13 @@ module SVMKit
       # 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]) Predicted probability per sample.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted probability of each class per sample.
       def predict_proba(x)
-        decision_function(x)
+        n_samples, = x.shape
+        proba = Numo::DFloat.zeros(n_samples, 2)
+        proba[true, 1] = decision_function(x)
+        proba[true, 0] = 1.0 - proba[true, 1]
+        proba
       end
 
       # Claculate the mean accuracy of the given testing data.

data/lib/svmkit/model_selection/cross_validation.rb

@@ -21,6 +21,10 @@ module SVMKit
       # @return [Splitter]
       attr_reader :splitter
 
+      # Return the evaluator that calculates score.
+      # @return [Evaluator]
+      attr_reader :evaluator
+
       # Return the flag indicating whether to caculate the score of training dataset.
       # @return [Boolean]
       attr_reader :return_train_score
@@ -29,10 +33,12 @@ module SVMKit
       #
       # @param estimator [Classifier] The classifier of which performance is evaluated.
       # @param splitter [Splitter] The splitter that divides dataset to training and testing dataset.
+      # @param evaluator [Evaluator] The evaluator that calculates score of estimator results.
       # @param return_train_score [Boolean] The flag indicating whether to calculate the score of training dataset.
-      def initialize(estimator: nil, splitter: nil, return_train_score: false)
+      def initialize(estimator: nil, splitter: nil, evaluator: nil, return_train_score: false)
         @estimator = estimator
         @splitter = splitter
+        @evaluator = evaluator
         @return_train_score = return_train_score
       end
 
@@ -49,7 +55,7 @@ module SVMKit
       #     the return_train_score is false.
       def perform(x, y)
         # Initialize the report of cross validation.
-        report = {test_score: [], train_score: nil, fit_time: []}
+        report = { test_score: [], train_score: nil, fit_time: [] }
         report[:train_score] = [] if @return_train_score
         # Evaluate the estimator on each split.
         @splitter.split(x, y).each do |train_ids, test_ids|
@@ -64,8 +70,13 @@ module SVMKit
           @estimator.fit(train_x, train_y)
           # Calculate scores and prepare the report.
           report[:fit_time].push(Time.now.to_i - start_time)
-          report[:test_score].push(@estimator.score(test_x, test_y))
-          report[:train_score].push(@estimator.score(train_x, train_y)) if @return_train_score
+          if @evaluator.nil?
+            report[:test_score].push(@estimator.score(test_x, test_y))
+            report[:train_score].push(@estimator.score(train_x, train_y)) if @return_train_score
+          else
+            report[:test_score].push(@evaluator.score(test_y, @estimator.predict(test_x)))
+            report[:train_score].push(@estimator.score(train_x, @estimator.predict(train_x))) if @return_train_score
+          end
         end
         report
       end

data/lib/svmkit/polynomial_model/factorization_machine_classifier.rb

@@ -0,0 +1,190 @@
+require 'svmkit/base/base_estimator'
+require 'svmkit/base/classifier'
+
+module SVMKit
+  # This module consists of the classes that implemnt polynomial models.
+  module PolynomialModel
+    # FactorizationMachineClassifier is a class that
+    # implements Fatorization Machine for binary classification
+    # with (mini-batch) stochastic gradient descent optimization.
+    # Note that this implementation uses hinge loss for the loss function.
+    #
+    # @example
+    #   estimator =
+    #     SVMKit::PolynomialModel::FactorizationMachineClassifier.new(
+    #      n_factors: 10, reg_param_bias: 0.001, reg_param_weight: 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 Transactions on Intelligent Systems and Technology, vol. 3 (3), pp. 57:1--57:22, 2012.
+    # - S. Rendle, "Factorization Machines," Proceedings of the 10th IEEE International Conference on Data Mining (ICDM'10), pp. 995--1000, 2010.
+    class FactorizationMachineClassifier
+      include Base::BaseEstimator
+      include Base::Classifier
+
+      # Return the factor matrix for Factorization Machine.
+      # @return [Numo::DFloat] (shape: [n_factors, n_features])
+      attr_reader :factor_mat
+
+      # Return the weight vector for Factorization Machine.
+      # @return [Numo::DFloat] (shape: [n_features])
+      attr_reader :weight_vec
+
+      # Return the bias term for Factoriazation Machine.
+      # @return [Float]
+      attr_reader :bias_term
+
+      # Return the random generator for transformation.
+      # @return [Random]
+      attr_reader :rng
+
+      # Create a new classifier with Support Vector Machine by the Pegasos algorithm.
+      #
+      # @param n_factors [Integer] The maximum number of iterations.
+      # @param reg_param_bias [Float] The regularization parameter for bias term.
+      # @param reg_param_weight [Float] The regularization parameter for weight vector.
+      # @param reg_param_factor [Float] The regularization parameter for factor matrix.
+      # @param init_std [Float] The standard deviation of normal random number for initialization of factor matrix.
+      # @param max_iter [Integer] The maximum number of iterations.
+      # @param batch_size [Integer] The size of the mini batches.
+      # @param random_seed [Integer] The seed value using to initialize the random generator.
+      def initialize(n_factors: 2, reg_param_bias: 1.0, reg_param_weight: 1.0, reg_param_factor: 1.0,
+                     init_std: 0.1, max_iter: 1000, batch_size: 10, random_seed: nil)
+        @params = {}
+        @params[:n_factors] = n_factors
+        @params[:reg_param_bias] = reg_param_bias
+        @params[:reg_param_weight] = reg_param_weight
+        @params[:reg_param_factor] = reg_param_factor
+        @params[:init_std] = init_std
+        @params[:max_iter] = max_iter
+        @params[:batch_size] = batch_size
+        @params[:random_seed] = random_seed
+        @params[:random_seed] ||= srand
+        @factor_mat = nil
+        @weight_vec = nil
+        @bias_term = 0.0
+        @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)
+        # Generate binary labels.
+        negative_label = y.to_a.uniq.sort.shift
+        bin_y = y.map { |l| l != negative_label ? 1.0 : -1.0 }
+        # Initialize some variables.
+        n_samples, n_features = x.shape
+        rand_ids = [*0...n_samples].shuffle(random: @rng)
+        @factor_mat = rand_normal([@params[:n_factors], n_features], 0, @params[:init_std])
+        @weight_vec = Numo::DFloat.zeros(n_features)
+        @bias_term = 0.0
+        # 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]
+          label = bin_y[subset_ids]
+          # Calculate gradients for loss function.
+          loss_grad = loss_gradient(data, label)
+          next if loss_grad.ne(0.0).count.zero?
+          # Update each parameter.
+          @bias_term -= learning_rate(@params[:reg_param_bias], t) * bias_gradient(loss_grad)
+          @weight_vec -= learning_rate(@params[:reg_param_weight], t) * weight_gradient(loss_grad, data)
+          @params[:n_factors].times do |n|
+            @factor_mat[n, true] -= learning_rate(@params[:reg_param_factor], t) *
+                                    factor_gradient(loss_grad, data, @factor_mat[n, true])
+          end
+        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)
+        linear_term = @bias_term + x.dot(@weight_vec)
+        factor_term = 0.5 * (@factor_mat.dot(x.transpose)**2 - (@factor_mat**2).dot(x.transpose**2)).sum
+        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)
+        Numo::Int32.cast(decision_function(x).map { |v| v >= 0.0 ? 1 : -1 })
+      end
+
+      # Claculate the mean accuracy of the given testing data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) Testing data.
+      # @param y [Numo::Int32] (shape: [n_samples]) True labels for testing data.
+      # @return [Float] Mean accuracy
+      def score(x, y)
+        p = predict(x)
+        n_hits = (y.to_a.map.with_index { |l, n| l == p[n] ? 1 : 0 }).inject(:+)
+        n_hits / y.size.to_f
+      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, 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]
+        @rng = obj[:rng]
+        nil
+      end
+
+      private
+
+      def loss_gradient(x, y)
+        evaluated = y * decision_function(x)
+        gradient = Numo::DFloat.zeros(evaluated.size)
+        gradient[evaluated < 1.0] = -y[evaluated < 1.0]
+        gradient
+      end
+
+      def learning_rate(reg_param, iter)
+        1.0 / (reg_param * (iter + 1))
+      end
+
+      def bias_gradient(loss_grad)
+        loss_grad.mean + @params[:reg_param_bias] * @bias_term
+      end
+
+      def weight_gradient(loss_grad, data)
+        (loss_grad.expand_dims(1) * data).mean(0) + @params[:reg_param_weight] * @weight_vec
+      end
+
+      def factor_gradient(loss_grad, data, factor)
+        reg_term = @params[:reg_param_factor] * factor
+        (loss_grad.expand_dims(1) * (data * data.dot(factor).expand_dims(1) - factor * (data**2))).mean(0) + reg_term
+      end
+
+      def rand_uniform(shape)
+        Numo::DFloat[*Array.new(shape.inject(&:*)) { @rng.rand }].reshape(*shape)
+      end
+
+      def rand_normal(shape, mu, sigma)
+        a = rand_uniform(shape)
+        b = rand_uniform(shape)
+        mu + sigma * (Numo::NMath.sqrt(-2.0 * Numo::NMath.log(a)) * Numo::NMath.sin(2.0 * Math::PI * b))
+      end
+    end
+  end
+end

data/lib/svmkit/version.rb

@@ -1,5 +1,5 @@
 # SVMKit is an experimental library of machine learning in Ruby.
 module SVMKit
   # @!visibility private
-  VERSION = '0.2.3'.freeze
+  VERSION = '0.2.4'.freeze
 end

data/lib/svmkit.rb

@@ -8,10 +8,12 @@ require 'svmkit/base/base_estimator'
 require 'svmkit/base/classifier'
 require 'svmkit/base/transformer'
 require 'svmkit/base/splitter'
+require 'svmkit/base/evaluator'
 require 'svmkit/kernel_approximation/rbf'
 require 'svmkit/linear_model/svc'
 require 'svmkit/linear_model/logistic_regression'
 require 'svmkit/kernel_machine/kernel_svc'
+require 'svmkit/polynomial_model/factorization_machine_classifier'
 require 'svmkit/multiclass/one_vs_rest_classifier'
 require 'svmkit/nearest_neighbors/k_neighbors_classifier'
 require 'svmkit/preprocessing/l2_normalizer'
@@ -20,3 +22,7 @@ require 'svmkit/preprocessing/standard_scaler'
 require 'svmkit/model_selection/k_fold'
 require 'svmkit/model_selection/stratified_k_fold'
 require 'svmkit/model_selection/cross_validation'
+require 'svmkit/evaluation_measure/accuracy'
+require 'svmkit/evaluation_measure/precision'
+require 'svmkit/evaluation_measure/recall'
+require 'svmkit/evaluation_measure/f_score'

data/svmkit.gemspec

@@ -11,12 +11,15 @@ Gem::Specification.new do |spec|
   spec.email         = ['yoshoku@outlook.com']
 
   spec.summary       = <<MSG
-SVMKit is an experimental library of machine learning in Ruby.
+SVMKit is a machine learninig library in Ruby.
+SVMKit implements machine learning algorithms with interfaces similar to Scikit-Learn in Python.
 MSG
   spec.description   = <<MSG
-SVMKit is a library for machine learninig in Ruby.
-SVMKit implements machine learning algorithms with an interface similar to Scikit-Learn in Python.
-However, since SVMKit is an experimental library, there are few machine learning algorithms implemented.
+SVMKit is a machine learninig library in Ruby.
+SVMKit implements machine learning algorithms with interfaces similar to Scikit-Learn in Python.
+Since the development of SVMKit has just getting started,
+the methods implemented in SVMKit are only Linear / Kernel SVC,
+Logistic Regression, Factorization Machine, K-nearest neighbor method, and cross-validation.
 MSG
   spec.homepage      = 'https://github.com/yoshoku/svmkit'
   spec.license       = 'BSD-2-Clause'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: svmkit
 version: !ruby/object:Gem::Version
-  version: 0.2.3
+  version: 0.2.4
 platform: ruby
 authors:
 - yoshoku
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-01-15 00:00:00.000000000 Z
+date: 2018-02-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -81,9 +81,11 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0.15'
 description: |
-  SVMKit is a library for machine learninig in Ruby.
-  SVMKit implements machine learning algorithms with an interface similar to Scikit-Learn in Python.
-  However, since SVMKit is an experimental library, there are few machine learning algorithms implemented.
+  SVMKit is a machine learninig library in Ruby.
+  SVMKit implements machine learning algorithms with interfaces similar to Scikit-Learn in Python.
+  Since the development of SVMKit has just getting started,
+  the methods implemented in SVMKit are only Linear / Kernel SVC,
+  Logistic Regression, Factorization Machine, K-nearest neighbor method, and cross-validation.
 email:
 - yoshoku@outlook.com
 executables: []
@@ -105,9 +107,15 @@ files:
 - lib/svmkit.rb
 - lib/svmkit/base/base_estimator.rb
 - lib/svmkit/base/classifier.rb
+- lib/svmkit/base/evaluator.rb
 - lib/svmkit/base/splitter.rb
 - lib/svmkit/base/transformer.rb
 - lib/svmkit/dataset.rb
+- lib/svmkit/evaluation_measure/accuracy.rb
+- lib/svmkit/evaluation_measure/f_score.rb
+- lib/svmkit/evaluation_measure/precision.rb
+- lib/svmkit/evaluation_measure/precision_recall.rb
+- lib/svmkit/evaluation_measure/recall.rb
 - lib/svmkit/kernel_approximation/rbf.rb
 - lib/svmkit/kernel_machine/kernel_svc.rb
 - lib/svmkit/linear_model/logistic_regression.rb
@@ -118,6 +126,7 @@ files:
 - lib/svmkit/multiclass/one_vs_rest_classifier.rb
 - lib/svmkit/nearest_neighbors/k_neighbors_classifier.rb
 - lib/svmkit/pairwise_metric.rb
+- lib/svmkit/polynomial_model/factorization_machine_classifier.rb
 - lib/svmkit/preprocessing/l2_normalizer.rb
 - lib/svmkit/preprocessing/min_max_scaler.rb
 - lib/svmkit/preprocessing/standard_scaler.rb
@@ -152,5 +161,6 @@ rubyforge_project:
 rubygems_version: 2.4.5.4
 signing_key: 
 specification_version: 4
-summary: SVMKit is an experimental library of machine learning in Ruby.
+summary: SVMKit is a machine learninig library in Ruby. SVMKit implements machine
+  learning algorithms with interfaces similar to Scikit-Learn in Python.
 test_files: []