svmkit 0.7.1 → 0.7.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1f708500e8ba450849736cd02b152b30e302c1bb
-  data.tar.gz: 210256fcd91375e96b4d68015fae2bf2a5b0d4be
+  metadata.gz: f20192e678f6f066eb1d40c066f0e9a0efefd3a0
+  data.tar.gz: 1be802cdbbfb2ee7a641fb78d1409c2ee49b8450
 SHA512:
-  metadata.gz: 4a03201b32dc7a5c0db43bfdfe742cc5b369449c2ce0dc63f4905e3e0b9186276f5b382c1b6bff45acdfb91f61712befc58538c1dfa74874722127bec5e2bf03
-  data.tar.gz: deea7c688685935ebe2574448973903115e727cc479b12ea42f382ea697f7218b0de27cccf978c7ea0f4aa0f0fa0bfd5a97ccbbb88e2ea0b87cd1a5ca00cc5f3
+  metadata.gz: 43471c5a4ef290781d5d2270732313fbcffba60a4351805d6c7bb8abec7537bcd8ac50260600fbfb1ff52c947c45c3f6f19b9ccecd47e6015e6ac45da5c855a6
+  data.tar.gz: 908f675396a2da835b82da8cf117a4a17d6d90d489618cf110e993de6c03d6ec8e6651115df333033314b0f54c1e931f68da8ff541a1b5e22886741f48496259

data/.travis.yml

@@ -3,10 +3,13 @@ os: linux
 dist: trusty
 language: ruby
 rvm:
+  - 2.1
   - 2.2
   - 2.3
   - 2.4
   - 2.5
   - 2.6
 before_install:
-  - gem install --no-document bundler -v '>= 1.17'
+  - travis_retry gem update --system || travis_retry gem update --system 2.7.8
+  - travis_retry gem install bundler --no-document || travis_retry gem install bundler --no-document -v 1.17.3
+

data/HISTORY.md

@@ -1,3 +1,7 @@
+# 0.7.2
+- Add class for Pipeline that constructs chain of transformers and estimators.
+- Fix some typos on document.
+
 # 0.7.1
 - Fix to use CSV class in parsing libsvm format file.
 - Refactor ensemble estimators.

data/README.md

@@ -124,6 +124,39 @@ mean_logloss = report[:test_score].inject(:+) / kf.n_splits
 puts("5-CV mean log-loss: %.3f" % mean_logloss)
 ```
 
+### Example 3. Pipeline
+
+```ruby
+require 'svmkit'
+
+# Load dataset.
+samples, labels = SVMKit::Dataset.load_libsvm_file('pendigits')
+samples = Numo::DFloat.cast(samples)
+
+# Construct pipeline with kernel approximation and SVC.
+rbf = SVMKit::KernelApproximation::RBF.new(gamma: 0.0001, n_components: 800, random_seed: 1)
+svc = SVMKit::LinearModel::SVC.new(reg_param: 0.0001, max_iter: 1000, random_seed: 1)
+pipeline = SVMKit::Pipeline::Pipeline.new(steps: { trns: rbf, clsf: svc })
+
+# Define the splitting strategy and cross validation.
+kf = SVMKit::ModelSelection::StratifiedKFold.new(n_splits: 5, shuffle: true, random_seed: 1)
+cv = SVMKit::ModelSelection::CrossValidation.new(estimator: pipeline, splitter: kf)
+
+# Perform 5-cross validation.
+report = cv.perform(samples, labels)
+
+# Output result.
+mean_accuracy = report[:test_score].inject(:+) / kf.n_splits
+puts("5-CV mean accuracy: %.1f %%" % (mean_accuracy * 100.0))
+```
+
+Execution of the above scripts result in the following.
+
+```bash
+$ ruby pipeline.rb
+5-CV mean accuracy: 99.2 %
+```
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.

data/lib/svmkit.rb

@@ -20,6 +20,7 @@ require 'svmkit/optimizer/sgd'
 require 'svmkit/optimizer/rmsprop'
 require 'svmkit/optimizer/nadam'
 require 'svmkit/optimizer/yellow_fin'
+require 'svmkit/pipeline/pipeline'
 require 'svmkit/kernel_approximation/rbf'
 require 'svmkit/linear_model/sgd_linear_estimator'
 require 'svmkit/linear_model/svc'

data/lib/svmkit/ensemble/ada_boost_regressor.rb

@@ -8,7 +8,7 @@ require 'svmkit/tree/decision_tree_regressor'
 
 module SVMKit
   module Ensemble
-    # AdaBoostRegressor is a class that implements random forest for regression
+    # AdaBoostRegressor is a class that implements random forest for regression.
     # This class uses decision tree for a weak learner.
     #
     # @example

data/lib/svmkit/nearest_neighbors/k_neighbors_classifier.rb

@@ -12,7 +12,7 @@ module SVMKit
     #
     # @example
     #   estimator =
-    #     SVMKit::NearestNeighbor::KNeighborsClassifier.new(n_neighbors = 5)
+    #     SVMKit::NearestNeighbors::KNeighborsClassifier.new(n_neighbors = 5)
     #   estimator.fit(training_samples, traininig_labels)
     #   results = estimator.predict(testing_samples)
     #

data/lib/svmkit/nearest_neighbors/k_neighbors_regressor.rb

@@ -11,7 +11,7 @@ module SVMKit
     #
     # @example
     #   estimator =
-    #     SVMKit::NearestNeighbor::KNeighborsRegressor.new(n_neighbors = 5)
+    #     SVMKit::NearestNeighbors::KNeighborsRegressor.new(n_neighbors = 5)
     #   estimator.fit(training_samples, traininig_target_values)
     #   results = estimator.predict(testing_samples)
     #

data/lib/svmkit/pipeline/pipeline.rb

@@ -0,0 +1,187 @@
+# 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)
+        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)
+        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)
+        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)
+        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)
+        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)
+        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)
+        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)
+        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)
+        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)
+        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/preprocessing/l2_normalizer.rb

@@ -49,6 +49,15 @@ module SVMKit
         fit(x)
         x / @norm_vec.tile(x.shape[1], 1).transpose
       end
+
+      # Calculate L2-norms of each sample, and then normalize samples to unit L2-norm.
+      # This method calls the fit_transform method. This method exists for the Pipeline class.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate L2-norms.
+      # @return [Numo::DFloat] The normalized samples.
+      def transform(x)
+        fit_transform(x)
+      end
     end
   end
 end

data/lib/svmkit/version.rb

@@ -3,5 +3,5 @@
 # SVMKit is a machine learning library in Ruby.
 module SVMKit
   # @!visibility private
-  VERSION = '0.7.1'.freeze
+  VERSION = '0.7.2'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: svmkit
 version: !ruby/object:Gem::Version
-  version: 0.7.1
+  version: 0.7.2
 platform: ruby
 authors:
 - yoshoku
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-12-17 00:00:00.000000000 Z
+date: 2019-01-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -157,6 +157,7 @@ files:
 - lib/svmkit/optimizer/sgd.rb
 - lib/svmkit/optimizer/yellow_fin.rb
 - lib/svmkit/pairwise_metric.rb
+- lib/svmkit/pipeline/pipeline.rb
 - lib/svmkit/polynomial_model/factorization_machine_classifier.rb
 - lib/svmkit/polynomial_model/factorization_machine_regressor.rb
 - lib/svmkit/preprocessing/l2_normalizer.rb