rumale-svm 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 40bfeaba6ea5d4b31d75b3c7c7573b121aa2390a
+  data.tar.gz: a59abc913381101d82c488e145c9e375d2e55f41
+SHA512:
+  metadata.gz: 333cce8eb4f15d6a23e7cc31b2cd5d122e3f59ce61971e0fa9d8c01144a4e67b44139a367132752d08c269b7564330503cb13558f93accc37e520f1542688c06
+  data.tar.gz: c5fc3f8c8287603369c1b801c6615644a13b75fdd75fb21f3470aa2f067d8d0800cac59b9b7fa9984405cf55a8edcf9e8e4ed46f2a65e0bf8e9791372fd5992c

data/.coveralls.yml

@@ -0,0 +1 @@
+service_name: travis-ci

data/.gitignore

@@ -0,0 +1,18 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status
+
+*.swp
+*.bundle
+tags
+.DS_Store
+.ruby-version

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.travis.yml

@@ -0,0 +1,13 @@
+---
+sudo: false
+os: linux
+dist: bionic
+language: ruby
+cache: bundler
+rvm:
+  - '2.4'
+  - '2.5'
+  - '2.6'
+
+before_install:
+  - gem install bundler -v 2.0.2

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at yoshoku@outlook.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,4 @@
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in rumale-svm.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,27 @@
+Copyright (c) 2019 Atsushi Tatsuma
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

data/README.md

@@ -0,0 +1,92 @@
+# Rumale::SVM
+
+[![Build Status](https://travis-ci.org/yoshoku/rumale-svm.svg?branch=master)](https://travis-ci.org/yoshoku/rumale-svm)
+[![Coverage Status](https://coveralls.io/repos/github/yoshoku/rumale-svm/badge.svg?branch=master)](https://coveralls.io/github/yoshoku/rumale-svm?branch=master)
+[![Gem Version](https://badge.fury.io/rb/rumale-svm.svg)](https://badge.fury.io/rb/rumale-svm)
+[![BSD 3-Clause License](https://img.shields.io/badge/License-BSD%203--Clause-orange.svg)](https://github.com/yoshoku/rumale-svm/blob/master/LICENSE.txt)
+[![Documentation](http://img.shields.io/badge/docs-rdoc.info-blue.svg)](https://yoshoku.github.io/rumale-svm/doc/)
+
+Rumale::SVM provides support vector machine algorithms in
+[LIBSVM](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) and [LIBLINEAR](https://www.csie.ntu.edu.tw/~cjlin/liblinear/)
+with [Rumale](https://github.com/yoshoku/rumale) interface.
+Many machine learning libraries use LIBSVM and LIBLINEAR as background libraries of support vector machine algorithms.
+On the other hand, Rumale implements support vector machine algorithms based on the mini-batch stochastic gradient descent method
+implemented in Ruby.
+Rumale::SVM adds the functions of support vector machine similar to general machine learning libraries to Rumale.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'rumale-svm'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install rumale-svm
+
+## Usage
+Download pendigits dataset from [LIBSVM DATA](https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/) web page.
+
+```sh
+$ wget https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/pendigits
+$ wget https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/pendigits.t
+```
+
+Training linear support vector classifier.
+
+```ruby
+require 'rumale/svm'
+require 'rumale/dataset'
+
+samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')
+svc = Rumale::SVM::LinearSVC.new(random_seed: 1)
+svc.fit(samples, labels)
+
+File.open('svc.dat', 'wb') { |f| f.write(Marshal.dump(svc)) }
+```
+
+Evaluate classifiction accuracy on testing datase.
+
+```ruby
+require 'rumale/svm'
+require 'rumale/dataset'
+
+samples, labels = Rumale::Dataset.load_libsvm_file('pendigits.t')
+svc = Marshal.load(File.binread('svc.dat'))
+
+puts "Accuracy: #{svc.score(samples, labels).round(3)}"
+```
+
+Execution result.
+
+```sh
+$ ruby rumale_svm_train.rb
+$ ls svc.dat
+svc.dat
+$ ruby rumale_svm_test.rb
+Accuracy: 0.835
+```
+
+## 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.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/rumale-svm. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+## License
+
+The gem is available as open source under the terms of the [BSD-3-Clause License](https://opensource.org/licenses/BSD-3-Clause).
+
+## Code of Conduct
+
+Everyone interacting in the Rumale::Svm project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/yoshoku/rumale-svm/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "rumale/svm"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/rumale/svm.rb

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+require 'rumale/svm/version'
+require 'rumale/svm/svc'
+require 'rumale/svm/svr'
+require 'rumale/svm/nu_svc'
+require 'rumale/svm/nu_svr'
+require 'rumale/svm/one_class_svm'
+require 'rumale/svm/linear_svc'
+require 'rumale/svm/linear_svr'
+require 'rumale/svm/logistic_regression'

data/lib/rumale/svm/linear_svc.rb

@@ -0,0 +1,238 @@
+# frozen_string_literal: true
+
+require 'numo/liblinear'
+require 'rumale/base/base_estimator'
+require 'rumale/base/classifier'
+require 'rumale/probabilistic_output'
+
+module Rumale
+  module SVM
+    # LinearSVC is a class that provides Support Vector Classifier in LIBLINEAR with Rumale interface.
+    #
+    # @example
+    #   estimator = Rumale::SVM::LinearSVC.new(penalty: 'l2', loss: 'squared_hinge', reg_param: 1.0, random_seed: 1)
+    #   estimator.fit(training_samples, traininig_labels)
+    #   results = estimator.predict(testing_samples)
+    class LinearSVC
+      include Base::BaseEstimator
+      include Base::Classifier
+
+      # Return the weight vector for LinearSVC.
+      # @return [Numo::DFloat] (shape: [n_classes, n_features])
+      attr_reader :weight_vec
+
+      # Return the bias term (a.k.a. intercept) for LinearSVC.
+      # @return [Numo::DFloat] (shape: [n_classes])
+      attr_reader :bias_term
+
+      # Create a new classifier with Support Vector Classifier.
+      #
+      # @param penalty [String] The type of norm used in the penalization ('l2' or 'l1').
+      # @param loss [String] The type of loss function ('squared_hinge' or 'hinge').
+      #   This parameter is ignored if penalty = 'l1'.
+      # @param dual [Boolean] The flag indicating whether to solve dual optimization problem.
+      #   When n_samples > n_features, dual = false is more preferable.
+      #   This parameter is ignored if loss = 'hinge'.
+      # @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.
+      #   This parameter is ignored if fit_bias = false.
+      # @param probability [Boolean] The flag indicating whether to train the parameter for probability estimation.
+      # @param tol [Float] The tolerance of termination criterion.
+      # @param verbose [Boolean] The flag indicating whether to output learning process message
+      # @param random_seed [Integer/Nil] The seed value using to initialize the random generator.
+      def initialize(penalty: 'l2', loss: 'squared_hinge', dual: true, reg_param: 1.0,
+                     fit_bias: true, bias_scale: 1.0, probability: false,
+                     tol: 1e-3, verbose: false, random_seed: nil)
+        check_params_string(penalty: penalty, loss: loss)
+        check_params_float(reg_param: reg_param, bias_scale: bias_scale, tol: tol)
+        check_params_boolean(dual: dual, fit_bias: fit_bias, probability: probability, verbose: verbose)
+        check_params_type_or_nil(Integer, random_seed: random_seed)
+        @params = {}
+        @params[:penalty] = penalty == 'l1' ? 'l1' : 'l2'
+        @params[:loss] = loss == 'hinge' ? 'hinge' : 'squared_hinge'
+        @params[:dual] = dual
+        @params[:reg_param] = reg_param
+        @params[:fit_bias] = fit_bias
+        @params[:bias_scale] = bias_scale
+        @params[:probability] = probability
+        @params[:tol] = tol
+        @params[:verbose] = verbose
+        @params[:random_seed] = random_seed
+        @model = nil
+        @weight_vec = nil
+        @bias_term = nil
+        @prob_param = 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 [LinearSVC] The learned classifier itself.
+      def fit(x, y)
+        check_sample_array(x)
+        check_label_array(y)
+        check_sample_label_size(x, y)
+        xx = fit_bias? ? expand_feature(x) : x
+        @model = Numo::Liblinear.train(xx, y, liblinear_params)
+        @weight_vec, @bias_term = weight_and_bias(@model[:w])
+        @prob_param = proba_model(decision_function(x), y)
+        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)
+        xx = fit_bias? ? expand_feature(x) : x
+        Numo::Liblinear.decision_function(xx, liblinear_params, @model)
+      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)
+        xx = fit_bias? ? expand_feature(x) : x
+        Numo::Int32.cast(Numo::Liblinear.predict(xx, liblinear_params, @model))
+      end
+
+      # Predict class probability for samples.
+      # This method works correctly only if the probability parameter is true.
+      #
+      # @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)
+        if binary_class?
+          probs = Numo::DFloat.zeros(x.shape[0], 2)
+          probs[true, 0] = 1.0 / (Numo::NMath.exp(@prob_param[0] * decision_function(x) + @prob_param[1]) + 1.0)
+          probs[true, 1] = 1.0 - probs[true, 0]
+        else
+          probs = 1.0 / (Numo::NMath.exp(@prob_param[true, 0] * decision_function(x) + @prob_param[true, 1]) + 1.0)
+          probs = (probs.transpose / probs.sum(axis: 1)).transpose.dup
+        end
+        probs
+      end
+
+      # Dump marshal data.
+      # @return [Hash] The marshal data about LinearSVC.
+      def marshal_dump
+        { params: @params,
+          model: @model,
+          weight_vec: @weight_vec,
+          bias_term: @bias_term,
+          prob_param: @prob_param }
+      end
+
+      # Load marshal data.
+      # @return [nil]
+      def marshal_load(obj)
+        @params = obj[:params]
+        @model = obj[:model]
+        @weight_vec = obj[:weight_vec]
+        @bias_term = obj[:bias_term]
+        @prob_param = obj[:prob_param]
+        nil
+      end
+
+      private
+
+      def expand_feature(x)
+        n_samples = x.shape[0]
+        Numo::NArray.hstack([x, Numo::DFloat.ones([n_samples, 1]) * bias_scale])
+      end
+
+      def weight_and_bias(base_weight)
+        if binary_class?
+          bias_vec = 0.0
+          weight_mat = base_weight.dup
+          if fit_bias?
+            bias_vec = weight_mat[-1]
+            weight_mat = weight_mat[0...-1].dup
+          end
+        else
+          bias_vec = Numo::DFloat.zeros(n_classes)
+          weight_mat = base_weight.reshape(n_features, n_classes).transpose.dup
+          if fit_bias?
+            bias_vec = weight_mat[true, -1].dup
+            weight_mat = weight_mat[true, 0...-1].dup
+          end
+        end
+        [weight_mat, bias_vec]
+      end
+
+      def proba_model(df, y)
+        res = binary_class? ? Numo::DFloat[1, 0] : Numo::DFloat.cast([[1, 0]] * n_classes)
+        return res unless fit_probability?
+
+        if binary_class?
+          bin_y = Numo::Int32.cast(y.eq(labels[0])) * 2 - 1
+          res = Rumale::ProbabilisticOutput.fit_sigmoid(df, bin_y)
+        else
+          labels.each_with_index do |c, n|
+            bin_y = Numo::Int32.cast(y.eq(c)) * 2 - 1
+            res[n, true] = Rumale::ProbabilisticOutput.fit_sigmoid(df[true, n], bin_y)
+          end
+        end
+        res
+      end
+
+      def liblinear_params
+        res = {}
+        res[:solver_type] = solver_type
+        res[:eps] = @params[:tol]
+        res[:C] = @params[:reg_param]
+        res[:verbose] = @params[:verbose]
+        res[:random_seed] = @params[:random_seed]
+        res
+      end
+
+      def solver_type
+        return Numo::Liblinear::SolverType::L1R_L2LOSS_SVC if @params[:penalty] == 'l1'
+
+        if @params[:loss] == 'squared_hinge'
+          if @params[:dual]
+            Numo::Liblinear::SolverType::L2R_L2LOSS_SVC_DUAL
+          else
+            Numo::Liblinear::SolverType::L2R_L2LOSS_SVC
+          end
+        else
+          Numo::Liblinear::SolverType::L2R_L1LOSS_SVC_DUAL
+        end
+      end
+
+      def binary_class?
+        @model[:nr_class] == 2
+      end
+
+      def fit_probability?
+        @params[:probability]
+      end
+
+      def fit_bias?
+        @params[:fit_bias]
+      end
+
+      def bias_scale
+        @params[:bias_scale]
+      end
+
+      def n_classes
+        @model[:nr_class]
+      end
+
+      def n_features
+        @model[:nr_feature]
+      end
+
+      def labels
+        @model[:label]
+      end
+    end
+  end
+end