numo-libsvm 1.1.2 → 2.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f321e889c3d7a6a617f6700885d5c39f00272a4cd2aad82e2efadb6818fe78aa
-  data.tar.gz: bc8062c42b4f20cc1b6cfe11a2cebff4fc2881be180c92ca287e5f3c85b74a76
+  metadata.gz: 37613a10119b2974024687c3f781d271ebaa30b15ccff6100df17c32642dcd2d
+  data.tar.gz: 210e072576d4fa859364fdb522e6f02c9be12458e5ed0647fcd8bebedfdb3e84
 SHA512:
-  metadata.gz: faa13722b019804975e539f4f10a64bb602a3052529d885e168e343801a61a074af186efa6f0c8e124f03ed8b95cfc7067a7c06eda334d89a9c41f4775d18c2c
-  data.tar.gz: 28b0830bd53f280c6511013ca838bf29ed510cf8062b7f47425d15aa287418452c14ea7f98567ee459518be9aa946cee40d3401a9011169e3f51d64f64f96ca8
+  metadata.gz: 142e15fe744460f679f7bd7978f1654e2e71a40a49ce3a414c3c0e68b507d6d9c286eec9edd37a10f5b9fc60a940079c42e59d1283ba607cd7748b80d16fa12f
+  data.tar.gz: 67909b309d9a186e77dc716cc2e8b1299d0be3baf10be7be87fc89f2bc67a47b087063827be2f8ba750378d354f745c58dec0feb072f8eea73c883c3c034a669

data/CHANGELOG.md

@@ -1,3 +1,16 @@
+# 2.1.0
+- Update bundled LIBSVM to 3.30.
+- Support for probilistic outputs of one-class SVM.
+
+# 2.0.1
+- Chnage to use memcpy to copy vector.
+- Refactor codes and configs with RuboCop.
+
+# 2.0.0
+- Redesign native extension codes.
+- Change not ot use git submodule for LIBSVM codes bundle.
+- Introduce conventional commits.
+
 # 1.1.2
 - Remove dependent gem's type declaration file from installation files.
 

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2019-2021 Atsushi Tatsuma
+Copyright (c) 2019-2022 Atsushi Tatsuma
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

data/README.md

@@ -189,12 +189,8 @@ param = {
 
 ## Contributing
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/numo-libsvm. 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.
+Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/numo-libsvm. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](https://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 Numo::Libsvm project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/yoshoku/numo-libsvm/blob/main/CODE_OF_CONDUCT.md).

data/ext/numo/libsvm/extconf.rb

@@ -8,10 +8,7 @@ $LOAD_PATH.each do |lp|
   end
 end
 
-unless have_header('numo/narray.h')
-  puts 'numo/narray.h not found.'
-  exit(1)
-end
+abort 'numo/narray.h not found.' unless have_header('numo/narray.h')
 
 if RUBY_PLATFORM =~ /mswin|cygwin|mingw/
   $LOAD_PATH.each do |lp|
@@ -20,20 +17,13 @@ if RUBY_PLATFORM =~ /mswin|cygwin|mingw/
       break
     end
   end
-  unless have_library('narray', 'nary_new')
-    puts 'libnarray.a not found.'
-    exit(1)
-  end
+  abort 'libnarray.a not found.' unless have_library('narray', 'nary_new')
 end
 
-$LDFLAGS << ' -lstdc++ '
+abort 'libstdc++ is not found.' unless have_library('stdc++')
 
-$srcs = Dir.glob("#{$srcdir}/*.c").map { |path| File.basename(path) }
-$srcs << 'svm.cpp'
-Dir.glob("#{$srcdir}/*/") do |path|
-  dir = File.basename(path)
-  $INCFLAGS << " -I$(srcdir)/#{dir}"
-  $VPATH << "$(srcdir)/#{dir}"
-end
+$srcs = Dir.glob("#{$srcdir}/**/*.cpp").map { |path| File.basename(path) }
+$INCFLAGS << " -I$(srcdir)/src"
+$VPATH << "$(srcdir)/src"
 
 create_makefile('numo/libsvm/libsvmext')

data/ext/numo/libsvm/libsvmext.cpp

@@ -0,0 +1,220 @@
+/**
+ * Copyright (c) 2019-2022 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.
+ */
+
+#include "libsvmext.hpp"
+
+extern "C" void Init_libsvmext(void) {
+  rb_require("numo/narray");
+
+  /**
+   * Document-module: Numo
+   * Numo is the top level namespace of NUmerical MOdules for Ruby.
+   */
+
+  /**
+   * Document-module: Numo::Libsvm
+   * Numo::Libsvm is a binding library for LIBSVM that handles dataset with Numo::NArray.
+   */
+  VALUE mLibsvm = rb_define_module_under(mNumo, "Libsvm");
+
+  /* The version of LIBSVM used in backgroud library. */
+  rb_define_const(mLibsvm, "LIBSVM_VERSION", INT2NUM(LIBSVM_VERSION));
+
+  /**
+   * Document-module: Numo::Libsvm::SvmType
+   * The module consisting of constants for SVM algorithm type that used for parameter of LIBSVM.
+   */
+  VALUE mSvmType = rb_define_module_under(mLibsvm, "SvmType");
+  /* C-SVM classification */
+  rb_define_const(mSvmType, "C_SVC", INT2NUM(C_SVC));
+  /* nu-SVM classification */
+  rb_define_const(mSvmType, "NU_SVC", INT2NUM(NU_SVC));
+  /* one-class-SVM */
+  rb_define_const(mSvmType, "ONE_CLASS", INT2NUM(ONE_CLASS));
+  /* epsilon-SVM regression */
+  rb_define_const(mSvmType, "EPSILON_SVR", INT2NUM(EPSILON_SVR));
+  /* nu-SVM regression */
+  rb_define_const(mSvmType, "NU_SVR", INT2NUM(NU_SVR));
+
+  /**
+   * Document-module: Numo::Libsvm::KernelType
+   * The module consisting of constants for kernel type that used for parameter of LIBSVM.
+   */
+  VALUE mKernelType = rb_define_module_under(mLibsvm, "KernelType");
+  /* Linear kernel; u' * v */
+  rb_define_const(mKernelType, "LINEAR", INT2NUM(LINEAR));
+  /* Polynomial kernel; (gamma * u' * v + coef0)^degree */
+  rb_define_const(mKernelType, "POLY", INT2NUM(POLY));
+  /* RBF kernel; exp(-gamma * ||u - v||^2) */
+  rb_define_const(mKernelType, "RBF", INT2NUM(RBF));
+  /* Sigmoid kernel; tanh(gamma * u' * v + coef0) */
+  rb_define_const(mKernelType, "SIGMOID", INT2NUM(SIGMOID));
+  /* Precomputed kernel */
+  rb_define_const(mKernelType, "PRECOMPUTED", INT2NUM(PRECOMPUTED));
+
+  /**
+   * Train the SVM model according to the given training data.
+   *
+   * @overload train(x, y, param) -> Hash
+   *   @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to be used for training the model.
+   *   @param y [Numo::DFloat] (shape: [n_samples]) The labels or target values for samples.
+   *   @param param [Hash] The parameters of an SVM model.
+   *
+   * @example
+   *   require 'numo/libsvm'
+   *
+   *   # Prepare XOR data.
+   *   x = Numo::DFloat[[-0.8, -0.7], [0.9, 0.8], [-0.7, 0.9], [0.8, -0.9]]
+   *   y = Numo::Int32[-1, -1, 1, 1]
+   *
+   *   # Train C-Support Vector Classifier with RBF kernel.
+   *   param = {
+   *     svm_type: Numo::Libsvm::SvmType::C_SVC,
+   *     kernel_type: Numo::Libsvm::KernelType::RBF,
+   *     gamma: 2.0,
+   *     C: 1,
+   *     random_seed: 1
+   *   }
+   *   model = Numo::Libsvm.train(x, y, param)
+   *
+   *   # Predict labels of test data.
+   *   x_test = Numo::DFloat[[-0.4, -0.5], [0.5, -0.4]]
+   *   result = Numo::Libsvm.predict(x_test, param, model)
+   *   p result
+   *   # Numo::DFloat#shape=[2]
+   *   # [-1, 1]
+   *
+   * @raise [ArgumentError] If the sample array is not 2-dimensional, the label array is not 1-dimensional,
+   *   the sample array and label array do not have the same number of samples, or
+   *   the hyperparameter has an invalid value, this error is raised.
+   * @return [Hash] The model obtained from the training procedure.
+   */
+  rb_define_module_function(mLibsvm, "train", RUBY_METHOD_FUNC(numo_libsvm_train), 3);
+  /**
+   * Perform cross validation under given parameters. The given samples are separated to n_fols folds.
+   * The predicted labels or values in the validation process are returned.
+   *
+   * @overload cv(x, y, param, n_folds) -> Numo::DFloat
+   *   @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to be used for training the model.
+   *   @param y [Numo::DFloat] (shape: [n_samples]) The labels or target values for samples.
+   *   @param param [Hash] The parameters of an SVM model.
+   *   @param n_folds [Integer] The number of folds.
+   *
+   * @example
+   *   require 'numo/libsvm'
+   *
+   *   # x: samples
+   *   # y: labels
+   *
+   *   # Define parameters of C-SVC with RBF Kernel.
+   *   param = {
+   *     svm_type: Numo::Libsvm::SvmType::C_SVC,
+   *     kernel_type: Numo::Libsvm::KernelType::RBF,
+   *     gamma: 1.0,
+   *     C: 1,
+   *     random_seed: 1,
+   *     verbose: true
+   *   }
+   *
+   *   # Perform 5-cross validation.
+   *   n_folds = 5
+   *   res = Numo::Libsvm.cv(x, y, param, n_folds)
+   *
+   *   # Print mean accuracy.
+   *   mean_accuracy = y.eq(res).count.fdiv(y.size)
+   *   puts "Accuracy: %.1f %%" % (100 * mean_accuracy)
+   *
+   * @raise [ArgumentError] If the sample array is not 2-dimensional, the label array is not 1-dimensional,
+   *   the sample array and label array do not have the same number of samples, or
+   *   the hyperparameter has an invalid value, this error is raised.
+   * @return [Numo::DFloat] (shape: [n_samples]) The predicted class label or value of each sample.
+   */
+  rb_define_module_function(mLibsvm, "cv", RUBY_METHOD_FUNC(numo_libsvm_cross_validation), 4);
+  /**
+   * Predict class labels or values for given samples.
+   *
+   * @overload predict(x, param, model) -> Numo::DFloat
+   *   @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate the scores.
+   *   @param param [Hash] The parameters of the trained SVM model.
+   *   @param model [Hash] The model obtained from the training procedure.
+   *
+   * @raise [ArgumentError] If the sample array is not 2-dimensional, this error is raised.
+   * @return [Numo::DFloat] (shape: [n_samples]) The predicted class label or value of each sample.
+   */
+  rb_define_module_function(mLibsvm, "predict", RUBY_METHOD_FUNC(numo_libsvm_predict), 3);
+  /**
+   * Calculate decision values for given samples.
+   *
+   * @overload decision_function(x, param, model) -> Numo::DFloat
+   *   @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate the scores.
+   *   @param param [Hash] The parameters of the trained SVM model.
+   *   @param model [Hash] The model obtained from the training procedure.
+   *
+   * @raise [ArgumentError] If the sample array is not 2-dimensional, this error is raised.
+   * @return [Numo::DFloat] (shape: [n_samples, n_classes * (n_classes - 1) / 2]) The decision value of each sample.
+   */
+  rb_define_module_function(mLibsvm, "decision_function", RUBY_METHOD_FUNC(numo_libsvm_decision_function), 3);
+  /**
+   * Predict class probability for given samples. The model must have probability information calcualted in training procedure.
+   * The parameter ':probability' set to 1 in training procedure.
+   *
+   * @overload predict_proba(x, param, model) -> Numo::DFloat
+   *   @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the class probabilities.
+   *   @param param [Hash] The parameters of the trained SVM model.
+   *   @param model [Hash] The model obtained from the training procedure.
+   *
+   * @raise [ArgumentError] If the sample array is not 2-dimensional, this error is raised.
+   * @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted probablity of each class per sample.
+   */
+  rb_define_module_function(mLibsvm, "predict_proba", RUBY_METHOD_FUNC(numo_libsvm_predict_proba), 3);
+  /**
+   * Load the SVM parameters and model from a text file with LIBSVM format.
+   *
+   * @overload load_svm_model(filename) -> Array
+   *   @param filename [String] The path to a file to load.
+   *
+   * @raise [IOError] This error raises when failed to load the model file.
+   * @return [Array] Array contains the SVM parameters and model.
+   */
+  rb_define_module_function(mLibsvm, "load_svm_model", RUBY_METHOD_FUNC(numo_libsvm_load_model), 1);
+  /**
+   * Save the SVM parameters and model as a text file with LIBSVM format. The saved file can be used with the libsvm tools.
+   * Note that the svm_save_model saves only the parameters necessary for estimation with the trained model.
+   *
+   * @overload save_svm_model(filename, param, model) -> Boolean
+   *   @param filename [String] The path to a file to save.
+   *   @param param [Hash] The parameters of the trained SVM model.
+   *   @param model [Hash] The model obtained from the training procedure.
+   *
+   * @raise [IOError] This error raises when failed to save the model file.
+   * @return [Boolean] true on success, or false if an error occurs.
+   */
+  rb_define_module_function(mLibsvm, "save_svm_model", RUBY_METHOD_FUNC(numo_libsvm_save_model), 3);
+}