rumale 0.13.7 → 0.13.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6b7030e096e10df1a95d79aefe6d275c0ca16406
-  data.tar.gz: 85f6b809e41ecb4743df7e07b99bc3fcf13710e1
+  metadata.gz: 581437e401cec76201212dbd1aa1e38ff6142eef
+  data.tar.gz: 42ce62c892dcee05d41a5857a28c80627da95833
 SHA512:
-  metadata.gz: efb25c2ea461c3ceb9b8d500a4ef77dd4db6e4a2c21400009e8fd940bd28dab6d4a725a320a5e3cc1a1b7676626d03b9c2ef73c9c02246c29e122461680488d7
-  data.tar.gz: 264c10852a7eb01ddb075c87969625f2cb82eb0bfa3050e21bf41f355d8213808c3684a63a0e7e95480965e0737ae76a85babee60b0a638274c31bc1741774b9
+  metadata.gz: 36d7bb281d676827b40f3382292a414b474a83c153e7260f5ceb8af2b7664d621ae0adb3ece7475f35e83debd6f6b1e031c804bf76260ec58be6aca315b0d431
+  data.tar.gz: 367c273c90a4685913eb48dde5cb1d109e871e87ac1b2aab76d06b565a283996ea25ece3aa9030b7df64348902f8636c2ee3580a19ac533224fbbe62a495e45c

data/CHANGELOG.md

@@ -1,8 +1,13 @@
+# 0.13.8
+- Add [module function](https://yoshoku.github.io/rumale/doc/Rumale/Dataset.html#make_blobs-class_method) for generating artificial dataset with gaussian blobs.
+- Add documents about Rumale::SVM.
+- Refactor specs.
+
 # 0.13.7
 - Add some evaluator classes for clustering.
-  - SilhouetteScore
-  - CalinskiHarabaszScore
-  - DaviesBouldinScore
+  - [SilhouetteScore](https://yoshoku.github.io/rumale/doc/Rumale/EvaluationMeasure/SilhouetteScore.html)
+  - [CalinskiHarabaszScore](https://yoshoku.github.io/rumale/doc/Rumale/EvaluationMeasure/CalinskiHarabaszScore.html)
+  - [DaviesBouldinScore](https://yoshoku.github.io/rumale/doc/Rumale/EvaluationMeasure/DaviesBouldinScore.html)
 
 # 0.13.6
 - Add transformer class for [FastICA](https://yoshoku.github.io/rumale/doc/Rumale/Decomposition/FastICA.html).

data/lib/rumale/dataset.rb

@@ -2,6 +2,8 @@
 
 require 'csv'
 require 'rumale/validation'
+require 'rumale/utils'
+require 'rumale/preprocessing/min_max_scaler'
 
 module Rumale
   # Module for loading and saving a dataset file.
@@ -126,6 +128,60 @@ module Rumale
         [x, y]
       end
 
+      # Generate Gaussian blobs.
+      #
+      # @param n_samples [Integer] The total number of samples.
+      # @param n_features [Integer] The number of features.
+      #   If "centers" parameter is given as a Numo::DFloat array, this parameter is ignored.
+      # @param centers [Integer/Numo::DFloat/Nil] The number of cluster centroids or the fixed cluster centroids.
+      #   If nil is given, the number of cluster centroids is set to 3.
+      # @param cluster_std [Float] The standard deviation of the clusters.
+      # @param center_box [Array] The bounding box for each cluster centroids.
+      #   If "centers" parameter is given as a Numo::DFloat array, this parameter is ignored.
+      # @param shuffle [Boolean] The flag indicating whether to shuffle the dataset
+      # @param random_seed [Integer] The seed value using to initialize the random generator.
+      def make_blobs(n_samples = 1000, n_features = 2,
+                     centers: nil, cluster_std: 1.0, center_box: [-10, 10], shuffle: true, random_seed: nil)
+        Rumale::Validation.check_params_integer(n_samples: n_samples, n_features: n_features)
+        Rumale::Validation.check_params_float(cluster_std: cluster_std)
+        Rumale::Validation.check_params_type(Array, center_box: center_box)
+        Rumale::Validation.check_params_boolean(shuffle: shuffle)
+        Rumale::Validation.check_params_type_or_nil(Integer, random_seed: random_seed)
+        # initialize rng.
+        rs = random_seed
+        rs ||= srand
+        rng = Random.new(rs)
+        # initialize centers.
+        if centers.is_a?(Numo::DFloat)
+          n_centers = centers.shape[0]
+          n_features = centers.shape[1]
+        else
+          n_centers = centers.is_a?(Integer) ? centers : 3
+          center_min = center_box.first
+          center_max = center_box.last
+          centers = Rumale::Utils.rand_uniform([n_centers, n_features], rng)
+          normalizer = Rumale::Preprocessing::MinMaxScaler.new(feature_range: [center_min, center_max])
+          centers = normalizer.fit_transform(centers)
+        end
+        # generate blobs.
+        sz_cluster = [n_samples / n_centers] * n_centers
+        (n_samples % n_centers).times { |n| sz_cluster[n] += 1 }
+        x = Rumale::Utils.rand_normal([sz_cluster[0], n_features], rng, 0.0, cluster_std) + centers[0, true]
+        y = Numo::Int32.zeros(sz_cluster[0])
+        (1...n_centers).each do |n|
+          c = Rumale::Utils.rand_normal([sz_cluster[n], n_features], rng, 0.0, cluster_std) + centers[n, true]
+          x = Numo::DFloat.vstack([x, c])
+          y = y.concatenate(Numo::Int32.zeros(sz_cluster[n]) + n)
+        end
+        # shuffle data.
+        if shuffle
+          rand_ids = [*0...n_samples].shuffle(random: rng.dup)
+          x = x[rand_ids, true].dup
+          y = y[rand_ids].dup
+        end
+        [x, y]
+      end
+
       private
 
       def parse_libsvm_line(line, zero_based)

data/lib/rumale/kernel_machine/kernel_svc.rb

@@ -11,6 +11,10 @@ module Rumale
     # with stochastic gradient descent (SGD) optimization.
     # For multiclass classification problem, it uses one-vs-the-rest strategy.
     #
+    # Rumale::SVM provides kernel support vector classifier based on LIBSVM.
+    # If you prefer execution speed, you should use Rumale::SVM::SVC.
+    # https://github.com/yoshoku/rumale-svm
+    #
     # @example
     #   training_kernel_matrix = Rumale::PairwiseMetric::rbf_kernel(training_samples)
     #   estimator =

data/lib/rumale/linear_model/logistic_regression.rb

@@ -9,6 +9,10 @@ module Rumale
     # with mini-batch stochastic gradient descent optimization.
     # For multiclass classification problem, it uses one-vs-the-rest strategy.
     #
+    # Rumale::SVM provides Logistic Regression based on LIBLINEAR.
+    # If you prefer execution speed, you should use Rumale::SVM::LogisticRegression.
+    # https://github.com/yoshoku/rumale-svm
+    #
     # @example
     #   estimator =
     #     Rumale::LinearModel::LogisticRegression.new(reg_param: 1.0, max_iter: 1000, batch_size: 20, random_seed: 1)

data/lib/rumale/linear_model/svc.rb

@@ -11,6 +11,10 @@ module Rumale
     # with mini-batch stochastic gradient descent optimization.
     # For multiclass classification problem, it uses one-vs-the-rest strategy.
     #
+    # Rumale::SVM provides linear support vector classifier based on LIBLINEAR.
+    # If you prefer execution speed, you should use Rumale::SVM::LinearSVC.
+    # https://github.com/yoshoku/rumale-svm
+    #
     # @example
     #   estimator =
     #     Rumale::LinearModel::SVC.new(reg_param: 1.0, max_iter: 1000, batch_size: 20, random_seed: 1)

data/lib/rumale/linear_model/svr.rb

@@ -8,6 +8,10 @@ module Rumale
     # SVR is a class that implements Support Vector Regressor
     # with mini-batch stochastic gradient descent optimization.
     #
+    # Rumale::SVM provides linear and kernel support vector regressor based on LIBLINEAR and LIBSVM.
+    # If you prefer execution speed, you should use Rumale::SVM::LinearSVR.
+    # https://github.com/yoshoku/rumale-svm
+    #
     # @example
     #   estimator =
     #     Rumale::LinearModel::SVR.new(reg_param: 1.0, epsilon: 0.1, max_iter: 1000, batch_size: 20, random_seed: 1)

data/lib/rumale/version.rb

@@ -3,5 +3,5 @@
 # Rumale is a machine learning library in Ruby.
 module Rumale
   # The version of Rumale you are using.
-  VERSION = '0.13.7'
+  VERSION = '0.13.8'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rumale
 version: !ruby/object:Gem::Version
-  version: 0.13.7
+  version: 0.13.8
 platform: ruby
 authors:
 - yoshoku
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-11-02 00:00:00.000000000 Z
+date: 2019-11-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray