rumale 0.14.2 → 0.14.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7fed739280b26a4afad6081eb1bb32fef9d5292f
-  data.tar.gz: 757d76214e895fd1dfebdf03b79be2e71b60a8e0
+  metadata.gz: d1df6dee93147a75173bc099cd68dd116e7729c1
+  data.tar.gz: da85a19ca4964ee95cf026a69f2610b0c5d2b92c
 SHA512:
-  metadata.gz: c76042f5fbaa269884191bd6856674fcf8c89f499d68e0cd4c5e653bdb16a041a647e25d5b2592d7fd840fe55a7da45c195b58cebaa8d81ca8b957088c2e97b9
-  data.tar.gz: a7d8220b679419e3f875e910b44a446dc571dee34e5a44296ef1a3506a65d18c96997d0f979a8ffb0d5195aabd5113ad301c9f9d60a6ea791ca02841be33669c
+  metadata.gz: 893ae704bf217de39ee1b4ccbb0601ffea3804252c992c5b4d79f9dc68171d6a7f0be8d6218af315cd540331bc6b91627d8c990cd53c10cf3d13e5a5123481c0
+  data.tar.gz: 5faf0ce1a7f38974a996534b0817557fea033bf0aea5a867f1fd2460db7153a09bc4ab7ddc233791d73be7c220be9da714830b8dcfbc20a9b366164ef48ea617

data/.rubocop.yml

@@ -48,7 +48,7 @@ Metrics/ParameterLists:
 Security/MarshalLoad:
   Enabled: false
 
-Naming/UncommunicativeMethodParamName:
+Naming/MethodParameterName:
   Enabled: false
 
 Naming/ConstantName:
@@ -66,6 +66,9 @@ Layout/EmptyLineAfterGuardClause:
 RSpec/MultipleExpectations:
   Enabled: false
 
+RSpec/NestedGroups:
+  Max: 4
+
 RSpec/ExampleLength:
   Max: 40
 

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+# 0.14.3
+- Fix documents of GradientBoosting, RandomForest, and ExtraTrees.
+- Refactor gaussian mixture clustering with Rubocop.
+- Refactor specs.
+
 # 0.14.2
 - Refactor extension codes of decision tree estimators.
 - Refactor specs.

data/README.md

@@ -15,7 +15,8 @@ Logistic Regression, Ridge, Lasso, Factorization Machine,
 Multi-layer Perceptron,
 Naive Bayes, Decision Tree, Gradient Tree Boosting, Random Forest,
 K-Means, Gaussian Mixture Model, DBSCAN, Spectral Clustering,
-Mutidimensional Scaling, t-SNE, Principal Component Analysis, and Non-negative Matrix Factorization.
+Mutidimensional Scaling, t-SNE, Principal Component Analysis, Non-negative Matrix Factorization,
+and many other algorithms.
 
 This project was formerly known as "SVMKit".
 If you are using SVMKit, please install Rumale and replace `SVMKit` constants with `Rumale`.

data/lib/rumale/clustering/gaussian_mixture.rb

@@ -229,9 +229,8 @@ module Rumale
       end
 
       def check_enable_linalg(method_name)
-        if (@params[:covariance_type] == 'full') && !enable_linalg?
-          raise "GaussianMixture##{method_name} requires Numo::Linalg when covariance_type is 'full' but that is not loaded."
-        end
+        return unless @params[:covariance_type] == 'full' && !enable_linalg?
+        raise "GaussianMixture##{method_name} requires Numo::Linalg when covariance_type is 'full' but that is not loaded."
       end
     end
   end

data/lib/rumale/ensemble/extra_trees_classifier.rb

@@ -46,7 +46,7 @@ module Rumale
       #   If nil is given, number of leaves is not limited.
       # @param min_samples_leaf [Integer] The minimum number of samples at a leaf node.
       # @param max_features [Integer] The number of features to consider when searching optimal split point.
-      #   If nil is given, split process considers all features.
+      #   If nil is given, split process considers 'Math.sqrt(n_features)' features.
       # @param n_jobs [Integer] The number of jobs for running the fit method in parallel.
       #   If nil is given, the method does not execute in parallel.
       #   If zero or less is given, it becomes equal to the number of processors.
@@ -77,7 +77,7 @@ module Rumale
         check_sample_label_size(x, y)
         # Initialize some variables.
         n_features = x.shape[1]
-        @params[:max_features] = Math.sqrt(n_features).to_i unless @params[:max_features].is_a?(Integer)
+        @params[:max_features] = Math.sqrt(n_features).to_i if @params[:max_features].nil?
         @params[:max_features] = [[1, @params[:max_features]].max, n_features].min
         @classes = Numo::Int32.asarray(y.to_a.uniq.sort)
         sub_rng = @rng.dup

data/lib/rumale/ensemble/extra_trees_regressor.rb

@@ -42,7 +42,7 @@ module Rumale
       #   If nil is given, number of leaves is not limited.
       # @param min_samples_leaf [Integer] The minimum number of samples at a leaf node.
       # @param max_features [Integer] The number of features to consider when searching optimal split point.
-      #   If nil is given, split process considers all features.
+      #   If nil is given, split process considers 'Math.sqrt(n_features)' features.
       # @param n_jobs [Integer] The number of jobs for running the fit and predict methods in parallel.
       #   If nil is given, the methods do not execute in parallel.
       #   If zero or less is given, it becomes equal to the number of processors.
@@ -73,7 +73,7 @@ module Rumale
         check_sample_tvalue_size(x, y)
         # Initialize some variables.
         n_features = x.shape[1]
-        @params[:max_features] = Math.sqrt(n_features).to_i unless @params[:max_features].is_a?(Integer)
+        @params[:max_features] = Math.sqrt(n_features).to_i if @params[:max_features].nil?
         @params[:max_features] = [[1, @params[:max_features]].max, n_features].min
         sub_rng = @rng.dup
         # Construct forest.

data/lib/rumale/ensemble/gradient_boosting_classifier.rb

@@ -49,6 +49,7 @@ module Rumale
       # @param n_estimators [Integer] The numeber of trees for contructing classifier.
       # @param learning_rate [Float] The boosting learining rate
       # @param reg_lambda [Float] The L2 regularization term on weight.
+      # @param subsample [Float] The subsampling ratio of the training samples.
       # @param max_depth [Integer] The maximum depth of the tree.
       #   If nil is given, decision tree grows without concern for depth.
       # @param max_leaf_nodes [Integer] The maximum number of leaves on decision tree.

data/lib/rumale/ensemble/gradient_boosting_regressor.rb

@@ -44,6 +44,7 @@ module Rumale
       # @param n_estimators [Integer] The numeber of trees for contructing regressor.
       # @param learning_rate [Float] The boosting learining rate
       # @param reg_lambda [Float] The L2 regularization term on weight.
+      # @param subsample [Float] The subsampling ratio of the training samples.
       # @param max_depth [Integer] The maximum depth of the tree.
       #   If nil is given, decision tree grows without concern for depth.
       # @param max_leaf_nodes [Integer] The maximum number of leaves on decision tree.

data/lib/rumale/ensemble/random_forest_classifier.rb

@@ -47,7 +47,7 @@ module Rumale
       #   If nil is given, number of leaves is not limited.
       # @param min_samples_leaf [Integer] The minimum number of samples at a leaf node.
       # @param max_features [Integer] The number of features to consider when searching optimal split point.
-      #   If nil is given, split process considers all features.
+      #   If nil is given, split process considers 'Math.sqrt(n_features)' features.
       # @param n_jobs [Integer] The number of jobs for running the fit method in parallel.
       #   If nil is given, the method does not execute in parallel.
       #   If zero or less is given, it becomes equal to the number of processors.
@@ -91,7 +91,7 @@ module Rumale
         check_sample_label_size(x, y)
         # Initialize some variables.
         n_samples, n_features = x.shape
-        @params[:max_features] = Math.sqrt(n_features).to_i unless @params[:max_features].is_a?(Integer)
+        @params[:max_features] = Math.sqrt(n_features).to_i if @params[:max_features].nil?
         @params[:max_features] = [[1, @params[:max_features]].max, n_features].min
         @classes = Numo::Int32.asarray(y.to_a.uniq.sort)
         sub_rng = @rng.dup

data/lib/rumale/ensemble/random_forest_regressor.rb

@@ -42,7 +42,7 @@ module Rumale
       #   If nil is given, number of leaves is not limited.
       # @param min_samples_leaf [Integer] The minimum number of samples at a leaf node.
       # @param max_features [Integer] The number of features to consider when searching optimal split point.
-      #   If nil is given, split process considers all features.
+      #   If nil is given, split process considers 'Math.sqrt(n_features)' features.
       # @param n_jobs [Integer] The number of jobs for running the fit and predict methods in parallel.
       #   If nil is given, the methods do not execute in parallel.
       #   If zero or less is given, it becomes equal to the number of processors.
@@ -85,7 +85,7 @@ module Rumale
         check_sample_tvalue_size(x, y)
         # Initialize some variables.
         n_samples, n_features = x.shape
-        @params[:max_features] = Math.sqrt(n_features).to_i unless @params[:max_features].is_a?(Integer)
+        @params[:max_features] = Math.sqrt(n_features).to_i if @params[:max_features].nil?
         @params[:max_features] = [[1, @params[:max_features]].max, n_features].min
         single_target = y.shape[1].nil?
         sub_rng = @rng.dup

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 = '0.14.2'
+  VERSION = '0.14.3'
 end

data/rumale.gemspec

@@ -20,7 +20,8 @@ Gem::Specification.new do |spec|
     Multi-layer Perceptron,
     Naive Bayes, Decision Tree, Gradient Tree Boosting, Random Forest,
     K-Means, Gaussian Mixture Model, DBSCAN, Spectral Clustering,
-    Mutidimensional Scaling, t-SNE, Principal Component Analysis, and Non-negative Matrix Factorization.
+    Mutidimensional Scaling, t-SNE, Principal Component Analysis, Non-negative Matrix Factorization,
+    and many other algorithms.
   MSG
   spec.homepage      = 'https://github.com/yoshoku/rumale'
   spec.license       = 'BSD-2-Clause'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rumale
 version: !ruby/object:Gem::Version
-  version: 0.14.2
+  version: 0.14.3
 platform: ruby
 authors:
 - yoshoku
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-12-06 00:00:00.000000000 Z
+date: 2019-12-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -130,7 +130,8 @@ description: |
   Multi-layer Perceptron,
   Naive Bayes, Decision Tree, Gradient Tree Boosting, Random Forest,
   K-Means, Gaussian Mixture Model, DBSCAN, Spectral Clustering,
-  Mutidimensional Scaling, t-SNE, Principal Component Analysis, and Non-negative Matrix Factorization.
+  Mutidimensional Scaling, t-SNE, Principal Component Analysis, Non-negative Matrix Factorization,
+  and many other algorithms.
 email:
 - yoshoku@outlook.com
 executables: []