Rumale (*Ru*by *ma*chine *le*arning) is a machine learning library in Ruby. Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python. Rumale supports Support Vector Machine, Logistic Regression, Ridge, Lasso, Multi-layer Perceptron, Naive Bayes, Decision Tree, Gradient Tree Boosting, Random Forest, K-Means, Gaussian Mixture Model, DBSCAN, Spectral Clustering, Mutidimensional Scaling, t-SNE, Fisher Discriminant Analysis, Neighbourhood Component Analysis, Principal Component Analysis, Non-negative Matrix Factorization, and many other algorithms.


Add this line to your application’s Gemfile:

gem 'rumale'

And then execute:

$ bundle

Or install it yourself as:

$ gem install rumale



Example 1. Pendigits dataset classification

Rumale provides function loading libsvm format dataset file. We start by downloading the pendigits dataset from LIBSVM Data web site.

$ wget
$ wget

Training of the classifier with Linear SVM and RBF kernel feature map is the following code.

require 'rumale'

# Load the training dataset.
samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')

# Map training data to RBF kernel feature space.
transformer = 0.0001, n_components: 1024, random_seed: 1)
transformed = transformer.fit_transform(samples)

# Train linear SVM classifier.
classifier = 0.0001), labels)

# Save the model.'transformer.dat', 'wb') { |f| f.write(Marshal.dump(transformer)) }'classifier.dat', 'wb') { |f| f.write(Marshal.dump(classifier)) }

Classifying testing data with the trained classifier is the following code.

require 'rumale'

# Load the testing dataset.
samples, labels = Rumale::Dataset.load_libsvm_file('pendigits.t')

# Load the model.
transformer = Marshal.load(File.binread('transformer.dat'))
classifier = Marshal.load(File.binread('classifier.dat'))

# Map testing data to RBF kernel feature space.
transformed = transformer.transform(samples)

# Classify the testing data and evaluate prediction results.
puts("Accuracy: %.1f%%" % (100.0 * classifier.score(transformed, labels)))

# Other evaluating approach
# results = classifier.predict(transformed)
# evaluator =
# puts("Accuracy: %.1f%%" % (100.0 * evaluator.score(results, labels)))

Execution of the above scripts result in the following.

$ ruby train.rb
$ ruby test.rb
Accuracy: 98.5%

Example 2. Cross-validation

require 'rumale'

# Load dataset.
samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')

# Define the estimator to be evaluated.
lr =

# Define the evaluation measure, splitting strategy, and cross validation.
ev =
kf = 5, shuffle: true, random_seed: 1)
cv = lr, splitter: kf, evaluator: ev)

# Perform 5-cross validation.
report = cv.perform(samples, labels)

# Output result.
mean_accuracy = report[:test_score].sum / kf.n_splits
puts "5-CV mean accuracy: %.1f%%" % (100.0 * mean_accuracy)

Execution of the above scripts result in the following.

$ ruby cross_validation.rb
5-CV mean accuracy: 95.5%



Rumale uses Numo::NArray for typed arrays. Loading the Numo::Linalg allows to perform matrix and vector product of Numo::NArray using BLAS libraries. Some machine learning algorithms frequently compute matrix and vector products, the execution speed of such algorithms can be expected to be accelerated.

Install Numo::Linalg gem.

$ gem install numo-linalg

In ruby script, just load Numo::Linalg along with Rumale.

require 'numo/linalg/autoloader'
require 'rumale'

Numo::Linalg allows user selection of background libraries for BLAS/LAPACK. Instead of fixing the background library, Numo::OpenBLAS and Numo::BLIS are available to simplify installation.


Numo::TinyLinalg is a subset library from Numo::Linalg consisting only of methods used in machine learning algorithms. Numo::TinyLinalg only supports OpenBLAS as a backend library for BLAS and LAPACK. If the OpenBLAS library is not found during installation, Numo::TinyLinalg downloads and builds that.

$ gem install numo-tiny_linalg

Load Numo::TinyLinalg instead of Numo::Linalg.

require 'numo/tiny_linalg'

Numo::Linalg = Numo::TinyLinalg

require 'rumale'


Several estimators in Rumale support parallel processing. Parallel processing in Rumale is realized by Parallel gem, so install and load it.

$ gem install parallel
require 'parallel'
require 'rumale'

Estimators that support parallel processing have n_jobs parameter. When -1 is given to n_jobs parameter, all processors are used.

estimator = -1, random_seed: 1)

Related Projects

  • Rumale::SVM provides support vector machine algorithms in LIBSVM and LIBLINEAR with Rumale interface.

  • Rumale::Torch provides the learning and inference by the neural network defined in torch.rb with Rumale interface.


The gem is available as open source under the terms of the BSD-3-Clause License.