padreati/rapaio

Disambiguation (Italian dictionary) Field of turnips. It is also a place where there is confusion, where tricks and sims are plotted. (Computer science) Statistics, data mining and machine learning library written in Java.

Try it online

Build status

Documentation

Rapaio is a rich collection of data mining, statistics and machine learning tools written completely in Java. Documentation for this library is hosted as github pages. Most of the documentation is written as Jupyter notebooks and can be seen at rapaio-book github repository.

The complete list of features is presented here. An incomplete list of implemented algorithms and features includes: core statistical tools, common distributions and hypothesis testing, Naive Bayes, Binary Logistic Regression, Decision Trees (regression and classification), Random Forests (regression and classification), AdaBoost, Gradient Boosting Trees (regression and classification), BinarySMO, SVM, Relevant Vector Machines (regression), Linear and Ridge Regression, PCA and KMeans. Additionally there is a fair share of graphical tools and linear algebra stuff. And the list is growing periodically.

Installation

Last published release on maven central is 8.1.0

<dependency>
    <groupId>io.github.padreati</groupId>
    <artifactId>rapaio-lib</artifactId>
    <version>8.1.0</version>
</dependency>

The best way for exploration is through jupyter / jupyter-lab notebooks. This is excellent for experimenting with interactive notebooks or to document the ideas you are working on. You have to install jupyter / jupyter-lab and rapaio-jupyter-kernel kernel. For more information you can follow the instruction from Rapaio Jupyter Kernel.

%dependency /add io.github.padreati:rapaio-lib:8.1.0
%dependency /resolve

Acknowledgements

Many thanks to JetBrains who provided open source licenses for their brilliant IDE . Update: unfortunately I was not able to receive open source licences for the current year (since September 2025). Still,