MLJAR AutoML vs Weka

MLJAR AutoML automates supervised machine learning for tabular data, including binary classification, multiclass classification, and regression. Users can work through MLJAR Studio notebooks or use the open-source Python package in scripts and notebooks. Its four modes—Explain, Perform, Compete, and Optuna—have configurable choices for algorithms, validation, metrics, time budget, and explanations. Depending on the selected mode and settings, workflows can preprocess data, select and tune models, engineer and select features, and create ensembles. Experiments include model comparisons, validation results, training times, explanations, and reusable artifacts; summaries are available in Markdown and JSON. Fairness-aware training evaluates models against a chosen metric and threshold and can try sample reweighting, but does not guarantee fairness. The Python package integrates with Mercury for prediction apps supporting individual and batch CSV predictions; apps can be previewed locally, published through MLJAR Platform, or self-hosted with Docker. The package is open source under the MIT license and costs nothing. AutoML is designed for supervised tabular tasks, and reports depend on task and settings.

Weka is open-source machine-learning software for building and evaluating models, with support for forecasting and time-series modeling. It is available free under the GNU General Public License, with Weka 3.8 as the stable release and 3.9 as the development version. The stable branch receives fixes and feature updates intended to preserve compatibility; development builds may introduce breaking changes. Weka provides a Java API, Javadoc for its API and command-line parameters, and can also be used through Jupyter notebooks. Official releases require Java 8 or later. Downloads are listed for Windows, Mac OS, and Linux, with Intel and ARM options. Both branches include a package manager for community extensions, though installing packages requires internet access. The software includes built-in help and a comprehensive manual, with additional assistance through documentation, mailing list archives, forums, and a mailing list. Distributed derivative works must use the GPL; commercial projects needing Weka code in a non-GPL program may be able to obtain a suitable license. Models serialized in version 3.7 are incompatible with 3.8, and the migrator has an exception for RandomForest.