MLlib is the scalable machine-learning library developed for Apache Spark. MLlib is usable in a variety of languages (Java, Python, etc.), enables the extraction of new knowledge from existing data, is easy to use in a variety of languages (Java, Python, etc.), and is easy to deploy in Hadoop clusters, as well as in standalone applications of Spark.



Extensible and simple environment for scalable algorithms. It includes several premade algorithms for existing database frameworks. Mahout is focused on filtering, classification and clustering, and provides math operations, mainly for statistics and linear algebra.



SAMOA basically offers a programming abstraction for distributed ML algorithms. Sustains massive online analysis, thus being ideal for cloud computation.