ELKI (Environment for Developing KDD-Applications Supported by Index-Structures) is a data mining (KDD, knowledge discovery in databases) software framework developed for use in research and teaching. It was originally at the database systems research unit of Professor Hans-Peter Kriegel at the Ludwig Maximilian University of Munich, Germany, and now continued at the Technical University of Dortmund, Germany. It aims at allowing the development and evaluation of advanced data mining algorithms and their interaction with database index structures.
Description
The ELKI framework is written in Java and built around a modular architecture. Most currently included algorithms belong to clustering, outlier detection, and database indexes. The object-oriented architecture allows the combination of arbitrary algorithms, data types, distance functions, indexes, and evaluation measures. The Java just-in-time compiler optimizes all combinations to a similar extent, making benchmarking results more comparable if they share large parts of the code. When developing new algorithms or index structures, the existing components can be easily reused, and the type safety of Java detects many programming errors at compile time.
ELKI has been used in data science for example to cluster sperm whale codas, phoneme clustering, for anomaly detection in spaceflight operations, for bike sharing redistribution, and traffic prediction.
Objectives
The university project is developed for use in teaching and research. The source code is written with extensibility and reusability in mind, but is also optimized for performance. The experimental evaluation of algorithms depends on many environmental factors and implementation details can have a large impact on the runtime. ELKI aims at providing a shared codebase with comparable implementations of many algorithms.
As research project, it currently does not offer integration with business intelligence applications or an interface to common database management systems via SQL. The copyleft (AGPL) license may also be a hindrance to an integration in commercial products; nevertheless it can be used to evaluate algorithms prior to developing an own implementation for a commercial product. Furthermore, the application of the algorithms requires knowledge about their usage, parameters, and study of original literature. The audience are students, researchers, data scientists, and software engineers.
Architecture
ELKI is modeled around a database-inspired core, which uses a vertical data layout that stores data in column groups (similar to column families in NoSQL databases). This database core provides nearest neighbor search, range/radius search, and distance query functionality with index acceleration for a wide range of dissimilarity measures. Algorithms based on such queries (e.g. k-nearest-neighbor algorithm, local outlier factor and DBSCAN) can be implemented easily and benefit from the index acceleration. The database core also provides fast and memory efficient collections for object collections and associative structures such as nearest neighbor lists.
ELKI makes extensive use of Java interfaces, so that it can be extended easily in many places. For example, custom data types, distance functions, index structures, algorithms, input parsers, and output modules can be added and combined without modifying the existing code. This includes the possibility of defining a custom distance function and using existing indexes for acceleration.
ELKI uses a service loader architecture to allow publishing extensions as separate jar files.
ELKI uses optimized collections for performance rather than the standard Java API. For loops for example are written similar to C++ iterators: for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) { relation.get(iter); // E.g., get the referenced object idcollection.add(iter); // E.g., add the reference to a DBID collection } In contrast to typical Java iterators (which can only iterate over objects), this conserves memory, because the iterator can internally use primitive values for data storage. The reduced garbage collection improves the runtime. Optimized collections libraries such as GNU Trove3, Koloboke, and fastutil employ similar optimizations. ELKI includes data structures such as object collections and heaps (for, e.g., nearest neighbor search) using such optimizations.