tech.ml.dataset

Dataset and ETL pipeline for machine learning. Datasets are currently in-memory columnwise databases. The backing store behind tech.ml.dataset is tablesaw. Further support is intended in the near future for Apache Arrow.

An example of using the dataset for advanced regression techniques.

Dataset Pipeline Processing

Dataset ETL for this library consists of loading heterogeneous columns of data and then operating on that data in a mainly columnwise fashion.

tech.v2.datatype subsystem which is described on our blog. Here is a cheatsheet.

The tablesaw column-level bindings are here. They use the generic table support and as such they do not use the actual tablesaw 'table' datatype.

Examples

• sequences of maps
• regression pipelines

License

Copyright © 2019 Complements of TechAscent, LLC

Distributed under the Eclipse Public License either version 1.0 or (at your option) any later version.