TPOT

What TPOT is

TPOT is a Python automated machine learning tool that uses genetic programming to optimize machine learning pipelines. Its current package includes genetic feature selection, flexible search space definitions, multi-objective optimization, and a modular evolutionary algorithm framework. Documentation covers classifiers and regressors as well as graph, sequential, tree, and union pipeline types. When preprocessing is enabled, TPOT imputes missing values, one-hot encodes categorical features, and standardizes data. It uses Dask for parallel processing and offers model evaluation, automated machine learning, and API access.

TPOT requires Python and can be installed manually or in a conda environment; the documented Python range is >=3.10 and <3.14. Installation documentation lists scikit-learn and an optional tpot[sklearnex] choice for extra scikit-learn extensions. The project is free software under the GNU Lesser General Public License version 3 or later, without warranty. Its documentation cautions that input formatting is not checked and assumes selected operators can handle the data. It also notes preprocessing is fitted and transformed on the full training set before cross-validation splitting. Scikit-learn extensions may have compatibility or performance issues on Arm-based CPUs such as M1 Macs.