GAMA is an AutoML package for end-users and AutoML researchers. It generates optimized machine learning pipelines given specific input data and resource constraints. A machine learning pipeline contains data preprocessing (e.g. PCA, normalization) as well as a machine learning algorithm (e.g. Logistic Regression, Random Forests), with fine-tuned hyperparameter settings (e.g. number of trees in a Random Forest). To find these pipelines, multiple search procedures have been implemented. GAMA can also combine multiple tuned machine learning pipelines together into an ensemble, which on average should help model performance. At the moment, GAMA is restricted to classification and regression problems on tabular data. In addition to its general use AutoML functionality, GAMA aims to serve AutoML researchers as well. During the optimization process, GAMA keeps an extensive log of progress made. Using this log, insight can be obtained on the behavior of the search procedure.
Link: https://openml-labs.github.io/gama/master/
View Resource