lazygrid

LazyGrid is a machine learning model comparator that follows the memoization paradigm, i.e. that is able to save fitted models and return them if required later. Lazygrid is supported on Python 3.5 and above. The package is compatible with scikit-learn 0.21 and Keras 2.2.5. In order to generate all possible pipelines given a set of steps, you should define a list of elements, which in turn are lists of pipeline steps, i.e. preprocessors, feature selectors, classifiers, etc. Each step could be either a sklearn object or a keras model.