PyMC3 is a Python package for probabilistic machine learning that enables users to build bespoke models for their specific problems using a probabilistic modeling framework. However, PyMC3 lacks the steps between creating a model and reusing it with new data in production. The missing steps include: scoring a model, saving a model for later use, and loading the model in production systems. In contrast, scikit-learn which has become the standard library for machine learning provides a simple API that makes it very easy for users to train, score, save and load models in production. However, scikit-learn may not have the model for a user's specific problem. These limitations have led to the development of the open source pymc3-models library which provides a template to build bespoke PyMC3 models on top of the scikit-learn API and reuse them in production. This enables users to easily and quickly train, score, save and load their bespoke models just like in scikit-learn. Our current research and development leverage the template in pymc3-models to develop custom nonparametric Bayesian models. This allows users to leverage the flexibility of nonparametric Bayesian models in a simple workflow that mimics the scikit-learn API.
Only a laptop with a modern web browser like Google chrome or Mozilla Firefox.