User Question: Are MindsDB’s ML models compatible with scikit-learn?
Great question! Yes, MindsDB is compatible with scikit-learn. With Lightwood—the framework that provides the building blocks for MindsDB—if you have rich vector representations, which is a step that you’ll have to take before you can fit any data that isn’t categorical or numerical that you get out of MindsDB into scikit-learn, then you're going to have to work to mix this information for what we call a mixer. The model for the mixer can be built with scikit-learn or it can be a neural network built on top of PyTorch or Tensorflow. When you choose to do it in scikit-learn, you also get to choose the specific scikit-learn model you want to use. As you’re going down that path, you can conduct a benchmark test that allows you to determine how the specific scikit-learn model you chose compares against a neural network over PyTorch, for example. Once you have this answer, you can go as far as building your own mixer combining those aspects. This is how we enable compatibility with scikit-learn since our goal is to make sure that the underlying tiers of MindsDB give you complete flexibility.
Jorge Torres is the Co-founder & CTO of MindsDB. He is also a visiting scholar at UC Berkeley researching machine learning automation and explainability. Prior to founding MindsDB, he worked for a number of data-intensive start-ups, most recently working with Aneesh Chopra (the first CTO in the US government) building data systems that analyze billions of patients records and lead to highest savings for millions of patients. He started his work on scaling solutions using machine learning in early 2008 while working as first full time engineer at Couchsurfing where he helped grow the company from a few thousand users to a few million. Jorge had degrees in electrical engineering & computer science, including a masters degree in computer systems (with a focus on applied Machine Learning) from the Australian National University.