Super easy automated machine learning in Python. Fast enough to run at production speeds. I'm the author, and would love any feedback you have! The whole point of the project is to make ML available to people like you who just like building things, and think their thing could be better with a bit of ML.
My dad keeps asking me how I plan on making money from this project, given the amount of effort I've poured into it. He grew even more confused once I told him that a company called DataRobot raised over a hundred million dollars to build essentially the same product.
But it just brings me joy to make ML available to everyone.
If you have any feedback, please let me know! I'd love to know how I can make automl better for you.
A couple notes on backwards compatibility I ran into yesterday when upgrading auto_ml to use the latest:
Keras now throws errors when trying to use some of the metrics they've deprecated. If you run into `UnboundLocalError: local variable 'class_name' referenced before assignment`, check that all your metrics are supported.
Keras also now ignores `nb_epoch` in favor of `epochs`. I must have misread the blog post, because I thought it would support `nb_epoch` for a bit and just use that in place of `epochs`.
Super easy automated machine learning in Python. Fast enough to run at production speeds. I'm the author, and would love any feedback you have! The whole point of the project is to make ML available to people like you who just like building things, and think their thing could be better with a bit of ML.