Deploying machine learning modules

If you are looking for an out of the box solution to deploy your model and get a REST endpoint/web app built for you on the fly, you can have a look at clouderizer. It provides you a clean GUI to drag n drop your packaged model file and deploy it on AWS/GCP/local machine. Here's a web app built for Heart failure prediction using clouderizer.

The simplest way I can think of is using streamlit as the framework to develop the app (which is based on Python scripts, really simple) which is very focused on displaying data, graphs and showing flexibility to play with several parameters values + Heroku as the deployment service provider, also via simple commands.

Correct me if I'm wrong here:

You've already written the code that test/trains the model and you're looking for a way to put that model on the web somewhere so users can interact with it?

There's a couple of way's you can go about that, but it depends on what you need out of the final product. Is this something clients will be using? Friends? Just you? Flask allows you to prototype quick web apps and still maintain a good amount of control over what the finished product looks like. Spyre is an amazing way to make a web app at near light speed, although it may not be suited well to your use case, depending on what you're doing. It's a little harder to make unique-looking things with Spyre, but I always suggest it to people.

At any rate, the standard thing to do here is to Pickle your model after it's trained and then load it to memory in a web app. After that you can call the model.predict(X) on an X that is sent to your program by a user.