Learn how to use Feyn and the QLattice
Feyn is a Python module built on top of the QLattice for supervised machine learning using symbolic regression.
Whether you're an absolute beginner or a seasoned veteran, this is the place to be for links and resources to learn more about how to use Feyn in practice.
Just starting out?
Here's a few good places to start exploring
Regression and classification
Get the details about Auto Run
Learn how Feyn handles categoricals
Learn how to use Feyn with the Titanic Dataset
Learn how to use Feyn with the Concrete Strength Dataset
Explainability
Learn about features that go into explainability
Learn about interpreting your models with the response plot
A simple regression case using the 1D response plot with quantiles to understand the model
Picking out multicollinearity with the QLattice
Hypothesis generation
Here's some cases that go into working with multiple hypotheses
How to use the query language to sample specific models
Substituting inputs in a model with correlated alternatives
A life science case that demonstrates expanding and constraining model complexity to understand relationships better
Custom Workflows
Did you know that training in Feyn is composed of primitive operations? Here's some examples of how to use them to customise your workflow
Build your own workflow with the primitive operations
Use the primitives to customise the plots during training
Predict the alcohol levels of wine using the primitive operations
Using Feyn in production
Here's some ideas on what to do after you've gotten a model you're happy with
How to save and load fitted models
Converting a model to a mathematical expression
