Welcome to genestboost’s documentation!

genestboost is an ML boosting library that separates the modeling algorithm from the boosting algorithm. The result is that you can boost any generic regression model, not just trees. Build a forward-thinking (forward-propagating) neural network if you wish, or build an ensemble of support vector machines if you would so desire. Mix and match link and loss functions at will.

Contents:

• Introduction
  • How it works
  • Limitations
• Quick Coding Example
• Additional Examples
  • Quantile Regression with Different Algorithms
  • Binary Target Boosting with Custom Model Callback Wrapper
  • BoostedLinearModel with SimplePLS Algorithm Example
  • Alternative Fitting Procedure with Surrogate Loss Function
  • Forward-Propagating Neural Network Example
• Custom Link Functions
• Custom Loss Functions
• Model Callbacks
• Weak Learners
• genestboost
  • genestboost package
• Installation
• Changelog
  • 0.3.1
  • 0.3.0
  • 0.2.0-beta
  • 0.1.1-beta
  • 0.1.0-beta
• GitHub Repo

Indices and tables

• Index

• Module Index

• Search Page