dswah/pyGAM

Health v2 · maintenance only

Adoption not part of the score

1021 stars · 295 forks observed · 2026-10-12

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

pyGAM is a Python library for building Generalized Additive Models (GAMs) with an emphasis on modularity and performance. Its API is designed to feel familiar to users of scikit-learn and scipy.

Use cases

• fit interpretable generalized additive models in python
• model nonlinear relationships with smooth terms
• build regression models with partial dependence per feature
• replace black-box models with explainable ml
• fit logistic gam for classification
• smooth time series or spatial data with splines

When to choose

• you need interpretable models where each feature's effect can be visualized
• you want scikit-learn-style fit/predict API for GAMs
• you need flexible link functions and distributions like Poisson or binomial
• you want automatic smoothing parameter selection

When to avoid

• you need deep learning or GPU-accelerated training
• you need tree ensembles like XGBoost for maximum predictive accuracy
• you work outside Python
• you need massive-scale distributed training

Facets

library · maturity active

machine-learning data-science math machine-learning data-science python generalized-additive-models gams interpretable-ml explainable-ai scikit-learn-compatible regression statistics

Member repositories

For agents

markdown · JSON · MCP: product_card(name="dswah/pyGAM")