Awesome

pyGAM

Generalized Additive Models in Python.

<img src=imgs/pygam_tensor.png>

Documentation

• Official pyGAM Documentation: Read the Docs
• Building interpretable models with Generalized additive models in Python

Installation

pip install pygam

scikit-sparse

To speed up optimization on large models with constraints, it helps to have scikit-sparse installed because it contains a slightly faster, sparse version of Cholesky factorization. The import from scikit-sparse references nose, so you'll need that too.

The easiest way is to use Conda:
conda install -c conda-forge scikit-sparse nose

scikit-sparse docs

Contributing - HELP REQUESTED

Contributions are most welcome!

You can help pyGAM in many ways including:

• Working on a known bug.
• Trying it out and reporting bugs or what was difficult.
• Helping improve the documentation.
• Writing new distributions, and link functions.
• If you need some ideas, please take a look at the issues.

To start:

• fork the project and cut a new branch
• Now install the testing dependencies

conda install cython
pip install --upgrade pip
pip install poetry
poetry install --with dev

Make some changes and write a test...

• Test your contribution (eg from the .../pyGAM): py.test -s
• When you are happy with your changes, make a pull request into the master branch of the main project.

About

Generalized Additive Models (GAMs) are smooth semi-parametric models of the form:

where X.T = [X_1, X_2, ..., X_p] are independent variables, y is the dependent variable, and g() is the link function that relates our predictor variables to the expected value of the dependent variable.

The feature functions f_i() are built using penalized B splines, which allow us to automatically model non-linear relationships without having to manually try out many different transformations on each variable.

<img src=imgs/pygam_basis.png>

GAMs extend generalized linear models by allowing non-linear functions of features while maintaining additivity. Since the model is additive, it is easy to examine the effect of each X_i on Y individually while holding all other predictors constant.

The result is a very flexible model, where it is easy to incorporate prior knowledge and control overfitting.

Citing pyGAM

Please consider citing pyGAM if it has helped you in your research or work:

Daniel Servén, & Charlie Brummitt. (2018, March 27). pyGAM: Generalized Additive Models in Python. Zenodo. DOI: 10.5281/zenodo.1208723

BibTex:

@misc{daniel\_serven\_2018_1208723,
  author       = {Daniel Servén and
                  Charlie Brummitt},
  title        = {pyGAM: Generalized Additive Models in Python},
  month        = mar,
  year         = 2018,
  doi          = {10.5281/zenodo.1208723},
  url          = {https://doi.org/10.5281/zenodo.1208723}
}

References

1. Simon N. Wood, 2006
   Generalized Additive Models: an introduction with R

2. Hastie, Tibshirani, Friedman
   The Elements of Statistical Learning
   http://statweb.stanford.edu/~tibs/ElemStatLearn/printings/ESLII_print10.pdf

3. James, Witten, Hastie and Tibshirani
   An Introduction to Statistical Learning
   http://www-bcf.usc.edu/~gareth/ISL/ISLR%20Sixth%20Printing.pdf

4. Paul Eilers & Brian Marx, 1996 Flexible Smoothing with B-splines and Penalties http://www.stat.washington.edu/courses/stat527/s13/readings/EilersMarx_StatSci_1996.pdf

5. Kim Larsen, 2015
   GAM: The Predictive Modeling Silver Bullet
   http://multithreaded.stitchfix.com/assets/files/gam.pdf

6. Deva Ramanan, 2008
   UCI Machine Learning: Notes on IRLS
   http://www.ics.uci.edu/~dramanan/teaching/ics273a_winter08/homework/irls_notes.pdf

7. Paul Eilers & Brian Marx, 2015
   International Biometric Society: A Crash Course on P-splines
   http://www.ibschannel2015.nl/project/userfiles/Crash_course_handout.pdf

8. Keiding, Niels, 1991
   Age-specific incidence and prevalence: a statistical perspective