EuroPOND/pySuStaIn

Python translation of the Subtype and Stage Inference (SuStaIn) model, including an example using simulated data.

pySuStaIn

SuStaIn algorithm in Python, with the option to describe the subtype progression patterns using either the event-based model or the piecewise linear z-score model.

Papers

• The SuStaIn algorithm: Young et al. 2018
• The event-based model: Fonteijn et al. 2012, (with Gaussian mixture modelling Young et al. 2014)
• The piecewise linear z-score model: Young et al. 2018

Dependencies

• Python >= 3.5
• NumPy >= 1.18
• SciPy
• Matplotlib
• Scikit-learn for cross-validation
• kde_ebm for mixture modelling (KDE and GMM included)
• pathos for parallelization

Parallelisation

• Added parallelized startpoints

Running different SuStaIn implementations

sustainType can be set to:

• "mixture_GMM" : SuStaIn with an event-based model progression pattern, with Gaussian mixture modelling of normal/abnormal.
• "mixture_KDE": SuStaIn with an event-based model progression pattern, with Kernel Density Estimation (KDE) mixture modelling of normal/abnormal.
• "zscore": SuStaIn with a piecewise linear z-score model progression pattern.

See simrun.py for examples of how to run these different implementations.

SuStaIn Tutorial

See the jupyter notebook for a tutorial on how to use SuStaIn using simulated data.