PCNToolkit version 0.31

version 0.31.0

Major changes:
Move to Poetry for dependency management in pyproject.toml.
PCNToolkit must now be installed using python -m pip install .. See the README for complete instructions.
A CLI command normative is automatically created, and can be used instead of python normative.py.
Nutpie can be used as a sampler for HBR by setting `nuts_sampler='nutpie''. Nutpie and numba must first be installed using conda.

Minor changes
torque jobs now support multicore jobs via the keyword 'n_cores_per_batch'
Backwards compatibilty improved by using pd.read_pickle instead of pickle.load
SHASH classes have been refactored and improved
HBR priors improved

What's Changed

• Dev by @amarquand in #210
• adjusted setup.py by @amarquand in #211
• Dev by @amarquand in #212
• Runs the testHBR script correctly on pymc==5.16 by @amarquand in #214
• fix anomaly_detection_auc print by @matei4501 in #217
• Address multiple issues by @AuguB in #219

New Contributors

• @matei4501 made their first contribution in #217

Full Changelog: v0.30...v0.31

PCNtoolkit version 0.30

Minor release over 0.29

• Added functionality for plotting centiles in HBR
• Added support for SLURM (via normative_parallel)

PCNtoolkit version 0.29

• Bug fixes (e.g. HBR predict crash, normative_paralell support for .txt input)
• Added docstrings for most functions
• Fixed some problems with exception handling
• Formatted whole project with autopep8
• Addedd functionality to compute SHASH z-scores from normative.py
• Updated requirements
• Basic pytest continuous integration framework implemented

PCNtoolkit version 0.28

• Updated to PyMC5 (including migrating back-end to PyTensor)
• Added support for longitudinal normative modelling with BLR (see Buckova-Rehak et al 2023)
• Changed default optimiser for trend surface models (for scalability)

PCNtoolkit version 0.27

• Configured more sensible default options for HBR (random slope and intercept for mu and random intercept for sigma)
• Fixed a translation problem between the previous naming convention for HBR models (only Gaussian models) and the current naming (also SHASH models)
• Minor updates to fix synchronisation problems in PCNportal (related to the HBR updates above)
• Added configuration files for containerisation with Docker

PCNtoolkit version 0.26

• Multiple bug fixes, relating to imports, predict() and transfer() functions
• Added support for web portal
• Provided a wrapper for blr to use transfer() functionality
• Also streamlined tutorials (PCNtoolkit-demo), so that all tutorials run with this version

PCNtoolkit version 0.25

• Minor bug fixes related to imports
• Minor bug fixes related to SHASH/HBR
• Minor bug fix in normative.py (affecting SMSE)

PCNtoolkit version 0.24

Only minor changes (functionally virtually equivalent to version 0.23)

• Minor bug fix related to SHASH/HBR
• Added change log

PCNtoolkit version 0.23

Changes:

• SHASH functionality for HBR added
• Bug fix for normative model predict() function

PCNtoolkit version 0.22

Some minor updates and bug fixes:

• updates to documentation and tutorials
• updates to normative_parallel (interactive usage)
• updates to HBR (merge functionality)
• other minor bug fixes related to cross-validation (computation of error metrics), import problems and calibration statistics