Recent Releases of pcntoolkit
pcntoolkit - v1.0.1 alpha 5
Preserve order of response variables in NormData.merge
- Jupyter Notebook
Published by AuguB 8 months ago
pcntoolkit - v1.0.1 alpha4
HBR model comparison Much faster Yhat estimation for BLR BLR transfer
- Jupyter Notebook
Published by AuguB 8 months ago
pcntoolkit - v1.0.1 alpha 2
Improve BLR Full Changelog: https://github.com/amarquand/PCNtoolkit/compare/v1.0.1-alpha...v1.0.1-alpha2
- Jupyter Notebook
Published by AuguB 8 months ago
pcntoolkit -
Some important changes, mostly affecting BLR - remove numpy version pin - add linear component to bspline basis function - change default parameters for niter and tolerance in BLR - move computation of lambda nvec to after reparameterization of beta - add skeleton for fixedeffectslope
- Jupyter Notebook
Published by AuguB 9 months ago
pcntoolkit - PCNtoolkit version 1.0.0
Major code refactor (effectively a re-write of the toolbox). Key changes include:
- Improved object-orientation
- Improved code readability
- Improved in-line documentation
- Human readable models (JSON format)
- Improved extendability
- Algorithmic improvements, e.g. merge, extend, transfer, harmonise, synthesize and improvments to HBR
- Completely revised documentation
- No longer supports Gaussian process regression
- Updated cluster job submission system
IMPORTANT: Models estimated on earlier versions of PCNtoolkit (up until v0.39) are NOT COMPATIBLE with this release. Please install the old version to continue working with legacy models
- Jupyter Notebook
Published by amarquand 9 months ago
pcntoolkit - PCNtoolkit version 1.0.1
Major code refactor (effectively a re-write of the toolbox). Key changes include:
- Improved object-orientation
- Improved code readability
- Improved in-line documentation
- Human readable models (JSON format)
- Improved extendability
- Algorithmic improvements, e.g. merge, extend, transfer, harmonise, synthesize and improvments to HBR
- Completely revised documentation
- No longer supports Gaussian process regression
- Updated cluster job submission system
IMPORTANT:
- Models estimated on earlier versions of PCNtoolkit (up until v0.39) are NOT COMPATIBLE with this release. Please install the old version to continue working with legacy models
- Jupyter Notebook
Published by amarquand 9 months ago
pcntoolkit - PCNtoolkit version 1.0.0
Major code refactor (effectively a re-write of the toolbox). Key changes include:
- Improved object-orientation
- Improved code readability
- Improved in-line documentation
- Human readable models (JSON format)
- Improved extendability
- Algorithmic improvements, e.g. merge, extend, transfer, harmonise, synthesize and improvments to HBR
- Completely revised documentation
- No longer supports Gaussian process regression
- Updated cluster job submission system
IMPORTANT:
- Models estimated on earlier versions of PCNtoolkit (up until v0.39) are NOT COMPATIBLE with this release. Please install the old version to continue working with legacy models
- Jupyter Notebook
Published by amarquand 9 months ago
pcntoolkit - v1 alpha 17
V1 alpha 17
Fix bug in evaluator
- Jupyter Notebook
Published by AuguB 9 months ago
pcntoolkit - v1 alpha 16
V1 alpha 16 Added version number to save files Add explained variance to evaluator Warning banner Small improvements to BLR, both mean and variance now have intercept column in the design matrix by defaults
Full Changelog: https://github.com/amarquand/PCNtoolkit/compare/v1.alpha.15...v1.alpha.16
- Jupyter Notebook
Published by AuguB 9 months ago
pcntoolkit - v1 Alpha 15
Correct computation of Yhat (although very slow for BLR) Complete example documentation Fix bugs in Beta distribution More small improvements
Full Changelog: https://github.com/amarquand/PCNtoolkit/compare/v1.alpha.14...v1.alpha.15
- Jupyter Notebook
Published by AuguB 9 months ago
pcntoolkit - V1 alpha 14
Attempt to solve bug with parallel transfer_predict
- Jupyter Notebook
Published by AuguB 10 months ago
pcntoolkit - v1.alpha.13
- Added beta likelihood to HBR
- Improved plotter
- More tests
- More documentation
Full Changelog: https://github.com/amarquand/PCNtoolkit/compare/v1.alpha.12...v1.alpha.13
- Jupyter Notebook
Published by AuguB 10 months ago
pcntoolkit - v1 Alpha 12
Attempt to fix bug in installation
- Jupyter Notebook
Published by AuguB 10 months ago
pcntoolkit - v1 Alpha 11
What's Changed
- Small improvement in the plot_centiles function
- Bump jinja2 from 3.1.4 to 3.1.5 by @dependabot in https://github.com/amarquand/PCNtoolkit/pull/232
New Contributors
- @dependabot made their first contribution in https://github.com/amarquand/PCNtoolkit/pull/232
Full Changelog: https://github.com/amarquand/PCNtoolkit/compare/v0.35...v1.alpha.11
- Jupyter Notebook
Published by AuguB 10 months ago
pcntoolkit - v1 Alpha 10
Transfer now also loops over respvar_intersection
- Jupyter Notebook
Published by AuguB 10 months ago
pcntoolkit - V1 alpha 9
Version 1.0.a9
Working on a better test suite Some small bug fixes
- Jupyter Notebook
Published by AuguB 10 months ago
pcntoolkit - v1 Alpha 8
Added normdata.load_results. Also moved all the save_zscores, save_centiles etc to the normdata class.
Fixed a bug where the plotter tries to sample more points than available batch effects. Now not using model.synthesize there.
To install:
1. download and unzip the source files.
2. Move into the unzipped folder.
3. activate the correct conda environment.
5. run python -m pip install . in the unzipped folder.
- Jupyter Notebook
Published by AuguB 11 months ago
pcntoolkit - v1 alpha 6
Small optimizations for the workshop
- Jupyter Notebook
Published by AuguB 11 months ago
pcntoolkit -
Alpha version 4.
Now with working example notebooks!
- Jupyter Notebook
Published by AuguB 11 months ago
pcntoolkit - v1 Alpha 3
Some small bug fixes Update example notebook
- Jupyter Notebook
Published by AuguB 11 months ago
pcntoolkit - PCNtoolkit version 0.35
- several bugfixes (mostly relating to normative_parallel and HBR fit/predict)
- replaced kwargs pop() with get()
- added slurm partition keyword argument
- Jupyter Notebook
Published by amarquand 12 months ago
pcntoolkit - PCNtoolkit version 0.34
Some bug fixes, including:
- fixed deprecation error related to nibabel
- some bug fixes for HBR
- Changes to support slurm job submission via PCNportal
- Jupyter Notebook
Published by amarquand about 1 year ago
pcntoolkit - v1.alpha.1
Improved after questions and comments.
- Got rid of the XXXconf objects in favor of classes integrating configuration and logic.
- The core class is a single NormativeModel class with a collection of RegressionModels
- RegressionModels have three core functions; fit, forward, and backward. Most functions of the NormativeModel (like predict, extend, zscores, centiles, harmonize) are defined in terms of forward and backward.
- More and better testing, now at 65%. A lot of what's not covered is cluster stuff.
- Added WarpCompose for BLR
- HBR now uses per-parameter basis expansions; we can have a bspline for mu and a linear basis for sigma.
- Nicer plots
- Better documentation
- A clear tutorial
- Jupyter Notebook
Published by AuguB about 1 year ago
pcntoolkit - v1.alpha
Alpha release of the dev_refactor branch.
What's Changed
- Everything
- Jupyter Notebook
Published by AuguB about 1 year ago
pcntoolkit - PCNtoolkit version 0.33
- more bugfixes relating to normative_parallel or transfer (mostly quite minor)
- Jupyter Notebook
Published by amarquand about 1 year ago
pcntoolkit - PCNtoolkit version 0.32
Updated BSpline implementation Bugfixes for HBR (merge + extend)
- Jupyter Notebook
Published by amarquand about 1 year ago
pcntoolkit - 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 'ncoresperbatch' Backwards compatibilty improved by using pd.readpickle instead of pickle.load SHASH classes have been refactored and improved HBR priors improved
What's Changed
- Dev by @amarquand in https://github.com/amarquand/PCNtoolkit/pull/210
- adjusted setup.py by @amarquand in https://github.com/amarquand/PCNtoolkit/pull/211
- Dev by @amarquand in https://github.com/amarquand/PCNtoolkit/pull/212
- Runs the testHBR script correctly on pymc==5.16 by @amarquand in https://github.com/amarquand/PCNtoolkit/pull/214
- fix anomalydetectionauc print by @matei4501 in https://github.com/amarquand/PCNtoolkit/pull/217
- Address multiple issues by @AuguB in https://github.com/amarquand/PCNtoolkit/pull/219
New Contributors
- @matei4501 made their first contribution in https://github.com/amarquand/PCNtoolkit/pull/217
Full Changelog: https://github.com/amarquand/PCNtoolkit/compare/v0.30...v0.31
- Jupyter Notebook
Published by AuguB over 1 year ago
pcntoolkit - PCNtoolkit version 0.30
Minor release over 0.29
- Added functionality for plotting centiles in HBR
- Added support for SLURM (via normative_parallel)
- Jupyter Notebook
Published by amarquand almost 2 years ago
pcntoolkit - 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
- Jupyter Notebook
Published by amarquand over 2 years ago
pcntoolkit - 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)
- Jupyter Notebook
Published by amarquand almost 3 years ago
pcntoolkit - 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
- Jupyter Notebook
Published by amarquand about 3 years ago
pcntoolkit - 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
- Jupyter Notebook
Published by amarquand about 3 years ago
pcntoolkit - 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)
- Jupyter Notebook
Published by amarquand over 3 years ago
pcntoolkit - PCNtoolkit version 0.24
Only minor changes (functionally virtually equivalent to version 0.23) - Minor bug fix related to SHASH/HBR - Added change log
- Jupyter Notebook
Published by amarquand almost 4 years ago
pcntoolkit - PCNtoolkit version 0.23
Changes:
- SHASH functionality for HBR added
- Bug fix for normative model predict() function
- Jupyter Notebook
Published by amarquand almost 4 years ago
pcntoolkit - 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
- Jupyter Notebook
Published by amarquand about 4 years ago
pcntoolkit - PCNtoolkit version 0.21
Relatively minor updates with respect to version 0.20, including:
- documentation updates
- minor updates to warp (including bug fix for the compostition)
- software version is saved in models
- utility functions for calibration descriptives and extreme values
- Jupyter Notebook
Published by amarquand over 4 years ago
pcntoolkit - PCNtoolkit version 0.20
Changes: - Major code refactoring - Requirements updated for python 3.8.3 - Updates to documentation and Integrations with Read the Docs - Addition of tutorial material - Performance improvements for BLR (not compatible with previous versions) - Addition of heteroskedastic noise for BLR - Addition of Bayesian Information Criterion for BLR - Addition of utility functions (e.g. design matrix construction) - Several minor bug fixes (mostly related to HBR and BLR)
- Jupyter Notebook
Published by amarquand over 4 years ago
pcntoolkit - PCNtoolkit version 0.19
Changes: - separate standardization of responses and covariates - standardization is no longer on by default - new standardization methods - pymc3 version fixed - minor bugs resolved (CV with HBR)
- Jupyter Notebook
Published by amarquand almost 5 years ago
pcntoolkit - PCNtoolkit version 0.18
Changes: - addition of cross-validation functionality for HBR - minor bug fixes for HBR
- Jupyter Notebook
Published by amarquand about 5 years ago
pcntoolkit - v0.17
PCNtoolkit version 0.17: Changes: - New syntax for functions related to parallelization (python path is automatically generated) - Support for slurm clusters has been added - Updates to hierarchical Bayesian regression (different priors for intercepts and noise) for improved transfer - Updated parameterisation for likelihood warping for improved stability - Now uses a fixed pickle protocol for better interoperability - Addition of a utility function for loading freesurfer measures - Updated sphinx documentation
- Jupyter Notebook
Published by amarquand about 5 years ago
pcntoolkit - v0.16
Minor bug fix relative to release 0.15. Fixed a transpose operation that would cause normative.py to fail in certain cases
- Jupyter Notebook
Published by amarquand over 5 years ago
pcntoolkit - v0.15
A number of new functions have been implemented and we decided to use a new version numbering system. This is version v0.15, the currently newest version. In future, we will increment this version numbering.
- Jupyter Notebook
Published by thomaswolfers over 5 years ago