Releases: scikit-learn-contrib/MAPIE
Releases · scikit-learn-contrib/MAPIE
Version 0.8.3
What's Changed
- Add fit parameters passing by @sami-ka in #391
- Fix: corrected some spelling errors by @isaiahthedev in #401
- Fix: corrected spelling throughout doc #402 by @isaiahthedev in #404
- Allow
MapieRegressor
to use K-fold iterator variants with stratification and groups. by @pidefrem in #393 - 410 mapiequantileregressor predict method causing memoryerror by @LacombeLouis in #412
- Added regression_MWI_score function by @Carl-McBride-Ellis in #408
- Update authors' email addresses by @LacombeLouis in #419
- Fix import order in Python files by @LacombeLouis in #420
- FIX: update history file by @LacombeLouis in #422
New Contributors
- @sami-ka made their first contribution in #391
- @isaiahthedev made their first contribution in #401
- @pidefrem made their first contribution in #393
- @Carl-McBride-Ellis made their first contribution in #408
Full Changelog: v0.8.2...v0.8.3
Bug fix for 0.8.0
What's Changed
- Fix issue with the pandas import by @thibaultcordier in #396
- Update mypy version to 1.7.1 by @LacombeLouis in #399
Full Changelog: v0.8.0...v0.8.2
Version 0.8.0
- Add Adaptative Conformal Inference (ACI) method for MapieTimeSeriesRegressor.
- Add Coverage Width-based Criterion (CWC) metric.
- Allow to use more split methods for MapieRegressor (ShuffleSplit, PredefinedSplit).
- Allow infinite prediction intervals to be produced in regressor classes.
- Integrate ConformityScore into MapieTimeSeriesRegressor.
- Add (extend) the optimal estimation strategy for the bounds of the prediction intervals for regression via ConformityScore.
- Add new checks for metrics calculations.
- Fix reference for residual normalised score in documentation.
Version 0.7.0
- Add prediction set estimation for binary classification.
- Add Learn-Then-Test method for multilabel-classification.
- Add documentation and notebooks for LTT.
- Add a new conformity score, ResidualNormalisedScore, that takes X into account and allows to compute adaptive intervals.
- Refactor MapieRegressor and ConformityScore to add the possibility to use X in ConformityScore.
- Separate the handling of the estimator from MapieRegressor into a new class called EnsembleEstimator.
- Add statistical calibration tests in binary classification.
- Rename methods (score to lac and cumulated_score to aps) in MapieClassifier.
- Add more notebooks and examples.
- Fix an unfixed random state in one of the classification tests.
- Fix and preserve the split behavior of the check_cv method with and without random state.
Version 0.6.5
- Add grouped conditional coverage metrics named SSC for regression and classification
- Add HSIC metric for regression
- Migrate conformity scores classes into conformity_scores module
- Migrate regression classes into regression module
- Add split conformal option for regression and classification
- Update check method for calibration
- Fix bug in MapieClassifier with different number of labels in calibration dataset.
Fix Runtime Warning with RAPS method
v0.6.4 Bump version: 0.6.3 → 0.6.4
Fix bug
Fix bug when labels are string or do not start at 0
Version 0.6.2
- Make MapieClassifier a scikit-learn object
- Update documentation for MapieClassifier
FIX issue #266 by taking into account very low scores in classification
v0.6.1 Bump version: 0.6.0 → 0.6.1
Version 0.6.0
- Add Risk-Controlling Prediction Sets (RCPS) and Conformal Risk Control (CRC)
- Add Top-Label Calibration
- Fix issues in CQR warning and cumulated scores in classification