Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
hwm v1.1.4
Released on 2024-04-27
Enhancements
Support for Probability Predictions in
twa_score
MetricThe :func:
hwm.metrics.twa_score
metric in :mod:hwm.metrics
has been enhanced tohandle probability predictions. This allows users to pass either class labels
or probability distributions as predictions, providing greater flexibility
in evaluating classification models.
Example:
.. code-block:: python
Batch Computation in
HammersteinWienerRegressor
The
HammersteinWienerRegressor
inhwm.estimators
has been optimized to handle largerdatasets by implementing batch computation. This improvement resolves memory errors
encountered in version 1.0.1 and enhances the model's scalability and performance when
working with extensive data.
Example:
.. code-block:: python
Enhancements
Renamed Classes for Improved Usability
The class names :class:
hwm.estimators.HammersteinWienerRegressor
and:class:
hwm.estimators.HammersteinWienerClassifier
have been renamed to:class:
hwm.estimators.HWRegressor
and :class:hwm.estimators.HWClassifier
respectively for brevity and ease of use.
Deprecation Notice:
HammersteinWienerRegressor
andHammersteinWienerClassifier
are now deprecated and willbe removed in version 1.1.3. Users are encouraged to
transition to the new class names to ensure future compatibility.
Example:
.. code-block:: python
Using Deprecated Class Names:
.. code-block:: python
Bug Fixes
**Resolved Memory Errors in :class:
hwm.estimators.HWRegressor
**Addressed memory consumption issues in the
HWRegressor
when processinglarge datasets by introducing batch processing mechanisms. This fix ensures stable and
efficient model training and prediction without exhausting system memory.
Documentation Updates
hwm/doc/source/
to reflect the new capabilities ofthe
twa_score
metric, including handling of probability predictions. Users canrefer to the :ref:
updated metrics <metrics>
module documentation for detailed usageinstructions and examples.
Upgrade Notes
accommodate the new batch processing parameters in :class:
hwm.estimators.HWRegressor
.hwm.metrics.twa_score
function now accepts both label arrays andprobability arrays. Ensure that the input
format aligns with the desired usage.
Known Issues
or feature requests.
Contributors
code to make this release possible.