Releases: interpretml/interpret-community
Releases · interpretml/interpret-community
release v0.14.3
SDK:
- hotfix for breaking change in latest version of dependency interpret-core perf_dict api
release v0.14.2
Visualization:
- Categorical cohort fix for explanation dashboard
SDK:
- String class labels fix with mimic explainer
- Add ipython as a dependency to visualization extra
- Fixed credentialed POST requests for predictions in dashboard (tested in notebook VM), and added support for remote VM with public IP
- Update reference to interpret-core to 0.2.1
Test:
- Fix for job retries in pipelines
release v0.14.1
SDK:
- improvements to docstrings/error messages around large datasets
Viz:
- added support for passing errors out of the dashboard for hosts to work with
Testing:
- improved notebook tests
- removed deprecated test pipelines
- added pypi release pipeline (trying it out for this release)
release v0.14.0
SDK
- MLflow
log_model
-based implementations oflog_explanation
andget_explanation
Dashboard
- update to categorical handling
- rework internals so hotkeys work better in Jupyter notebooks
Internal
- lots of updates to test pipelines
- README improvements
release v0.12.1
External:
- MLflow functions now accessible from
interpret_community.mlflow
rather thaninterpret_community.mlflow.mlflow
- Multiclass visualization available in the new dashboard
Internal:
- tracking URI in MLflow testing now configurable
- linting for TS visualization code
- websocket-extensions upgrades for security
- additional
explanation_method
information will be passed to the dashboard for display - pin keras dependency for testing
- added Janhavi as an author!
release v0.12.0
Visualization
- chart improvements
- support for regression in new dashboard
- tooltips for charts
- additional bugfixes
SDK
- rework of explanation serialization code in preparation for MLflow integration
- experimental MLflow log function added
release v0.11.2
- Cohort functionality added to the dashboard
- Improvement in PFI behavior when passing true_labels as a kwarg
- Improve type handling in the list sorting util
release v0.11.1
- add support for passing in a theme object to the dashboard
- fixes for the latest version of scikit-learn
- improve warning/error messaging in the dashboard
- optimize
get_ranked_per_class_names()
memory usage - improve PFI error messaging
- improvements to documentation
- workaround for XGBoost and TreeExplainer
release v0.11.0
- v2 version of the dashboard has been added!
- theme improvement for sphinx API documentation
- improvement for port handling within the dashboard
- improvement to scipy sparse import syntax
release v0.10.2
- Dashboard auto focus update
- Bugfix for sparse data on when using MimicExplainer with a linear surrogate for binary classification
- Set up port forwarding so that the dashboard can be shown in Azure environments
- Bugfix for true ys that aren't lists