Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.
bootstrap5
and dash-bootstrap-components
v1
(which is also based on bootstrap5), this
may break older custom dashboards that included bootstrap5 components from dash-bootstrap-components<1
3.6
and 3.7
as the latest version of scikit-learn
(1.1) dropped support as well
and explainerdashboard depends on the improved pipeline feature naming in scikit-learn>=1.1
max_idxs_in_dropdown
(defaults to 1000)..get_feature_names_out()
methodshap_kwargs
parameter to the explainers that allow you to pass additional kwargs to the shap values generating call, e.g. shap_kwargs=dict(check_addivity=False)
explainerfile_absolute_path
when dumping dashboard.yaml
with db.to_yaml(...)
dash
and jupyter-dash
hub.to_html()
and hub.save_html()
methodsto_zip()
methodexplainer.set_shap_values()
explainer.set_shap_interaction_values()
</div>
)Bumps dash requirement to 1.20 which introduced the new dcc.Download component used to download the static html from the dashboard.
dashboard.to_html()
.
to_html()
methods, see the documentation.save_html(filename)
method to all ExplainerComponents
and ExplainerDashboard
ExplainerHub
adds a new parameter index_to_base_route
:
Dispatches Hub to /base_route/index
instead of the default /
and /index
.
Useful when the host root is not reserved for the ExplainerHubdashboard.to_html()
.
to_html()
methods, see the documentation.save_html(filename)
method to all ExplainerComponents
and ExplainerDashboard
ExplainerHub
adds a new parameter index_to_base_route
:
Dispatches Hub to /base_route/index
instead of the default /
and /index
.
Useful when the host root is not reserved for the ExplainerHubPyTorch
Neural Networks! (as long as they are wrapped by skorch
)SimplifiedClassifierComposite
and SimplifiedRegressionComposite
to explainerdashboard.custom
simple=True
to load these simplified one page dashboards: ExplainerDashboard(explainer, simple=True)
ExtraTreesClassifier
and ExtraTreesRegressor
FeatureDescriptionsComponent
to explainerdashboard.custom
and the Importances tab/add_dashboard
route
with add_dashboard_route=True
(will only work if you're running the Hub as a single worker/node though!)ExplainerDashboard.to_yaml("dashboards/dashboard.yaml", dump_explainer=True)
will now dump the explainer in the correct subdirectory (and also default
to explainer.joblib)