You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Examples deployed at: [Fly.io](https://titanicexplainer.fly.dev), [Hugging Face Space](https://huggingface.co/spaces/oegedijk/explainingtitanic),
28
28
detailed documentation at [explainerdashboard.readthedocs.io](http://explainerdashboard.readthedocs.io),
29
29
example notebook on how to launch dashboard for different models [here](notebooks/dashboard_examples.ipynb), and an example notebook on how to interact with the explainer object [here](notebooks/explainer_examples.ipynb).
30
30
@@ -87,7 +87,7 @@ Auto-detection uses the presence of `/opt/ml/metadata/resource-metadata.json`.
(for live demonstration see [titanicexplainer.herokuapp.com](http://titanicexplainer.herokuapp.com))
90
+
(for live demonstration see [Fly.io](https://titanicexplainer.fly.dev) or [Hugging Face Space](https://huggingface.co/spaces/oegedijk/explainingtitanic))
91
91
## Background
92
92
93
93
In a lot of organizations, especially governmental, but with the GDPR also increasingly in private sector, it is becoming more and more important to be able to explain the inner workings of your machine learning algorithms. Customers have to some extent a right to an explanation why they received a certain prediction, and more and more internal and external regulators require it. With recent innovations in explainable AI (e.g. SHAP values) the old black box trope is no longer valid, but it can still take quite a bit of data wrangling and plot manipulation to get the explanations out of a model. This library aims to make this easy.
@@ -533,7 +533,7 @@ own model, project and needs. You can use the [ExplainerComposites](https://gith
533
533
are used for the tabs of the default dashboard as a starting point, and edit
534
534
them to reorganize components, add text, etc.
535
535
See [custom dashboard documentation](https://explainerdashboard.readthedocs.io/en/latest/custom.html)
536
-
for more details. A deployed custom dashboard can be found [here](http://titanicexplainer.herokuapp.com/custom/)([source code](https://github.com/oegedijk/explainingtitanic/blob/master/buildcustom.py)).
536
+
for more details. A deployed custom dashboard can be found on [Fly.io](https://titanicexplainer.fly.dev/custom/)([source code](https://github.com/oegedijk/explainingtitanic/blob/master/buildcustom.py)).
537
537
538
538
## Deployment
539
539
@@ -543,6 +543,10 @@ start the server with e.g. `gunicorn dashboard:app`
543
543
(assuming the file you defined the dashboard in was called `dashboard.py`).
544
544
See also the [ExplainerDashboard section](https://explainerdashboard.readthedocs.io/en/latest/dashboards.html)
545
545
and the [deployment section of the documentation](https://explainerdashboard.readthedocs.io/en/latest/deployment.html).
546
+
For platform-specific guides, see:
547
+
[Deploying to Fly.io](https://explainerdashboard.readthedocs.io/en/latest/deployment.html#deploying-to-fly-io)
548
+
and
549
+
[Deploying to Hugging Face Spaces](https://explainerdashboard.readthedocs.io/en/latest/deployment.html#deploying-to-hugging-face-spaces).
546
550
547
551
It can be helpful to store your `explainer` and dashboard layout to disk, and
548
552
then reload, e.g.:
@@ -647,7 +651,7 @@ Example notebook on how to design a custom dashboard: [custom_examples.ipynb](no
647
651
648
652
## Deployed example:
649
653
650
-
You can find an example dashboard at [titanicexplainer.herokuapp.com](http://titanicexplainer.herokuapp.com)
654
+
You can find example dashboards at [Fly.io](https://titanicexplainer.fly.dev) and [Hugging Face Space](https://huggingface.co/spaces/oegedijk/explainingtitanic)
651
655
652
656
(source code at [https://github.com/oegedijk/explainingtitanic](https://github.com/oegedijk/explainingtitanic))
0 commit comments