Trust score high level docs and exposing confidence in alibi (#53)

alibi/__init__.py

@@ -1,4 +1,4 @@
-from . import datasets, explainers, utils
+from . import confidence, datasets, explainers, utils
 from .version import __version__
 
-__all__ = ['datasets', 'explainers', 'utils']
+__all__ = ['confidence', 'datasets', 'explainers', 'utils']

doc/source/methods/Trust Scores.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "[source](../api/alibi.confidence.rst)"
+    "[[source]](../api/alibi.confidence.rst)"
    ]
   },
   {

doc/source/overview/algorithms.md

@@ -27,3 +27,14 @@ of the instance to keep the same prediciton). The PN instance identifies the fea
 minimally and necessarily absent to maintain the original prediction (a PN acts as the closest
 instance that would result in a different prediction). [Documentation](../methods/CEM.ipynb),
 [tabular example](../examples/cem_iris.ipynb), [image classification](../examples/cem_mnist.ipynb).
+
+
+## Model Confidence
+These algorihtms provide instance-specific scores measuring the model confidence for making a
+certain prediction.
+
+|Algorithm|Classification|Regression|Categorical features|Tabular|Text|Images|Needs training set|
+|---|---|---|---|---|
+|[Trust Scores](../methods/Trust\ Scores.ipynb)|✔|✘|✘|✔|✔[^1]|✔[^2]|Yes|
+[^1]: Depending on model
+[^2]: May require dimensionality reduction

doc/source/overview/getting_started.md

@@ -17,14 +17,25 @@ To get a list of the latest available model explanation algorithms, you can type
 import alibi
 alibi.explainers.__all__
 ```
-<div class="highlight"><pre>
+```
 ['AnchorTabular', 'AnchorText', 'AnchorImage', 'CEM'] 
-</pre></div>
+```
+
+For gauging model confidence:
+```python
+alibi.confidence.__all__
+```
+```
+['TrustScore']
+```
+
+
 
 For detailed information on the methods:
 *  [Overview of available methods](../overview/algorithms.md)
     * [Anchor explanations](../methods/Anchors.ipynb)
     * [Contrastive Explanation Method (CEM)](../methods/CEM.ipynb)
+    * [Trust Scores](../methods/Trust\ Scores.ipynb)
 
 ## Basic Usage
 We will use the [Anchor method on tabular data](../methods/Anchors.ipynb#Tabular-Data) to illustrate