alibi

Open source

Algorithms for explaining machine learning models

2.6K stars0 likes1 views

About

Algorithms for explaining machine learning models

Alibi is a source-available Python library aimed at machine learning model inspection and interpretation. The focus of the library is to provide high-quality implementations of black-box, white-box, local and global explanation methods for classification and regression models.

Documentation

If you're interested in outlier detection, concept drift or adversarial instance detection, check out our sister project alibi-detect.

Anchor explanations for images

    </a>
</td>
<td width="50%">
    <a href="https://docs.seldon.io/projects/alibi/en/stable/examples/integrated_gradients_imdb.html">
        <br>
        <b>Integrated Gradients for text</b>
        <br>
        <br>
        
    </a>
</td>

Counterfactual examples

    </a>
</td>
<td width="50%">
    <a href="https://docs.seldon.io/projects/alibi/en/stable/methods/ALE.html">
        <br>
        <b>Accumulated Local Effects</b>
        <br>
        <br>
        
    </a>
</td>

Installation and Usage
Supported Methods
Citations

Installation and Usage

Alibi can be installed from:

PyPI or GitHub source (with pip)
Anaconda (with conda/mamba)

With pip

Alibi can be installed from PyPI:
bash
```
pip install alibi
```
Alternatively, the development version can be installed:
bash
```
pip install git+https://github.com/SeldonIO/alibi.git 
```
To take advantage of distributed computation of explanations, install alibi with ray:
bash
```
pip install alibi[ray]
```
For SHAP support, install alibi as follows:
bash
```
pip install alibi[shap]
```

With conda

To install from conda-forge it is recommended to use mamba, which can be installed to the base conda enviroment with:

bash

conda install mamba -n base -c conda-forge

For the standard Alibi install:
bash
```
mamba install -c conda-forge alibi
```
For distributed computing support:
bash
```
mamba install -c conda-forge alibi ray
```
For SHAP support:
bash
```
mamba install -c conda-forge alibi shap
```

Usage

The alibi explanation API takes inspiration from scikit-learn, consisting of distinct initialize, fit and explain steps. We will use the AnchorTabular explainer to illustrate the API:

python

from alibi.explainers import AnchorTabular

# initialize and fit explainer by passing a prediction function and any other required arguments
explainer = AnchorTabular(predict_fn, feature_names=feature_names, category_map=category_map)
explainer.fit(X_train)

# explain an instance
explanation = explainer.explain(x)

The explanation returned is an Explanation object with attributes meta and data. meta is a dictionary containing the explainer metadata and any hyperparameters and data is a dictionary containing everything related to the computed explanation. For example, for the Anchor algorithm the explanation can be accessed via explanation.data['anchor'] (or explanation.anchor). The exact details of available fields varies from method to method so we encourage the reader to become familiar with the types of methods supported.

Supported Methods

The following tables summarize the possible use cases for each method.

Model Explanations

Method	Models	Explanations	Classification	Regression	Tabular	Text	Images	Categorical features	Train set required	Distributed
ALE	BB	global	✔	✔	✔
Partial Dependence	BB WB	global	✔	✔	✔			✔
PD Variance	BB WB	global	✔	✔	✔			✔
Permutation Importance	BB	global	✔	✔	✔			✔
Anchors	BB	local	✔		✔	✔	✔	✔	For Tabular
CEM	BB* TF/Keras	local	✔		✔		✔		Optional
Counterfactuals	BB* TF/Keras	local	✔		✔		✔		No
Prototype Counterfactuals	BB* TF/Keras	local	✔		✔		✔	✔	Optional
Counterfactuals with RL	BB	local	✔		✔		✔	✔	✔
Integrated Gradients	TF/Keras	local	✔	✔	✔	✔	✔	✔	Optional
Kernel SHAP	BB	local global	✔	✔	✔			✔	✔	✔
Tree SHAP	WB	local global	✔	✔	✔			✔	Optional
Similarity explanations	WB	local	✔	✔	✔	✔	✔	✔	✔

Model Confidence

These algorithms provide instance-specific scores measuring the model confidence for making a particular prediction.

Method	Models	Classification	Regression	Tabular	Text	Images	Categorical Features	Train set required
Trust Scores	BB	✔		✔	✔(1)	✔(2)		Yes
Linearity Measure	BB	✔	✔	✔		✔		Optional

Key:

BB - black-box (only require a prediction function)
BB* - black-box but assume model is differentiable
WB - requires white-box model access. There may be limitations on models supported
TF/Keras - TensorFlow models via the Keras API
Local - instance specific explanation, why was this prediction made?
Global - explains the model with respect to a set of instances
(1) - depending on model
(2) - may require dimensionality reduction