Metadata-Version: 2.1
Name: alibi
Version: 0.2.1
Summary: Algorithms for monitoring and explaining machine learning models
Home-page: https://github.com/SeldonIO/alibi
Author: Seldon Technologies Ltd.
Author-email: hello@seldon.io
License: Apache 2.0
Description: <p align="center">
          <img src="doc/source/_static/Alibi_Logo.png" alt="Alibi Logo" width="50%">
        </p>
        
        [![Build Status](https://travis-ci.com/SeldonIO/alibi.svg?branch=master)](https://travis-ci.com/SeldonIO/alibi)
        [![Documentation Status](https://readthedocs.org/projects/alibi/badge/?version=v0.2.0)](https://docs.seldon.io/projects/alibi/en/v0.2.0/?badge=v0.2.0)
        ![Python version](https://img.shields.io/badge/python-3.5%20%7C%203.6%20%7C%203.7-blue.svg)
        [![PyPI version](https://badge.fury.io/py/alibi.svg)](https://badge.fury.io/py/alibi)
        ![GitHub Licence](https://img.shields.io/github/license/seldonio/alibi.svg)
        [![Slack channel](https://img.shields.io/badge/chat-on%20slack-e51670.svg)](http://seldondev.slack.com/messages/alibi)
        ---
        [Alibi](https://docs.seldon.io/projects/alibi) is an open source Python library aimed at machine learning model inspection and interpretation. The initial focus on the library is on black-box, instance based model explanations.
        
        *  [Documentation](https://docs.seldon.io/projects/alibi)
        
        ## Goals
        * Provide high quality reference implementations of black-box ML model explanation algorithms
        * Define a consistent API for interpretable ML methods
        * Support multiple use cases (e.g. tabular, text and image data classification, regression)
        * Implement the latest model explanation, concept drift, algorithmic bias detection and other ML
          model monitoring and interpretation methods
        
        ## Installation
        Alibi can be installed from [PyPI](https://pypi.org/project/alibi):
        ```bash
        pip install alibi
        ```
        This will install `alibi` with all its dependencies:
        ```bash
          beautifulsoup4
          numpy
          Pillow
          pandas
          requests
          scikit-learn
          spacy
          scikit-image
          tensorflow
        ```
        
        To run all the example notebooks, you may additionally run `pip install alibi[examples]` which will
        install the following:
        ```bash
          seaborn
          Keras
        ```
        
        ## Examples
        
        [**Anchor method applied to the InceptionV3 model trained on ImageNet:**](examples/anchor_image_imagenet.ipynb)
        
        Prediction: Persian Cat             | Anchor explanation
        :-------------------------:|:------------------:
        ![Persian Cat](doc/source/methods/persiancat.png)| ![Persian Cat Anchor](doc/source/methods/persiancatanchor.png)
        
        [**Contrastive Explanation method applied to a CNN trained on MNIST:**](examples/cem_mnist.ipynb)
        
        Prediction: 4             |  Pertinent Negative: 9               | Pertinent Positive: 4
        :-------------------------:|:-------------------:|:------------------:
        ![mnist_orig](doc/source/methods/mnist_orig.png)  | ![mnsit_pn](doc/source/methods/mnist_pn.png) | ![mnist_pp](doc/source/methods/mnist_pp.png)
        
        [**Trust scores applied to a softmax classifier trained on MNIST:**](examples/trustscore_mnist.ipynb)
        
        ![trust_mnist](doc/source/_static/trustscores.png)
        
        
Platform: UNKNOWN
Requires-Python: >3.5.1
Description-Content-Type: text/markdown
Provides-Extra: examples
