mercury-explainability
mercury-explainability is a library with implementations of different state-of-the-art methods in the field of explainability. They are designed to work efficiently and to be easily integrated with the main Machine Learning frameworks.
Mercury project at BBVA
Mercury is a collaborative library that was developed by the Advanced Analytics community at BBVA. Originally, it was created as an InnerSource project but after some time, we decided to release certain parts of the project as Open Source.
That's the case with the mercury-explainability package.
The basic block of mercury-explainability is the Explainer class. Each one of the explainers in mercury-explainability offers a different method for explaining your models and often will return an Explanation type object containing the result of that particular explainer.
The usage of most of the explainers you will find in this library follows this schema:
from mercury.explainability import ExplainerExample
explainer = ExplainerExample(function_to_explain)
explanation = explainer.explain(dataset)
Basically, you simply need to instantiate your desired Explainer (note that the above example ExplainerExample does not exist)
providing your custom function you desire to get an explanation for, which usually will be your model’s inference or evaluation function.
These explainers are ready to work efficiently with most of the frameworks you will likely use as a data scientist (yes, included Spark).
If you're interested in learning more about the Mercury project, we recommend reading this blog post from www.bbvaaifactory.com
User installation
The easiest way to install mercury-explainability is using pip:
pip install mercury-explainability
Help and support
This library is currently maintained by a dedicated team of data scientists and machine learning engineers from BBVA.
Documentation
website: https://bbva.github.io/mercury-explainability/site/
1 maintainer
Metadata
1 maintainer
Release files for mercury-explainability 1.2.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mercury_explainability-1.2.3.tar.gz | 3.3 MB | Without provenance | Details for mercury_explainability-1.2.3.tar.gz |
Release files / mercury_explainability-1.2.3.tar.gz
| Download URL | mercury_explainability-1.2.3.tar.gz |
|---|---|
| Size | 3.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ad00070222265915f25c839891f6943b848dca76327aa56014e3ace87148bad4
|
|
BLAKE2b-256 checksum How to use checksums |
e840605d650222703b77db29a270c2b6bc00e9b42f32a8262c0811b06e7193f6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Security for mercury-explainability 1.2.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
