Metadata-Version: 2.1
Name: sliceguard
Version: 0.0.32
Summary: A library for detecting critical data slices in structured and unstructured data based on features, metadata and model predictions.
Author-email: Renumics GmbH <info@renumics.com>, Daniel Klitzke <daniel.klitzke@renumics.com>
Project-URL: Homepage, https://github.com/Renumics/sliceguard
Project-URL: Bug Tracker, https://github.com/Renumics/sliceguard/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: hnne >=0.1.10
Requires-Dist: numpy >=1.17.2
Requires-Dist: pandas >=2.0.0
Requires-Dist: fairlearn >=0.8.0
Requires-Dist: scikit-learn >=1.3.0
Requires-Dist: umap-learn >=0.5.3
Requires-Dist: tqdm >=4.65.0
Requires-Dist: renumics-spotlight >=1.5.3
Requires-Dist: datasets >=2.13.1
Requires-Dist: puremagic >=1.15
Provides-Extra: all
Requires-Dist: flaml >=2.0.0 ; extra == 'all'
Requires-Dist: xgboost <2.0.0,>=1.7.6 ; extra == 'all'
Requires-Dist: transformers[torch] >=4.30.2 ; extra == 'all'
Requires-Dist: sentence-transformers >=2.2.1 ; extra == 'all'
Requires-Dist: torchaudio >=2.0.2 ; extra == 'all'
Requires-Dist: datasets[audio,vision] >=2.13.1 ; extra == 'all'
Requires-Dist: bing-image-downloader ==1.1.2 ; extra == 'all'
Provides-Extra: automl
Requires-Dist: flaml >=2.0.0 ; extra == 'automl'
Requires-Dist: xgboost <2.0.0,>=1.7.6 ; extra == 'automl'
Provides-Extra: docs
Requires-Dist: sphinxcontrib-applehelp >=1.0.7 ; extra == 'docs'
Requires-Dist: sphinxcontrib-devhelp >=1.0.5 ; extra == 'docs'
Requires-Dist: sphinxcontrib-htmlhelp >=2.0.4 ; extra == 'docs'
Requires-Dist: sphinxcontrib-jsmath >=1.0.1 ; extra == 'docs'
Requires-Dist: sphinxcontrib-qthelp >=1.0.6 ; extra == 'docs'
Requires-Dist: sphinxcontrib-serializinghtml >=1.1.9 ; extra == 'docs'
Requires-Dist: myst-parser >=2.0.0 ; extra == 'docs'
Provides-Extra: embedding
Requires-Dist: transformers[torch] >=4.30.2 ; extra == 'embedding'
Requires-Dist: sentence-transformers >=2.2.1 ; extra == 'embedding'
Requires-Dist: torchaudio >=2.0.2 ; extra == 'embedding'
Requires-Dist: datasets[audio,vision] >=2.13.1 ; extra == 'embedding'
Provides-Extra: tutorials
Requires-Dist: bing-image-downloader ==1.1.2 ; extra == 'tutorials'

<p align="center"><a href="https://github.com/Renumics/sliceguard"><img src="https://github.com/Renumics/sliceguard/raw/main/static/img/sliceguard.svg" alt="Sliceguard Logo" height="80"/></a></p>
<h1 align="center">sliceguard</h1>
<p align="center">Detect problematic data slices in unstructured and structured data – fast.</p>

<p align="center">
 	<a href="https://pypi.org/project/sliceguard/"><img src="https://img.shields.io/pypi/pyversions/sliceguard" height="20"/></a>
 	<a href="https://pypi.org/project/sliceguard/"><img src="https://img.shields.io/pypi/wheel/sliceguard" height="20"/></a>
	<a href="https://sliceguard.readthedocs.io/en/latest/index.html"><img src="https://readthedocs.org/projects/sliceguard/badge/?version=latest&amp;style=flat" height="20"></a>
</p>

<p align="center"><img src="https://github.com/Renumics/sliceguard/raw/main/static/img/sliceguard_github.gif" width="100%"/><img src="https://github.com/Renumics/sliceguard/raw/main/static/img/dropshadow.png" width="100%"/></p>

## 🚀 Introduction

Sliceguard helps you to quickly discover **problematic data segments**. It supports structured data as well as unstructured data like images, text or audio. Sliceguard generates an **interactive report** with just a few lines of code:

```python
from sliceguard import SliceGuard

sg = SliceGuard()
issues = sg.find_issues(df, features=["image"])

sg.report()
```

## ⏱️ Quickstart

Install sliceguard by running `pip install sliceguard`.

Go straight to our quickstart examples for your use case:

* 🖼️ **[Unstructured Data (Images, Audio, Text)](https://github.com/Renumics/sliceguard/blob/main/examples/quickstart_unstructured_data.ipynb)** **–** **[🕹️ Interactive Demo](https://huggingface.co/spaces/renumics/sliceguard-unstructured-data)**
* 📈 **[Structured Data (Numerical, Categorical Variables)](https://github.com/Renumics/sliceguard/blob/main/examples/quickstart_structured_data.ipynb)** **–** **[🕹️ Interactive Demo](https://huggingface.co/spaces/renumics/sliceguard-structured-data)**
* 📊 **[Mixed Data (Contains Both)](https://github.com/Renumics/sliceguard/blob/main/examples/quickstart_mixed_data.ipynb)** **–** **[🕹️ Interactive Demo](https://huggingface.co/spaces/renumics/sliceguard-mixed-data)**

## 🗺️ Public Roadmap
We maintain a **[public roadmap](https://github.com/Renumics/sliceguard/blob/main/ROADMAP.md)** so you can follow along the development of this library.
