TADkit: Time-series Anomaly Detection Kit with Interactivity and Tools

A toolkit integrating and wrapping all anomaly detection components with a possibility to: interact between the various components (preprocessing, engeering, modeling) interact with a visualization/annotation tool (e.g. Debiai) via an API intended for expert-in-the-loop iterations

Documentation

An online documentation is available here

Methodological Guidelines

• Methodological Guideline for Anomaly Detection Models
• Methodological Guideline for Time Series Anomaly Detection

Benchmarks

• Unsupervised Anomaly Detection and Explainability tools for Time Series

Applications over use-cases

• Anomaly Detection Models Use Case level document

Demonstrator

A restricted demonstrator is included, it covers synthetic data and times series data quality use cases.

Support

Support for TADkit must be obtained by sending an email to support@confiance.ai

Ensure your email contains :

• Your name
• A link to this page
• the version you are working with
• A clear description of the problematic (bug, crash, feature or help request)
• A full description of the problem whichallow to reproduce it
• Any file or screenshort element mandatory for the full understanding of the problematic

Available files

• tadkit.1.1.0.tar.gz : The installable python package of the library. You can install it directly in your python environnement by using the pip install tadkit-1.1.0.tar.gz command
• tadkit-1.1.0.zip : The source code of the library