leockl/sklearn-diagnose

🔍 AI-powered diagnosis for Scikit-learn models: Detect overfitting, data leakage, class imbalance & more with LLM-generated insights

52
/ 100
Established

This helps data scientists and machine learning engineers understand why their Scikit-learn models aren't performing as expected. You input your trained model and datasets, and it outputs a detailed report identifying common issues like overfitting, data leakage, or class imbalance, along with actionable recommendations. It acts as an 'MRI scan' to diagnose your model's health.

Available on PyPI.

Use this if you need clear, evidence-based insights into why your machine learning model is underperforming and want specific steps to improve it, without having to manually dig through metrics.

Not ideal if you are looking for a tool that automatically fixes or retrains your model, as this only provides diagnosis and recommendations.

machine-learning-debugging model-evaluation data-science-workflow predictive-modeling
Maintenance 10 / 25
Adoption 8 / 25
Maturity 22 / 25
Community 12 / 25

How are scores calculated?

Stars

52

Forks

6

Language

Python

License

MIT

Last pushed

Jan 30, 2026

Commits (30d)

0

Dependencies

14

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leockl/sklearn-diagnose"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.