awsm-research/PyExplainer
PyExplainer: A Local Rule-Based Model-Agnostic Technique (Explainable AI)
When developing software, PyExplainer helps you understand why a machine learning model predicted a specific code commit as 'defective' right when it happens. It takes your existing 'Just-In-Time' defect prediction model and a particular code commit as input, then outputs clear, rule-based explanations for that prediction. This is valuable for software engineers and quality assurance teams who need to quickly identify and fix potential issues in their code.
No commits in the last 6 months. Available on PyPI.
Use this if you are a software engineer or QA professional needing to understand the specific reasons behind a defect prediction for a particular code commit, rather than just knowing it's defective.
Not ideal if you are looking for a general defect prediction model, as this tool focuses on explaining the predictions of an *existing* model.
Stars
30
Forks
10
Language
Python
License
MIT
Last pushed
Jun 21, 2024
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/awsm-research/PyExplainer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...