edahelsinki/slisemap
SLISEMAP: Combining supervised dimensionality reduction with local explanations
This tool helps data scientists and machine learning practitioners understand why their "black box" models make certain predictions. You provide your data and your model's predictions, and it outputs a simplified, interactive 2D map showing similar data points grouped together, along with clear, local explanations for each prediction. This allows you to visually explore and interpret complex model behavior.
No commits in the last 6 months. Available on PyPI.
Use this if you need to explain the individual predictions of a complex regression or classification model to stakeholders who are not data scientists.
Not ideal if you primarily need to improve your model's overall accuracy, rather than explain its existing predictions.
Stars
21
Forks
3
Language
Python
License
MIT
Last pushed
Apr 24, 2025
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/edahelsinki/slisemap"
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...