AustinRochford/PyCEbox
⬛ Python Individual Conditional Expectation Plot Toolbox
When analyzing a predictive model, it helps you understand how a single input variable affects the model's predictions for each individual data point. You input your predictive model and a dataset, and it outputs a set of plots showing how predictions change. This is for data scientists and machine learning engineers who need to explain model behavior.
163 stars. No commits in the last 6 months. Available on PyPI.
Use this if you want to visualize and explain how your 'black box' machine learning model responds to changes in a specific input for individual cases, rather than just overall average effects.
Not ideal if you only need aggregate insights into your model's feature importance or global relationships, rather than individual prediction explanations.
Stars
163
Forks
35
Language
Jupyter Notebook
License
MIT
Last pushed
May 29, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AustinRochford/PyCEbox"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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...