TikaaVo/deskit
A Python library for Dynamic Ensemble Selection
When you have multiple machine learning models and need to combine their predictions to get a single, more accurate result, this tool helps you dynamically select the best models or combine their outputs with smart weighting for each individual prediction. It takes your validation data and pre-computed model predictions, then gives you optimal weights for each model. This is for machine learning practitioners, data scientists, and ML engineers who deploy and manage predictive models.
Available on PyPI.
Use this if you are working with classification or regression tasks, have an ensemble of pre-trained models, and want to improve predictive accuracy by dynamically selecting the best models for each unique prediction scenario.
Not ideal if your datasets are very homogeneous, have low diversity, or if a single model already dominates your dataset's performance.
Stars
7
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TikaaVo/deskit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
iamDecode/sklearn-pmml-model
A library to parse and convert PMML models into Scikit-learn estimators.
vecxoz/vecstack
Python package for stacking (machine learning technique)
yzhao062/combo
(AAAI' 20) A Python Toolbox for Machine Learning Model Combination
flennerhag/mlens
ML-Ensemble – high performance ensemble learning
aws-samples/aws-machine-learning-university-dte
Machine Learning University: Decision Trees and Ensemble Methods