3zhang/Python-Lasso-ElasticNet-Ridge-Regression-with-Customized-Penalties
An extension of sklearn's Lasso/ElasticNet/Ridge model to allow users to customize the penalties of different covariates. Works similar to penalty.factor parameter in R's glmnet.
This tool helps data scientists, statisticians, and researchers refine their predictive models when they have specific knowledge about which factors are most important. It takes your dataset and your expert judgments about the importance of each predictor, and it outputs a more accurate and interpretable regression model. This is especially useful for those who want their models to reflect real-world insights beyond what standard algorithms provide.
No commits in the last 6 months.
Use this if you are building a regression model and have prior domain knowledge that certain predictors should be more (or less) strongly weighted than others, or should not be penalized at all.
Not ideal if you prefer a 'black box' approach where all predictors are treated equally by the regularization algorithm without manual intervention or if you only need standard Lasso, Elastic Net, or Ridge regression.
Stars
7
Forks
—
Language
Jupyter Notebook
License
BSD-2-Clause
Category
Last pushed
Apr 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/3zhang/Python-Lasso-ElasticNet-Ridge-Regression-with-Customized-Penalties"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
stabgan/Multiple-Linear-Regression
Implementation of Multiple Linear Regression both in Python and R
SENATOROVAI/Normal-equation-solver-multiple-linear-regression-course
Multiple Linear Regression (MLR) models the linear relationship between a continuous dependent...
SENATOROVAI/Normal-equations-scalar-form-solver-simple-linear-regression-course
The normal equations for simple linear regression are a system of two linear equations used to...
SENATOROVAI/underfitting-overfitting-polynomial-regression-course
Underfitting and overfitting are critical concepts in machine learning, particularly when using...
andrescorrada/IntroductionToAlgebraicEvaluation
A collection of essays and code on algebraic methods to evaluate noisy judges on unlabeled test data.