vanderschaarlab/hyperimpute

A framework for prototyping and benchmarking imputation methods

39
/ 100
Emerging

When preparing data for machine learning, you often encounter missing values that can hinder your analysis. HyperImpute helps you automatically select and apply the best method to fill in these gaps, taking raw datasets with missing information and producing complete datasets ready for your models. This is ideal for data scientists, machine learning engineers, and researchers who regularly work with real-world, imperfect data.

196 stars. No commits in the last 6 months.

Use this if you need to reliably handle missing data in your datasets and want to experiment with or automate the selection of various imputation techniques.

Not ideal if you prefer to manually implement imputation methods from scratch or need extremely fine-grained, manual control over every step of the imputation process.

data-preprocessing missing-data-handling machine-learning-preparation data-quality predictive-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

196

Forks

17

Language

Python

License

MIT

Last pushed

Apr 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vanderschaarlab/hyperimpute"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.