vinta
add machine learning library
Adding feature-engine to the machine learning collection.
Features:
- 320k + downloads per month
- 2k+ github stars
- 50 contributors
- 10k+ doc views per month
What is this Python project?
Most exhaustive collection of transformers for feature engineering including: imputation, categorical encoding, discretization, transformation, feature creation.
Feature engine also contains the widest library of feature selection methods after sklearn.
What's the difference between this Python project and similar ones?
The feature selection methods are not present elsewhere in the python ecosystem.
Many of the feature transformation and creation methods are also not present in other python libraries.
It enriches sklearn capabilities dramatically by adding additional tools to transform and select variables.
--
Anyone who agrees with this pull request could submit an Approve review to it.
🛰️ Git Commit Hash Detected: e0152380d4da96812cc88f8ac0e32763443a4aa7
This looks like a SHA-1 commit ID — likely referencing a specific change in your repository.
How Would You Like to Use This?
Here are a few possible follow-up actions:
🔍 1. Show Commit Summary
“Show commit details for e015...” I’ll extract the commit message, changes, and affected files (if available locally or described).
🔗 2. Link This Commit
“Link this to issue #42” I’ll format a commit message like:
git commit --amend -m "fix: resolve delimiter bug in README parser (#42) See commit: e0152380d4da96812cc88f8ac0e32763443a4aa7"
🧱 3. Use in Changelog
“Add this commit to CHANGELOG.md” I’ll format it under 🐛 Fixes or ✨ Features, e.g.:
🐛 Fixes - Fix delimiter parsing bug in sort.py (e015238)
📦 4. Rebuild ZIP with this Commit
“Bundle this commit into ZIP” I’ll include it in your release-automation-repo-fullboost.zip with changelog updates.
Let me know your next move:
“Show commit details”
“Add to changelog”
“Link to issue”
“Bundle this commit”
Or paste a new hash or instruction
🧠 Commit recognized. Awaiting directive.
What do you mean by "acks basic essentials"? In the docs? or in the code implementations?
It expands sklearn feature engineering and feature selection tools quite dramatically. It has the most comprehensive feature selection toolset.
And regarding feature engineering, it has imputation and encoding methods that go beyond those supported by sklearn, and it also provides tools to tackle outliers, and create features for time series.
If you could be more specific, I'd be happy to expand. Thank you!