https://github.com/mewwts/feng

feng - feature engineering for machine-learning champions
https://github.com/mewwts/feng

feature-engineering machine-learning pandas

Last synced: 6 months ago
JSON representation

feng - feature engineering for machine-learning champions

• Host: GitHub
• URL: https://github.com/mewwts/feng
• Owner: mewwts
• Archived: true
• Created: 2016-05-01T20:57:47.000Z (about 10 years ago)
• Default Branch: master
• Last Pushed: 2017-03-08T08:29:16.000Z (over 9 years ago)
• Last Synced: 2025-11-16T19:22:04.704Z (8 months ago)
• Topics: feature-engineering, machine-learning, pandas
• Language: Python
• Homepage:
• Size: 20.5 KB
• Stars: 27
• Watchers: 4
• Forks: 6
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
## feng - feature engineering for machine-learning champions

[![Build Status](https://travis-ci.org/mewwts/feng.svg?branch=master)](https://travis-ci.org/mewwts/feng)

feng is a Python module for smoothly engineering features from your Pandas DataFrame so that you can win that Kaggle competition.

### Why feng?

> *We spent most of our efforts in feature engineering.*

> 

> -- Xavier Cohort, [after winning one of many Kaggle competitions](http://blog.kaggle.com/2013/04/10/qa-with-xavier-conort/)

feng helps data scientists in what is arguably the most critical part of a machine-learning pipeline: [feature engineering](https://en.wikipedia.org/wiki/Feature_engineering). 

It's built for fans of [Pandas](http://pandas.pydata.org/) and makes use of [scikit-learn](http://scikit-learn.org/) pipelines and transformers.

> *... some machine learning projects succeed and some fail. What makes the difference? Easily the most important factor is the features used.*

>

> -- Pedro Domingos, [A Few Useful Things to Know about Machine Learning](http://homes.cs.washington.edu/~pedrod/papers/cacm12.pdf)

Made with ♥️ in Barcelona.