Engineering new features

Preprocessing for Machine Learning in Python

James Chapman

Curriculum Manager, DataCamp

UFO feature engineering

date length_of_time desc
6/16/2013 21:00 5 minutes Sabino Canyon Tucson Arizona night UFO sighting.
9/12/2005 22:35 5 minutes Star like objects hovering in sky, slowly m...
12/31/2013 22:25 3 minutes Three orange fireballs spotted by witness in E...

 

  • Dates: .dt.month or .dt.hour attributes
  • Regex: \d and .group()
  • Text: tf-idf and TfidfVectorizer
Preprocessing for Machine Learning in Python

Let's practice!

Preprocessing for Machine Learning in Python

Preparing Video For Download...