search

alteryx / predict-taxi-trip-duration

Predict taxi trip duration based on historical trips using automated feature engineering
BSD 3-Clause "New" or "Revised" License
60 stars 21 forks source link

A small query about label leakage #2

Closed manojj2891 closed 6 years ago

manojj2891 commented 6 years ago

Hi,

Thanks for the detailed code.

But have a doubt about label leakage here. While calculating features we are also including "trip_duration". Also saw a couple of features being created using the feature. Shouldn't we remove the variable before calculating features?

Thanks, Manoj

kmax12 commented 6 years ago

@manojj2891 We'd be happy to answer. Can you post this question on StackOverflow with the featuretools tag? https://stackoverflow.com/questions/tagged/featuretools.