Why scale continuous columns

Screen Link: https://app.dataquest.io/m/186/feature-preparation%2C-selection-and-engineering/2/preparing-more-features

Hi guys,

Will appreciate some guidance as to why are we rescaling the 3 continuous columns in this screen. I would have expected the scikit-learn’s ML models would would handle the difference in scales natively?


1 Like

I had exactly the same doubt.

I did not understand why rescaling was necessary in this situation. I thought that rescaling like this would only be necessary if we were using algorithms such as K-Nearest neighbors, were we are relying on euclidian distances.

Can someone explain why it was necessary?

I also wondered if it was necessary. Would be great if someone could shine light on this given that it’s been almost a year since the question was first asked…