Code Review: Kaggle TAMS AIS Winter 2022 competition

How I used linear regression to achieve a top score on a Kaggle competition.

[gecarter]

Hi, this code review was very informative. In line 18 you normalized the entire data set. Does this introduce data leakage, since the training set will have some "knowledge" of the test set through the normalization process. Should the training and test sets be normalized separately? Thanks.