Hacker News new | ask | show | jobs
by jamesblonde 148 days ago
If they are exploding categorical variables using OHE and storing the columns - that is the wrong thing to do. You should only ever store untransformed feature data in tables. You apply the feature transformations, like OHE, on reading from the tables, as those transformations are parameterized by the data you read (the training data subset you select).

Reference: https://www.hopsworks.ai/post/a-taxonomy-for-data-transforma...