Q1: scaling numerical and categorical variables together can improve the predictive accuracy of the models?
For categorical features, it is generally common to omit scaling when features are encoded with a OneHotEncoder
since the feature values are already on a similar scale.
1 Like
Q2: When we perform Normalization and Standardization are there any criteria or rules of thumb? have some set of doubts about these two terms👆@ArturoAmorQ can you make a comment on it. Thanks in advance
I found this post which has a quite clear explanation on both kinds of scaling.
I would add that in the Wrap-up quiz 3 you will study the impact of using different preprocessors in a given model by treating them as hyperparameters that have to be tuned.
1 Like
Thanks once again,