0

I am new in Machine Learning so please excuse me of my limited knowledge. I am currently working on to learn more on normalization and standardization of data as I understand it is an essential step before application of any ML Model.

That being said, the text referred that when you have to decide if you want to apply Normalization or Standardization procedures, you must find out if your data follows a gaussian distribution, if it does not you use Normalization and if it does you use Standardization.

Now, in practice when you have a dataframe, do you go on to finding gaussian distribution one column at a time or do it for the entire dataset?

axiomatic
  • 1
  • 6
    This question is predicated on multiple fallacies, which makes it difficult to answer constructively. Is there a more specific question you could ask? – whuber Jun 03 '21 at 18:38
  • But see https://stats.stackexchange.com/questions/201909/when-to-normalize-data-in-regression/202002#202002 – kjetil b halvorsen Jun 04 '21 at 22:14

0 Answers0