I have a dataset with a couple skewed variables that with the use of sqrt() function turns them into a normal distribution variable.
I have read somewhere that I should have a normal distributed dataset so I could use MinMaxScaler()...
What's your advice to deal with such skewed variable, should I just use minmax or first turn them into normal distributed variables and then use minmax?
I have used sqrt() to turn a skewed distribution into a normal distributed variable.
After that I used MinMaxScaler(), but I am not sure this is the correct way to do things