search

EHWUSF / HS68_2018_Project_1

0 stars 9 forks source link

Normalization/ Rescaling #5

Open kamehta2 opened 6 years ago

kamehta2 commented 6 years ago

The normalization is the process of rescaling attributes to the range of 0 to 1. This means that the largest value for each attribute is 1 and the smallest value is 0. I propose that it is a good technique to use when there are different units in the data and also when some attributes which have a wide range of values.

nirveshk commented 6 years ago

Hi kinjal, I believe this is too general. I think there is already syntax/function that accomplishes your proposed idea. May be proposing a precised idea of different approach to normalization would be a way to go :-) Please feel free to correct me if I am wrong.

kamehta2 commented 6 years ago

@nirveshk Yes, it is little general but we can think of making some module which can suggest if the dataset needs normalization/ rescaling or not. And if yes then it can do it for you. For example, It can check if there is a wide range of values in the dataset and we can set some kind of limit or something and then it will give you rescaled dataset.

kamehta2 commented 6 years ago

And I will check some more things about this.