Hi,
i have on question.
Is it useful to log normalize the target data??
They are 5 classes depending on the value, it is class 1 or 2,3,4,5.
The problem is, the ranges are very small.
I have Data like
x<=5 mg/kg == class 1
x<=10 mg /kg == class 2
x<= 50 mgkg == class 3
x<= 500 mg/kg == class 4
x<= 5000mg/kg == class 5 ( just arbitrary values for an example)
I have some values about 220.000 mg/kg which are some "outliers"...
so make it sense to normalize the data? The problem is, if I normalize the
data, i can't classifie the data afterwards. or should i normalize
1,2,3,4,5 also and make the boundries depending on the log normalized
classes 1,2,3,4,5?
Best,
Herb
------------------------------------------------------------------------------
Don't Limit Your Business. Reach for the Cloud.
GigeNET's Cloud Solutions provide you with the tools and support that
you need to offload your IT needs and focus on growing your business.
Configured For All Businesses. Start Your Cloud Today.
https://www.gigenetcloud.com/
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
