> On Aug 18, 2019, at 9:20 AM, Senhaji Rhazi hamza > <hamza.senhajirh...@gmail.com> wrote: > > Hey Steven, > > I think there is a way to map x <- [1; + inf] to y <- [0;1] by putting y = 1/x >
One big issue with using that mapping is it doesn’t preserve many of the characteristics of the initial distribution. If the x distribution is low waited, then the y distribution is high weighted. If you want to try to preserve the shape, the fact that you are mapping a distribution that goes to infinity to a value with an upper limit says it can’t be precisely done and maintain distribution. You could shift it down by subtracting 1, possible scale it, and then truncate it if you get a value to large (either redraw or just saturate to 1). This will give you something with close to the right shape, depending on how you want to define a mapping of an infinite range to a finite range. _______________________________________________ Python-ideas mailing list -- python-ideas@python.org To unsubscribe send an email to python-ideas-le...@python.org https://mail.python.org/mailman3/lists/python-ideas.python.org/ Message archived at https://mail.python.org/archives/list/python-ideas@python.org/message/KECLDYIPCGWR4A27HF5D2JTE2YKQ6M7N/ Code of Conduct: http://python.org/psf/codeofconduct/