search

LBL-EESA / fastkde

Other
50 stars 10 forks source link

Score samples function #4

Closed simonpedrogonzalez closed 9 months ago

simonpedrogonzalez commented 3 years ago

Is there a way to score samples with natural or log density estimate?

taobrienlbl commented 3 years ago

Hi @simonpedrogonzalez -- glad that fastKDE might be of interest!

I'm not certain I understand what you're asking. Are you asking about weighting the samples prior to performing the KDE? If so, then no, that capability doesn't yet exist.

If you're talking about taking the log of the samples prior to performing the KDE, then yes, that does. You can use the logAxes=True option for that.

aleksyprok commented 2 years ago

Hi @taobrienlbl. Are you planning on adding the ability to weigh the samples prior to performing the KDE?

taobrienlbl commented 2 years ago

Hi @aleksyprok - thanks for reaching out. I don't have concrete plans to add this feature. It's something that I have considered. I anticipate that the implementation would be relatively easy, but I would want to make sure it's done in a way that maintains the optimality of the unweighted fastKDE method. That will take some theoretical work (and is likely worth writing a paper on).