Numpy parity: statistics fitting

scalanlp / breeze

Breeze is/was a numerical processing library for Scala.

https://www.scalanlp.org

Apache License 2.0

3.44k stars 692 forks source link

Numpy parity: statistics fitting #217

Open stucchio opened 10 years ago

stucchio commented 10 years ago

Numpy gives the fit function, letting you input data and get a distribution as output. Would be nice to have that.

[ ] chisquare
[ ] f
[ ] gumbel
[ ] hypergeometric
[ ] laplace
[ ] lognormal
[ ] logseries
[ ] multivariate_normal
[ ] noncentral_chisquare
[ ] noncentral f
[ ] pareto
[ ] power
[ ] rayleigh
[ ] student's t
[ ] triangular
[ ] wald
[ ] weibull
[ ] zipf

dlwh commented 10 years ago

as mentioned on the PR: I have code for fitting many of the older distributions. It can be modernized/improved, but the functionality is at least partially there.

https://github.com/scalanlp/breeze/blob/master/src/main/scala/breeze/stats/distributions/Beta.scala#L128 etc.