Hi Everyone,
I am currently struggling with rpy2, I hope someone could help me.
I am trying to do a maximum likelihood using the mle() task in the stats4
R library,
as part of a python script. mle() receives a R function to calculate the
negative log-likelihood,
my problem is that so far I have could not figure out how to give a numpy
vector to the function,
or make the vector understandable for the R environment. Is there a way to
do this?
With the following example will be clearer.
This is a short version, trying to use mle() in a normal distribution.
"I need to make the XX vector understandable for rfunction":
======================================================================
import rpy2.robjects as robjects
from rpy2.robjects.packages import importr
import rpy2.robjects.numpy2ri
import numpy as np
r = robjects.r
stats4 = importr("stats4")
#Normal vector to test the script, which I need to give to the R function ll
XX = np.random.normal(loc=10.0, scale=2.0, size=100)
N = len(XX)
#negative logarithmic likelihood function of a Gaussian distribution
#This function should receive the XX numpy vector someway
rfunction = '''ll <- function(mean,sigma){
n <- %i
x <- XX ##This is the critical point##
-(-0.5*n*log(2*pi)-n*log(sigma)-0.5*sum(((x-mean)/sigma)^2))
}''' % (N)
fx=r(rfunction)
starterd = {'mean':10,'sigma':1}
starter= robjects.DataFrame(starterd)
fit = stats4.mle(minuslog=fx,start=starter)
summary = R.summary(fit)
print summary
==========================================================================
I hope someone can help me with this or point me out a better solution
By the way, I am using:
rpy2 v2.1.9
R v2.11.0
python v2.6
Thank you!
--
Eduardo Bañados Torres
------------------------------------------------------------------------------
Simplify data backup and recovery for your virtual environment with vRanger.
Installation's a snap, and flexible recovery options mean your data is safe,
secure and there when you need it. Discover what all the cheering's about.
Get your free trial download today.
http://p.sf.net/sfu/quest-dev2dev2
_______________________________________________
rpy-list mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/rpy-list
