hddm-devs / hddm

HDDM is a python module that implements Hierarchical Bayesian parameter estimation of Drift Diffusion Models (via PyMC).
http://ski.clps.brown.edu/hddm_docs/
Other
260 stars 118 forks source link

Fix gsquare optimization #10

Closed twiecki closed 11 years ago

twiecki commented 12 years ago

FloatingPointError: invalid value encountered in log

/home/wiecki/working/projects/hddm/hddm/likelihoods.py(191)gsquare() 190 return -np.inf --> 191 return 2 * sum(self._freq_obs * np.log(theo_proportion)) 192

ipdb> theo_proportion array([ 0.00005721, 0.00774484, 0.4890562 , 0.00001 , 0.00001 , 0.00001 , 0.00001 , 0.00001 , 0.26693313, 0.24014853, 0.00001 , -0.0039399 ])

isofer commented 11 years ago

can you reproduce it?