v0.4.2
Pre-release
Pre-release
New features:
- AsymptoticLimits functions are more memory efficient. New keyword
histo_theta_batchsize
sets number of parameter points for which histogram data is loaded in parallel. - New keyword
n_observables
forAsymptoticLimits.observed_limits()
allows overwriting the number of events (= rescaling the log likelihood).
Bug fixes:
- Fixed bugs that caused the training of
DoubleParameterizedRatioEstimator
andLikelihoodEstimator
instances to crash - Added more sanity checks when evaluating observables, both in
LHEReader
andDelphesReader