You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In fit.and.evaluate, we include options for weibull, gamma, exp and lnorm which are distributions that only have data density for positive values. This is counter-intuitive given that we generate our distribution of aggregated z-scores by summing up negative z-scores.
The text was updated successfully, but these errors were encountered:
I think it should be noted that in the functions cosine.similarity.cutoff and cosine.similarity.iterative, the signs of the data are flipped before fitting distributions. We should probably add a parameter to fit.and.evaluate to match to avoid confusion.
In
fit.and.evaluate
, we include options forweibull
,gamma
,exp
andlnorm
which are distributions that only have data density for positive values. This is counter-intuitive given that we generate our distribution of aggregated z-scores by summing up negative z-scores.The text was updated successfully, but these errors were encountered: