BinLwr-class.RdA predx class for binned probabilistic predictions with sequential numeric bins specified by the (inclusive) lower bound of each bin.
BinLwr(x) is.BinLwr(x) # S4 method for BinLwr predx_to_json(x) # S4 method for BinLwr as.data.frame(x, row.names = NULL, optional = FALSE, ...) # S4 method for BinLwr transform_predx(x, to_class, ...)
Bins are equally spaced and specified by an inclusive lower bound (lwr). If the bin width is 0.1, lwr could be 0, 0.1, 0.2, etc. in which case the bins are 0 <= x < 0.1, 0.1 <= x < 0.2, etc. The non-inclusive upper bound of the final bin is assumed to be the maximum value of lwr plus the uniform bin width. Individual probabilities (prob) must be greater than or equal to 0 and less than or equal to 1 and the vector of probabilities must sum to 1.
lwr and prob must be paired when a BinLwr object is created, but do not need to be in the order of lwr. The BinLwr object will order them.
In JSON and CSV representations, the bins are named lwr and the probabilities are named prob.
predxA numeric matrix with two columns: lwr and prob.