specifies the default variable as the response. To clarify: I can see from the italicised text that the lattice formula does seem to represent the same information as my two vectors, I'm just unclear as to how to put them in the required format, and looking at ?xyplot has only confused me further. Here, we have supplied four arguments to the train() function form the caret package. Am I just confused as to what kind of plot calibration() produces? If not then how do I turn my vector of predictions and vector of true values into the required 'lattice formula'? The inputs I was expecting to have to give were a vector of predictions for my classifier, together with the vector of corresponding true values, in order to plot something like the first of the two graphs in this image. TheĬlassification variable should have two levels. Numeric ranking variable for a model (e.g. so at each counter R can generate a different data set for asreml to run. The right-hand side specifies one or model columns corresponding to a I was struggling to install caret package on my upgraded R. Of the formula is a factor class variable of the observed outcome and X a lattice formula (see xyplot for syntax) where the left-hand side Unfortunately I am having trouble understanding the documentation given by ?calibration: I would like to use the function 'calibration' from the caret package to produce calibration plots for a few classifiers that I have.
0 Comments
Leave a Reply. |