chemicalchecker.tool.targetmate.nonconformist.nc.MarginErrFunc
- class MarginErrFunc[source]
Bases:
ClassificationErrFuncCalculates the margin error.
For each correct output in
y, nonconformity is defined as0.5 - \dfrac{\hat{P}(y_i | x) - max_{y \, != \, y_i} \hat{P}(y | x)}{2}
Methods
Apply the nonconformity function.
- apply(prediction, y)[source]
Apply the nonconformity function.
Parameters
- predictionnumpy array of shape [n_samples, n_classes]
Class probability estimates for each sample.
- ynumpy array of shape [n_samples]
True output labels of each sample.
Returns
- ncnumpy array of shape [n_samples]
Nonconformity scores of the samples.