hinge_set: Calculate the hinge loss

In aaronjfisher/mcr: Computes model class reliance, i.e., the most and least that models from a class may rely on variables of interest

Description

hinge_pred computes the in-sample hinge loss, given a set of predictions. hinge_w computes predictions, and passes these to hinge_pred to compute the in-sample hinge loss.

Usage

hinge_pred(pred, y, m = 1)

hinge_w(w, X, ...)

Arguments

pred	y predictions from the model w
y	outcome vector, with elements -1 or 1
m	margin parameter
w	weight vector (linear classification model). First element should be an interecept term. For example, the output of optimize_hinge_general.
X	covariate matrix, should not include a constant (intercept) column.
...	passed to hinge_pred

aaronjfisher/mcr documentation built on Jan. 2, 2020, 4:38 p.m.