maxnet (version 0.1.1)

hinge: Maxent feature classes

Description

Create and evaluate Maxent's feature classes

Usage

hinge(x, nknots = 50) thresholds(x, nknots=50) categorical(x) hingeval(x, min, max) thresholdval(x, knot) categoricalval(x, category)

Arguments

x
a predictor: a factor for categorical and categoricalval, otherwise numeric.
nknots
number of knots.
min
value of x at which hinge feature is 0.
max
value of x at which hinge feature is 1.
knot
value of x at which threshold feature changes from 0 to 1.
category
a level of x

Value

hinge, threshold and categorical return a matrix with a column for each feature of the specified type. hinge creates 2*nknots hinge features, half with min=min(x) and half with max=max(x), and knots evenly spaced between min(x) and max(x). hingeval calculates a single hinge feature: 0 if the predictor is below min, 1 if the predictor is above max, and linearly interpolated inbetween. thresholdval calculates a single threshold feature: 1 if the predictor is above the knot, 0 otherwise. categoricalval calculates a categorical feature: 1 if the predictor matches the category.