fastPR: Precision-Recall curve

In traversc/trqwe: Performance oriented statistical metrics and utility functions.

Description

Calculates the points in a Precision-Recall from the results of a classifcation model.

Usage

fastPR(probs, class)

Arguments

probs	A numeric vector of probabilities or likelihoods for each data point.
class	A numeric vector where 1 is positive and 0 is negative.

Value

a list containing the ROC curve.

Examples

library(AppliedPredictiveModeling)
data(abalone)
library(glmnet)
class <- factor(as.numeric(abalone$Type == "M"))
data <- data.matrix(abalone[,-1])
fit <- cv.glmnet(data, class, family="binomial")
probs <- predict(fit, newx=data)[,1]
with(fastPR(probs, class), plot(recall, precision, type="l"))

traversc/trqwe documentation built on Dec. 4, 2020, 4:21 a.m.