In chuvanan/calibcurve: Calibration of Predicted Probabilities

knitr::opts_chunk$set(
                      collapse = TRUE,
                      comment = "#>",
                      dpi = 300, 
                      fig.path = "man/figures/README-",
                      out.width = "100%",
                      warning = FALSE,
                      message = FALSE
                  )

calibcurve

calibcurve implements functions to compute true and predicted probabilities and visualise a calibration curve, aka reliability diagram (Niculescu-Mizil & Caruana, 2005).

• calibcurve is powered by the yardstick's infrastructure and its implementation of related curve metrics.

• calibcurve borrowed some ideas from sklearn's calibration module.

Installation

You can install the released version of calibcurve from CRAN with:

# install.packages("calibcurve")
# Not yet!

And the development version from GitHub with:

# install.packages("devtools")
devtools::install_github("chuvanan/calibcurve")

Example

This is a basic example which shows you how to solve a common problem:

library(calibcurve)
library(magrittr)
library(ggplot2)

data(two_class_example, package = "yardstick")
head(two_class_example)

two_class_example %>%
    calibration_curve(truth, Class1)

two_class_example %>%
    calibration_curve(truth, Class1) %>%
    autoplot()

Code of Conduct

Please note that the calibcurve project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.

chuvanan/calibcurve documentation built on June 19, 2020, 12:14 a.m.