pretty_pr_curve: Pretty Precision-Recall curves

In mai00fti/prettyPROC: Print pretty PR and ROC curves

Pretty Precision-Recall curves

Description

This function plots a pretty PR (precision-recall curve) using the values from the [tidyverse::tibble()] that can be generated with the package function [get_threshold_data()]. It colors the curve according to the value of the threshold.

Usage

pretty_pr_curve(
  df,
  plot_title = "Precision-recall curve",
  x_col = "Recall",
  y_col = "Precision",
  col_col = "threshold",
  f1_col = "F1",
  colors = c("#00007F", "blue", "#007FFF", "cyan", "#7FFF7F", "yellow", "#FF7F00",
    "red", "#7F0000"),
  annotate = NULL
)

Arguments

df	- The tibble that can be generated with the package function [get_threshold_data()]
plot_title	- A title for your plot
x_col	- The column name of the values 2B plotted on the x-axis. Default = "Recall".
y_col	- The column name of the values 2B plotted on the x-axis. Default = "Precision".
col_col	- The column name of the values for coloring the points. Default = "threshold".
colors	- A vector of colors from which a gradient will be generated. Default: c("#00007F", "blue", "#007FFF", "cyan", "#7FFF7F", "yellow", "#FF7F00", "red", "#7F0000")
annotate	A threshold between 0 and 1 (digits = 2) that should be annotated at the curve. You may select one of the thresholds that you can get using the package function [select_threshold].
auc_col	- The column name of the values that contain the AUC. Default = "roc-auc". Set to 'NA' if you do not want to show the AUC line

Value

The plot as ggplot2.

Examples

y_true <- sample(c(0,1), replace = TRUE, size = 1000)
y_predicted <- runif(1000)
data <- get_threshold_data(truth = y_true, prediction = y_predicted)
pr <- pretty_pr_curve(df = data,
                      plot_title = "Precision-recall curve")
show(pr$plot)

mai00fti/prettyPROC documentation built on Aug. 16, 2024, 4:48 p.m.