draw_calibration: Draw calibration plot

In egenn/rtemis: Machine Learning and Visualization

Draw calibration plot

Description

Draw calibration plot

Usage

draw_calibration(
  true_labels,
  predicted_prob,
  n_bins = 10L,
  bin_method = c("quantile", "equidistant"),
  binclasspos = 2L,
  main = NULL,
  subtitle = NULL,
  xlab = "Mean predicted probability",
  ylab = "Empirical risk",
  show_marginal_x = TRUE,
  marginal_x_y = -0.02,
  marginal_col = NULL,
  marginal_size = 10,
  mode = "markers+lines",
  show_brier = TRUE,
  theme = choose_theme(),
  filename = NULL,
  ...
)

Arguments

true_labels	Factor or list of factors with true class labels
predicted_prob	Numeric vector or list of numeric vectors with predicted probabilities
n_bins	Integer: Number of windows to split the data into
bin_method	Character: "quantile" or "equidistant": Method to bin the estimated probabilities.
binclasspos	Integer: Index of the positive class. The convention used in the package is the second level is the positive class.
main	Character: Main title
subtitle	Character: Subtitle, placed bottom right of plot
xlab	Character: x-axis label
ylab	Character: y-axis label
show_marginal_x	Logical: Add marginal plot of distribution of estimated probabilities
marginal_x_y	Numeric: y position of marginal plot
marginal_col	Character: Color of marginal plot
marginal_size	Numeric: Size of marginal plot
mode	Character: "lines", "markers", "lines+markers": How to plot.
show_brier	Logical: If TRUE, add Brier scores to trace names.
theme	Theme object.
filename	Character: Path to save output.
...	Additional arguments passed to draw_scatter

Value

plotly object.

Author(s)

EDG

Examples

## Not run: 
data(segment_logistic, package = "probably")

# Plot the calibration curve of the original predictions
draw_calibration(
  true_labels = segment_logistic$Class,
  predicted_prob = segment_logistic$.pred_poor,
  n_bins = 10L,
  binclasspos = 2L
)

# Plot the calibration curve of the calibrated predictions
draw_calibration(
  true_labels = segment_logistic$Class,
  predicted_prob = calibrate(
    segment_logistic$Class,
    segment_logistic$.pred_poor
  )$fitted.values,
  n_bins = 10L,
  binclasspos = 2L
)

## End(Not run)

egenn/rtemis documentation built on June 14, 2025, 11:54 p.m.