adjust_equivocal_zone: Apply an equivocal zone to a binary classification model.

In tailor: Iterative Steps for Postprocessing Model Predictions

Apply an equivocal zone to a binary classification model.

Description

Equivocal zones describe intervals of predicted probabilities that are deemed too uncertain or ambiguous to be assigned a hard class. Rather than predicting a hard class when the probability is very close to a threshold, tailors using this adjustment predict "[EQ]".

Usage

adjust_equivocal_zone(x, value = 0.1, threshold = NULL)

Arguments

x	A tailor().
value	A numeric value (between zero and 1/2) or hardhat::tune(). The value is the size of the buffer around the threshold.
threshold	A numeric value (between zero and one) or hardhat::tune(). Defaults to adjust_probability_threshold(threshold) if previously set in x, or 1 / 2 if not.

Details

This function transforms the class prediction column estimate to have type class_pred from probably::class_pred(). You can loosely think of this column type as a factor, except there's a possible entry "[EQ]" that is not a level and will be excluded from performance metric calculations. As a result, the output column has the same number of levels as the input, except now has a possible entry "[EQ]" that tidymodels functions know to exclude from further analyses.

Value

An updated tailor() containing the new operation.

Data Usage

This adjustment doesn't require estimation and, as such, the same data that's used to train it with fit() can be predicted on with predict(); fitting this adjustment just collects metadata on the supplied column names and does not risk data leakage.

Examples

library(dplyr)
library(modeldata)

head(two_class_example)

# `predicted` gives hard class predictions based on probabilities
two_class_example |> count(predicted)

# when probabilities are within (.25, .75), consider them equivocal
tlr <-
  tailor() |>
  adjust_equivocal_zone(value = 1 / 4)

tlr

# fit by supplying column names.
tlr_fit <- fit(
  tlr,
  two_class_example,
  outcome = c(truth),
  estimate = c(predicted),
  probabilities = c(Class1, Class2)
)

tlr_fit

# adjust hard class predictions
predict(tlr_fit, two_class_example) |> count(predicted)

tailor documentation built on Aug. 25, 2025, 9:50 a.m.