Binary Confusion Transpose Role Change Tool

Description

Transpose the roles of binary confusion axes.

Classifier metrics count particular outcomes on a declared population and positive-label convention. Precision, recall and accepted-only measures use different denominators. A reporting value at an empty denominator is a policy choice, while one cell, derivative or contribution does not constitute a complete performance evaluation.

Transpose the roles of binary confusion axes.

When to use this tool

Use Binary Confusion Transpose Role Change when checking the stated confusion-count, metric contribution or abstention-denominator convention.

How to use the tool and how it works

Enter tp, tn, fp, fn. Use the units and conventions below.
Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
Read tp, tn, fp, fn. Use the output convention below.

Transpose the roles of binary confusion axes. Require nonnegative whole cells; preserve TP/TN and exchange FP/FN.^[1]

Input field	Meaning and units	Accepted input
tp	Tp	Required. Safe integer.
tn	Tn	Required. Safe integer.
fp	Fp	Required. Safe integer.
fn	Fn	Required. Safe integer.

Output field	Interpretation	Returned shape
tp	Tp	Required. Safe integer.
tn	Tn	Required. Safe integer.
fp	Fp	Required. Safe integer.
fn	Fn	Required. Safe integer.

json

{
  "input": {
    "tp": 30,
    "tn": 50,
    "fp": 8,
    "fn": 12
  },
  "output": {
    "tp": 30,
    "tn": 50,
    "fp": 12,
    "fn": 8
  }
}

Limitations and assumptions

This assumes the two axes are actual/predicted for the same positive label; it is not the separate operation of swapping positive/negative labels.
Inputs must satisfy both the field types and the cross-field conditions above. Invalid input causes an error; a successful false flag or documented placeholder is a different result.
Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Numeric signed-zero results are exported as zero.

Alternative or Complementary methods

Evaluate the complete confusion table, relevant class supports and abstention coverage together; use suitable uncertainty and validation methods for conclusions about predictive performance.

References

Calculation and input contract: classification/binary-confusion-transpose-role-change — tool.io

Similar or alternative tools

Binary Confusion Predicted Prevalence Term
Return predicted-positive count and prevalence.
Classification: Binary Confusion Positive Label Swap
Relabel a binary confusion table's positive class.