Description
Return positive for score above threshold or exact equality when equalityIsPositive.
A classification summary depends on which axis represents actual labels, which represents predictions, and how a decision threshold handles equality. A local matrix transformation or threshold check does not measure overall model quality.
Return positive for score above threshold or exact equality when equalityIsPositive.
When to use this tool
Use Classifier Threshold Equality Policy when you need one explicit classification-record component.
How to use the tool and how it works
- Enter score, threshold, equalityIsPositive. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read positive, equalityEncountered. Inspect positive, equalityEncountered before interpreting the associated values.
Return positive for score above threshold or exact equality when equalityIsPositive. Independently mark equalityEncountered.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| score | Score | Required. Finite number. |
| threshold | Threshold | Required. Finite number. |
| equalityIsPositive | Equality Is Positive | Required. Boolean. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| positive | Positive | Required. Boolean. |
| equalityEncountered | Equality Encountered | Required. Boolean. |
{
"input": {
"score": 0.6,
"threshold": 0.6,
"equalityIsPositive": true
},
"output": {
"positive": true,
"equalityEncountered": true
}
}Limitations and assumptions
- Score is not required to be a probability; thresholds are supplied and no classifier quality, calibration, fairness, or diagnosis is established.
- 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 prediction set and report suitable metrics under a documented label and threshold convention.
References
Similar or alternative tools
- Clipped Minmax Scalar
Clamp value into that interval, normalize to (clamped-min)/(max-min), and flag clipped only for strict original outliers.
- Confusion Table Transpose Convention
Retain it when rowsAreActual or transpose it otherwise, returning actualRowsPredictedColumns.