Description
List distinct supplied predicted labels absent from actual labels.
Classification terms depend on label vocabularies, decision thresholds and denominator definitions. One class recall is not a full balanced-accuracy metric, and a row or column total is not automatically a precision or recall denominator. Empty or zero-total cases need an explicit defined flag or convention.
List distinct supplied predicted labels absent from actual labels.
When to use this tool
Use Multilabel Item Excess Prediction Count when you already have predictedLabels, actualLabels and need to list distinct supplied predicted labels absent from actual labels.
How to use the tool and how it works
- Enter predictedLabels, actualLabels. Follow any array-alignment requirements below. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read extraPredictedLabels, extraCount. Use the output convention below.
Deduplicate predictedLabels in first-occurrence order, keep labels not literally in actualLabels, and return the list and count.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| predictedLabels | Predicted Labels | Required. Array of text; maximum UTF-16 length 8192; maximum items 256. |
| actualLabels | Actual Labels | Required. Array of text; maximum UTF-16 length 8192; maximum items 256. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| extraPredictedLabels | Distinct predicted labels absent from actualLabels, in first-occurrence order. | Required. Array of text; maximum UTF-16 length 8192; maximum items 256. |
| extraCount | Extra Count | Required. Safe integer. |
{
"input": {
"predictedLabels": [
"A",
"B",
"B",
"C"
],
"actualLabels": [
"B",
"D"
]
},
"output": {
"extraPredictedLabels": [
"A",
"C"
],
"extraCount": 2
}
}Limitations and assumptions
- Empty labels/lists are accepted. This is one item's extra-label set, not false-positive rate, a full multilabel metric, label validity or actual ground truth.
- 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.
Alternative or Complementary methods
Evaluate the complete prediction set, confusion structure and decision policy. Report missingness, class scope and uncertainty with the full metric; local threshold flags or one-cell fractions cannot characterize overall model performance.
References
Similar or alternative tools
- Binary Predicted Label Count Balance
Sum supplied binary confusion cells into predicted-label totals.
- Confusion Cell Row Share Column Share
Calculate a supplied confusion cell's row and column shares.