Description
Return every positive maximum off-diagonal error pair, retaining ties; an error-free table has maximum zero and no invented error pair.
A confusion table uses actual labels as rows and predicted labels as columns. Cells can contain occurrence counts or supplied nonnegative weights; the axis label order must stay with the matrix. Row, column and joint normalization have different denominators, and a zero denominator needs an explicit undefined result.
Return every positive maximum off-diagonal error pair, retaining ties; an error-free table has maximum zero and no invented error pair.
When to use this tool
Use this tool to return every positive maximum off-diagonal error pair, retaining ties; an error-free table has maximum zero and no invented error pair.
How to use the tool and how it works
- Enter matrix, labels using the input definitions below.
- Run the operation. Resolve malformed-input errors before interpreting the result.
- Read result.maximum, result.pairs. Interpret signs, units, ordering and null values using the rules below.
Find the largest off-diagonal value with zero as a floor. Return every strictly positive cell equal to that maximum, in row-major order, with actual and predicted label names.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| matrix | Square nonnegative finite table: matrix[actualIndex][predictedIndex], both axes in labels order. | Dense list of at most 128 rows of at most 128 finite numbers; the operation’s shape constraints also apply. |
| labels | Distinct label strings defining actual row and predicted column order; score tools require at least one label. | Dense list of at most 128 strings, each at most 8,192 UTF-16 code units. |
| Output field | Interpretation |
|---|---|
| result | Object containing the fields below. |
| result.maximum | Maximum off-diagonal error weight, or zero if no positive error exists. |
| result.pairs | Every positive maximum off-diagonal cell as {actual,predicted,value}, in row-major order. |
{
"input": {
"matrix": [
[
2,
1
],
[
0,
1
]
],
"labels": [
"a",
"b"
]
},
"output": {
"result": {
"maximum": 1,
"pairs": [
{
"actual": "a",
"predicted": "b",
"value": 1
}
]
}
}
}Limitations and assumptions
- An error-free table returns maximum = 0 and no pairs; the operation does not rank normalized error rates.
- Label strings are compared exactly. Confusion values may be nonnegative fractional weights; a count interpretation requires count data. Probability-like score rows use [0,1] entries with sum tolerance 10⁻⁸, without establishing calibration.
- Every declared top-level input is required and unknown fields are rejected. Ordinary strings are limited to 8,192 UTF-16 code units and lists to 128 entries, with tighter operation-specific bounds where stated. JSON text has bounded nesting and node counts.
- Numeric outputs must be finite and within the absolute safe-integer magnitude; exact larger integers use decimal text. Source positions are zero-based UTF-16 offsets and span ends are exclusive unless a different convention is explicitly stated.
Alternative or Complementary methods
Check label coverage and axis order before comparing tables. Use a separate evaluation design for uncertainty, calibration, operating thresholds and the consequences of real-world decisions.
References
Similar or alternative tools
- Confusion Actual Support Table
Report actual row support totals without calculating per-class rates.
- Confusion Column Rate Table
Normalize each predicted column independently with null for zero-support columns; no calibrated probability claim.