Data provided by National Institute of Standards and Technology
With this tool, users can rapidly calculate binary classifier metrics like Matthew's Correlation Coefficient, F-Scores, and Average Precision Scores from scalar and binary predictions. It is primarily used to calculate threshold sensitivity studies, and has several routines to significantly speed up metric calculation (or approximation) when aggregate measures of performance over all thresholds are needed.
About this Dataset
Updated: 2026-09-04
Metadata Last Updated:
2026-03-19 00:00:00
Date Created:
N/A
Data Provided by:
Dataset Owner:
N/A
| Title | Contingency: a python library for fast, vectorized metrology with binary contingency counts. |
|---|---|
| Description | With this tool, users can rapidly calculate binary classifier metrics like Matthew's Correlation Coefficient, F-Scores, and Average Precision Scores from scalar and binary predictions. It is primarily used to calculate threshold sensitivity studies, and has several routines to significantly speed up metric calculation (or approximation) when aggregate measures of performance over all thresholds are needed. |
| Modified | 2026-03-19 00:00:00 |
| Publisher Name | National Institute of Standards and Technology |
| Contact | mailto:[email protected] |
| Keywords | binary classification , classifier , machine learning , metrics , performance , experiments , accuracy , recall , precision , contingency table , marginal counts , error , type I , type II , vectorized , batched , approximation |
{
"identifier": "ark:\/88434\/mds2-4079",
"accessLevel": "public",
"contactPoint": {
"hasEmail": "mailto:[email protected]",
"fn": "Rachael Sexton"
},
"programCode": [
"006:045"
],
"landingPage": "https:\/\/data.nist.gov\/od\/id\/mds2-4079",
"title": "Contingency: a python library for fast, vectorized metrology with binary contingency counts.",
"description": "With this tool, users can rapidly calculate binary classifier metrics like Matthew's Correlation Coefficient, F-Scores, and Average Precision Scores from scalar and binary predictions. It is primarily used to calculate threshold sensitivity studies, and has several routines to significantly speed up metric calculation (or approximation) when aggregate measures of performance over all thresholds are needed.",
"language": [
"en"
],
"distribution": [
{
"accessURL": "https:\/\/github.com\/usnistgov\/Contingency",
"format": "git repository",
"description": "GitHub repository within the usnistgov organization.",
"title": "Contingency (source repository)"
},
{
"downloadURL": "https:\/\/data.nist.gov\/od\/ds\/mds2-4079\/README-contingency.md",
"mediaType": "text\/x-web-markdown",
"title": "README-contingency"
}
],
"bureauCode": [
"006:55"
],
"modified": "2026-03-19 00:00:00",
"publisher": {
"@type": "org:Organization",
"name": "National Institute of Standards and Technology"
},
"theme": [
"Metrology:Metric",
"Mathematics and Statistics:Statistical analysis",
"Mathematics and Statistics:Numerical methods and software",
"Mathematics and Statistics:Experiment design",
"Information Technology:Data and informatics",
"Information Technology:Computational science"
],
"keyword": [
"binary classification",
"classifier",
"machine learning",
"metrics",
"performance",
"experiments",
"accuracy",
"recall",
"precision",
"contingency table",
"marginal counts",
"error",
"type I",
"type II",
"vectorized",
"batched",
"approximation"
]
}
