Binary Classification Metrics
Enter true positive, false positive, false negative and true negative times, and calculate the commonly used evaluation indicators for classification models.
Binary Classification Metrics User manual
- Fill in the parameters or select the file according to the form, and check the unit and format first.
- When TP is 40, FP is 10, Fn is 5, and TN is 45, the error type reflected by different indicators is compared.
- Click the processing button to view the results, you can copy or download and save.
Calculation method and processing rules
The accuracy, precision, recall, specificity, F1 and Matthews correlation coefficients are calculated from the four grid counts.
scope of use
Count 0 to 1 million, at least one sample; the zero denominator indicator is undefined, and the missing indicator is not marked as zero, and there is no substitution for the evaluation of the independent test set.
Will the input content be saved on the server?
This tool handles input in the browser, and does not upload files or form content. Typing practice scores are only saved in the native browser.
Why may the result be different from other tools?
Count 0 to 1 million, at least one sample; the zero denominator indicator is undefined, and the missing indicator is not marked as zero, and there is no substitution for the evaluation of the independent test set. Please compare the input unit, rounding method, applicable rules and data version first.