Project

Namespaces

Public Vars

confuse.multi-class-metrics

macro-avg-fmeasure
(macro-avg-fmeasure actual predicted)(macro-avg-fmeasure actual predicted classes)
returns the macro averaged fmeasure, defined as mean of F-measure for each class.
See Section 4.2 in this paper: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.104.8244&rep=rep1&type=pdf
macro-avg-precision
(macro-avg-precision actual predicted)(macro-avg-precision actual predicted classes)
returns the macro averaged precision, defined as the mean of precision for each class

macro-avg-recall
(macro-avg-recall actual predicted)(macro-avg-recall actual predicted classes)
returns the macro averaged recall, defined as the mean of recall for each class

micro-avg-fmeasure
(micro-avg-fmeasure actual predicted)(micro-avg-fmeasure actual predicted classes)
returns the micro averaged fmeasure, defined as harmonic mean of precision and recall, where precision and recall are calculated by summing over all classes.
See Section 4.2 in this paper: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.104.8244&rep=rep1&type=pdf
micro-avg-precision
(micro-avg-precision actual predicted)(micro-avg-precision actual predicted classes)
returns the micro averaged precision, defined as the sum of true positives for all classes,
divided by the sum of true positives and false positives for all classes.
micro-avg-recall
(micro-avg-recall actual predicted)(micro-avg-recall actual predicted classes)
returns the micro averaged recall, defined as the sum of true positives for all classes,
divided by the sum of true positives and false negatives for all classes