list of topN values (used as keys for the count maps)
list of threshold values (correspond to thresholds at the indices of the arrays in the count maps)
map from topN value to an array of counts of correct classifications at each threshold
map from topN value to an array of counts of incorrect classifications at each threshold
map from topN value to an array of counts of no prediction at each threshold
map from topN value to an array of counts of correct classifications at each threshold
map from topN value to an array of counts of incorrect classifications at each threshold
map from topN value to an array of counts of no prediction at each threshold
list of threshold values (correspond to thresholds at the indices of the arrays in the count maps)
Write this instance to json string
Write this instance to json string
should pretty print
json string of the instance
Convert metrics class to a map
Convert metrics class to a map
a map from metric name to metric value
Convert metrics into Metadata for saving
Convert metrics into Metadata for saving
skip unsupported values
Metadata metadata
RuntimeException
in case of unsupported value type
This instance json string
This instance json string
json string of the instance
list of topN values (used as keys for the count maps)
Threshold-based metrics for multiclass classification
Classifications being correct, incorrect, or no classification are defined in terms of the topN and score threshold to be: Correct - score of the true label is in the top N scores AND the score of the true label is >= threshold Incorrect - score of top predicted label >= threshold AND (true label NOT in top N predicted labels OR score of true label < threshold) No prediction - otherwise (score of top predicted label < threshold)
list of topN values (used as keys for the count maps)
list of threshold values (correspond to thresholds at the indices of the arrays in the count maps)
map from topN value to an array of counts of correct classifications at each threshold
map from topN value to an array of counts of incorrect classifications at each threshold
map from topN value to an array of counts of no prediction at each threshold