Performance Vectors (and Confusion Matrix)
Hello everyone,
I have a process in which I train a classifier and test its performance afterwards. My example set has a binominal label and when I output the data generated by the binominal performance evaluator I get a nice view with information about (in this case) accuracy, precision and recall.
My problem is that the wrong label value is treated as positive class so is there an easy way to change that? Or is there an easy way to access the elements of the confusion matrix?
I have a process in which I train a classifier and test its performance afterwards. My example set has a binominal label and when I output the data generated by the binominal performance evaluator I get a nice view with information about (in this case) accuracy, precision and recall.
My problem is that the wrong label value is treated as positive class so is there an easy way to change that? Or is there an easy way to access the elements of the confusion matrix?
Find more posts tagged with
Sort by:
1 - 2 of
21
First of all, thanks for your advice.
I also noticed that I can read the desired sample counts from the Performance Vector if I set the right flags in the Performance Evaluator Operator beforehand.
I also noticed that I can read the desired sample counts from the Performance Vector if I set the right flags in the Performance Evaluator Operator beforehand.
just use the remap binominals operator to define which value should be positive and which should be treated as negative.
Greetings,
Sebastian