The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
"How to easily compute Percentage of Predictions PRED(25) from Cross Validation?"
Contributor II
Dear all,
I need to compute a regression performance measure named "percentage of predictions within 25%" or known as PRED(25). Basically, it requires the predicted values from the whole test set we use in the experiment. The whole procedure to compute PRED(25) as follows:
r = | actualValue - predictedValue |
Pred(25) = count the number of (r / actualValue) which are less than 25% and divide the result by the number of instances
I know that there is possibility to extend a Performance node in RapidMiner, but I think it is not easy for beginner.
In RapidMiner, if I use cross validation, I can only get the test set from last iteration. However, to compute PRED(25), I need the whole test set from each iteration. Is there any way to get the whole test set from a cross validation?
Thanks in advance.
Cheers,
Ikhwan
I need to compute a regression performance measure named "percentage of predictions within 25%" or known as PRED(25). Basically, it requires the predicted values from the whole test set we use in the experiment. The whole procedure to compute PRED(25) as follows:
r = | actualValue - predictedValue |
Pred(25) = count the number of (r / actualValue) which are less than 25% and divide the result by the number of instances
I know that there is possibility to extend a Performance node in RapidMiner, but I think it is not easy for beginner.
In RapidMiner, if I use cross validation, I can only get the test set from last iteration. However, to compute PRED(25), I need the whole test set from each iteration. Is there any way to get the whole test set from a cross validation?
Thanks in advance.
Cheers,
Ikhwan
Tagged:
0
