Hi,
The idea was that you could automatically evaluate your models if you implemented the Evalable interface. These were in the code I inherited 5 years ago and I haven't deleted them nor used them in that time. Evaluation tends to be pretty specific to a task so I haven't tried to make any automatic evaluation at the model level other than the reporting that happens when you train a model. Hope this helps...Tom
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Thanks for the help. Would you mind to give me a simple demo about how to use the TrainEval class and the interface Evalable. I don't know how to implement the method getNegativeOutcome() for the Evalable interface (binary decision). I saw an example on the web where they always returned "F". Thanks in advance.
Predict output:
For context: U_nacal |U|0_5 |U|1_3 |U|all_2
+class[0.7181] -class[0.2819]
/**
* The outcome that should be considered a negative result. This is used
* for computing recall. In the case of binary decisions, this would be
* the false one.
*
* @return the events that this EventCollector has gathered
*/
public String getNegativeOutcome();
Regards,
MyD
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi @ all,
Would you mind to let me know how the class traineval and the interface evalable has to be used? Thanks in advance.
Regards,
MyD
Hi,
The idea was that you could automatically evaluate your models if you implemented the Evalable interface. These were in the code I inherited 5 years ago and I haven't deleted them nor used them in that time. Evaluation tends to be pretty specific to a task so I haven't tried to make any automatic evaluation at the model level other than the reporting that happens when you train a model. Hope this helps...Tom
Hi Tom,
Thanks for the help. Would you mind to give me a simple demo about how to use the TrainEval class and the interface Evalable. I don't know how to implement the method getNegativeOutcome() for the Evalable interface (binary decision). I saw an example on the web where they always returned "F". Thanks in advance.
Predict output:
For context: U_nacal |U|0_5 |U|1_3 |U|all_2
+class[0.7181] -class[0.2819]
/**
* The outcome that should be considered a negative result. This is used
* for computing recall. In the case of binary decisions, this would be
* the false one.
*
* @return the events that this EventCollector has gathered
*/
public String getNegativeOutcome();
Regards,
MyD