Cross-Validation

[@davidcanas105]

Excelent video. Wich software do you use in that video? Seems perfect to teach. Greetings from Colombia.

[@OrangeDataMining]

Orange Data Mining, it's also in the video description :)

[@Raffing86]

Good evening. I don't understand why in the Test and Score I get a CA (average over the classes) of 0.335 but if I do the average over all the classes manually I get 0.81.

[@OrangeDataMining]

When Target class is (Average over classes), methods return scores that are weighted averages over all classes. For example, in case of the classifier with 3 classes, scores are computed for class 1 as a target class, class 2 as a target class, and class 3 as a target class. Those scores are averaged with weights based on the class size to retrieve the final score.

[@Raffing86]

​@@OrangeDataMiningthanks In my case we have seven classes. I am creating my own dataset and in the meanwhile testing it. The instances of the dataset are yet a bit.

[@hayderusama668]

please how we can display the all 10 value of cross validation results ?

[@OrangeDataMining]

It is not possible to show AUC and other evaluation scores for each fold. However, you can observe predictions in a Data Table, where there's a column Fold that shows in which fold a given instance was left out (used for testing).

[@hayderusama668]

@@OrangeDataMining thanks alot ,do you have video about that ?