Timeline for high precision and recall but low cross validated accuracy
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 4, 2017 at 5:55 | comment | added | Elliot |
Yes ! You can normally use Y_pred = cross_val_predict(clf, Y, cv=5, method='predict_proba')
|
|
| Dec 4, 2017 at 5:52 | comment | added | physics_2015 | OK, thanks! By the way, how would one get the predicted probabilities using the same scheme? cross_val_predict gives the class prediction through some cross validation. Is there a corresponding way to get the class probabilities? | |
| Dec 4, 2017 at 5:34 | history | edited | Elliot | CC BY-SA 3.0 |
added 273 characters in body
|
| Dec 4, 2017 at 3:44 | history | answered | Elliot | CC BY-SA 3.0 |