Courbes ROC et quiz AUC

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Ban ñaari limu courbe ROC di tracé seen biir?
   • Taux Positif Dëgg ak Taux Positif Njuumte
   • Precision ak fàttaliku
   • Jaar-jaar vs.
   • Sensitivite ak. Njàngale
2. Ban valeur AUC moo méngoo ak classificateur bi gënawul def ludul guessing random?
   • 0.0
   • 0.5
   • 0.75
   • 1.0
3. AUC mën nañu ko tekki ni probabilite bi model bi:
   • Xaajale ci anam wu jaar yoon misaal buñ tànnee ci anam wu mucc
   • Defna lu ëpp 90% ci dëggu
   • Njortu ab positif bu bari poñ moo gëna rëy ab negatif bu bari
   • Amul benn njuumte bu baax
4. Lu tax ñuy wax AUC ni 'moom boppam ci threshold'?
   • Du dox ludul ci 0.5
   • Dafay baña bàyyi xel ci klaas bu baax bi
   • Dafay laaj probabilite yuñ kalibre
   • Dafay boole performance ci bépp threshold bu mëna am
5. Ngir dataset bu desekilibre bu baax, ban courbe lañuy faral di digal ñu boole ci wala ci palaasu ROC ndax ROC mën na nuru lu ëpp yaakaar?
   • Courbe de précision
   • courbe d'apprentissage
   • Courbe d'étalonnage
   • courbe de perte
6. Benn poñ ci koñu cammoy bi ci kaw ci espace ROC mooy:
   • Njuumteg positive yu bari ak positive dëgg yu néew
   • Tàqale bu jaar yoon wala bu jege jaar yoon
   • Performance aleatoire
   • Modèle buñu kalibrewul
7. Why can a model have a high ROC-AUC but poorly calibrated probability estimates?
   • AUC directly measures the distance between every predicted probability and its true label
   • Calibration is guaranteed whenever the ROC curve is above the diagonal
   • AUC depends on score ranking, so a monotonic score transformation can preserve ranking while changing probability values
   • AUC uses only one fixed classification threshold
8. What does partial AUC let an evaluator emphasize?
   • Only the model's training loss
   • Probability calibration across all score values
   • The number of labels in a multiclass model
   • Performance in a selected false-positive-rate region, such as the low-FPR range