Upload report-Model-1_Queries-2_Prompt-2_Strategies-argmax-threshold0.05-threshold0.25-threshold0.5-threshold0.75-topk9-topk7-topk5-topk3.csv

Reports/report-Model-1_Queries-2_Prompt-2_Strategies-argmax-threshold0.05-threshold0.25-threshold0.5-threshold0.75-topk9-topk7-topk5-topk3.csv

@@ -0,0 +1,189 @@
+argmax_max,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,1,0,0.5,1.0,0.6666666666666666,0.75
+1,1,30,30,6,3,0.2,0.6666666666666666,0.30769230769230765,0.55
+2,2,288,288,179,137,0.6215277777777778,0.5664556962025317,0.5927152317880795,0.5729166666666666
+3,3,87,87,61,31,0.7011494252873564,0.6630434782608695,0.6815642458100558,0.6724137931034483
+4,4,94,94,36,18,0.3829787234042553,0.6666666666666666,0.48648648648648646,0.5957446808510638
+5,5,62,62,16,15,0.25806451612903225,0.5161290322580645,0.3440860215053763,0.5080645161290323
+6,6,63,63,40,0,0.6349206349206349,1.0,0.7766990291262136,0.8174603174603174
+7,7,17,17,6,2,0.35294117647058826,0.75,0.48,0.6176470588235294
+8,8,65,65,14,6,0.2153846153846154,0.7,0.32941176470588235,0.5615384615384615
+9,9,31,31,3,0,0.0967741935483871,1.0,0.17647058823529413,0.5483870967741935
+10,10,57,57,29,11,0.5087719298245614,0.725,0.5979381443298969,0.6578947368421053
+11,11,48,48,4,3,0.08333333333333333,0.5714285714285714,0.14545454545454545,0.5104166666666666
+12,12,36,36,9,3,0.25,0.75,0.375,0.5833333333333334
+13,13,17,17,13,2,0.7647058823529411,0.8666666666666667,0.8125,0.8235294117647058
+14,14,77,77,33,20,0.42857142857142855,0.6226415094339622,0.5076923076923078,0.5844155844155844
+15,15,40,40,18,13,0.45,0.5806451612903226,0.5070422535211268,0.5625
+16,16,29,29,5,1,0.1724137931034483,0.8333333333333334,0.28571428571428575,0.5689655172413793
+17,total,1043,1043,473,265,,,,
+18,,,,,Micro avg.,0.4534995206136146,0.6409214092140921,0.5311622683885457,0.599712368168744
+19,,,,,Macro avg.,0.38950220177108,0.7340398107180973,0.47489022816050147,0.6167781083300287
+threshold-0.05,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,0,1.0,1.0,1.0,1.0
+1,1,30,30,19,12,0.6333333333333333,0.6129032258064516,0.6229508196721313,0.6166666666666667
+2,2,288,288,263,257,0.9131944444444444,0.5057692307692307,0.650990099009901,0.5104166666666666
+3,3,87,87,84,83,0.9655172413793104,0.5029940119760479,0.6614173228346456,0.5057471264367817
+4,4,94,94,71,58,0.7553191489361702,0.5503875968992248,0.6367713004484306,0.5691489361702128
+5,5,62,62,31,36,0.5,0.4626865671641791,0.4806201550387597,0.4596774193548387
+6,6,63,63,52,16,0.8253968253968254,0.7647058823529411,0.7938931297709922,0.7857142857142857
+7,7,17,17,13,6,0.7647058823529411,0.6842105263157895,0.7222222222222222,0.7058823529411765
+8,8,65,65,51,52,0.7846153846153846,0.49514563106796117,0.6071428571428571,0.49230769230769234
+9,9,31,31,19,11,0.6129032258064516,0.6333333333333333,0.6229508196721313,0.6290322580645161
+10,10,57,57,46,35,0.8070175438596491,0.5679012345679012,0.6666666666666666,0.5964912280701754
+11,11,48,48,41,41,0.8541666666666666,0.5,0.6307692307692309,0.5
+12,12,36,36,23,15,0.6388888888888888,0.6052631578947368,0.6216216216216216,0.6111111111111112
+13,13,17,17,15,7,0.8823529411764706,0.6818181818181818,0.7692307692307693,0.7352941176470589
+14,14,77,77,70,51,0.9090909090909091,0.5785123966942148,0.707070707070707,0.6233766233766234
+15,15,40,40,37,34,0.925,0.5211267605633803,0.6666666666666667,0.5375
+16,16,29,29,26,26,0.896551724137931,0.5,0.6419753086419753,0.5
+17,total,1043,1043,863,740,,,,
+18,,,,,Micro avg.,0.8274209012464045,0.5383655645664379,0.6523053665910808,0.5589645254074784
+19,,,,,Macro avg.,0.8040031858873751,0.5980445727778574,0.6766446880282181,0.6104921461486945
+threshold-0.25,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,1,0,0.5,1.0,0.6666666666666666,0.75
+1,1,30,30,14,10,0.4666666666666667,0.5833333333333334,0.5185185185185186,0.5666666666666667
+2,2,288,288,249,235,0.8645833333333334,0.5144628099173554,0.6450777202072538,0.5243055555555556
+3,3,87,87,82,72,0.9425287356321839,0.5324675324675324,0.6804979253112033,0.5574712643678161
+4,4,94,94,56,41,0.5957446808510638,0.5773195876288659,0.5863874345549738,0.5797872340425532
+5,5,62,62,25,28,0.4032258064516129,0.4716981132075472,0.43478260869565216,0.47580645161290325
+6,6,63,63,51,6,0.8095238095238095,0.8947368421052632,0.8500000000000001,0.8571428571428571
+7,7,17,17,9,3,0.5294117647058824,0.75,0.6206896551724139,0.6764705882352942
+8,8,65,65,42,36,0.6461538461538462,0.5384615384615384,0.5874125874125874,0.5461538461538461
+9,9,31,31,13,3,0.41935483870967744,0.8125,0.5531914893617021,0.6612903225806451
+10,10,57,57,40,23,0.7017543859649122,0.6349206349206349,0.6666666666666666,0.6491228070175439
+11,11,48,48,32,25,0.6666666666666666,0.5614035087719298,0.6095238095238096,0.5729166666666666
+12,12,36,36,17,10,0.4722222222222222,0.6296296296296297,0.5396825396825397,0.5972222222222222
+13,13,17,17,15,6,0.8823529411764706,0.7142857142857143,0.7894736842105262,0.7647058823529411
+14,14,77,77,66,42,0.8571428571428571,0.6111111111111112,0.7135135135135134,0.6558441558441559
+15,15,40,40,26,24,0.65,0.52,0.5777777777777778,0.525
+16,16,29,29,21,18,0.7241379310344828,0.5384615384615384,0.6176470588235294,0.5517241379310345
+17,total,1043,1043,759,582,,,,
+18,,,,,Micro avg.,0.7277085330776606,0.5659955257270693,0.636744966442953,0.5848513902205177
+19,,,,,Macro avg.,0.6547923815432758,0.6402818761354113,0.6269123327117254,0.6183312151995706
+threshold-0.5,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,1,0,0.5,1.0,0.6666666666666666,0.75
+1,1,30,30,12,5,0.4,0.7058823529411765,0.5106382978723405,0.6166666666666667
+2,2,288,288,222,193,0.7708333333333334,0.5349397590361445,0.631578947368421,0.5503472222222222
+3,3,87,87,71,51,0.8160919540229885,0.5819672131147541,0.679425837320574,0.6149425287356322
+4,4,94,94,47,35,0.5,0.573170731707317,0.5340909090909091,0.5638297872340425
+5,5,62,62,21,23,0.3387096774193548,0.4772727272727273,0.39622641509433965,0.4838709677419355
+6,6,63,63,48,6,0.7619047619047619,0.8888888888888888,0.8205128205128205,0.8333333333333334
+7,7,17,17,8,3,0.47058823529411764,0.7272727272727273,0.5714285714285714,0.6470588235294118
+8,8,65,65,24,21,0.36923076923076925,0.5333333333333333,0.43636363636363634,0.5230769230769231
+9,9,31,31,4,3,0.12903225806451613,0.5714285714285714,0.2105263157894737,0.5161290322580645
+10,10,57,57,36,19,0.631578947368421,0.6545454545454545,0.6428571428571428,0.6491228070175439
+11,11,48,48,25,15,0.5208333333333334,0.625,0.5681818181818181,0.6041666666666666
+12,12,36,36,15,6,0.4166666666666667,0.7142857142857143,0.5263157894736842,0.625
+13,13,17,17,15,4,0.8823529411764706,0.7894736842105263,0.8333333333333333,0.8235294117647058
+14,14,77,77,57,33,0.7402597402597403,0.6333333333333333,0.6826347305389222,0.6558441558441559
+15,15,40,40,16,16,0.4,0.5,0.4444444444444445,0.5
+16,16,29,29,21,13,0.7241379310344828,0.6176470588235294,0.6666666666666667,0.6379310344827587
+17,total,1043,1043,643,446,,,,
+18,,,,,Micro avg.,0.6164908916586769,0.5904499540863177,0.6031894934333959,0.5944391179290508
+19,,,,,Macro avg.,0.5513070911240563,0.6546142088349527,0.5777583731178685,0.6232264329749448
+threshold-0.75,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,1,0,0.5,1.0,0.6666666666666666,0.75
+1,1,30,30,8,2,0.26666666666666666,0.8,0.4,0.6
+2,2,288,288,180,136,0.625,0.569620253164557,0.5960264900662252,0.5763888888888888
+3,3,87,87,48,19,0.5517241379310345,0.7164179104477612,0.6233766233766233,0.6666666666666666
+4,4,94,94,34,27,0.3617021276595745,0.5573770491803278,0.4387096774193549,0.5372340425531915
+5,5,62,62,17,21,0.27419354838709675,0.4473684210526316,0.33999999999999997,0.46774193548387094
+6,6,63,63,44,2,0.6984126984126984,0.9565217391304348,0.8073394495412843,0.8333333333333334
+7,7,17,17,6,3,0.35294117647058826,0.6666666666666666,0.46153846153846156,0.5882352941176471
+8,8,65,65,12,10,0.18461538461538463,0.5454545454545454,0.27586206896551724,0.5153846153846153
+9,9,31,31,3,1,0.0967741935483871,0.75,0.1714285714285714,0.532258064516129
+10,10,57,57,33,14,0.5789473684210527,0.7021276595744681,0.6346153846153846,0.6666666666666666
+11,11,48,48,16,9,0.3333333333333333,0.64,0.4383561643835616,0.5729166666666666
+12,12,36,36,11,3,0.3055555555555556,0.7857142857142857,0.43999999999999995,0.6111111111111112
+13,13,17,17,14,3,0.8235294117647058,0.8235294117647058,0.8235294117647058,0.8235294117647058
+14,14,77,77,40,15,0.5194805194805194,0.7272727272727273,0.6060606060606061,0.6623376623376623
+15,15,40,40,8,7,0.2,0.5333333333333333,0.2909090909090909,0.5125
+16,16,29,29,15,5,0.5172413793103449,0.75,0.6122448979591838,0.6724137931034483
+17,total,1043,1043,490,277,,,,
+18,,,,,Micro avg.,0.4697986577181208,0.6388526727509778,0.5414364640883977,0.6021093000958773
+19,,,,,Macro avg.,0.42294808832687897,0.7042002354562615,0.5074507979232492,0.6228657736820356
+topk-9,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,0,1.0,1.0,1.0,1.0
+1,1,30,30,23,14,0.7666666666666667,0.6216216216216216,0.6865671641791045,0.65
+2,2,288,288,279,276,0.96875,0.5027027027027027,0.6619217081850534,0.5052083333333334
+3,3,87,87,84,86,0.9655172413793104,0.49411764705882355,0.6536964980544747,0.4885057471264368
+4,4,94,94,75,81,0.7978723404255319,0.4807692307692308,0.6,0.46808510638297873
+5,5,62,62,29,37,0.46774193548387094,0.4393939393939394,0.453125,0.43548387096774194
+6,6,63,63,56,23,0.8888888888888888,0.7088607594936709,0.7887323943661971,0.7619047619047619
+7,7,17,17,14,10,0.8235294117647058,0.5833333333333334,0.6829268292682927,0.6176470588235294
+8,8,65,65,55,54,0.8461538461538461,0.5045871559633027,0.632183908045977,0.5076923076923077
+9,9,31,31,22,16,0.7096774193548387,0.5789473684210527,0.6376811594202899,0.5967741935483871
+10,10,57,57,49,40,0.8596491228070176,0.550561797752809,0.6712328767123288,0.5789473684210527
+11,11,48,48,44,44,0.9166666666666666,0.5,0.6470588235294118,0.5
+12,12,36,36,28,18,0.7777777777777778,0.6086956521739131,0.6829268292682927,0.6388888888888888
+13,13,17,17,17,9,1.0,0.6538461538461539,0.7906976744186047,0.7352941176470589
+14,14,77,77,72,57,0.935064935064935,0.5581395348837209,0.6990291262135921,0.5974025974025974
+15,15,40,40,40,39,1.0,0.5063291139240507,0.6722689075630253,0.5125
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,918,833,,,,
+18,,,,,Micro avg.,0.8801534036433365,0.5242718446601942,0.6571224051539012,0.5407478427612655
+19,,,,,Macro avg.,0.8661150736725914,0.5759944712551954,0.68392444505243,0.5937843736552396
+topk-7,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,0,1.0,1.0,1.0,1.0
+1,1,30,30,19,13,0.6333333333333333,0.59375,0.6129032258064516,0.6
+2,2,288,288,272,266,0.9444444444444444,0.5055762081784386,0.658595641646489,0.5104166666666666
+3,3,87,87,83,86,0.9540229885057471,0.4911242603550296,0.6484375,0.4827586206896552
+4,4,94,94,69,71,0.7340425531914894,0.4928571428571429,0.5897435897435898,0.48936170212765956
+5,5,62,62,25,30,0.4032258064516129,0.45454545454545453,0.42735042735042733,0.4596774193548387
+6,6,63,63,55,16,0.873015873015873,0.7746478873239436,0.8208955223880596,0.8095238095238095
+7,7,17,17,13,7,0.7647058823529411,0.65,0.7027027027027027,0.6764705882352942
+8,8,65,65,50,51,0.7692307692307693,0.49504950495049505,0.6024096385542169,0.49230769230769234
+9,9,31,31,19,9,0.6129032258064516,0.6785714285714286,0.6440677966101694,0.6612903225806451
+10,10,57,57,44,37,0.7719298245614035,0.5432098765432098,0.6376811594202898,0.5614035087719298
+11,11,48,48,39,34,0.8125,0.5342465753424658,0.6446280991735538,0.5520833333333334
+12,12,36,36,23,10,0.6388888888888888,0.696969696969697,0.6666666666666666,0.6805555555555556
+13,13,17,17,17,7,1.0,0.7083333333333334,0.8292682926829268,0.7941176470588235
+14,14,77,77,70,46,0.9090909090909091,0.603448275862069,0.7253886010362693,0.6558441558441559
+15,15,40,40,40,38,1.0,0.5128205128205128,0.6779661016949152,0.525
+16,16,29,29,29,28,1.0,0.5087719298245614,0.6744186046511628,0.5172413793103449
+17,total,1043,1043,869,749,,,,
+18,,,,,Micro avg.,0.8331735378715245,0.5370828182941904,0.6531379180759113,0.5575263662511984
+19,,,,,Macro avg.,0.8130196764043449,0.6025836522045755,0.6801837394192877,0.6157677883153179
+topk-5,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,0,1.0,1.0,1.0,1.0
+1,1,30,30,15,10,0.5,0.6,0.5454545454545454,0.5833333333333334
+2,2,288,288,263,251,0.9131944444444444,0.5116731517509727,0.655860349127182,0.5208333333333334
+3,3,87,87,82,81,0.9425287356321839,0.5030674846625767,0.6559999999999999,0.5057471264367817
+4,4,94,94,63,60,0.6702127659574468,0.5121951219512195,0.5806451612903226,0.5159574468085106
+5,5,62,62,22,25,0.3548387096774194,0.46808510638297873,0.4036697247706422,0.47580645161290325
+6,6,63,63,50,8,0.7936507936507936,0.8620689655172413,0.8264462809917354,0.8333333333333334
+7,7,17,17,12,5,0.7058823529411765,0.7058823529411765,0.7058823529411765,0.7058823529411765
+8,8,65,65,47,41,0.7230769230769231,0.5340909090909091,0.6143790849673202,0.5461538461538461
+9,9,31,31,14,7,0.45161290322580644,0.6666666666666666,0.5384615384615384,0.6129032258064516
+10,10,57,57,39,29,0.6842105263157895,0.5735294117647058,0.6239999999999999,0.5877192982456141
+11,11,48,48,29,24,0.6041666666666666,0.5471698113207547,0.5742574257425742,0.5520833333333334
+12,12,36,36,18,9,0.5,0.6666666666666666,0.5714285714285715,0.625
+13,13,17,17,16,6,0.9411764705882353,0.7272727272727273,0.8205128205128205,0.7941176470588235
+14,14,77,77,67,41,0.8701298701298701,0.6203703703703703,0.7243243243243243,0.6688311688311688
+15,15,40,40,40,37,1.0,0.5194805194805194,0.6837606837606837,0.5375
+16,16,29,29,28,24,0.9655172413793104,0.5384615384615384,0.691358024691358,0.5689655172413793
+17,total,1043,1043,807,658,,,,
+18,,,,,Micro avg.,0.7737296260786194,0.5508532423208191,0.6435406698564594,0.5714285714285714
+19,,,,,Macro avg.,0.7423646119815333,0.620981223782413,0.659790640497929,0.6255392596747051
+topk-3,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,1,0,0.5,1.0,0.6666666666666666,0.75
+1,1,30,30,13,5,0.43333333333333335,0.7222222222222222,0.5416666666666666,0.6333333333333333
+2,2,288,288,247,213,0.8576388888888888,0.5369565217391304,0.660427807486631,0.5590277777777778
+3,3,87,87,77,66,0.8850574712643678,0.5384615384615384,0.6695652173913044,0.5632183908045977
+4,4,94,94,56,43,0.5957446808510638,0.5656565656565656,0.5803108808290155,0.5691489361702128
+5,5,62,62,19,23,0.3064516129032258,0.4523809523809524,0.36538461538461536,0.46774193548387094
+6,6,63,63,46,3,0.7301587301587301,0.9387755102040817,0.8214285714285714,0.8412698412698413
+7,7,17,17,9,4,0.5294117647058824,0.6923076923076923,0.5999999999999999,0.6470588235294118
+8,8,65,65,29,27,0.4461538461538462,0.5178571428571429,0.4793388429752066,0.5153846153846153
+9,9,31,31,11,4,0.3548387096774194,0.7333333333333333,0.47826086956521735,0.6129032258064516
+10,10,57,57,35,22,0.6140350877192983,0.6140350877192983,0.6140350877192983,0.6140350877192983
+11,11,48,48,18,16,0.375,0.5294117647058824,0.4390243902439025,0.5208333333333334
+12,12,36,36,12,5,0.3333333333333333,0.7058823529411765,0.45283018867924524,0.5972222222222222
+13,13,17,17,16,5,0.9411764705882353,0.7619047619047619,0.8421052631578947,0.8235294117647058
+14,14,77,77,59,35,0.7662337662337663,0.6276595744680851,0.6900584795321637,0.6558441558441559
+15,15,40,40,35,30,0.875,0.5384615384615384,0.6666666666666667,0.5625
+16,16,29,29,22,15,0.7586206896551724,0.5945945945945946,0.6666666666666667,0.6206896551724138
+17,total,1043,1043,705,516,,,,
+18,,,,,Micro avg.,0.675934803451582,0.5773955773955773,0.622791519434629,0.5906040268456376
+19,,,,,Macro avg.,0.6060110814980331,0.6511706561151763,0.6020256988858665,0.6208082791538966