Upload report-Model-1_Queries-0_Prompt-0_Strategies-argmax-threshold0.05-threshold0.25-threshold0.5-threshold0.75-topk9-topk7-topk5-topk3.csv

Reports/report-Model-1_Queries-0_Prompt-0_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
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,48,25,0.16666666666666666,0.6575342465753424,0.2659279778393352,0.5399305555555556
+3,3,87,87,20,10,0.22988505747126436,0.6666666666666666,0.34188034188034183,0.5574712643678161
+4,4,94,94,10,3,0.10638297872340426,0.7692307692307693,0.18691588785046728,0.5372340425531915
+5,5,62,62,2,2,0.03225806451612903,0.5,0.06060606060606061,0.5
+6,6,63,63,7,0,0.1111111111111111,1.0,0.19999999999999998,0.5555555555555556
+7,7,17,17,6,1,0.35294117647058826,0.8571428571428571,0.5,0.6470588235294118
+8,8,65,65,4,9,0.06153846153846154,0.3076923076923077,0.10256410256410257,0.46153846153846156
+9,9,31,31,8,1,0.25806451612903225,0.8888888888888888,0.39999999999999997,0.6129032258064516
+10,10,57,57,10,6,0.17543859649122806,0.625,0.273972602739726,0.5350877192982456
+11,11,48,48,9,3,0.1875,0.75,0.3,0.5625
+12,12,36,36,4,3,0.1111111111111111,0.5714285714285714,0.18604651162790697,0.5138888888888888
+13,13,17,17,6,6,0.35294117647058826,0.5,0.41379310344827586,0.5
+14,14,77,77,3,3,0.03896103896103896,0.5,0.07228915662650602,0.5
+15,15,40,40,1,1,0.025,0.5,0.047619047619047616,0.5
+16,16,29,29,23,24,0.7931034482758621,0.48936170212765956,0.6052631578947368,0.4827586206896552
+17,total,1043,1043,161,97,,,,
+18,,,,,Micro avg.,0.15436241610738255,0.624031007751938,0.24750192159877019,0.5306807286673059
+19,,,,,Macro avg.,0.17664137670214622,0.5637027064560625,0.23275752651155918,0.5297604210460726
+threshold-0.05,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,2,0,0.06666666666666667,1.0,0.125,0.5333333333333333
+2,2,288,288,159,155,0.5520833333333334,0.5063694267515924,0.5282392026578074,0.5069444444444444
+3,3,87,87,76,57,0.8735632183908046,0.5714285714285714,0.6909090909090909,0.6091954022988506
+4,4,94,94,34,23,0.3617021276595745,0.5964912280701754,0.4503311258278146,0.5585106382978723
+5,5,62,62,13,14,0.20967741935483872,0.48148148148148145,0.29213483146067415,0.49193548387096775
+6,6,63,63,51,17,0.8095238095238095,0.75,0.7786259541984734,0.7698412698412699
+7,7,17,17,12,10,0.7058823529411765,0.5454545454545454,0.6153846153846153,0.5588235294117647
+8,8,65,65,50,45,0.7692307692307693,0.5263157894736842,0.625,0.5384615384615384
+9,9,31,31,27,29,0.8709677419354839,0.48214285714285715,0.6206896551724138,0.46774193548387094
+10,10,57,57,47,33,0.8245614035087719,0.5875,0.6861313868613139,0.6228070175438597
+11,11,48,48,44,38,0.9166666666666666,0.5365853658536586,0.676923076923077,0.5625
+12,12,36,36,31,32,0.8611111111111112,0.49206349206349204,0.6262626262626263,0.4861111111111111
+13,13,17,17,15,12,0.8823529411764706,0.5555555555555556,0.6818181818181819,0.5882352941176471
+14,14,77,77,54,37,0.7012987012987013,0.5934065934065934,0.6428571428571428,0.6103896103896104
+15,15,40,40,6,16,0.15,0.2727272727272727,0.19354838709677416,0.375
+16,16,29,29,29,28,1.0,0.5087719298245614,0.6744186046511628,0.5172413793103449
+17,total,1043,1043,650,546,,,,
+18,,,,,Micro avg.,0.62320230105465,0.5434782608695652,0.5806163465832962,0.549856184084372
+19,,,,,Macro avg.,0.6208993095763635,0.5297820064255319,0.524016110710657,0.546886587524499
+threshold-0.25,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,119,115,0.4131944444444444,0.5085470085470085,0.4559386973180076,0.5069444444444444
+3,3,87,87,69,46,0.7931034482758621,0.6,0.6831683168316831,0.632183908045977
+4,4,94,94,26,7,0.2765957446808511,0.7878787878787878,0.4094488188976378,0.601063829787234
+5,5,62,62,8,7,0.12903225806451613,0.5333333333333333,0.2077922077922078,0.5080645161290323
+6,6,63,63,46,8,0.7301587301587301,0.8518518518518519,0.7863247863247863,0.8015873015873016
+7,7,17,17,12,6,0.7058823529411765,0.6666666666666666,0.6857142857142857,0.6764705882352942
+8,8,65,65,35,37,0.5384615384615384,0.4861111111111111,0.510948905109489,0.4846153846153846
+9,9,31,31,13,14,0.41935483870967744,0.48148148148148145,0.4482758620689655,0.4838709677419355
+10,10,57,57,34,25,0.5964912280701754,0.576271186440678,0.5862068965517242,0.5789473684210527
+11,11,48,48,38,26,0.7916666666666666,0.59375,0.6785714285714286,0.625
+12,12,36,36,24,22,0.6666666666666666,0.5217391304347826,0.5853658536585366,0.5277777777777778
+13,13,17,17,11,8,0.6470588235294118,0.5789473684210527,0.6111111111111113,0.5882352941176471
+14,14,77,77,27,17,0.35064935064935066,0.6136363636363636,0.4462809917355372,0.564935064935065
+15,15,40,40,3,10,0.075,0.23076923076923078,0.11320754716981132,0.4125
+16,16,29,29,29,27,1.0,0.5178571428571429,0.6823529411764707,0.5344827586206896
+17,total,1043,1043,494,375,,,,
+18,,,,,Micro avg.,0.473633748801534,0.5684695051783659,0.5167364016736401,0.5570469798657718
+19,,,,,Macro avg.,0.4784303583128865,0.5028729802017347,0.46415933235480494,0.5603928943799316
+threshold-0.5,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,89,70,0.3090277777777778,0.559748427672956,0.3982102908277405,0.5329861111111112
+3,3,87,87,62,37,0.7126436781609196,0.6262626262626263,0.6666666666666667,0.6436781609195402
+4,4,94,94,16,2,0.1702127659574468,0.8888888888888888,0.2857142857142857,0.574468085106383
+5,5,62,62,6,7,0.0967741935483871,0.46153846153846156,0.15999999999999998,0.49193548387096775
+6,6,63,63,31,4,0.49206349206349204,0.8857142857142857,0.6326530612244897,0.7142857142857143
+7,7,17,17,8,3,0.47058823529411764,0.7272727272727273,0.5714285714285714,0.6470588235294118
+8,8,65,65,25,24,0.38461538461538464,0.5102040816326531,0.43859649122807015,0.5076923076923077
+9,9,31,31,6,4,0.1935483870967742,0.6,0.2926829268292683,0.532258064516129
+10,10,57,57,26,13,0.45614035087719296,0.6666666666666666,0.5416666666666666,0.6140350877192983
+11,11,48,48,30,19,0.625,0.6122448979591837,0.6185567010309279,0.6145833333333334
+12,12,36,36,12,9,0.3333333333333333,0.5714285714285714,0.4210526315789474,0.5416666666666666
+13,13,17,17,7,7,0.4117647058823529,0.5,0.45161290322580644,0.5
+14,14,77,77,11,5,0.14285714285714285,0.6875,0.23655913978494625,0.538961038961039
+15,15,40,40,1,5,0.025,0.16666666666666666,0.04347826086956522,0.45
+16,16,29,29,26,25,0.896551724137931,0.5098039215686274,0.65,0.5172413793103449
+17,total,1043,1043,356,234,,,,
+18,,,,,Micro avg.,0.34132310642377756,0.6033898305084746,0.4360073484384568,0.5584851390220518
+19,,,,,Macro avg.,0.33647771597660314,0.5278788366630773,0.37699285865152665,0.5541676621777792
+threshold-0.75,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,51,25,0.17708333333333334,0.6710526315789473,0.2802197802197802,0.5451388888888888
+3,3,87,87,24,20,0.27586206896551724,0.5454545454545454,0.36641221374045796,0.5229885057471264
+4,4,94,94,10,2,0.10638297872340426,0.8333333333333334,0.18867924528301885,0.5425531914893617
+5,5,62,62,5,3,0.08064516129032258,0.625,0.14285714285714285,0.5161290322580645
+6,6,63,63,16,1,0.25396825396825395,0.9411764705882353,0.39999999999999997,0.6190476190476191
+7,7,17,17,3,1,0.17647058823529413,0.75,0.2857142857142857,0.5588235294117647
+8,8,65,65,13,13,0.2,0.5,0.28571428571428575,0.5
+9,9,31,31,2,3,0.06451612903225806,0.4,0.1111111111111111,0.4838709677419355
+10,10,57,57,16,7,0.2807017543859649,0.6956521739130435,0.39999999999999997,0.5789473684210527
+11,11,48,48,13,3,0.2708333333333333,0.8125,0.40625,0.6041666666666666
+12,12,36,36,5,4,0.1388888888888889,0.5555555555555556,0.22222222222222227,0.5138888888888888
+13,13,17,17,2,4,0.11764705882352941,0.3333333333333333,0.1739130434782609,0.4411764705882353
+14,14,77,77,4,0,0.05194805194805195,1.0,0.09876543209876544,0.525974025974026
+15,15,40,40,1,2,0.025,0.3333333333333333,0.046511627906976744,0.4875
+16,16,29,29,22,21,0.7586206896551724,0.5116279069767442,0.6111111111111112,0.5172413793103449
+17,total,1043,1043,187,109,,,,
+18,,,,,Micro avg.,0.17929050814956854,0.6317567567567568,0.2793129200896191,0.537392138063279
+19,,,,,Macro avg.,0.17520989944607793,0.5592952520039454,0.23644008832102462,0.5269086196725868
+topk-9,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,1,0.0,0.0,0.0,0.25
+1,1,30,30,4,0,0.13333333333333333,1.0,0.23529411764705882,0.5666666666666667
+2,2,288,288,207,193,0.71875,0.5175,0.6017441860465116,0.5243055555555556
+3,3,87,87,82,68,0.9425287356321839,0.5466666666666666,0.6919831223628692,0.5804597701149425
+4,4,94,94,58,45,0.6170212765957447,0.5631067961165048,0.5888324873096447,0.5691489361702128
+5,5,62,62,15,11,0.24193548387096775,0.5769230769230769,0.3409090909090909,0.532258064516129
+6,6,63,63,53,24,0.8412698412698413,0.6883116883116883,0.7571428571428571,0.7301587301587301
+7,7,17,17,17,12,1.0,0.5862068965517241,0.7391304347826086,0.6470588235294118
+8,8,65,65,54,49,0.8307692307692308,0.5242718446601942,0.6428571428571429,0.5384615384615384
+9,9,31,31,31,31,1.0,0.5,0.6666666666666666,0.5
+10,10,57,57,49,43,0.8596491228070176,0.532608695652174,0.6577181208053693,0.5526315789473685
+11,11,48,48,43,39,0.8958333333333334,0.524390243902439,0.6615384615384615,0.5416666666666666
+12,12,36,36,35,35,0.9722222222222222,0.5,0.660377358490566,0.5
+13,13,17,17,16,11,0.9411764705882353,0.5925925925925926,0.7272727272727272,0.6470588235294118
+14,14,77,77,66,44,0.8571428571428571,0.6,0.7058823529411764,0.6428571428571429
+15,15,40,40,18,17,0.45,0.5142857142857142,0.48,0.5125
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,777,652,,,,
+18,,,,,Micro avg.,0.7449664429530202,0.5437368789363191,0.6286407766990292,0.5599232981783318
+19,,,,,Macro avg.,0.7236254063273511,0.5451096597448691,0.5778832819670247,0.5491313115984574
+topk-7,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,177,173,0.6145833333333334,0.5057142857142857,0.554858934169279,0.5069444444444444
+3,3,87,87,80,64,0.9195402298850575,0.5555555555555556,0.6926406926406926,0.5919540229885057
+4,4,94,94,50,35,0.5319148936170213,0.5882352941176471,0.5586592178770949,0.5797872340425532
+5,5,62,62,9,9,0.14516129032258066,0.5,0.22500000000000003,0.5
+6,6,63,63,52,14,0.8253968253968254,0.7878787878787878,0.8062015503875969,0.8015873015873016
+7,7,17,17,13,9,0.7647058823529411,0.5909090909090909,0.6666666666666667,0.6176470588235294
+8,8,65,65,49,43,0.7538461538461538,0.532608695652174,0.624203821656051,0.5461538461538461
+9,9,31,31,30,29,0.967741935483871,0.5084745762711864,0.6666666666666666,0.5161290322580645
+10,10,57,57,44,38,0.7719298245614035,0.5365853658536586,0.6330935251798562,0.5526315789473685
+11,11,48,48,38,32,0.7916666666666666,0.5428571428571428,0.6440677966101694,0.5625
+12,12,36,36,33,31,0.9166666666666666,0.515625,0.66,0.5277777777777778
+13,13,17,17,16,10,0.9411764705882353,0.6153846153846154,0.744186046511628,0.6764705882352942
+14,14,77,77,59,37,0.7662337662337663,0.6145833333333334,0.6820809248554913,0.6428571428571429
+15,15,40,40,13,16,0.325,0.4482758620689655,0.3768115942028986,0.4625
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,692,569,,,,
+18,,,,,Micro avg.,0.663470757430489,0.548770816812054,0.6006944444444445,0.5589645254074784
+19,,,,,Macro avg.,0.6491508199385012,0.49074632974096716,0.5412825943582799,0.5638200016538722
+topk-5,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,151,144,0.5243055555555556,0.511864406779661,0.5180102915951973,0.5121527777777778
+3,3,87,87,75,56,0.8620689655172413,0.5725190839694656,0.6880733944954128,0.6091954022988506
+4,4,94,94,34,14,0.3617021276595745,0.7083333333333334,0.4788732394366197,0.6063829787234043
+5,5,62,62,7,8,0.11290322580645161,0.4666666666666667,0.18181818181818182,0.49193548387096775
+6,6,63,63,39,8,0.6190476190476191,0.8297872340425532,0.7090909090909091,0.746031746031746
+7,7,17,17,11,9,0.6470588235294118,0.55,0.5945945945945946,0.5588235294117647
+8,8,65,65,33,38,0.5076923076923077,0.4647887323943662,0.48529411764705876,0.46153846153846156
+9,9,31,31,28,25,0.9032258064516129,0.5283018867924528,0.6666666666666666,0.5483870967741935
+10,10,57,57,40,31,0.7017543859649122,0.5633802816901409,0.625,0.5789473684210527
+11,11,48,48,35,26,0.7291666666666666,0.5737704918032787,0.6422018348623854,0.59375
+12,12,36,36,30,26,0.8333333333333334,0.5357142857142857,0.6521739130434783,0.5555555555555556
+13,13,17,17,16,8,0.9411764705882353,0.6666666666666666,0.7804878048780487,0.7352941176470589
+14,14,77,77,42,23,0.5454545454545454,0.6461538461538462,0.5915492957746479,0.6233766233766234
+15,15,40,40,10,14,0.25,0.4166666666666667,0.3125,0.45
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,580,459,,,,
+18,,,,,Micro avg.,0.5560882070949185,0.5582290664100096,0.5571565802113352,0.5580057526366251
+19,,,,,Macro avg.,0.5611111666627921,0.5020360930984343,0.5054706417982275,0.5630218318486738
+topk-3,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,119,97,0.4131944444444444,0.5509259259259259,0.4722222222222222,0.5381944444444444
+3,3,87,87,70,48,0.8045977011494253,0.5932203389830508,0.6829268292682927,0.6264367816091954
+4,4,94,94,24,7,0.2553191489361702,0.7741935483870968,0.384,0.5904255319148937
+5,5,62,62,3,6,0.04838709677419355,0.3333333333333333,0.08450704225352113,0.47580645161290325
+6,6,63,63,20,3,0.31746031746031744,0.8695652173913043,0.46511627906976744,0.6349206349206349
+7,7,17,17,10,6,0.5882352941176471,0.625,0.6060606060606061,0.6176470588235294
+8,8,65,65,25,22,0.38461538461538464,0.5319148936170213,0.44642857142857145,0.5230769230769231
+9,9,31,31,21,16,0.6774193548387096,0.5675675675675675,0.6176470588235294,0.5806451612903226
+10,10,57,57,29,21,0.5087719298245614,0.58,0.5420560747663552,0.5701754385964912
+11,11,48,48,25,10,0.5208333333333334,0.7142857142857143,0.6024096385542168,0.65625
+12,12,36,36,25,18,0.6944444444444444,0.5813953488372093,0.6329113924050633,0.5972222222222222
+13,13,17,17,11,7,0.6470588235294118,0.6111111111111112,0.6285714285714287,0.6176470588235294
+14,14,77,77,23,10,0.2987012987012987,0.696969696969697,0.41818181818181815,0.5844155844155844
+15,15,40,40,6,7,0.15,0.46153846153846156,0.22641509433962265,0.4875
+16,16,29,29,29,27,1.0,0.5178571428571429,0.6823529411764707,0.5344827586206896
+17,total,1043,1043,440,305,,,,
+18,,,,,Micro avg.,0.4218600191754554,0.5906040268456376,0.49217002237136465,0.5647171620325983
+19,,,,,Macro avg.,0.429943445421726,0.5299340176943903,0.4406945292424403,0.566755650021845