Upload report-Model-0_Queries-3_Prompt-0_Strategies-argmax-threshold0.05-threshold0.25-threshold0.5-threshold0.75-topk9-topk7-topk5-topk3.csv

Reports/report-Model-0_Queries-3_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
+1,1,30,30,1,0,0.03333333333333333,1.0,0.06451612903225806,0.5166666666666667
+2,2,288,288,38,46,0.13194444444444445,0.4523809523809524,0.2043010752688172,0.4861111111111111
+3,3,87,87,0,0,0.0,0.0,0.0,0.5
+4,4,94,94,0,0,0.0,0.0,0.0,0.5
+5,5,62,62,0,0,0.0,0.0,0.0,0.5
+6,6,63,63,0,0,0.0,0.0,0.0,0.5
+7,7,17,17,0,0,0.0,0.0,0.0,0.5
+8,8,65,65,0,0,0.0,0.0,0.0,0.5
+9,9,31,31,2,0,0.06451612903225806,1.0,0.12121212121212122,0.532258064516129
+10,10,57,57,0,0,0.0,0.0,0.0,0.5
+11,11,48,48,0,0,0.0,0.0,0.0,0.5
+12,12,36,36,2,0,0.05555555555555555,1.0,0.10526315789473684,0.5277777777777778
+13,13,17,17,2,1,0.11764705882352941,0.6666666666666666,0.2,0.5294117647058824
+14,14,77,77,0,0,0.0,0.0,0.0,0.5
+15,15,40,40,0,0,0.0,0.0,0.0,0.5
+16,16,29,29,18,20,0.6206896551724138,0.47368421052631576,0.5373134328358208,0.46551724137931033
+17,total,1043,1043,63,67,,,,
+18,,,,,Micro avg.,0.06040268456375839,0.4846153846153846,0.10741687979539642,0.4980824544582934
+19,,,,,Macro avg.,0.06021683390361968,0.2701606958572903,0.07250623036727966,0.5033966250680516
+threshold-0.05,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,2,1,0.5,0.6666666666666666,0.5
+1,1,30,30,30,30,1,0.5,0.6666666666666666,0.5
+2,2,288,288,288,288,1,0.5,0.6666666666666666,0.5
+3,3,87,87,87,87,1,0.5,0.6666666666666666,0.5
+4,4,94,94,94,94,1,0.5,0.6666666666666666,0.5
+5,5,62,62,62,62,1,0.5,0.6666666666666666,0.5
+6,6,63,63,63,63,1,0.5,0.6666666666666666,0.5
+7,7,17,17,17,17,1,0.5,0.6666666666666666,0.5
+8,8,65,65,65,65,1,0.5,0.6666666666666666,0.5
+9,9,31,31,31,31,1,0.5,0.6666666666666666,0.5
+10,10,57,57,57,57,1,0.5,0.6666666666666666,0.5
+11,11,48,48,48,48,1,0.5,0.6666666666666666,0.5
+12,12,36,36,36,36,1,0.5,0.6666666666666666,0.5
+13,13,17,17,17,17,1,0.5,0.6666666666666666,0.5
+14,14,77,77,77,77,1,0.5,0.6666666666666666,0.5
+15,15,40,40,40,40,1,0.5,0.6666666666666666,0.5
+16,16,29,29,29,29,1,0.5,0.6666666666666666,0.5
+17,total,1043,1043,1043,1043,,,,
+18,,,,,Micro avg.,1.0,0.5,0.6666666666666666,0.5
+19,,,,,Macro avg.,1.0,0.5,0.6666666666666665,0.5
+threshold-0.25,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,2,1,0.5,0.6666666666666666,0.5
+1,1,30,30,30,30,1,0.5,0.6666666666666666,0.5
+2,2,288,288,288,288,1,0.5,0.6666666666666666,0.5
+3,3,87,87,87,87,1,0.5,0.6666666666666666,0.5
+4,4,94,94,94,93,1,0.5026737967914439,0.6690391459074733,0.5053191489361702
+5,5,62,62,62,62,1,0.5,0.6666666666666666,0.5
+6,6,63,63,63,63,1,0.5,0.6666666666666666,0.5
+7,7,17,17,17,17,1,0.5,0.6666666666666666,0.5
+8,8,65,65,65,65,1,0.5,0.6666666666666666,0.5
+9,9,31,31,31,31,1,0.5,0.6666666666666666,0.5
+10,10,57,57,57,57,1,0.5,0.6666666666666666,0.5
+11,11,48,48,48,48,1,0.5,0.6666666666666666,0.5
+12,12,36,36,36,36,1,0.5,0.6666666666666666,0.5
+13,13,17,17,17,17,1,0.5,0.6666666666666666,0.5
+14,14,77,77,77,77,1,0.5,0.6666666666666666,0.5
+15,15,40,40,40,40,1,0.5,0.6666666666666666,0.5
+16,16,29,29,29,29,1,0.5,0.6666666666666666,0.5
+17,total,1043,1043,1043,1042,,,,
+18,,,,,Micro avg.,1.0,0.5002398081534772,0.6668797953964195,0.5004793863854267
+19,,,,,Macro avg.,1.0,0.5001572821642026,0.666806224269067,0.5003128911138923
+threshold-0.5,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,1,1.0,0.6666666666666666,0.8,0.75
+1,1,30,30,29,30,0.9666666666666667,0.4915254237288136,0.651685393258427,0.48333333333333334
+2,2,288,288,288,287,1.0,0.5008695652173913,0.6674391657010429,0.5017361111111112
+3,3,87,87,86,85,0.9885057471264368,0.5029239766081871,0.6666666666666666,0.5057471264367817
+4,4,94,94,90,90,0.9574468085106383,0.5,0.656934306569343,0.5
+5,5,62,62,62,61,1.0,0.5040650406504065,0.6702702702702703,0.5080645161290323
+6,6,63,63,62,63,0.9841269841269841,0.496,0.6595744680851063,0.49206349206349204
+7,7,17,17,17,17,1.0,0.5,0.6666666666666666,0.5
+8,8,65,65,65,65,1.0,0.5,0.6666666666666666,0.5
+9,9,31,31,30,31,0.967741935483871,0.4918032786885246,0.6521739130434782,0.4838709677419355
+10,10,57,57,57,57,1.0,0.5,0.6666666666666666,0.5
+11,11,48,48,48,48,1.0,0.5,0.6666666666666666,0.5
+12,12,36,36,36,36,1.0,0.5,0.6666666666666666,0.5
+13,13,17,17,17,17,1.0,0.5,0.6666666666666666,0.5
+14,14,77,77,68,72,0.8831168831168831,0.4857142857142857,0.6267281105990783,0.474025974025974
+15,15,40,40,40,40,1.0,0.5,0.6666666666666666,0.5
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,1026,1029,,,,
+18,,,,,Micro avg.,0.9837008628954937,0.4992700729927007,0.6623628147191737,0.49856184084372
+19,,,,,Macro avg.,0.9851532367665579,0.5082098963102515,0.6696944486780438,0.5116965600495094
+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
+1,1,30,30,16,12,0.5333333333333333,0.5714285714285714,0.5517241379310344,0.5666666666666667
+2,2,288,288,285,287,0.9895833333333334,0.4982517482517482,0.6627906976744186,0.4965277777777778
+3,3,87,87,5,6,0.05747126436781609,0.45454545454545453,0.10204081632653061,0.4942528735632184
+4,4,94,94,31,33,0.32978723404255317,0.484375,0.3924050632911392,0.48936170212765956
+5,5,62,62,34,46,0.5483870967741935,0.425,0.47887323943661964,0.4032258064516129
+6,6,63,63,23,31,0.36507936507936506,0.42592592592592593,0.39316239316239315,0.4365079365079365
+7,7,17,17,13,14,0.7647058823529411,0.48148148148148145,0.5909090909090909,0.47058823529411764
+8,8,65,65,51,44,0.7846153846153846,0.5368421052631579,0.6375000000000001,0.5538461538461539
+9,9,31,31,27,25,0.8709677419354839,0.5192307692307693,0.6506024096385542,0.532258064516129
+10,10,57,57,21,20,0.3684210526315789,0.5121951219512195,0.4285714285714285,0.5087719298245614
+11,11,48,48,28,25,0.5833333333333334,0.5283018867924528,0.5544554455445545,0.53125
+12,12,36,36,32,31,0.8888888888888888,0.5079365079365079,0.6464646464646465,0.5138888888888888
+13,13,17,17,17,17,1.0,0.5,0.6666666666666666,0.5
+14,14,77,77,7,6,0.09090909090909091,0.5384615384615384,0.15555555555555556,0.5064935064935064
+15,15,40,40,15,12,0.375,0.5555555555555556,0.44776119402985076,0.5375
+16,16,29,29,28,29,0.9655172413793104,0.49122807017543857,0.6511627906976745,0.4827586206896552
+17,total,1043,1043,633,638,,,,
+18,,,,,Micro avg.,0.6069031639501438,0.4980330448465775,0.547104580812446,0.49760306807286675
+19,,,,,Macro avg.,0.5597647201750945,0.4723976315882248,0.47121444564118575,0.501405774273405
+topk-9,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
+1,1,30,30,11,10,0.36666666666666664,0.5238095238095238,0.4313725490196078,0.5166666666666667
+2,2,288,288,283,287,0.9826388888888888,0.4964912280701754,0.6596736596736597,0.4930555555555556
+3,3,87,87,3,2,0.034482758620689655,0.6,0.06521739130434784,0.5057471264367817
+4,4,94,94,21,21,0.22340425531914893,0.5,0.3088235294117647,0.5
+5,5,62,62,29,38,0.46774193548387094,0.43283582089552236,0.44961240310077516,0.4274193548387097
+6,6,63,63,14,28,0.2222222222222222,0.3333333333333333,0.26666666666666666,0.3888888888888889
+7,7,17,17,12,15,0.7058823529411765,0.4444444444444444,0.5454545454545455,0.4117647058823529
+8,8,65,65,45,45,0.6923076923076923,0.5,0.5806451612903226,0.5
+9,9,31,31,28,26,0.9032258064516129,0.5185185185185185,0.6588235294117647,0.532258064516129
+10,10,57,57,15,7,0.2631578947368421,0.6818181818181818,0.3797468354430379,0.5701754385964912
+11,11,48,48,24,21,0.5,0.5333333333333333,0.5161290322580646,0.53125
+12,12,36,36,35,30,0.9722222222222222,0.5384615384615384,0.693069306930693,0.5694444444444444
+13,13,17,17,17,16,1.0,0.5151515151515151,0.6799999999999999,0.5294117647058824
+14,14,77,77,2,1,0.025974025974025976,0.6666666666666666,0.05,0.5064935064935064
+15,15,40,40,13,4,0.325,0.7647058823529411,0.456140350877193,0.6125
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,581,580,,,,
+18,,,,,Micro avg.,0.5570469798657718,0.5004306632213609,0.5272232304900181,0.5004793863854267
+19,,,,,Macro avg.,0.5108780424608859,0.5029158815797468,0.4357671545593594,0.5055926774720829
+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
+1,1,30,30,6,2,0.2,0.75,0.31578947368421056,0.5666666666666667
+2,2,288,288,283,285,0.9826388888888888,0.4982394366197183,0.6612149532710281,0.4965277777777778
+3,3,87,87,1,1,0.011494252873563218,0.5,0.02247191011235955,0.5
+4,4,94,94,12,14,0.1276595744680851,0.46153846153846156,0.2,0.48936170212765956
+5,5,62,62,13,27,0.20967741935483872,0.325,0.2549019607843137,0.3870967741935484
+6,6,63,63,7,13,0.1111111111111111,0.35,0.1686746987951807,0.4523809523809524
+7,7,17,17,4,10,0.23529411764705882,0.2857142857142857,0.2580645161290323,0.3235294117647059
+8,8,65,65,33,30,0.5076923076923077,0.5238095238095238,0.515625,0.5230769230769231
+9,9,31,31,25,23,0.8064516129032258,0.5208333333333334,0.6329113924050633,0.532258064516129
+10,10,57,57,7,3,0.12280701754385964,0.7,0.208955223880597,0.5350877192982456
+11,11,48,48,15,11,0.3125,0.5769230769230769,0.4054054054054054,0.5416666666666666
+12,12,36,36,34,25,0.9444444444444444,0.576271186440678,0.7157894736842105,0.625
+13,13,17,17,17,16,1.0,0.5151515151515151,0.6799999999999999,0.5294117647058824
+14,14,77,77,0,0,0.0,0.0,0.0,0.5
+15,15,40,40,2,3,0.05,0.4,0.0888888888888889,0.4875
+16,16,29,29,28,29,0.9655172413793104,0.49122807017543857,0.6511627906976745,0.4827586206896552
+17,total,1043,1043,487,492,,,,
+18,,,,,Micro avg.,0.4669223394055609,0.4974463738508682,0.4817012858555885,0.49760306807286675
+19,,,,,Macro avg.,0.38748752872392317,0.43968875821800185,0.3399915110434097,0.49837194375675375
+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
+1,1,30,30,4,0,0.13333333333333333,1.0,0.23529411764705882,0.5666666666666667
+2,2,288,288,280,282,0.9722222222222222,0.498220640569395,0.6588235294117647,0.4965277777777778
+3,3,87,87,0,0,0.0,0.0,0.0,0.5
+4,4,94,94,5,6,0.05319148936170213,0.45454545454545453,0.09523809523809525,0.4946808510638298
+5,5,62,62,7,10,0.11290322580645161,0.4117647058823529,0.17721518987341772,0.47580645161290325
+6,6,63,63,3,3,0.047619047619047616,0.5,0.08695652173913042,0.5
+7,7,17,17,2,4,0.11764705882352941,0.3333333333333333,0.1739130434782609,0.4411764705882353
+8,8,65,65,12,8,0.18461538461538463,0.6,0.2823529411764706,0.5307692307692308
+9,9,31,31,22,20,0.7096774193548387,0.5238095238095238,0.6027397260273972,0.532258064516129
+10,10,57,57,2,1,0.03508771929824561,0.6666666666666666,0.06666666666666667,0.5087719298245614
+11,11,48,48,7,5,0.14583333333333334,0.5833333333333334,0.23333333333333336,0.5208333333333334
+12,12,36,36,25,20,0.6944444444444444,0.5555555555555556,0.6172839506172839,0.5694444444444444
+13,13,17,17,16,16,0.9411764705882353,0.5,0.6530612244897959,0.5
+14,14,77,77,0,0,0.0,0.0,0.0,0.5
+15,15,40,40,1,2,0.025,0.3333333333333333,0.046511627906976744,0.4875
+16,16,29,29,25,28,0.8620689655172413,0.4716981132075472,0.6097560975609757,0.4482758620689655
+17,total,1043,1043,411,405,,,,
+18,,,,,Micro avg.,0.3940556088207095,0.5036764705882353,0.44217321140398064,0.50287631831256
+19,,,,,Macro avg.,0.29616588907753,0.4371918035433233,0.2670085920686252,0.5042771225097693
+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
+1,1,30,30,1,0,0.03333333333333333,1.0,0.06451612903225806,0.5166666666666667
+2,2,288,288,230,224,0.7986111111111112,0.5066079295154186,0.6199460916442049,0.5104166666666666
+3,3,87,87,0,0,0.0,0.0,0.0,0.5
+4,4,94,94,2,0,0.02127659574468085,1.0,0.04166666666666667,0.5106382978723404
+5,5,62,62,2,1,0.03225806451612903,0.6666666666666666,0.06153846153846154,0.5080645161290323
+6,6,63,63,0,0,0.0,0.0,0.0,0.5
+7,7,17,17,1,0,0.058823529411764705,1.0,0.1111111111111111,0.5294117647058824
+8,8,65,65,2,1,0.03076923076923077,0.6666666666666666,0.05882352941176471,0.5076923076923077
+9,9,31,31,7,6,0.22580645161290322,0.5384615384615384,0.3181818181818182,0.5161290322580645
+10,10,57,57,0,0,0.0,0.0,0.0,0.5
+11,11,48,48,1,0,0.020833333333333332,1.0,0.04081632653061225,0.5104166666666666
+12,12,36,36,10,6,0.2777777777777778,0.625,0.3846153846153846,0.5555555555555556
+13,13,17,17,13,15,0.7647058823529411,0.4642857142857143,0.5777777777777777,0.4411764705882353
+14,14,77,77,0,0,0.0,0.0,0.0,0.5
+15,15,40,40,0,0,0.0,0.0,0.0,0.5
+16,16,29,29,23,25,0.7931034482758621,0.4791666666666667,0.5974025974025974,0.46551724137931033
+17,total,1043,1043,292,278,,,,
+18,,,,,Micro avg.,0.2799616490891659,0.512280701754386,0.3620582765034098,0.5067114093959731
+19,,,,,Macro avg.,0.1798411034258275,0.467462069544863,0.16919975846545043,0.5042167756576897