Upload report-Model-1_Queries-0_Prompt-2_Strategies-argmax-threshold0.05-threshold0.25-threshold0.5-threshold0.75-topk9-topk7-topk5-topk3.csv

Reports/report-Model-1_Queries-0_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
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,42,24,0.14583333333333334,0.6363636363636364,0.23728813559322035,0.53125
+3,3,87,87,29,12,0.3333333333333333,0.7073170731707317,0.453125,0.5977011494252874
+4,4,94,94,13,3,0.13829787234042554,0.8125,0.23636363636363636,0.5531914893617021
+5,5,62,62,4,3,0.06451612903225806,0.5714285714285714,0.11594202898550726,0.5080645161290323
+6,6,63,63,31,1,0.49206349206349204,0.96875,0.6526315789473683,0.7380952380952381
+7,7,17,17,5,3,0.29411764705882354,0.625,0.4,0.5588235294117647
+8,8,65,65,13,10,0.2,0.5652173913043478,0.29545454545454547,0.5230769230769231
+9,9,31,31,20,8,0.6451612903225806,0.7142857142857143,0.6779661016949152,0.6935483870967742
+10,10,57,57,20,11,0.3508771929824561,0.6451612903225806,0.45454545454545453,0.5789473684210527
+11,11,48,48,22,8,0.4583333333333333,0.7333333333333333,0.5641025641025641,0.6458333333333334
+12,12,36,36,14,7,0.3888888888888889,0.6666666666666666,0.49122807017543857,0.5972222222222222
+13,13,17,17,12,5,0.7058823529411765,0.7058823529411765,0.7058823529411765,0.7058823529411765
+14,14,77,77,24,13,0.3116883116883117,0.6486486486486487,0.4210526315789474,0.5714285714285714
+15,15,40,40,1,5,0.025,0.16666666666666666,0.04347826086956522,0.45
+16,16,29,29,14,12,0.4827586206896552,0.5384615384615384,0.509090909090909,0.5344827586206896
+17,total,1043,1043,264,125,,,,
+18,,,,,Micro avg.,0.25311601150527324,0.6786632390745502,0.3687150837988827,0.5666347075743049
+19,,,,,Macro avg.,0.29627951752988635,0.5709225225643301,0.3681265453143088,0.5757381082096333
+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
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,63,43,0.21875,0.5943396226415094,0.31979695431472077,0.5347222222222222
+3,3,87,87,45,21,0.5172413793103449,0.6818181818181818,0.5882352941176471,0.6379310344827587
+4,4,94,94,32,7,0.3404255319148936,0.8205128205128205,0.48120300751879697,0.6329787234042553
+5,5,62,62,10,10,0.16129032258064516,0.5,0.24390243902439024,0.5
+6,6,63,63,47,7,0.746031746031746,0.8703703703703703,0.8034188034188035,0.8174603174603174
+7,7,17,17,10,5,0.5882352941176471,0.6666666666666666,0.625,0.6470588235294118
+8,8,65,65,28,20,0.4307692307692308,0.5833333333333334,0.49557522123893816,0.5615384615384615
+9,9,31,31,18,17,0.5806451612903226,0.5142857142857142,0.5454545454545455,0.5161290322580645
+10,10,57,57,39,21,0.6842105263157895,0.65,0.6666666666666667,0.6578947368421053
+11,11,48,48,37,28,0.7708333333333334,0.5692307692307692,0.6548672566371682,0.59375
+12,12,36,36,21,16,0.5833333333333334,0.5675675675675675,0.5753424657534246,0.5694444444444444
+13,13,17,17,10,6,0.5882352941176471,0.625,0.6060606060606061,0.6176470588235294
+14,14,77,77,36,23,0.4675324675324675,0.6101694915254238,0.5294117647058822,0.5844155844155844
+15,15,40,40,1,8,0.025,0.1111111111111111,0.04081632653061225,0.4125
+16,16,29,29,17,16,0.5862068965517241,0.5151515151515151,0.5483870967741935,0.5172413793103449
+17,total,1043,1043,414,248,,,,
+18,,,,,Micro avg.,0.3969319271332694,0.6253776435045317,0.4856304985337243,0.5795781399808245
+19,,,,,Macro avg.,0.4287494421881838,0.522326892012646,0.4543610851891997,0.5765124599253824
+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
+2,2,288,288,38,23,0.13194444444444445,0.6229508196721312,0.2177650429799427,0.5260416666666666
+3,3,87,87,16,4,0.1839080459770115,0.8,0.29906542056074764,0.5689655172413793
+4,4,94,94,14,3,0.14893617021276595,0.8235294117647058,0.25225225225225223,0.5585106382978723
+5,5,62,62,6,6,0.0967741935483871,0.5,0.16216216216216214,0.5
+6,6,63,63,37,4,0.5873015873015873,0.9024390243902439,0.7115384615384616,0.7619047619047619
+7,7,17,17,4,3,0.23529411764705882,0.5714285714285714,0.3333333333333333,0.5294117647058824
+8,8,65,65,16,15,0.24615384615384617,0.5161290322580645,0.3333333333333333,0.5076923076923077
+9,9,31,31,14,6,0.45161290322580644,0.7,0.5490196078431372,0.6290322580645161
+10,10,57,57,29,12,0.5087719298245614,0.7073170731707317,0.5918367346938775,0.6491228070175439
+11,11,48,48,27,12,0.5625,0.6923076923076923,0.6206896551724138,0.65625
+12,12,36,36,12,4,0.3333333333333333,0.75,0.46153846153846156,0.6111111111111112
+13,13,17,17,3,4,0.17647058823529413,0.42857142857142855,0.25,0.47058823529411764
+14,14,77,77,19,7,0.24675324675324675,0.7307692307692307,0.36893203883495146,0.577922077922078
+15,15,40,40,1,4,0.025,0.2,0.04444444444444445,0.4625
+16,16,29,29,15,9,0.5172413793103449,0.625,0.5660377358490567,0.603448275862069
+17,total,1043,1043,251,116,,,,
+18,,,,,Micro avg.,0.24065196548418025,0.6839237057220708,0.35602836879432626,0.5647171620325983
+19,,,,,Macro avg.,0.26188210505692283,0.562967193196047,0.3389381579139162,0.565441260104724
+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
+2,2,288,288,23,11,0.0798611111111111,0.6764705882352942,0.14285714285714285,0.5208333333333334
+3,3,87,87,4,0,0.04597701149425287,1.0,0.08791208791208792,0.5229885057471264
+4,4,94,94,10,2,0.10638297872340426,0.8333333333333334,0.18867924528301885,0.5425531914893617
+5,5,62,62,3,3,0.04838709677419355,0.5,0.08823529411764706,0.5
+6,6,63,63,32,2,0.5079365079365079,0.9411764705882353,0.6597938144329897,0.7380952380952381
+7,7,17,17,3,1,0.17647058823529413,0.75,0.2857142857142857,0.5588235294117647
+8,8,65,65,12,13,0.18461538461538463,0.48,0.2666666666666667,0.49230769230769234
+9,9,31,31,9,2,0.2903225806451613,0.8181818181818182,0.4285714285714286,0.6129032258064516
+10,10,57,57,20,7,0.3508771929824561,0.7407407407407407,0.47619047619047616,0.6140350877192983
+11,11,48,48,19,6,0.3958333333333333,0.76,0.5205479452054795,0.6354166666666666
+12,12,36,36,8,4,0.2222222222222222,0.6666666666666666,0.3333333333333333,0.5555555555555556
+13,13,17,17,1,2,0.058823529411764705,0.3333333333333333,0.1,0.47058823529411764
+14,14,77,77,7,2,0.09090909090909091,0.7777777777777778,0.1627906976744186,0.5324675324675324
+15,15,40,40,1,2,0.025,0.3333333333333333,0.046511627906976744,0.4875
+16,16,29,29,13,6,0.4482758620689655,0.6842105263157895,0.5416666666666666,0.6206896551724138
+17,total,1043,1043,165,63,,,,
+18,,,,,Micro avg.,0.15819750719079578,0.7236842105263158,0.25963808025177026,0.5488974113135187
+19,,,,,Macro avg.,0.178346734733126,0.605601446382725,0.2546747477960364,0.5532210264156797
+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
+2,2,288,288,8,4,0.027777777777777776,0.6666666666666666,0.05333333333333333,0.5069444444444444
+3,3,87,87,1,0,0.011494252873563218,1.0,0.022727272727272724,0.5057471264367817
+4,4,94,94,8,2,0.0851063829787234,0.8,0.15384615384615383,0.5319148936170213
+5,5,62,62,1,2,0.016129032258064516,0.3333333333333333,0.03076923076923077,0.49193548387096775
+6,6,63,63,18,0,0.2857142857142857,1.0,0.4444444444444445,0.6428571428571429
+7,7,17,17,2,0,0.11764705882352941,1.0,0.21052631578947367,0.5588235294117647
+8,8,65,65,2,3,0.03076923076923077,0.4,0.05714285714285715,0.49230769230769234
+9,9,31,31,2,0,0.06451612903225806,1.0,0.12121212121212122,0.532258064516129
+10,10,57,57,11,3,0.19298245614035087,0.7857142857142857,0.30985915492957744,0.5701754385964912
+11,11,48,48,7,1,0.14583333333333334,0.875,0.25000000000000006,0.5625
+12,12,36,36,3,2,0.08333333333333333,0.6,0.14634146341463414,0.5138888888888888
+13,13,17,17,0,0,0.0,0.0,0.0,0.5
+14,14,77,77,1,0,0.012987012987012988,1.0,0.025641025641025647,0.5064935064935064
+15,15,40,40,0,1,0.0,0.0,0.0,0.4875
+16,16,29,29,8,1,0.27586206896551724,0.8888888888888888,0.42105263157894735,0.6206896551724138
+17,total,1043,1043,72,19,,,,
+18,,,,,Micro avg.,0.06903163950143816,0.7912087912087912,0.12698412698412698,0.5254074784276127
+19,,,,,Macro avg.,0.07942072676394005,0.6088001867413633,0.1321703532252395,0.5308256392125438
+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
+1,1,30,30,10,6,0.3333333333333333,0.625,0.43478260869565216,0.5666666666666667
+2,2,288,288,173,153,0.6006944444444444,0.5306748466257669,0.5635179153094463,0.5347222222222222
+3,3,87,87,83,73,0.9540229885057471,0.532051282051282,0.6831275720164609,0.5574712643678161
+4,4,94,94,64,44,0.6808510638297872,0.5925925925925926,0.6336633663366336,0.6063829787234043
+5,5,62,62,24,15,0.3870967741935484,0.6153846153846154,0.47524752475247517,0.5725806451612904
+6,6,63,63,57,35,0.9047619047619048,0.6195652173913043,0.735483870967742,0.6746031746031746
+7,7,17,17,15,16,0.8823529411764706,0.4838709677419355,0.625,0.47058823529411764
+8,8,65,65,57,47,0.8769230769230769,0.5480769230769231,0.6745562130177515,0.5769230769230769
+9,9,31,31,30,29,0.967741935483871,0.5084745762711864,0.6666666666666666,0.5161290322580645
+10,10,57,57,52,44,0.9122807017543859,0.5416666666666666,0.6797385620915032,0.5701754385964912
+11,11,48,48,46,46,0.9583333333333334,0.5,0.6571428571428571,0.5
+12,12,36,36,35,33,0.9722222222222222,0.5147058823529411,0.6730769230769229,0.5277777777777778
+13,13,17,17,16,13,0.9411764705882353,0.5517241379310345,0.6956521739130435,0.5882352941176471
+14,14,77,77,73,66,0.948051948051948,0.5251798561151079,0.6759259259259259,0.5454545454545454
+15,15,40,40,14,22,0.35,0.3888888888888889,0.36842105263157887,0.4
+16,16,29,29,28,29,0.9655172413793104,0.49122807017543857,0.6511627906976745,0.4827586206896552
+17,total,1043,1043,777,671,,,,
+18,,,,,Micro avg.,0.7449664429530202,0.5366022099447514,0.6238458450421518,0.5508149568552253
+19,,,,,Macro avg.,0.7432564929400952,0.5040637954862168,0.5819509425436666,0.540615821932703
+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
+1,1,30,30,8,2,0.26666666666666666,0.8,0.4,0.6
+2,2,288,288,146,128,0.5069444444444444,0.5328467153284672,0.5195729537366549,0.53125
+3,3,87,87,77,63,0.8850574712643678,0.55,0.6784140969162996,0.5804597701149425
+4,4,94,94,58,27,0.6170212765957447,0.6823529411764706,0.6480446927374303,0.6648936170212766
+5,5,62,62,18,12,0.2903225806451613,0.6,0.3913043478260869,0.5483870967741935
+6,6,63,63,55,17,0.873015873015873,0.7638888888888888,0.8148148148148149,0.8015873015873016
+7,7,17,17,12,14,0.7058823529411765,0.46153846153846156,0.558139534883721,0.4411764705882353
+8,8,65,65,54,38,0.8307692307692308,0.5869565217391305,0.6878980891719746,0.6230769230769231
+9,9,31,31,30,26,0.967741935483871,0.5357142857142857,0.6896551724137931,0.5645161290322581
+10,10,57,57,49,36,0.8596491228070176,0.5764705882352941,0.6901408450704225,0.6140350877192983
+11,11,48,48,43,43,0.8958333333333334,0.5,0.6417910447761194,0.5
+12,12,36,36,34,30,0.9444444444444444,0.53125,0.6799999999999999,0.5555555555555556
+13,13,17,17,16,11,0.9411764705882353,0.5925925925925926,0.7272727272727272,0.6470588235294118
+14,14,77,77,69,51,0.8961038961038961,0.575,0.700507614213198,0.6168831168831169
+15,15,40,40,12,17,0.3,0.41379310344827586,0.34782608695652173,0.4375
+16,16,29,29,27,29,0.9310344827586207,0.48214285714285715,0.6352941176470589,0.46551724137931033
+17,total,1043,1043,708,544,,,,
+18,,,,,Micro avg.,0.6788111217641419,0.5654952076677316,0.6169934640522876,0.5786193672099712
+19,,,,,Macro avg.,0.6889213871683579,0.5402674679885131,0.5770985963786365,0.5701115960742247
+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
+1,1,30,30,3,0,0.1,1.0,0.18181818181818182,0.55
+2,2,288,288,120,96,0.4166666666666667,0.5555555555555556,0.4761904761904762,0.5416666666666666
+3,3,87,87,71,53,0.8160919540229885,0.5725806451612904,0.6729857819905214,0.603448275862069
+4,4,94,94,47,16,0.5,0.746031746031746,0.5987261146496815,0.6648936170212766
+5,5,62,62,14,10,0.22580645161290322,0.5833333333333334,0.3255813953488372,0.532258064516129
+6,6,63,63,52,12,0.8253968253968254,0.8125,0.8188976377952756,0.8174603174603174
+7,7,17,17,11,9,0.6470588235294118,0.55,0.5945945945945946,0.5588235294117647
+8,8,65,65,45,31,0.6923076923076923,0.5921052631578947,0.6382978723404255,0.6076923076923076
+9,9,31,31,27,22,0.8709677419354839,0.5510204081632653,0.6749999999999999,0.5806451612903226
+10,10,57,57,46,30,0.8070175438596491,0.6052631578947368,0.6917293233082706,0.6403508771929824
+11,11,48,48,43,40,0.8958333333333334,0.5180722891566265,0.6564885496183206,0.53125
+12,12,36,36,30,26,0.8333333333333334,0.5357142857142857,0.6521739130434783,0.5555555555555556
+13,13,17,17,16,7,0.9411764705882353,0.6956521739130435,0.7999999999999999,0.7647058823529411
+14,14,77,77,66,37,0.8571428571428571,0.6407766990291263,0.7333333333333333,0.6883116883116883
+15,15,40,40,10,13,0.25,0.43478260869565216,0.3174603174603175,0.4625
+16,16,29,29,27,28,0.9310344827586207,0.4909090909090909,0.6428571428571428,0.4827586206896552
+17,total,1043,1043,628,430,,,,
+18,,,,,Micro avg.,0.6021093000958773,0.5935727788279773,0.5978105663969537,0.5949185043144775
+19,,,,,Macro avg.,0.6241078927345882,0.5814292503950381,0.5574196843734621,0.5930776802366868
+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
+2,2,288,288,96,54,0.3333333333333333,0.64,0.4383561643835616,0.5729166666666666
+3,3,87,87,63,40,0.7241379310344828,0.6116504854368932,0.6631578947368421,0.632183908045977
+4,4,94,94,34,9,0.3617021276595745,0.7906976744186046,0.4963503649635036,0.6329787234042553
+5,5,62,62,8,7,0.12903225806451613,0.5333333333333333,0.2077922077922078,0.5080645161290323
+6,6,63,63,43,6,0.6825396825396826,0.8775510204081632,0.7678571428571428,0.7936507936507936
+7,7,17,17,11,6,0.6470588235294118,0.6470588235294118,0.6470588235294118,0.6470588235294118
+8,8,65,65,32,23,0.49230769230769234,0.5818181818181818,0.5333333333333333,0.5692307692307692
+9,9,31,31,25,20,0.8064516129032258,0.5555555555555556,0.6578947368421053,0.5806451612903226
+10,10,57,57,40,24,0.7017543859649122,0.625,0.6611570247933884,0.6403508771929824
+11,11,48,48,36,21,0.75,0.631578947368421,0.6857142857142857,0.65625
+12,12,36,36,26,17,0.7222222222222222,0.6046511627906976,0.6582278481012659,0.625
+13,13,17,17,16,5,0.9411764705882353,0.7619047619047619,0.8421052631578947,0.8235294117647058
+14,14,77,77,54,30,0.7012987012987013,0.6428571428571429,0.6708074534161491,0.6558441558441559
+15,15,40,40,5,6,0.125,0.45454545454545453,0.196078431372549,0.4875
+16,16,29,29,22,23,0.7586206896551724,0.4888888888888889,0.5945945945945945,0.4827586206896552
+17,total,1043,1043,512,291,,,,
+18,,,,,Micro avg.,0.49089165867689355,0.6376089663760897,0.5547128927410617,0.6059443911792906
+19,,,,,Macro avg.,0.5241158390843821,0.6145347901679713,0.5167648058012054,0.6073311231826704