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

Reports/report-Model-0_Queries-2_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
+0,0,2,2,1,0,0.5,1.0,0.6666666666666666,0.75
+1,1,30,30,7,1,0.23333333333333334,0.875,0.3684210526315789,0.6
+2,2,288,288,118,81,0.4097222222222222,0.592964824120603,0.48459958932238195,0.5642361111111112
+3,3,87,87,20,8,0.22988505747126436,0.7142857142857143,0.3478260869565217,0.5689655172413793
+4,4,94,94,49,20,0.5212765957446809,0.7101449275362319,0.6012269938650306,0.6542553191489362
+5,5,62,62,7,2,0.11290322580645161,0.7777777777777778,0.19718309859154928,0.5403225806451613
+6,6,63,63,23,2,0.36507936507936506,0.92,0.5227272727272727,0.6666666666666666
+7,7,17,17,6,1,0.35294117647058826,0.8571428571428571,0.5,0.6470588235294118
+8,8,65,65,17,13,0.26153846153846155,0.5666666666666667,0.3578947368421053,0.5307692307692308
+9,9,31,31,2,1,0.06451612903225806,0.6666666666666666,0.1176470588235294,0.5161290322580645
+10,10,57,57,25,16,0.43859649122807015,0.6097560975609756,0.5102040816326531,0.5789473684210527
+11,11,48,48,8,5,0.16666666666666666,0.6153846153846154,0.26229508196721313,0.53125
+12,12,36,36,4,8,0.1111111111111111,0.3333333333333333,0.16666666666666666,0.4444444444444444
+13,13,17,17,13,4,0.7647058823529411,0.7647058823529411,0.7647058823529412,0.7647058823529411
+14,14,77,77,28,9,0.36363636363636365,0.7567567567567568,0.4912280701754386,0.6233766233766234
+15,15,40,40,4,9,0.1,0.3076923076923077,0.15094339622641512,0.4375
+16,16,29,29,9,7,0.3103448275862069,0.5625,0.4,0.5344827586206896
+17,total,1043,1043,341,187,,,,
+18,,,,,Micro avg.,0.32694151486097794,0.6458333333333334,0.4341183959261617,0.5738255033557047
+19,,,,,Macro avg.,0.3121327593694109,0.6841634368986734,0.4064844550263509,0.5854770799168069
+threshold-0.05,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,2,1.0,0.5,0.6666666666666666,0.5
+1,1,30,30,30,30,1.0,0.5,0.6666666666666666,0.5
+2,2,288,288,286,288,0.9930555555555556,0.49825783972125437,0.6635730858468678,0.4965277777777778
+3,3,87,87,87,84,1.0,0.5087719298245614,0.6744186046511628,0.5172413793103449
+4,4,94,94,94,94,1.0,0.5,0.6666666666666666,0.5
+5,5,62,62,62,62,1.0,0.5,0.6666666666666666,0.5
+6,6,63,63,63,59,1.0,0.5163934426229508,0.6810810810810811,0.5317460317460317
+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
+9,9,31,31,31,31,1.0,0.5,0.6666666666666666,0.5
+10,10,57,57,56,53,0.9824561403508771,0.5137614678899083,0.6746987951807228,0.5263157894736842
+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
+13,13,17,17,17,16,1.0,0.5151515151515151,0.6799999999999999,0.5294117647058824
+14,14,77,77,75,74,0.974025974025974,0.5033557046979866,0.6637168141592921,0.5064935064935064
+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,1043,1043,1038,1028,,,,
+18,,,,,Micro avg.,0.9952061361457335,0.5024201355275896,0.6677388227725958,0.5047938638542665
+19,,,,,Macro avg.,0.9970316276430826,0.5032759941122457,0.6688718655442623,0.5063374264416015
+threshold-0.25,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,0,1.0,1.0,1.0,1.0
+1,1,30,30,28,26,0.9333333333333333,0.5185185185185185,0.6666666666666667,0.5333333333333333
+2,2,288,288,282,280,0.9791666666666666,0.501779359430605,0.6635294117647058,0.5034722222222222
+3,3,87,87,83,72,0.9540229885057471,0.535483870967742,0.6859504132231404,0.5632183908045977
+4,4,94,94,92,92,0.9787234042553191,0.5,0.6618705035971223,0.5
+5,5,62,62,44,58,0.7096774193548387,0.43137254901960786,0.5365853658536586,0.3870967741935484
+6,6,63,63,61,51,0.9682539682539683,0.5446428571428571,0.6971428571428572,0.5793650793650794
+7,7,17,17,16,11,0.9411764705882353,0.5925925925925926,0.7272727272727272,0.6470588235294118
+8,8,65,65,63,64,0.9692307692307692,0.49606299212598426,0.6562499999999999,0.49230769230769234
+9,9,31,31,31,31,1.0,0.5,0.6666666666666666,0.5
+10,10,57,57,52,47,0.9122807017543859,0.5252525252525253,0.6666666666666667,0.543859649122807
+11,11,48,48,48,44,1.0,0.5217391304347826,0.6857142857142856,0.5416666666666666
+12,12,36,36,31,36,0.8611111111111112,0.4626865671641791,0.6019417475728156,0.4305555555555556
+13,13,17,17,17,11,1.0,0.6071428571428571,0.7555555555555554,0.6764705882352942
+14,14,77,77,70,63,0.9090909090909091,0.5263157894736842,0.6666666666666666,0.5454545454545454
+15,15,40,40,38,38,0.95,0.5,0.6551724137931034,0.5
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,987,953,,,,
+18,,,,,Micro avg.,0.9463087248322147,0.5087628865979381,0.6617499161917532,0.5162991371045063
+19,,,,,Macro avg.,0.9450628083614871,0.5449170358391726,0.685901094989606,0.5555211365171032
+threshold-0.5,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,2,0,1.0,1.0,1.0,1.0
+1,1,30,30,23,13,0.7666666666666667,0.6388888888888888,0.696969696969697,0.6666666666666666
+2,2,288,288,260,246,0.9027777777777778,0.5138339920948617,0.654911838790932,0.5243055555555556
+3,3,87,87,70,50,0.8045977011494253,0.5833333333333334,0.6763285024154589,0.6149425287356322
+4,4,94,94,77,82,0.8191489361702128,0.48427672955974843,0.6086956521739131,0.4734042553191489
+5,5,62,62,33,41,0.532258064516129,0.44594594594594594,0.4852941176470588,0.43548387096774194
+6,6,63,63,58,31,0.9206349206349206,0.651685393258427,0.763157894736842,0.7142857142857143
+7,7,17,17,13,5,0.7647058823529411,0.7222222222222222,0.7428571428571428,0.7352941176470589
+8,8,65,65,58,58,0.8923076923076924,0.5,0.6408839779005525,0.5
+9,9,31,31,21,16,0.6774193548387096,0.5675675675675675,0.6176470588235294,0.5806451612903226
+10,10,57,57,47,41,0.8245614035087719,0.5340909090909091,0.6482758620689655,0.5526315789473685
+11,11,48,48,41,33,0.8541666666666666,0.5540540540540541,0.6721311475409837,0.5833333333333334
+12,12,36,36,28,32,0.7777777777777778,0.4666666666666667,0.5833333333333334,0.4444444444444444
+13,13,17,17,16,9,0.9411764705882353,0.64,0.7619047619047621,0.7058823529411765
+14,14,77,77,66,45,0.8571428571428571,0.5945945945945946,0.7021276595744681,0.6363636363636364
+15,15,40,40,28,27,0.7,0.509090909090909,0.5894736842105263,0.5125
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,870,758,,,,
+18,,,,,Micro avg.,0.8341323106423778,0.5343980343980343,0.6514414077124673,0.5536912751677853
+19,,,,,Macro avg.,0.8256083630646344,0.5827206591981253,0.6770975880949903,0.5988343068528117
+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
+1,1,30,30,11,3,0.36666666666666664,0.7857142857142857,0.5,0.6333333333333333
+2,2,288,288,187,149,0.6493055555555556,0.5565476190476191,0.5993589743589743,0.5659722222222222
+3,3,87,87,40,19,0.45977011494252873,0.6779661016949152,0.5479452054794521,0.6206896551724138
+4,4,94,94,57,38,0.6063829787234043,0.6,0.6031746031746033,0.601063829787234
+5,5,62,62,17,9,0.27419354838709675,0.6538461538461539,0.38636363636363635,0.5645161290322581
+6,6,63,63,45,12,0.7142857142857143,0.7894736842105263,0.7500000000000001,0.7619047619047619
+7,7,17,17,10,2,0.5882352941176471,0.8333333333333334,0.6896551724137931,0.7352941176470589
+8,8,65,65,35,33,0.5384615384615384,0.5147058823529411,0.5263157894736842,0.5153846153846153
+9,9,31,31,11,5,0.3548387096774194,0.6875,0.4680851063829787,0.5967741935483871
+10,10,57,57,43,25,0.7543859649122807,0.6323529411764706,0.688,0.6578947368421053
+11,11,48,48,29,19,0.6041666666666666,0.6041666666666666,0.6041666666666666,0.6041666666666666
+12,12,36,36,22,15,0.6111111111111112,0.5945945945945946,0.6027397260273972,0.5972222222222222
+13,13,17,17,14,5,0.8235294117647058,0.7368421052631579,0.7777777777777778,0.7647058823529411
+14,14,77,77,48,31,0.6233766233766234,0.6075949367088608,0.6153846153846154,0.6103896103896104
+15,15,40,40,17,17,0.425,0.5,0.45945945945945943,0.5
+16,16,29,29,28,27,0.9655172413793104,0.509090909090909,0.6666666666666667,0.5172413793103449
+17,total,1043,1043,615,409,,,,
+18,,,,,Micro avg.,0.5896452540747843,0.6005859375,0.5950653120464441,0.5987535953978907
+19,,,,,Macro avg.,0.5799545376487217,0.6637487772764962,0.597162356840963,0.6233266679891869
+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
+1,1,30,30,24,16,0.8,0.6,0.6857142857142857,0.6333333333333333
+2,2,288,288,276,261,0.9583333333333334,0.5139664804469274,0.6690909090909091,0.5260416666666666
+3,3,87,87,77,49,0.8850574712643678,0.6111111111111112,0.7230046948356809,0.6609195402298851
+4,4,94,94,78,88,0.8297872340425532,0.46987951807228917,0.6,0.44680851063829785
+5,5,62,62,30,36,0.4838709677419355,0.45454545454545453,0.46874999999999994,0.45161290322580644
+6,6,63,63,58,34,0.9206349206349206,0.6304347826086957,0.7483870967741935,0.6904761904761905
+7,7,17,17,14,8,0.8235294117647058,0.6363636363636364,0.717948717948718,0.6764705882352942
+8,8,65,65,57,58,0.8769230769230769,0.4956521739130435,0.6333333333333333,0.49230769230769234
+9,9,31,31,24,20,0.7741935483870968,0.5454545454545454,0.64,0.5645161290322581
+10,10,57,57,49,41,0.8596491228070176,0.5444444444444444,0.6666666666666667,0.5701754385964912
+11,11,48,48,42,34,0.875,0.5526315789473685,0.6774193548387096,0.5833333333333334
+12,12,36,36,31,34,0.8611111111111112,0.47692307692307695,0.6138613861386139,0.4583333333333333
+13,13,17,17,17,9,1.0,0.6538461538461539,0.7906976744186047,0.7352941176470589
+14,14,77,77,65,48,0.8441558441558441,0.5752212389380531,0.6842105263157895,0.6103896103896104
+15,15,40,40,36,37,0.9,0.4931506849315068,0.6371681415929203,0.4875
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,909,802,,,,
+18,,,,,Micro avg.,0.8715244487056567,0.5312682641729982,0.6601307189542482,0.551294343240652
+19,,,,,Macro avg.,0.864249767186233,0.5737426400321357,0.6837011443726524,0.5933830816144265
+topk-7,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
+1,1,30,30,19,7,0.6333333333333333,0.7307692307692307,0.6785714285714285,0.7
+2,2,288,288,269,245,0.9340277777777778,0.5233463035019456,0.6708229426433916,0.5416666666666666
+3,3,87,87,67,43,0.7701149425287356,0.6090909090909091,0.6802030456852791,0.6379310344827587
+4,4,94,94,70,83,0.7446808510638298,0.45751633986928103,0.5668016194331983,0.4308510638297872
+5,5,62,62,27,26,0.43548387096774194,0.5094339622641509,0.46956521739130436,0.5080645161290323
+6,6,63,63,56,26,0.8888888888888888,0.6829268292682927,0.7724137931034482,0.7380952380952381
+7,7,17,17,11,8,0.6470588235294118,0.5789473684210527,0.6111111111111113,0.5882352941176471
+8,8,65,65,49,55,0.7538461538461538,0.47115384615384615,0.5798816568047337,0.45384615384615384
+9,9,31,31,21,15,0.6774193548387096,0.5833333333333334,0.626865671641791,0.5967741935483871
+10,10,57,57,48,37,0.8421052631578947,0.5647058823529412,0.676056338028169,0.5964912280701754
+11,11,48,48,37,27,0.7708333333333334,0.578125,0.6607142857142857,0.6041666666666666
+12,12,36,36,28,33,0.7777777777777778,0.45901639344262296,0.5773195876288659,0.4305555555555556
+13,13,17,17,17,8,1.0,0.68,0.8095238095238095,0.7647058823529411
+14,14,77,77,59,40,0.7662337662337663,0.5959595959595959,0.6704545454545454,0.6233766233766234
+15,15,40,40,31,29,0.775,0.5166666666666667,0.62,0.525
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,839,711,,,,
+18,,,,,Micro avg.,0.8044103547459253,0.5412903225806451,0.6471268800617047,0.5613614573346117
+19,,,,,Macro avg.,0.7598120080751385,0.5906465682996392,0.6472728462393349,0.5876329480433902
+topk-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
+1,1,30,30,17,7,0.5666666666666667,0.7083333333333334,0.6296296296296297,0.6666666666666666
+2,2,288,288,253,225,0.8784722222222222,0.5292887029288703,0.660574412532637,0.5486111111111112
+3,3,87,87,58,37,0.6666666666666666,0.6105263157894737,0.6373626373626373,0.6206896551724138
+4,4,94,94,70,68,0.7446808510638298,0.5072463768115942,0.603448275862069,0.5106382978723404
+5,5,62,62,21,16,0.3387096774193548,0.5675675675675675,0.42424242424242425,0.5403225806451613
+6,6,63,63,48,18,0.7619047619047619,0.7272727272727273,0.7441860465116279,0.7380952380952381
+7,7,17,17,10,5,0.5882352941176471,0.6666666666666666,0.625,0.6470588235294118
+8,8,65,65,45,50,0.6923076923076923,0.47368421052631576,0.5625,0.46153846153846156
+9,9,31,31,15,8,0.4838709677419355,0.6521739130434783,0.5555555555555556,0.6129032258064516
+10,10,57,57,45,35,0.7894736842105263,0.5625,0.656934306569343,0.5877192982456141
+11,11,48,48,29,26,0.6041666666666666,0.5272727272727272,0.5631067961165047,0.53125
+12,12,36,36,22,27,0.6111111111111112,0.4489795918367347,0.5176470588235293,0.4305555555555556
+13,13,17,17,15,7,0.8823529411764706,0.6818181818181818,0.7692307692307693,0.7352941176470589
+14,14,77,77,55,35,0.7142857142857143,0.6111111111111112,0.6586826347305389,0.6298701298701299
+15,15,40,40,27,24,0.675,0.5294117647058824,0.5934065934065933,0.5375
+16,16,29,29,28,29,0.9655172413793104,0.49122807017543857,0.6511627906976745,0.4827586206896552
+17,total,1043,1043,759,617,,,,
+18,,,,,Micro avg.,0.7277085330776606,0.5515988372093024,0.6275320380322447,0.5680728667305849
+19,,,,,Macro avg.,0.6743189505259162,0.605593015344712,0.6187845057610706,0.5900865754379571
+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
+1,1,30,30,14,2,0.4666666666666667,0.875,0.608695652173913,0.7
+2,2,288,288,214,182,0.7430555555555556,0.5404040404040404,0.6257309941520468,0.5555555555555556
+3,3,87,87,41,26,0.47126436781609193,0.6119402985074627,0.5324675324675324,0.5862068965517241
+4,4,94,94,59,43,0.6276595744680851,0.5784313725490197,0.6020408163265305,0.5851063829787234
+5,5,62,62,15,9,0.24193548387096775,0.625,0.3488372093023256,0.5483870967741935
+6,6,63,63,39,8,0.6190476190476191,0.8297872340425532,0.7090909090909091,0.746031746031746
+7,7,17,17,9,2,0.5294117647058824,0.8181818181818182,0.6428571428571428,0.7058823529411765
+8,8,65,65,37,32,0.5692307692307692,0.5362318840579711,0.5522388059701493,0.5384615384615384
+9,9,31,31,9,6,0.2903225806451613,0.6,0.3913043478260869,0.5483870967741935
+10,10,57,57,40,26,0.7017543859649122,0.6060606060606061,0.6504065040650407,0.6228070175438597
+11,11,48,48,17,18,0.3541666666666667,0.4857142857142857,0.40963855421686746,0.4895833333333333
+12,12,36,36,15,19,0.4166666666666667,0.4411764705882353,0.42857142857142855,0.4444444444444444
+13,13,17,17,14,5,0.8235294117647058,0.7368421052631579,0.7777777777777778,0.7647058823529411
+14,14,77,77,47,21,0.6103896103896104,0.6911764705882353,0.6482758620689656,0.6688311688311688
+15,15,40,40,20,16,0.5,0.5555555555555556,0.5263157894736842,0.55
+16,16,29,29,24,23,0.8275862068965517,0.5106382978723404,0.631578947368421,0.5172413793103449
+17,total,1043,1043,615,438,,,,
+18,,,,,Micro avg.,0.5896452540747843,0.584045584045584,0.5868320610687023,0.5848513902205177
+19,,,,,Macro avg.,0.5466286664915243,0.6495376729050166,0.5736761729632641,0.6071548171697027