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

Reports/report-Model-0_Queries-0_Prompt-3_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
+2,2,288,288,89,70,0.3090277777777778,0.559748427672956,0.3982102908277405,0.5329861111111112
+3,3,87,87,11,5,0.12643678160919541,0.6875,0.21359223300970878,0.5344827586206896
+4,4,94,94,21,4,0.22340425531914893,0.84,0.3529411764705882,0.5904255319148937
+5,5,62,62,5,2,0.08064516129032258,0.7142857142857143,0.14492753623188404,0.5241935483870968
+6,6,63,63,6,0,0.09523809523809523,1.0,0.17391304347826084,0.5476190476190477
+7,7,17,17,5,1,0.29411764705882354,0.8333333333333334,0.4347826086956522,0.6176470588235294
+8,8,65,65,5,4,0.07692307692307693,0.5555555555555556,0.13513513513513514,0.5076923076923077
+9,9,31,31,8,9,0.25806451612903225,0.47058823529411764,0.3333333333333333,0.4838709677419355
+10,10,57,57,13,9,0.22807017543859648,0.5909090909090909,0.32911392405063294,0.5350877192982456
+11,11,48,48,28,23,0.5833333333333334,0.5490196078431373,0.5656565656565657,0.5520833333333334
+12,12,36,36,11,8,0.3055555555555556,0.5789473684210527,0.4000000000000001,0.5416666666666666
+13,13,17,17,0,0,0.0,0.0,0.0,0.5
+14,14,77,77,9,5,0.11688311688311688,0.6428571428571429,0.1978021978021978,0.525974025974026
+15,15,40,40,0,0,0.0,0.0,0.0,0.5
+16,16,29,29,13,12,0.4482758620689655,0.52,0.48148148148148145,0.5172413793103449
+17,total,1043,1043,224,152,,,,
+18,,,,,Micro avg.,0.21476510067114093,0.5957446808510638,0.31571529245947855,0.534515819750719
+19,,,,,Macro avg.,0.18505737380147297,0.5025143809513,0.24475820742195187,0.5300570856760723
+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
+1,1,30,30,29,23,0.9666666666666667,0.5576923076923077,0.7073170731707317,0.6
+2,2,288,288,285,282,0.9895833333333334,0.5026455026455027,0.6666666666666667,0.5052083333333334
+3,3,87,87,78,59,0.896551724137931,0.5693430656934306,0.6964285714285714,0.6091954022988506
+4,4,94,94,91,87,0.9680851063829787,0.5112359550561798,0.6691176470588236,0.5212765957446809
+5,5,62,62,39,47,0.6290322580645161,0.45348837209302323,0.527027027027027,0.43548387096774194
+6,6,63,63,60,54,0.9523809523809523,0.5263157894736842,0.6779661016949152,0.5476190476190477
+7,7,17,17,16,16,0.9411764705882353,0.5,0.6530612244897959,0.5
+8,8,65,65,52,45,0.8,0.5360824742268041,0.6419753086419753,0.5538461538461539
+9,9,31,31,31,31,1.0,0.5,0.6666666666666666,0.5
+10,10,57,57,54,42,0.9473684210526315,0.5625,0.7058823529411765,0.6052631578947368
+11,11,48,48,48,47,1.0,0.5052631578947369,0.6713286713286714,0.5104166666666666
+12,12,36,36,35,36,0.9722222222222222,0.49295774647887325,0.6542056074766356,0.4861111111111111
+13,13,17,17,13,15,0.7647058823529411,0.4642857142857143,0.5777777777777777,0.4411764705882353
+14,14,77,77,72,68,0.935064935064935,0.5142857142857142,0.663594470046083,0.525974025974026
+15,15,40,40,29,33,0.725,0.46774193548387094,0.5686274509803921,0.45
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,963,916,,,,
+18,,,,,Micro avg.,0.9232981783317353,0.5125066524747206,0.6591375770020534,0.5225311601150527
+19,,,,,Macro avg.,0.9110492924851379,0.5096375138417554,0.651822114748779,0.5171512256496814
+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
+1,1,30,30,20,12,0.6666666666666666,0.625,0.6451612903225806,0.6333333333333333
+2,2,288,288,254,234,0.8819444444444444,0.5204918032786885,0.6546391752577319,0.5347222222222222
+3,3,87,87,65,42,0.7471264367816092,0.6074766355140186,0.6701030927835052,0.632183908045977
+4,4,94,94,64,43,0.6808510638297872,0.5981308411214953,0.6368159203980099,0.6117021276595744
+5,5,62,62,26,27,0.41935483870967744,0.49056603773584906,0.45217391304347826,0.49193548387096775
+6,6,63,63,56,33,0.8888888888888888,0.6292134831460674,0.7368421052631579,0.6825396825396826
+7,7,17,17,15,15,0.8823529411764706,0.5,0.6382978723404256,0.5
+8,8,65,65,41,30,0.6307692307692307,0.5774647887323944,0.6029411764705882,0.5846153846153846
+9,9,31,31,31,31,1.0,0.5,0.6666666666666666,0.5
+10,10,57,57,42,23,0.7368421052631579,0.6461538461538462,0.6885245901639344,0.6666666666666666
+11,11,48,48,47,46,0.9791666666666666,0.5053763440860215,0.6666666666666667,0.5104166666666666
+12,12,36,36,30,34,0.8333333333333334,0.46875,0.6,0.4444444444444444
+13,13,17,17,6,6,0.35294117647058826,0.5,0.41379310344827586,0.5
+14,14,77,77,64,58,0.8311688311688312,0.5245901639344263,0.6432160804020102,0.538961038961039
+15,15,40,40,11,17,0.275,0.39285714285714285,0.32352941176470584,0.425
+16,16,29,29,28,27,0.9655172413793104,0.509090909090909,0.6666666666666667,0.5172413793103449
+17,total,1043,1043,801,678,,,,
+18,,,,,Micro avg.,0.7679769894534996,0.5415821501014199,0.6352101506740683,0.5589645254074784
+19,,,,,Macro avg.,0.7218778744440391,0.5644212938618153,0.610159082254416,0.5602213140197827
+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
+1,1,30,30,2,0,0.06666666666666667,1.0,0.125,0.5333333333333333
+2,2,288,288,122,114,0.4236111111111111,0.5169491525423728,0.465648854961832,0.5138888888888888
+3,3,87,87,36,7,0.41379310344827586,0.8372093023255814,0.5538461538461538,0.6666666666666666
+4,4,94,94,28,10,0.2978723404255319,0.7368421052631579,0.4242424242424243,0.5957446808510638
+5,5,62,62,9,10,0.14516129032258066,0.47368421052631576,0.2222222222222222,0.49193548387096775
+6,6,63,63,36,7,0.5714285714285714,0.8372093023255814,0.679245283018868,0.7301587301587301
+7,7,17,17,12,4,0.7058823529411765,0.75,0.7272727272727272,0.7352941176470589
+8,8,65,65,17,9,0.26153846153846155,0.6538461538461539,0.37362637362637363,0.5615384615384615
+9,9,31,31,21,16,0.6774193548387096,0.5675675675675675,0.6176470588235294,0.5806451612903226
+10,10,57,57,30,17,0.5263157894736842,0.6382978723404256,0.5769230769230769,0.6140350877192983
+11,11,48,48,36,33,0.75,0.5217391304347826,0.6153846153846153,0.53125
+12,12,36,36,22,18,0.6111111111111112,0.55,0.5789473684210527,0.5555555555555556
+13,13,17,17,1,0,0.058823529411764705,1.0,0.1111111111111111,0.5294117647058824
+14,14,77,77,19,23,0.24675324675324675,0.4523809523809524,0.31932773109243695,0.474025974025974
+15,15,40,40,2,1,0.05,0.6666666666666666,0.09302325581395349,0.5125
+16,16,29,29,22,20,0.7586206896551724,0.5238095238095238,0.6197183098591549,0.5344827586206896
+17,total,1043,1043,415,289,,,,
+18,,,,,Micro avg.,0.39789069990412274,0.5894886363636364,0.47510017172295366,0.5604026845637584
+19,,,,,Macro avg.,0.3861763305368274,0.6309530552958283,0.41783450391879595,0.568262744992523
+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
+2,2,288,288,15,8,0.052083333333333336,0.6521739130434783,0.09646302250803859,0.5121527777777778
+3,3,87,87,4,0,0.04597701149425287,1.0,0.08791208791208792,0.5229885057471264
+4,4,94,94,5,1,0.05319148936170213,0.8333333333333334,0.09999999999999999,0.5212765957446809
+5,5,62,62,1,0,0.016129032258064516,1.0,0.031746031746031744,0.5080645161290323
+6,6,63,63,6,0,0.09523809523809523,1.0,0.17391304347826084,0.5476190476190477
+7,7,17,17,1,0,0.058823529411764705,1.0,0.1111111111111111,0.5294117647058824
+8,8,65,65,2,2,0.03076923076923077,0.5,0.057971014492753624,0.5
+9,9,31,31,1,1,0.03225806451612903,0.5,0.06060606060606061,0.5
+10,10,57,57,11,4,0.19298245614035087,0.7333333333333333,0.3055555555555555,0.5614035087719298
+11,11,48,48,18,9,0.375,0.6666666666666666,0.4800000000000001,0.59375
+12,12,36,36,9,4,0.25,0.6923076923076923,0.3673469387755102,0.5694444444444444
+13,13,17,17,0,0,0.0,0.0,0.0,0.5
+14,14,77,77,3,5,0.03896103896103896,0.375,0.07058823529411765,0.487012987012987
+15,15,40,40,0,0,0.0,0.0,0.0,0.5
+16,16,29,29,11,9,0.3793103448275862,0.55,0.4489795918367347,0.5344827586206896
+17,total,1043,1043,87,43,,,,
+18,,,,,Micro avg.,0.08341323106423777,0.6692307692307692,0.1483375959079284,0.5210930009587728
+19,,,,,Macro avg.,0.09533668390067931,0.558989114040265,0.14071721725389777,0.5228004062690352
+topk-9,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,1,2,0.5,0.3333333333333333,0.4,0.25
+1,1,30,30,20,13,0.6666666666666666,0.6060606060606061,0.6349206349206349,0.6166666666666667
+2,2,288,288,278,261,0.9652777777777778,0.5157699443413729,0.6723095525997581,0.5295138888888888
+3,3,87,87,68,42,0.7816091954022989,0.6181818181818182,0.6903553299492386,0.6494252873563219
+4,4,94,94,71,67,0.7553191489361702,0.5144927536231884,0.6120689655172413,0.5212765957446809
+5,5,62,62,21,24,0.3387096774193548,0.4666666666666667,0.39252336448598124,0.47580645161290325
+6,6,63,63,53,35,0.8412698412698413,0.6022727272727273,0.7019867549668876,0.6428571428571429
+7,7,17,17,16,16,0.9411764705882353,0.5,0.6530612244897959,0.5
+8,8,65,65,44,36,0.676923076923077,0.55,0.6068965517241379,0.5615384615384615
+9,9,31,31,31,31,1.0,0.5,0.6666666666666666,0.5
+10,10,57,57,42,24,0.7368421052631579,0.6363636363636364,0.6829268292682926,0.6578947368421053
+11,11,48,48,47,47,0.9791666666666666,0.5,0.6619718309859155,0.5
+12,12,36,36,30,32,0.8333333333333334,0.4838709677419355,0.6122448979591837,0.4722222222222222
+13,13,17,17,10,4,0.5882352941176471,0.7142857142857143,0.6451612903225806,0.6764705882352942
+14,14,77,77,63,56,0.8181818181818182,0.5294117647058824,0.6428571428571428,0.5454545454545454
+15,15,40,40,16,10,0.4,0.6153846153846154,0.4848484848484849,0.575
+16,16,29,29,27,28,0.9310344827586207,0.4909090909090909,0.6428571428571428,0.4827586206896552
+17,total,1043,1043,838,728,,,,
+18,,,,,Micro avg.,0.8034515819750719,0.5351213282247765,0.6423917209658874,0.552732502396932
+19,,,,,Macro avg.,0.7502203267826274,0.5398237434629758,0.6119798037893579,0.5386403063593463
+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
+1,1,30,30,14,4,0.4666666666666667,0.7777777777777778,0.5833333333333334,0.6666666666666666
+2,2,288,288,270,253,0.9375,0.5162523900573613,0.6658446362515413,0.5295138888888888
+3,3,87,87,64,36,0.735632183908046,0.64,0.6844919786096256,0.6609195402298851
+4,4,94,94,63,48,0.6702127659574468,0.5675675675675675,0.6146341463414634,0.5797872340425532
+5,5,62,62,19,16,0.3064516129032258,0.5428571428571428,0.39175257731958757,0.5241935483870968
+6,6,63,63,50,22,0.7936507936507936,0.6944444444444444,0.7407407407407406,0.7222222222222222
+7,7,17,17,16,14,0.9411764705882353,0.5333333333333333,0.6808510638297872,0.5588235294117647
+8,8,65,65,29,28,0.4461538461538462,0.5087719298245614,0.4754098360655738,0.5076923076923077
+9,9,31,31,31,31,1.0,0.5,0.6666666666666666,0.5
+10,10,57,57,40,20,0.7017543859649122,0.6666666666666666,0.6837606837606838,0.6754385964912281
+11,11,48,48,44,45,0.9166666666666666,0.4943820224719101,0.6423357664233577,0.4895833333333333
+12,12,36,36,30,29,0.8333333333333334,0.5084745762711864,0.631578947368421,0.5138888888888888
+13,13,17,17,6,2,0.35294117647058826,0.75,0.48,0.6176470588235294
+14,14,77,77,58,51,0.7532467532467533,0.5321100917431193,0.6236559139784947,0.5454545454545454
+15,15,40,40,10,3,0.25,0.7692307692307693,0.37735849056603776,0.5875
+16,16,29,29,26,28,0.896551724137931,0.48148148148148145,0.6265060240963856,0.46551724137931033
+17,total,1043,1043,771,630,,,,
+18,,,,,Micro avg.,0.7392138063279002,0.550321199143469,0.6309328968903437,0.5675934803451582
+19,,,,,Macro avg.,0.6765846105675556,0.6166676584545484,0.6020933807069628,0.5820499177595423
+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
+1,1,30,30,3,1,0.1,0.75,0.17647058823529416,0.5333333333333333
+2,2,288,288,243,209,0.84375,0.5376106194690266,0.6567567567567567,0.5590277777777778
+3,3,87,87,56,29,0.6436781609195402,0.6588235294117647,0.6511627906976745,0.6551724137931034
+4,4,94,94,56,31,0.5957446808510638,0.6436781609195402,0.6187845303867403,0.6329787234042553
+5,5,62,62,16,14,0.25806451612903225,0.5333333333333333,0.34782608695652173,0.5161290322580645
+6,6,63,63,44,10,0.6984126984126984,0.8148148148148148,0.7521367521367521,0.7698412698412699
+7,7,17,17,14,13,0.8235294117647058,0.5185185185185185,0.6363636363636364,0.5294117647058824
+8,8,65,65,23,16,0.35384615384615387,0.5897435897435898,0.44230769230769235,0.5538461538461539
+9,9,31,31,30,28,0.967741935483871,0.5172413793103449,0.6741573033707866,0.532258064516129
+10,10,57,57,35,18,0.6140350877192983,0.660377358490566,0.6363636363636364,0.6491228070175439
+11,11,48,48,41,41,0.8541666666666666,0.5,0.6307692307692309,0.5
+12,12,36,36,27,25,0.75,0.5192307692307693,0.6136363636363638,0.5277777777777778
+13,13,17,17,2,1,0.11764705882352941,0.6666666666666666,0.2,0.5294117647058824
+14,14,77,77,38,33,0.4935064935064935,0.5352112676056338,0.5135135135135136,0.5324675324675324
+15,15,40,40,4,1,0.1,0.8,0.1777777777777778,0.5375
+16,16,29,29,24,23,0.8275862068965517,0.5106382978723404,0.631578947368421,0.5172413793103449
+17,total,1043,1043,656,493,,,,
+18,,,,,Micro avg.,0.6289549376797698,0.5709312445604874,0.5985401459854014,0.5781399808245445
+19,,,,,Macro avg.,0.5318652394717414,0.5738757826698182,0.4917415062729881,0.5632658702797088
+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
+2,2,288,288,195,154,0.6770833333333334,0.5587392550143266,0.6122448979591836,0.5711805555555556
+3,3,87,87,45,18,0.5172413793103449,0.7142857142857143,0.6000000000000001,0.6551724137931034
+4,4,94,94,41,14,0.43617021276595747,0.7454545454545455,0.5503355704697986,0.6436170212765957
+5,5,62,62,6,10,0.0967741935483871,0.375,0.15384615384615383,0.46774193548387094
+6,6,63,63,29,2,0.4603174603174603,0.9354838709677419,0.6170212765957446,0.7142857142857143
+7,7,17,17,11,8,0.6470588235294118,0.5789473684210527,0.6111111111111113,0.5882352941176471
+8,8,65,65,14,8,0.2153846153846154,0.6363636363636364,0.3218390804597701,0.5461538461538461
+9,9,31,31,26,25,0.8387096774193549,0.5098039215686274,0.6341463414634145,0.5161290322580645
+10,10,57,57,28,16,0.49122807017543857,0.6363636363636364,0.5544554455445544,0.6052631578947368
+11,11,48,48,35,33,0.7291666666666666,0.5147058823529411,0.603448275862069,0.5208333333333334
+12,12,36,36,22,20,0.6111111111111112,0.5238095238095238,0.5641025641025642,0.5277777777777778
+13,13,17,17,1,1,0.058823529411764705,0.5,0.10526315789473684,0.5
+14,14,77,77,22,19,0.2857142857142857,0.5365853658536586,0.37288135593220334,0.5194805194805194
+15,15,40,40,2,0,0.05,1.0,0.09523809523809523,0.525
+16,16,29,29,19,21,0.6551724137931034,0.475,0.5507246376811594,0.46551724137931033
+17,total,1043,1043,496,349,,,,
+18,,,,,Micro avg.,0.47555129434324067,0.58698224852071,0.5254237288135594,0.5704697986577181
+19,,,,,Macro avg.,0.3982326924988962,0.5435613364973768,0.40862693906826814,0.5509639907523574