================================================================= hyp_gbm_train.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[2107 0 0 0 0 0 0 0 0] [ 0 0 0 0 0 0 0 0 0] [ 0 0 3133 0 0 0 0 0 0] [ 0 0 0 419 0 0 0 0 0] [ 0 0 0 0 0 0 0 0 0] [ 0 0 0 0 0 509 0 0 0] [ 0 0 0 0 0 0 746 0 0] [ 0 0 0 0 0 0 0 0 0] [ 0 0 0 0 0 0 0 0 2426]] Scoring Summary: (0) norm = 0.0000% (2) nneo = 0.0000% (3) infl = 0.0000% (5) dcis = 0.0000% (6) indc = 0.0000% (8) bckg = 0.0000% avg lbls = 0.0000% avg bckg = 0.0000% score = 0.0000% <** ================================================================= hyp_gbm_dev.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[ 782 4 359 1 0 6 51 3 135] [ 0 0 0 0 0 0 0 0 0] [ 402 2 1061 24 0 44 89 15 179] [ 10 1 98 155 0 18 27 8 3] [ 0 0 0 0 0 0 0 0 0] [ 26 0 190 14 0 35 24 3 4] [ 38 3 137 7 0 10 88 8 11] [ 0 0 0 0 0 0 0 0 0] [ 73 7 39 0 0 0 12 6 1198]] Scoring Summary: (0) norm = 41.6853% (2) nneo = 41.5749% (3) infl = 51.5625% (5) dcis = 88.1757% (6) indc = 70.8609% (8) bckg = 10.2622% avg lbls = 58.7719% avg bckg = 10.2622% score = 53.9209% <** ================================================================= hyp_gbm_eval.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[314 62 462 42 0 38 79 33 319] [ 0 0 0 0 0 0 0 0 0] [505 104 809 60 0 54 121 43 517] [ 55 9 98 2 0 3 11 0 53] [ 0 0 0 0 0 0 0 0 0] [ 50 12 86 9 0 5 19 7 55] [ 92 24 179 12 0 11 39 4 103] [ 0 0 0 0 0 0 0 0 0] [254 41 444 46 0 32 87 26 252]] Scoring Summary: (0) norm = 76.7235% (2) nneo = 63.4433% (3) infl = 99.1342% (5) dcis = 97.9424% (6) indc = 91.5948% (8) bckg = 78.6802% avg lbls = 85.7676% avg bckg = 78.6802% score = 85.0589% <** ======================================================================== ================================================================= hyp_res_train.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[1453 5 193 7 13 43 270 8 115] [ 0 0 0 0 0 0 0 0 0] [ 598 12 873 137 20 406 683 61 343] [ 1 0 6 375 0 10 27 0 0] [ 0 0 0 0 0 0 0 0 0] [ 12 0 27 15 3 367 74 1 10] [ 16 0 27 42 2 43 593 1 22] [ 0 0 0 0 0 0 0 0 0] [ 29 13 21 3 33 8 53 14 2252]] Scoring Summary: (0) norm = 31.0394% (2) nneo = 72.1353% (3) infl = 10.5012% (5) dcis = 27.8978% (6) indc = 20.5094% (8) bckg = 7.1723% avg lbls = 32.4166% avg bckg = 7.1723% score = 29.8922% <** ================================================================= hyp_res_dev.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[ 808 6 116 20 11 41 198 7 134] [ 0 0 0 0 0 0 0 0 0] [ 412 10 385 62 15 223 403 53 253] [ 9 0 13 253 0 24 21 0 0] [ 0 0 0 0 0 0 0 0 0] [ 18 1 41 14 0 127 70 5 20] [ 13 1 20 30 3 29 193 1 12] [ 0 0 0 0 0 0 0 0 0] [ 68 25 20 6 46 10 33 27 1100]] Scoring Summary: (0) norm = 39.7465% (2) nneo = 78.7996% (3) infl = 20.9375% (5) dcis = 57.0946% (6) indc = 36.0927% (8) bckg = 17.6030% avg lbls = 46.5342% avg bckg = 17.6030% score = 43.6410% <** ================================================================= hyp_res_eval.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[273 49 155 74 21 107 261 48 361] [ 0 0 0 0 0 0 0 0 0] [475 91 284 118 29 195 416 58 547] [ 56 4 29 5 5 23 43 10 56] [ 0 0 0 0 0 0 0 0 0] [ 43 7 33 15 2 18 51 5 69] [ 87 24 64 20 3 42 100 10 114] [ 0 0 0 0 0 0 0 0 0] [242 33 120 77 13 112 261 46 278]] Scoring Summary: (0) norm = 79.7628% (2) nneo = 87.1667% (3) infl = 97.8355% (5) dcis = 92.5926% (6) indc = 78.4483% (8) bckg = 76.4805% avg lbls = 87.1612% avg bckg = 76.4805% score = 86.0931% <** ========================================================================