/////////////////////////////////////////// // Running CTAB-GAN on imblearn_ozone_level /////////////////////////////////////////// Load 'data_input/imblearn_ozone_level' from imblearn Data loaded. -> Shuffling data ### Start exercise for synthetic point generator ====== Step 1/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 1/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 477, 16 LR fn, tp: 9, 6 LR f1 score: 0.324 LR cohens kappa score: 0.300 LR average precision score: 0.388 -> test with 'GB' GB tn, fp: 489, 4 GB fn, tp: 12, 3 GB f1 score: 0.273 GB cohens kappa score: 0.259 -> test with 'KNN' KNN tn, fp: 489, 4 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.013 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 470, 23 LR fn, tp: 9, 6 LR f1 score: 0.273 LR cohens kappa score: 0.243 LR average precision score: 0.166 -> test with 'GB' GB tn, fp: 492, 1 GB fn, tp: 12, 3 GB f1 score: 0.316 GB cohens kappa score: 0.307 -> test with 'KNN' KNN tn, fp: 482, 11 KNN fn, tp: 14, 1 KNN f1 score: 0.074 KNN cohens kappa score: 0.049 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 469, 24 LR fn, tp: 8, 7 LR f1 score: 0.304 LR cohens kappa score: 0.276 LR average precision score: 0.184 -> test with 'GB' GB tn, fp: 491, 2 GB fn, tp: 14, 1 GB f1 score: 0.111 GB cohens kappa score: 0.102 -> test with 'KNN' KNN tn, fp: 488, 5 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.015 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 477, 16 LR fn, tp: 12, 3 LR f1 score: 0.176 LR cohens kappa score: 0.148 LR average precision score: 0.116 -> test with 'GB' GB tn, fp: 487, 6 GB fn, tp: 13, 2 GB f1 score: 0.174 GB cohens kappa score: 0.157 -> test with 'KNN' KNN tn, fp: 488, 5 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.015 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 473, 18 LR fn, tp: 9, 4 LR f1 score: 0.229 LR cohens kappa score: 0.203 LR average precision score: 0.123 -> test with 'GB' GB tn, fp: 488, 3 GB fn, tp: 13, 0 GB f1 score: 0.000 GB cohens kappa score: -0.010 -> test with 'KNN' KNN tn, fp: 481, 10 KNN fn, tp: 13, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.023 ====== Step 2/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 2/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 479, 14 LR fn, tp: 10, 5 LR f1 score: 0.294 LR cohens kappa score: 0.270 LR average precision score: 0.253 -> test with 'GB' GB tn, fp: 488, 5 GB fn, tp: 13, 2 GB f1 score: 0.182 GB cohens kappa score: 0.166 -> test with 'KNN' KNN tn, fp: 482, 11 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.026 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 478, 15 LR fn, tp: 9, 6 LR f1 score: 0.333 LR cohens kappa score: 0.310 LR average precision score: 0.186 -> test with 'GB' GB tn, fp: 491, 2 GB fn, tp: 13, 2 GB f1 score: 0.211 GB cohens kappa score: 0.201 -> test with 'KNN' KNN tn, fp: 487, 6 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.017 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 477, 16 LR fn, tp: 8, 7 LR f1 score: 0.368 LR cohens kappa score: 0.345 LR average precision score: 0.261 -> test with 'GB' GB tn, fp: 488, 5 GB fn, tp: 13, 2 GB f1 score: 0.182 GB cohens kappa score: 0.166 -> test with 'KNN' KNN tn, fp: 478, 15 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.030 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 465, 28 LR fn, tp: 13, 2 LR f1 score: 0.089 LR cohens kappa score: 0.052 LR average precision score: 0.110 -> test with 'GB' GB tn, fp: 490, 3 GB fn, tp: 13, 2 GB f1 score: 0.200 GB cohens kappa score: 0.188 -> test with 'KNN' KNN tn, fp: 486, 7 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.019 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 471, 20 LR fn, tp: 9, 4 LR f1 score: 0.216 LR cohens kappa score: 0.189 LR average precision score: 0.146 -> test with 'GB' GB tn, fp: 489, 2 GB fn, tp: 12, 1 GB f1 score: 0.125 GB cohens kappa score: 0.116 -> test with 'KNN' KNN tn, fp: 485, 6 KNN fn, tp: 13, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.017 ====== Step 3/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 3/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 477, 16 LR fn, tp: 10, 5 LR f1 score: 0.278 LR cohens kappa score: 0.252 LR average precision score: 0.228 -> test with 'GB' GB tn, fp: 488, 5 GB fn, tp: 13, 2 GB f1 score: 0.182 GB cohens kappa score: 0.166 -> test with 'KNN' KNN tn, fp: 486, 7 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.019 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 477, 16 LR fn, tp: 12, 3 LR f1 score: 0.176 LR cohens kappa score: 0.148 LR average precision score: 0.106 -> test with 'GB' GB tn, fp: 489, 4 GB fn, tp: 13, 2 GB f1 score: 0.190 GB cohens kappa score: 0.177 -> test with 'KNN' KNN tn, fp: 490, 3 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.010 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 477, 16 LR fn, tp: 7, 8 LR f1 score: 0.410 LR cohens kappa score: 0.388 LR average precision score: 0.299 -> test with 'GB' GB tn, fp: 489, 4 GB fn, tp: 11, 4 GB f1 score: 0.348 GB cohens kappa score: 0.334 -> test with 'KNN' KNN tn, fp: 489, 4 KNN fn, tp: 14, 1 KNN f1 score: 0.100 KNN cohens kappa score: 0.087 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 477, 16 LR fn, tp: 11, 4 LR f1 score: 0.229 LR cohens kappa score: 0.202 LR average precision score: 0.143 -> test with 'GB' GB tn, fp: 492, 1 GB fn, tp: 13, 2 GB f1 score: 0.222 GB cohens kappa score: 0.214 -> test with 'KNN' KNN tn, fp: 486, 7 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.019 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 465, 26 LR fn, tp: 9, 4 LR f1 score: 0.186 LR cohens kappa score: 0.156 LR average precision score: 0.213 -> test with 'GB' GB tn, fp: 484, 7 GB fn, tp: 13, 0 GB f1 score: 0.000 GB cohens kappa score: -0.018 -> test with 'KNN' KNN tn, fp: 486, 5 KNN fn, tp: 13, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.015 ====== Step 4/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 4/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 475, 18 LR fn, tp: 12, 3 LR f1 score: 0.167 LR cohens kappa score: 0.137 LR average precision score: 0.135 -> test with 'GB' GB tn, fp: 491, 2 GB fn, tp: 13, 2 GB f1 score: 0.211 GB cohens kappa score: 0.201 -> test with 'KNN' KNN tn, fp: 485, 8 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.021 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 476, 17 LR fn, tp: 12, 3 LR f1 score: 0.171 LR cohens kappa score: 0.142 LR average precision score: 0.152 -> test with 'GB' GB tn, fp: 491, 2 GB fn, tp: 13, 2 GB f1 score: 0.211 GB cohens kappa score: 0.201 -> test with 'KNN' KNN tn, fp: 489, 4 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.013 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 469, 24 LR fn, tp: 9, 6 LR f1 score: 0.267 LR cohens kappa score: 0.237 LR average precision score: 0.147 -> test with 'GB' GB tn, fp: 493, 0 GB fn, tp: 13, 2 GB f1 score: 0.235 GB cohens kappa score: 0.230 -> test with 'KNN' KNN tn, fp: 484, 9 KNN fn, tp: 14, 1 KNN f1 score: 0.080 KNN cohens kappa score: 0.058 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 484, 9 LR fn, tp: 7, 8 LR f1 score: 0.500 LR cohens kappa score: 0.484 LR average precision score: 0.424 -> test with 'GB' GB tn, fp: 491, 2 GB fn, tp: 13, 2 GB f1 score: 0.211 GB cohens kappa score: 0.201 -> test with 'KNN' KNN tn, fp: 484, 9 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.023 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 475, 16 LR fn, tp: 7, 6 LR f1 score: 0.343 LR cohens kappa score: 0.321 LR average precision score: 0.181 -> test with 'GB' GB tn, fp: 488, 3 GB fn, tp: 10, 3 GB f1 score: 0.316 GB cohens kappa score: 0.304 -> test with 'KNN' KNN tn, fp: 483, 8 KNN fn, tp: 13, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.020 ====== Step 5/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 5/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 477, 16 LR fn, tp: 7, 8 LR f1 score: 0.410 LR cohens kappa score: 0.388 LR average precision score: 0.275 -> test with 'GB' GB tn, fp: 491, 2 GB fn, tp: 12, 3 GB f1 score: 0.300 GB cohens kappa score: 0.290 -> test with 'KNN' KNN tn, fp: 485, 8 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.021 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 479, 14 LR fn, tp: 11, 4 LR f1 score: 0.242 LR cohens kappa score: 0.217 LR average precision score: 0.200 -> test with 'GB' GB tn, fp: 489, 4 GB fn, tp: 14, 1 GB f1 score: 0.100 GB cohens kappa score: 0.087 -> test with 'KNN' KNN tn, fp: 488, 5 KNN fn, tp: 14, 1 KNN f1 score: 0.095 KNN cohens kappa score: 0.080 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 482, 11 LR fn, tp: 10, 5 LR f1 score: 0.323 LR cohens kappa score: 0.301 LR average precision score: 0.242 -> test with 'GB' GB tn, fp: 493, 0 GB fn, tp: 14, 1 GB f1 score: 0.125 GB cohens kappa score: 0.122 -> test with 'KNN' KNN tn, fp: 481, 12 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.027 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 475, 18 LR fn, tp: 10, 5 LR f1 score: 0.263 LR cohens kappa score: 0.236 LR average precision score: 0.203 -> test with 'GB' GB tn, fp: 490, 3 GB fn, tp: 12, 3 GB f1 score: 0.286 GB cohens kappa score: 0.273 -> test with 'KNN' KNN tn, fp: 486, 7 KNN fn, tp: 15, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.019 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 1912 synthetic samples -> test with 'LR' LR tn, fp: 474, 17 LR fn, tp: 10, 3 LR f1 score: 0.182 LR cohens kappa score: 0.155 LR average precision score: 0.151 -> test with 'GB' GB tn, fp: 488, 3 GB fn, tp: 10, 3 GB f1 score: 0.316 GB cohens kappa score: 0.304 -> test with 'KNN' KNN tn, fp: 487, 4 KNN fn, tp: 13, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.012 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 484, 28 LR fn, tp: 13, 8 LR f1 score: 0.500 LR cohens kappa score: 0.484 LR average precision score: 0.424 average: LR tn, fp: 475.0, 17.6 LR fn, tp: 9.6, 5.0 LR f1 score: 0.270 LR cohens kappa score: 0.244 LR average precision score: 0.201 minimum: LR tn, fp: 465, 9 LR fn, tp: 7, 2 LR f1 score: 0.089 LR cohens kappa score: 0.052 LR average precision score: 0.106 -----[ GB ]----- maximum: GB tn, fp: 493, 7 GB fn, tp: 14, 4 GB f1 score: 0.348 GB cohens kappa score: 0.334 average: GB tn, fp: 489.6, 3.0 GB fn, tp: 12.6, 2.0 GB f1 score: 0.201 GB cohens kappa score: 0.189 minimum: GB tn, fp: 484, 0 GB fn, tp: 10, 0 GB f1 score: 0.000 GB cohens kappa score: -0.018 -----[ KNN ]----- maximum: KNN tn, fp: 490, 15 KNN fn, tp: 15, 1 KNN f1 score: 0.100 KNN cohens kappa score: 0.087 average: KNN tn, fp: 485.4, 7.2 KNN fn, tp: 14.44, 0.16 KNN f1 score: 0.014 KNN cohens kappa score: -0.005 minimum: KNN tn, fp: 478, 3 KNN fn, tp: 13, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.030