/////////////////////////////////////////// // Running CTAB-GAN on kaggle_creditcard /////////////////////////////////////////// Load 'data_input/kaggle_creditcard' 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 227059 synthetic samples -> test with 'LR' LR tn, fp: 56837, 26 LR fn, tp: 30, 69 LR f1 score: 0.711 LR cohens kappa score: 0.711 LR average precision score: 0.560 -> test with 'GB' GB tn, fp: 56848, 15 GB fn, tp: 27, 72 GB f1 score: 0.774 GB cohens kappa score: 0.774 -> test with 'KNN' KNN tn, fp: 56509, 354 KNN fn, tp: 92, 7 KNN f1 score: 0.030 KNN cohens kappa score: 0.028 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56847, 16 LR fn, tp: 20, 79 LR f1 score: 0.814 LR cohens kappa score: 0.814 LR average precision score: 0.744 -> test with 'GB' GB tn, fp: 56856, 7 GB fn, tp: 26, 73 GB f1 score: 0.816 GB cohens kappa score: 0.815 -> test with 'KNN' KNN tn, fp: 56523, 340 KNN fn, tp: 93, 6 KNN f1 score: 0.027 KNN cohens kappa score: 0.024 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56838, 25 LR fn, tp: 20, 79 LR f1 score: 0.778 LR cohens kappa score: 0.778 LR average precision score: 0.657 -> test with 'GB' GB tn, fp: 56851, 12 GB fn, tp: 20, 79 GB f1 score: 0.832 GB cohens kappa score: 0.831 -> test with 'KNN' KNN tn, fp: 56600, 263 KNN fn, tp: 97, 2 KNN f1 score: 0.011 KNN cohens kappa score: 0.008 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56829, 34 LR fn, tp: 15, 84 LR f1 score: 0.774 LR cohens kappa score: 0.774 LR average precision score: 0.757 -> test with 'GB' GB tn, fp: 56851, 12 GB fn, tp: 17, 82 GB f1 score: 0.850 GB cohens kappa score: 0.849 -> test with 'KNN' KNN tn, fp: 56548, 315 KNN fn, tp: 98, 1 KNN f1 score: 0.005 KNN cohens kappa score: 0.002 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227056 synthetic samples -> test with 'LR' LR tn, fp: 56850, 13 LR fn, tp: 19, 77 LR f1 score: 0.828 LR cohens kappa score: 0.828 LR average precision score: 0.812 -> test with 'GB' GB tn, fp: 56856, 7 GB fn, tp: 18, 78 GB f1 score: 0.862 GB cohens kappa score: 0.862 -> test with 'KNN' KNN tn, fp: 56543, 320 KNN fn, tp: 94, 2 KNN f1 score: 0.010 KNN cohens kappa score: 0.007 ====== 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 227059 synthetic samples -> test with 'LR' LR tn, fp: 56810, 53 LR fn, tp: 15, 84 LR f1 score: 0.712 LR cohens kappa score: 0.711 LR average precision score: 0.694 -> test with 'GB' GB tn, fp: 56847, 16 GB fn, tp: 19, 80 GB f1 score: 0.821 GB cohens kappa score: 0.820 -> test with 'KNN' KNN tn, fp: 56522, 341 KNN fn, tp: 96, 3 KNN f1 score: 0.014 KNN cohens kappa score: 0.011 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56835, 28 LR fn, tp: 17, 82 LR f1 score: 0.785 LR cohens kappa score: 0.784 LR average precision score: 0.619 -> test with 'GB' GB tn, fp: 56850, 13 GB fn, tp: 19, 80 GB f1 score: 0.833 GB cohens kappa score: 0.833 -> test with 'KNN' KNN tn, fp: 56508, 355 KNN fn, tp: 98, 1 KNN f1 score: 0.004 KNN cohens kappa score: 0.002 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56840, 23 LR fn, tp: 23, 76 LR f1 score: 0.768 LR cohens kappa score: 0.767 LR average precision score: 0.646 -> test with 'GB' GB tn, fp: 56850, 13 GB fn, tp: 23, 76 GB f1 score: 0.809 GB cohens kappa score: 0.808 -> test with 'KNN' KNN tn, fp: 56557, 306 KNN fn, tp: 94, 5 KNN f1 score: 0.024 KNN cohens kappa score: 0.022 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56836, 27 LR fn, tp: 21, 78 LR f1 score: 0.765 LR cohens kappa score: 0.764 LR average precision score: 0.713 -> test with 'GB' GB tn, fp: 56856, 7 GB fn, tp: 21, 78 GB f1 score: 0.848 GB cohens kappa score: 0.848 -> test with 'KNN' KNN tn, fp: 56433, 430 KNN fn, tp: 95, 4 KNN f1 score: 0.015 KNN cohens kappa score: 0.012 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227056 synthetic samples -> test with 'LR' LR tn, fp: 56850, 13 LR fn, tp: 23, 73 LR f1 score: 0.802 LR cohens kappa score: 0.802 LR average precision score: 0.750 -> test with 'GB' GB tn, fp: 56852, 11 GB fn, tp: 23, 73 GB f1 score: 0.811 GB cohens kappa score: 0.811 -> test with 'KNN' KNN tn, fp: 56594, 269 KNN fn, tp: 93, 3 KNN f1 score: 0.016 KNN cohens kappa score: 0.014 ====== 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 227059 synthetic samples -> test with 'LR' LR tn, fp: 56838, 25 LR fn, tp: 21, 78 LR f1 score: 0.772 LR cohens kappa score: 0.772 LR average precision score: 0.703 -> test with 'GB' GB tn, fp: 56852, 11 GB fn, tp: 25, 74 GB f1 score: 0.804 GB cohens kappa score: 0.804 -> test with 'KNN' KNN tn, fp: 56349, 514 KNN fn, tp: 95, 4 KNN f1 score: 0.013 KNN cohens kappa score: 0.010 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56836, 27 LR fn, tp: 22, 77 LR f1 score: 0.759 LR cohens kappa score: 0.758 LR average precision score: 0.666 -> test with 'GB' GB tn, fp: 56851, 12 GB fn, tp: 21, 78 GB f1 score: 0.825 GB cohens kappa score: 0.825 -> test with 'KNN' KNN tn, fp: 56501, 362 KNN fn, tp: 95, 4 KNN f1 score: 0.017 KNN cohens kappa score: 0.015 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56844, 19 LR fn, tp: 25, 74 LR f1 score: 0.771 LR cohens kappa score: 0.770 LR average precision score: 0.733 -> test with 'GB' GB tn, fp: 56858, 5 GB fn, tp: 18, 81 GB f1 score: 0.876 GB cohens kappa score: 0.875 -> test with 'KNN' KNN tn, fp: 56504, 359 KNN fn, tp: 95, 4 KNN f1 score: 0.017 KNN cohens kappa score: 0.015 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56839, 24 LR fn, tp: 20, 79 LR f1 score: 0.782 LR cohens kappa score: 0.782 LR average precision score: 0.747 -> test with 'GB' GB tn, fp: 56853, 10 GB fn, tp: 16, 83 GB f1 score: 0.865 GB cohens kappa score: 0.864 -> test with 'KNN' KNN tn, fp: 56447, 416 KNN fn, tp: 92, 7 KNN f1 score: 0.027 KNN cohens kappa score: 0.024 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227056 synthetic samples -> test with 'LR' LR tn, fp: 56844, 19 LR fn, tp: 21, 75 LR f1 score: 0.789 LR cohens kappa score: 0.789 LR average precision score: 0.757 -> test with 'GB' GB tn, fp: 56853, 10 GB fn, tp: 24, 72 GB f1 score: 0.809 GB cohens kappa score: 0.809 -> test with 'KNN' KNN tn, fp: 56518, 345 KNN fn, tp: 94, 2 KNN f1 score: 0.009 KNN cohens kappa score: 0.006 ====== 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 227059 synthetic samples -> test with 'LR' LR tn, fp: 56837, 26 LR fn, tp: 16, 83 LR f1 score: 0.798 LR cohens kappa score: 0.798 LR average precision score: 0.680 -> test with 'GB' GB tn, fp: 56849, 14 GB fn, tp: 17, 82 GB f1 score: 0.841 GB cohens kappa score: 0.841 -> test with 'KNN' KNN tn, fp: 56571, 292 KNN fn, tp: 97, 2 KNN f1 score: 0.010 KNN cohens kappa score: 0.008 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56844, 19 LR fn, tp: 32, 67 LR f1 score: 0.724 LR cohens kappa score: 0.724 LR average precision score: 0.646 -> test with 'GB' GB tn, fp: 56851, 12 GB fn, tp: 21, 78 GB f1 score: 0.825 GB cohens kappa score: 0.825 -> test with 'KNN' KNN tn, fp: 56551, 312 KNN fn, tp: 96, 3 KNN f1 score: 0.014 KNN cohens kappa score: 0.012 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56837, 26 LR fn, tp: 22, 77 LR f1 score: 0.762 LR cohens kappa score: 0.762 LR average precision score: 0.680 -> test with 'GB' GB tn, fp: 56854, 9 GB fn, tp: 25, 74 GB f1 score: 0.813 GB cohens kappa score: 0.813 -> test with 'KNN' KNN tn, fp: 56591, 272 KNN fn, tp: 94, 5 KNN f1 score: 0.027 KNN cohens kappa score: 0.024 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56851, 12 LR fn, tp: 19, 80 LR f1 score: 0.838 LR cohens kappa score: 0.837 LR average precision score: 0.775 -> test with 'GB' GB tn, fp: 56852, 11 GB fn, tp: 17, 82 GB f1 score: 0.854 GB cohens kappa score: 0.854 -> test with 'KNN' KNN tn, fp: 56552, 311 KNN fn, tp: 96, 3 KNN f1 score: 0.015 KNN cohens kappa score: 0.012 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227056 synthetic samples -> test with 'LR' LR tn, fp: 56847, 16 LR fn, tp: 25, 71 LR f1 score: 0.776 LR cohens kappa score: 0.776 LR average precision score: 0.710 -> test with 'GB' GB tn, fp: 56845, 18 GB fn, tp: 21, 75 GB f1 score: 0.794 GB cohens kappa score: 0.793 -> test with 'KNN' KNN tn, fp: 56541, 322 KNN fn, tp: 88, 8 KNN f1 score: 0.038 KNN cohens kappa score: 0.035 ====== 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 227059 synthetic samples -> test with 'LR' LR tn, fp: 56841, 22 LR fn, tp: 24, 75 LR f1 score: 0.765 LR cohens kappa score: 0.765 LR average precision score: 0.677 -> test with 'GB' GB tn, fp: 56857, 6 GB fn, tp: 25, 74 GB f1 score: 0.827 GB cohens kappa score: 0.827 -> test with 'KNN' KNN tn, fp: 56487, 376 KNN fn, tp: 96, 3 KNN f1 score: 0.013 KNN cohens kappa score: 0.010 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56799, 64 LR fn, tp: 16, 83 LR f1 score: 0.675 LR cohens kappa score: 0.674 LR average precision score: 0.733 -> test with 'GB' GB tn, fp: 56854, 9 GB fn, tp: 20, 79 GB f1 score: 0.845 GB cohens kappa score: 0.845 -> test with 'KNN' KNN tn, fp: 56409, 454 KNN fn, tp: 93, 6 KNN f1 score: 0.021 KNN cohens kappa score: 0.019 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56841, 22 LR fn, tp: 24, 75 LR f1 score: 0.765 LR cohens kappa score: 0.765 LR average precision score: 0.677 -> test with 'GB' GB tn, fp: 56852, 11 GB fn, tp: 20, 79 GB f1 score: 0.836 GB cohens kappa score: 0.836 -> test with 'KNN' KNN tn, fp: 56608, 255 KNN fn, tp: 96, 3 KNN f1 score: 0.017 KNN cohens kappa score: 0.014 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227059 synthetic samples -> test with 'LR' LR tn, fp: 56841, 22 LR fn, tp: 18, 81 LR f1 score: 0.802 LR cohens kappa score: 0.802 LR average precision score: 0.734 -> test with 'GB' GB tn, fp: 56856, 7 GB fn, tp: 20, 79 GB f1 score: 0.854 GB cohens kappa score: 0.854 -> test with 'KNN' KNN tn, fp: 56449, 414 KNN fn, tp: 97, 2 KNN f1 score: 0.008 KNN cohens kappa score: 0.005 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples 0%| | 0/10 [00:00 create 227056 synthetic samples -> test with 'LR' LR tn, fp: 56843, 20 LR fn, tp: 19, 77 LR f1 score: 0.798 LR cohens kappa score: 0.798 LR average precision score: 0.661 -> test with 'GB' GB tn, fp: 56846, 17 GB fn, tp: 22, 74 GB f1 score: 0.791 GB cohens kappa score: 0.791 -> test with 'KNN' KNN tn, fp: 56548, 315 KNN fn, tp: 94, 2 KNN f1 score: 0.010 KNN cohens kappa score: 0.007 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 56851, 64 LR fn, tp: 32, 84 LR f1 score: 0.838 LR cohens kappa score: 0.837 LR average precision score: 0.812 average: LR tn, fp: 56838.16, 24.84 LR fn, tp: 21.08, 77.32 LR f1 score: 0.773 LR cohens kappa score: 0.772 LR average precision score: 0.701 minimum: LR tn, fp: 56799, 12 LR fn, tp: 15, 67 LR f1 score: 0.675 LR cohens kappa score: 0.674 LR average precision score: 0.560 -----[ GB ]----- maximum: GB tn, fp: 56858, 18 GB fn, tp: 27, 83 GB f1 score: 0.876 GB cohens kappa score: 0.875 average: GB tn, fp: 56852.0, 11.0 GB fn, tp: 21.0, 77.4 GB f1 score: 0.829 GB cohens kappa score: 0.828 minimum: GB tn, fp: 56845, 5 GB fn, tp: 16, 72 GB f1 score: 0.774 GB cohens kappa score: 0.774 -----[ KNN ]----- maximum: KNN tn, fp: 56608, 514 KNN fn, tp: 98, 8 KNN f1 score: 0.038 KNN cohens kappa score: 0.035 average: KNN tn, fp: 56518.52, 344.48 KNN fn, tp: 94.72, 3.68 KNN f1 score: 0.016 KNN cohens kappa score: 0.014 minimum: KNN tn, fp: 56349, 255 KNN fn, tp: 88, 1 KNN f1 score: 0.004 KNN cohens kappa score: 0.002