/////////////////////////////////////////// // Running SimpleGAN on imblearn_webpage /////////////////////////////////////////// Load 'data_input/imblearn_webpage' from imblearn non empty cut in data_input/imblearn_webpage! (76 points) 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 Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6726, 34 LR fn, tp: 60, 137 LR f1 score: 0.745 LR cohens kappa score: 0.738 LR average precision score: 0.797 -> test with 'GB' GB tn, fp: 6755, 5 GB fn, tp: 88, 109 GB f1 score: 0.701 GB cohens kappa score: 0.695 -> test with 'KNN' KNN tn, fp: 6753, 7 KNN fn, tp: 114, 83 KNN f1 score: 0.578 KNN cohens kappa score: 0.571 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6729, 31 LR fn, tp: 55, 142 LR f1 score: 0.768 LR cohens kappa score: 0.761 LR average precision score: 0.815 -> test with 'GB' GB tn, fp: 6754, 6 GB fn, tp: 86, 111 GB f1 score: 0.707 GB cohens kappa score: 0.701 -> test with 'KNN' KNN tn, fp: 6757, 3 KNN fn, tp: 117, 80 KNN f1 score: 0.571 KNN cohens kappa score: 0.564 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6740, 20 LR fn, tp: 52, 145 LR f1 score: 0.801 LR cohens kappa score: 0.796 LR average precision score: 0.848 -> test with 'GB' GB tn, fp: 6755, 5 GB fn, tp: 82, 115 GB f1 score: 0.726 GB cohens kappa score: 0.720 -> test with 'KNN' KNN tn, fp: 6760, 0 KNN fn, tp: 112, 85 KNN f1 score: 0.603 KNN cohens kappa score: 0.596 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6733, 27 LR fn, tp: 60, 137 LR f1 score: 0.759 LR cohens kappa score: 0.753 LR average precision score: 0.793 -> test with 'GB' GB tn, fp: 6752, 8 GB fn, tp: 93, 104 GB f1 score: 0.673 GB cohens kappa score: 0.666 -> test with 'KNN' KNN tn, fp: 6752, 8 KNN fn, tp: 123, 74 KNN f1 score: 0.530 KNN cohens kappa score: 0.523 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26252 synthetic samples -> test with 'LR' LR tn, fp: 6724, 35 LR fn, tp: 58, 135 LR f1 score: 0.744 LR cohens kappa score: 0.737 LR average precision score: 0.780 -> test with 'GB' GB tn, fp: 6749, 10 GB fn, tp: 89, 104 GB f1 score: 0.678 GB cohens kappa score: 0.671 -> test with 'KNN' KNN tn, fp: 6756, 3 KNN fn, tp: 122, 71 KNN f1 score: 0.532 KNN cohens kappa score: 0.525 ====== Step 2/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 2/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6736, 24 LR fn, tp: 66, 131 LR f1 score: 0.744 LR cohens kappa score: 0.738 LR average precision score: 0.820 -> test with 'GB' GB tn, fp: 6755, 5 GB fn, tp: 83, 114 GB f1 score: 0.722 GB cohens kappa score: 0.715 -> test with 'KNN' KNN tn, fp: 6755, 5 KNN fn, tp: 121, 76 KNN f1 score: 0.547 KNN cohens kappa score: 0.539 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6734, 26 LR fn, tp: 55, 142 LR f1 score: 0.778 LR cohens kappa score: 0.772 LR average precision score: 0.831 -> test with 'GB' GB tn, fp: 6752, 8 GB fn, tp: 85, 112 GB f1 score: 0.707 GB cohens kappa score: 0.700 -> test with 'KNN' KNN tn, fp: 6753, 7 KNN fn, tp: 124, 73 KNN f1 score: 0.527 KNN cohens kappa score: 0.519 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6726, 34 LR fn, tp: 56, 141 LR f1 score: 0.758 LR cohens kappa score: 0.751 LR average precision score: 0.787 -> test with 'GB' GB tn, fp: 6754, 6 GB fn, tp: 86, 111 GB f1 score: 0.707 GB cohens kappa score: 0.701 -> test with 'KNN' KNN tn, fp: 6756, 4 KNN fn, tp: 114, 83 KNN f1 score: 0.585 KNN cohens kappa score: 0.577 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6726, 34 LR fn, tp: 64, 133 LR f1 score: 0.731 LR cohens kappa score: 0.724 LR average precision score: 0.801 -> test with 'GB' GB tn, fp: 6756, 4 GB fn, tp: 95, 102 GB f1 score: 0.673 GB cohens kappa score: 0.667 -> test with 'KNN' KNN tn, fp: 6759, 1 KNN fn, tp: 113, 84 KNN f1 score: 0.596 KNN cohens kappa score: 0.589 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26252 synthetic samples -> test with 'LR' LR tn, fp: 6741, 18 LR fn, tp: 60, 133 LR f1 score: 0.773 LR cohens kappa score: 0.768 LR average precision score: 0.823 -> test with 'GB' GB tn, fp: 6754, 5 GB fn, tp: 84, 109 GB f1 score: 0.710 GB cohens kappa score: 0.704 -> test with 'KNN' KNN tn, fp: 6758, 1 KNN fn, tp: 124, 69 KNN f1 score: 0.525 KNN cohens kappa score: 0.518 ====== Step 3/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 3/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6723, 37 LR fn, tp: 57, 140 LR f1 score: 0.749 LR cohens kappa score: 0.742 LR average precision score: 0.781 -> test with 'GB' GB tn, fp: 6751, 9 GB fn, tp: 83, 114 GB f1 score: 0.712 GB cohens kappa score: 0.706 -> test with 'KNN' KNN tn, fp: 6759, 1 KNN fn, tp: 121, 76 KNN f1 score: 0.555 KNN cohens kappa score: 0.548 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6738, 22 LR fn, tp: 56, 141 LR f1 score: 0.783 LR cohens kappa score: 0.778 LR average precision score: 0.823 -> test with 'GB' GB tn, fp: 6755, 5 GB fn, tp: 87, 110 GB f1 score: 0.705 GB cohens kappa score: 0.699 -> test with 'KNN' KNN tn, fp: 6757, 3 KNN fn, tp: 122, 75 KNN f1 score: 0.545 KNN cohens kappa score: 0.538 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6739, 21 LR fn, tp: 76, 121 LR f1 score: 0.714 LR cohens kappa score: 0.707 LR average precision score: 0.759 -> test with 'GB' GB tn, fp: 6756, 4 GB fn, tp: 105, 92 GB f1 score: 0.628 GB cohens kappa score: 0.621 -> test with 'KNN' KNN tn, fp: 6758, 2 KNN fn, tp: 132, 65 KNN f1 score: 0.492 KNN cohens kappa score: 0.485 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6724, 36 LR fn, tp: 48, 149 LR f1 score: 0.780 LR cohens kappa score: 0.774 LR average precision score: 0.857 -> test with 'GB' GB tn, fp: 6751, 9 GB fn, tp: 84, 113 GB f1 score: 0.708 GB cohens kappa score: 0.702 -> test with 'KNN' KNN tn, fp: 6750, 10 KNN fn, tp: 103, 94 KNN f1 score: 0.625 KNN cohens kappa score: 0.617 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26252 synthetic samples -> test with 'LR' LR tn, fp: 6733, 26 LR fn, tp: 59, 134 LR f1 score: 0.759 LR cohens kappa score: 0.753 LR average precision score: 0.822 -> test with 'GB' GB tn, fp: 6759, 0 GB fn, tp: 83, 110 GB f1 score: 0.726 GB cohens kappa score: 0.720 -> test with 'KNN' KNN tn, fp: 6757, 2 KNN fn, tp: 112, 81 KNN f1 score: 0.587 KNN cohens kappa score: 0.580 ====== Step 4/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 4/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6733, 27 LR fn, tp: 56, 141 LR f1 score: 0.773 LR cohens kappa score: 0.767 LR average precision score: 0.791 -> test with 'GB' GB tn, fp: 6753, 7 GB fn, tp: 82, 115 GB f1 score: 0.721 GB cohens kappa score: 0.715 -> test with 'KNN' KNN tn, fp: 6759, 1 KNN fn, tp: 130, 67 KNN f1 score: 0.506 KNN cohens kappa score: 0.498 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6729, 31 LR fn, tp: 60, 137 LR f1 score: 0.751 LR cohens kappa score: 0.744 LR average precision score: 0.794 -> test with 'GB' GB tn, fp: 6757, 3 GB fn, tp: 99, 98 GB f1 score: 0.658 GB cohens kappa score: 0.651 -> test with 'KNN' KNN tn, fp: 6750, 10 KNN fn, tp: 117, 80 KNN f1 score: 0.557 KNN cohens kappa score: 0.549 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6733, 27 LR fn, tp: 55, 142 LR f1 score: 0.776 LR cohens kappa score: 0.770 LR average precision score: 0.828 -> test with 'GB' GB tn, fp: 6756, 4 GB fn, tp: 95, 102 GB f1 score: 0.673 GB cohens kappa score: 0.667 -> test with 'KNN' KNN tn, fp: 6759, 1 KNN fn, tp: 121, 76 KNN f1 score: 0.555 KNN cohens kappa score: 0.548 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6722, 38 LR fn, tp: 64, 133 LR f1 score: 0.723 LR cohens kappa score: 0.715 LR average precision score: 0.796 -> test with 'GB' GB tn, fp: 6748, 12 GB fn, tp: 74, 123 GB f1 score: 0.741 GB cohens kappa score: 0.735 -> test with 'KNN' KNN tn, fp: 6754, 6 KNN fn, tp: 116, 81 KNN f1 score: 0.570 KNN cohens kappa score: 0.563 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26252 synthetic samples -> test with 'LR' LR tn, fp: 6736, 23 LR fn, tp: 52, 141 LR f1 score: 0.790 LR cohens kappa score: 0.784 LR average precision score: 0.832 -> test with 'GB' GB tn, fp: 6755, 4 GB fn, tp: 86, 107 GB f1 score: 0.704 GB cohens kappa score: 0.698 -> test with 'KNN' KNN tn, fp: 6757, 2 KNN fn, tp: 113, 80 KNN f1 score: 0.582 KNN cohens kappa score: 0.575 ====== Step 5/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 5/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6727, 33 LR fn, tp: 58, 139 LR f1 score: 0.753 LR cohens kappa score: 0.747 LR average precision score: 0.801 -> test with 'GB' GB tn, fp: 6753, 7 GB fn, tp: 85, 112 GB f1 score: 0.709 GB cohens kappa score: 0.703 -> test with 'KNN' KNN tn, fp: 6750, 10 KNN fn, tp: 112, 85 KNN f1 score: 0.582 KNN cohens kappa score: 0.574 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6734, 26 LR fn, tp: 67, 130 LR f1 score: 0.737 LR cohens kappa score: 0.730 LR average precision score: 0.768 -> test with 'GB' GB tn, fp: 6753, 7 GB fn, tp: 93, 104 GB f1 score: 0.675 GB cohens kappa score: 0.669 -> test with 'KNN' KNN tn, fp: 6752, 8 KNN fn, tp: 125, 72 KNN f1 score: 0.520 KNN cohens kappa score: 0.512 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6726, 34 LR fn, tp: 61, 136 LR f1 score: 0.741 LR cohens kappa score: 0.734 LR average precision score: 0.802 -> test with 'GB' GB tn, fp: 6752, 8 GB fn, tp: 82, 115 GB f1 score: 0.719 GB cohens kappa score: 0.712 -> test with 'KNN' KNN tn, fp: 6755, 5 KNN fn, tp: 113, 84 KNN f1 score: 0.587 KNN cohens kappa score: 0.580 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26255 synthetic samples -> test with 'LR' LR tn, fp: 6731, 29 LR fn, tp: 51, 146 LR f1 score: 0.785 LR cohens kappa score: 0.779 LR average precision score: 0.849 -> test with 'GB' GB tn, fp: 6755, 5 GB fn, tp: 76, 121 GB f1 score: 0.749 GB cohens kappa score: 0.744 -> test with 'KNN' KNN tn, fp: 6744, 16 KNN fn, tp: 119, 78 KNN f1 score: 0.536 KNN cohens kappa score: 0.527 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 26252 synthetic samples -> test with 'LR' LR tn, fp: 6726, 33 LR fn, tp: 69, 124 LR f1 score: 0.709 LR cohens kappa score: 0.701 LR average precision score: 0.773 -> test with 'GB' GB tn, fp: 6754, 5 GB fn, tp: 94, 99 GB f1 score: 0.667 GB cohens kappa score: 0.660 -> test with 'KNN' KNN tn, fp: 6757, 2 KNN fn, tp: 115, 78 KNN f1 score: 0.571 KNN cohens kappa score: 0.564 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 6741, 38 LR fn, tp: 76, 149 LR f1 score: 0.801 LR cohens kappa score: 0.796 LR average precision score: 0.857 average: LR tn, fp: 6730.76, 29.04 LR fn, tp: 59.0, 137.2 LR f1 score: 0.757 LR cohens kappa score: 0.750 LR average precision score: 0.807 minimum: LR tn, fp: 6722, 18 LR fn, tp: 48, 121 LR f1 score: 0.709 LR cohens kappa score: 0.701 LR average precision score: 0.759 -----[ GB ]----- maximum: GB tn, fp: 6759, 12 GB fn, tp: 105, 123 GB f1 score: 0.749 GB cohens kappa score: 0.744 average: GB tn, fp: 6753.76, 6.04 GB fn, tp: 87.16, 109.04 GB f1 score: 0.700 GB cohens kappa score: 0.694 minimum: GB tn, fp: 6748, 0 GB fn, tp: 74, 92 GB f1 score: 0.628 GB cohens kappa score: 0.621 -----[ KNN ]----- maximum: KNN tn, fp: 6760, 16 KNN fn, tp: 132, 94 KNN f1 score: 0.625 KNN cohens kappa score: 0.617 average: KNN tn, fp: 6755.08, 4.72 KNN fn, tp: 118.2, 78.0 KNN f1 score: 0.559 KNN cohens kappa score: 0.551 minimum: KNN tn, fp: 6744, 0 KNN fn, tp: 103, 65 KNN f1 score: 0.492 KNN cohens kappa score: 0.485