/////////////////////////////////////////// // Running SimpleGAN on folding_hypothyroid /////////////////////////////////////////// Load 'data_input/folding_hypothyroid' from pickle file non empty cut in data_input/folding_hypothyroid! (1 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 2289 synthetic samples -> test with 'LR' LR tn, fp: 595, 8 LR fn, tp: 20, 11 LR f1 score: 0.440 LR cohens kappa score: 0.418 LR average precision score: 0.440 -> test with 'GB' GB tn, fp: 601, 2 GB fn, tp: 8, 23 GB f1 score: 0.821 GB cohens kappa score: 0.813 -> test with 'KNN' KNN tn, fp: 600, 3 KNN fn, tp: 15, 16 KNN f1 score: 0.640 KNN cohens kappa score: 0.626 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 592, 11 LR fn, tp: 19, 12 LR f1 score: 0.444 LR cohens kappa score: 0.420 LR average precision score: 0.501 -> test with 'GB' GB tn, fp: 595, 8 GB fn, tp: 9, 22 GB f1 score: 0.721 GB cohens kappa score: 0.707 -> test with 'KNN' KNN tn, fp: 596, 7 KNN fn, tp: 15, 16 KNN f1 score: 0.593 KNN cohens kappa score: 0.575 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 594, 9 LR fn, tp: 24, 7 LR f1 score: 0.298 LR cohens kappa score: 0.274 LR average precision score: 0.402 -> test with 'GB' GB tn, fp: 597, 6 GB fn, tp: 6, 25 GB f1 score: 0.806 GB cohens kappa score: 0.797 -> test with 'KNN' KNN tn, fp: 599, 4 KNN fn, tp: 16, 15 KNN f1 score: 0.600 KNN cohens kappa score: 0.585 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 594, 9 LR fn, tp: 21, 10 LR f1 score: 0.400 LR cohens kappa score: 0.377 LR average precision score: 0.436 -> test with 'GB' GB tn, fp: 600, 3 GB fn, tp: 10, 21 GB f1 score: 0.764 GB cohens kappa score: 0.753 -> test with 'KNN' KNN tn, fp: 601, 2 KNN fn, tp: 16, 15 KNN f1 score: 0.625 KNN cohens kappa score: 0.612 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2288 synthetic samples -> test with 'LR' LR tn, fp: 595, 5 LR fn, tp: 17, 10 LR f1 score: 0.476 LR cohens kappa score: 0.460 LR average precision score: 0.578 -> test with 'GB' GB tn, fp: 596, 4 GB fn, tp: 5, 22 GB f1 score: 0.830 GB cohens kappa score: 0.823 -> test with 'KNN' KNN tn, fp: 597, 3 KNN fn, tp: 16, 11 KNN f1 score: 0.537 KNN cohens kappa score: 0.523 ====== 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 2289 synthetic samples -> test with 'LR' LR tn, fp: 596, 7 LR fn, tp: 20, 11 LR f1 score: 0.449 LR cohens kappa score: 0.428 LR average precision score: 0.521 -> test with 'GB' GB tn, fp: 596, 7 GB fn, tp: 12, 19 GB f1 score: 0.667 GB cohens kappa score: 0.651 -> test with 'KNN' KNN tn, fp: 598, 5 KNN fn, tp: 22, 9 KNN f1 score: 0.400 KNN cohens kappa score: 0.381 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 595, 8 LR fn, tp: 23, 8 LR f1 score: 0.340 LR cohens kappa score: 0.318 LR average precision score: 0.507 -> test with 'GB' GB tn, fp: 597, 6 GB fn, tp: 8, 23 GB f1 score: 0.767 GB cohens kappa score: 0.755 -> test with 'KNN' KNN tn, fp: 600, 3 KNN fn, tp: 15, 16 KNN f1 score: 0.640 KNN cohens kappa score: 0.626 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 596, 7 LR fn, tp: 17, 14 LR f1 score: 0.538 LR cohens kappa score: 0.519 LR average precision score: 0.495 -> test with 'GB' GB tn, fp: 601, 2 GB fn, tp: 11, 20 GB f1 score: 0.755 GB cohens kappa score: 0.744 -> test with 'KNN' KNN tn, fp: 601, 2 KNN fn, tp: 16, 15 KNN f1 score: 0.625 KNN cohens kappa score: 0.612 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 595, 8 LR fn, tp: 26, 5 LR f1 score: 0.227 LR cohens kappa score: 0.204 LR average precision score: 0.369 -> test with 'GB' GB tn, fp: 600, 3 GB fn, tp: 5, 26 GB f1 score: 0.867 GB cohens kappa score: 0.860 -> test with 'KNN' KNN tn, fp: 596, 7 KNN fn, tp: 16, 15 KNN f1 score: 0.566 KNN cohens kappa score: 0.548 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2288 synthetic samples -> test with 'LR' LR tn, fp: 592, 8 LR fn, tp: 17, 10 LR f1 score: 0.444 LR cohens kappa score: 0.425 LR average precision score: 0.563 -> test with 'GB' GB tn, fp: 597, 3 GB fn, tp: 5, 22 GB f1 score: 0.846 GB cohens kappa score: 0.840 -> test with 'KNN' KNN tn, fp: 595, 5 KNN fn, tp: 12, 15 KNN f1 score: 0.638 KNN cohens kappa score: 0.625 ====== 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 2289 synthetic samples -> test with 'LR' LR tn, fp: 598, 5 LR fn, tp: 22, 9 LR f1 score: 0.400 LR cohens kappa score: 0.381 LR average precision score: 0.533 -> test with 'GB' GB tn, fp: 603, 0 GB fn, tp: 12, 19 GB f1 score: 0.760 GB cohens kappa score: 0.751 -> test with 'KNN' KNN tn, fp: 602, 1 KNN fn, tp: 19, 12 KNN f1 score: 0.545 KNN cohens kappa score: 0.532 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 594, 9 LR fn, tp: 23, 8 LR f1 score: 0.333 LR cohens kappa score: 0.309 LR average precision score: 0.351 -> test with 'GB' GB tn, fp: 594, 9 GB fn, tp: 5, 26 GB f1 score: 0.788 GB cohens kappa score: 0.776 -> test with 'KNN' KNN tn, fp: 598, 5 KNN fn, tp: 16, 15 KNN f1 score: 0.588 KNN cohens kappa score: 0.572 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 595, 8 LR fn, tp: 16, 15 LR f1 score: 0.556 LR cohens kappa score: 0.536 LR average precision score: 0.659 -> test with 'GB' GB tn, fp: 598, 5 GB fn, tp: 6, 25 GB f1 score: 0.820 GB cohens kappa score: 0.811 -> test with 'KNN' KNN tn, fp: 596, 7 KNN fn, tp: 15, 16 KNN f1 score: 0.593 KNN cohens kappa score: 0.575 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 596, 7 LR fn, tp: 20, 11 LR f1 score: 0.449 LR cohens kappa score: 0.428 LR average precision score: 0.511 -> test with 'GB' GB tn, fp: 596, 7 GB fn, tp: 7, 24 GB f1 score: 0.774 GB cohens kappa score: 0.763 -> test with 'KNN' KNN tn, fp: 599, 4 KNN fn, tp: 17, 14 KNN f1 score: 0.571 KNN cohens kappa score: 0.555 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2288 synthetic samples -> test with 'LR' LR tn, fp: 595, 5 LR fn, tp: 21, 6 LR f1 score: 0.316 LR cohens kappa score: 0.298 LR average precision score: 0.394 -> test with 'GB' GB tn, fp: 597, 3 GB fn, tp: 8, 19 GB f1 score: 0.776 GB cohens kappa score: 0.766 -> test with 'KNN' KNN tn, fp: 599, 1 KNN fn, tp: 14, 13 KNN f1 score: 0.634 KNN cohens kappa score: 0.623 ====== 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 2289 synthetic samples -> test with 'LR' LR tn, fp: 592, 11 LR fn, tp: 22, 9 LR f1 score: 0.353 LR cohens kappa score: 0.327 LR average precision score: 0.382 -> test with 'GB' GB tn, fp: 598, 5 GB fn, tp: 6, 25 GB f1 score: 0.820 GB cohens kappa score: 0.811 -> test with 'KNN' KNN tn, fp: 600, 3 KNN fn, tp: 21, 10 KNN f1 score: 0.455 KNN cohens kappa score: 0.438 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 593, 10 LR fn, tp: 21, 10 LR f1 score: 0.392 LR cohens kappa score: 0.368 LR average precision score: 0.494 -> test with 'GB' GB tn, fp: 600, 3 GB fn, tp: 9, 22 GB f1 score: 0.786 GB cohens kappa score: 0.776 -> test with 'KNN' KNN tn, fp: 599, 4 KNN fn, tp: 18, 13 KNN f1 score: 0.542 KNN cohens kappa score: 0.525 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 600, 3 LR fn, tp: 21, 10 LR f1 score: 0.455 LR cohens kappa score: 0.438 LR average precision score: 0.611 -> test with 'GB' GB tn, fp: 601, 2 GB fn, tp: 7, 24 GB f1 score: 0.842 GB cohens kappa score: 0.835 -> test with 'KNN' KNN tn, fp: 600, 3 KNN fn, tp: 17, 14 KNN f1 score: 0.583 KNN cohens kappa score: 0.568 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 594, 9 LR fn, tp: 18, 13 LR f1 score: 0.491 LR cohens kappa score: 0.469 LR average precision score: 0.520 -> test with 'GB' GB tn, fp: 600, 3 GB fn, tp: 7, 24 GB f1 score: 0.828 GB cohens kappa score: 0.819 -> test with 'KNN' KNN tn, fp: 597, 6 KNN fn, tp: 17, 14 KNN f1 score: 0.549 KNN cohens kappa score: 0.531 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2288 synthetic samples -> test with 'LR' LR tn, fp: 592, 8 LR fn, tp: 19, 8 LR f1 score: 0.372 LR cohens kappa score: 0.351 LR average precision score: 0.442 -> test with 'GB' GB tn, fp: 597, 3 GB fn, tp: 10, 17 GB f1 score: 0.723 GB cohens kappa score: 0.713 -> test with 'KNN' KNN tn, fp: 593, 7 KNN fn, tp: 12, 15 KNN f1 score: 0.612 KNN cohens kappa score: 0.597 ====== 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 2289 synthetic samples -> test with 'LR' LR tn, fp: 588, 15 LR fn, tp: 19, 12 LR f1 score: 0.414 LR cohens kappa score: 0.386 LR average precision score: 0.484 -> test with 'GB' GB tn, fp: 599, 4 GB fn, tp: 8, 23 GB f1 score: 0.793 GB cohens kappa score: 0.783 -> test with 'KNN' KNN tn, fp: 599, 4 KNN fn, tp: 17, 14 KNN f1 score: 0.571 KNN cohens kappa score: 0.555 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 600, 3 LR fn, tp: 20, 11 LR f1 score: 0.489 LR cohens kappa score: 0.473 LR average precision score: 0.543 -> test with 'GB' GB tn, fp: 602, 1 GB fn, tp: 8, 23 GB f1 score: 0.836 GB cohens kappa score: 0.829 -> test with 'KNN' KNN tn, fp: 599, 4 KNN fn, tp: 18, 13 KNN f1 score: 0.542 KNN cohens kappa score: 0.525 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 594, 9 LR fn, tp: 18, 13 LR f1 score: 0.491 LR cohens kappa score: 0.469 LR average precision score: 0.546 -> test with 'GB' GB tn, fp: 598, 5 GB fn, tp: 14, 17 GB f1 score: 0.642 GB cohens kappa score: 0.626 -> test with 'KNN' KNN tn, fp: 598, 5 KNN fn, tp: 18, 13 KNN f1 score: 0.531 KNN cohens kappa score: 0.513 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2289 synthetic samples -> test with 'LR' LR tn, fp: 600, 3 LR fn, tp: 22, 9 LR f1 score: 0.419 LR cohens kappa score: 0.402 LR average precision score: 0.497 -> test with 'GB' GB tn, fp: 599, 4 GB fn, tp: 5, 26 GB f1 score: 0.852 GB cohens kappa score: 0.845 -> test with 'KNN' KNN tn, fp: 601, 2 KNN fn, tp: 14, 17 KNN f1 score: 0.680 KNN cohens kappa score: 0.668 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2288 synthetic samples -> test with 'LR' LR tn, fp: 592, 8 LR fn, tp: 19, 8 LR f1 score: 0.372 LR cohens kappa score: 0.351 LR average precision score: 0.382 -> test with 'GB' GB tn, fp: 594, 6 GB fn, tp: 10, 17 GB f1 score: 0.680 GB cohens kappa score: 0.667 -> test with 'KNN' KNN tn, fp: 597, 3 KNN fn, tp: 17, 10 KNN f1 score: 0.500 KNN cohens kappa score: 0.486 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 600, 15 LR fn, tp: 26, 15 LR f1 score: 0.556 LR cohens kappa score: 0.536 LR average precision score: 0.659 average: LR tn, fp: 594.68, 7.72 LR fn, tp: 20.2, 10.0 LR f1 score: 0.414 LR cohens kappa score: 0.393 LR average precision score: 0.486 minimum: LR tn, fp: 588, 3 LR fn, tp: 16, 5 LR f1 score: 0.227 LR cohens kappa score: 0.204 LR average precision score: 0.351 -----[ GB ]----- maximum: GB tn, fp: 603, 9 GB fn, tp: 14, 26 GB f1 score: 0.867 GB cohens kappa score: 0.860 average: GB tn, fp: 598.24, 4.16 GB fn, tp: 8.04, 22.16 GB f1 score: 0.783 GB cohens kappa score: 0.773 minimum: GB tn, fp: 594, 0 GB fn, tp: 5, 17 GB f1 score: 0.642 GB cohens kappa score: 0.626 -----[ KNN ]----- maximum: KNN tn, fp: 602, 7 KNN fn, tp: 22, 17 KNN f1 score: 0.680 KNN cohens kappa score: 0.668 average: KNN tn, fp: 598.4, 4.0 KNN fn, tp: 16.36, 13.84 KNN f1 score: 0.574 KNN cohens kappa score: 0.559 minimum: KNN tn, fp: 593, 1 KNN fn, tp: 12, 9 KNN f1 score: 0.400 KNN cohens kappa score: 0.381