/////////////////////////////////////////// // Running convGAN-proxymary-full on folding_yeast5 /////////////////////////////////////////// Load 'data_input/folding_yeast5' from pickle file 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 -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 282, 6 GAN fn, tp: 7, 2 GAN f1 score: 0.235 GAN cohens kappa score: 0.213 -> test with 'LR' LR tn, fp: 276, 12 LR fn, tp: 0, 9 LR f1 score: 0.600 LR cohens kappa score: 0.582 LR average precision score: 0.884 -> test with 'GB' GB tn, fp: 287, 1 GB fn, tp: 3, 6 GB f1 score: 0.750 GB cohens kappa score: 0.743 -> test with 'KNN' KNN tn, fp: 280, 8 KNN fn, tp: 1, 8 KNN f1 score: 0.640 KNN cohens kappa score: 0.625 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 282, 6 GAN fn, tp: 2, 7 GAN f1 score: 0.636 GAN cohens kappa score: 0.623 -> test with 'LR' LR tn, fp: 273, 15 LR fn, tp: 0, 9 LR f1 score: 0.545 LR cohens kappa score: 0.524 LR average precision score: 0.663 -> test with 'GB' GB tn, fp: 284, 4 GB fn, tp: 1, 8 GB f1 score: 0.762 GB cohens kappa score: 0.753 -> test with 'KNN' KNN tn, fp: 274, 14 KNN fn, tp: 0, 9 KNN f1 score: 0.562 KNN cohens kappa score: 0.543 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 280, 8 GAN fn, tp: 3, 6 GAN f1 score: 0.522 GAN cohens kappa score: 0.503 -> test with 'LR' LR tn, fp: 279, 9 LR fn, tp: 1, 8 LR f1 score: 0.615 LR cohens kappa score: 0.600 LR average precision score: 0.604 -> test with 'GB' GB tn, fp: 285, 3 GB fn, tp: 3, 6 GB f1 score: 0.667 GB cohens kappa score: 0.656 -> test with 'KNN' KNN tn, fp: 278, 10 KNN fn, tp: 1, 8 KNN f1 score: 0.593 KNN cohens kappa score: 0.575 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 287, 1 GAN fn, tp: 6, 3 GAN f1 score: 0.462 GAN cohens kappa score: 0.451 -> test with 'LR' LR tn, fp: 280, 8 LR fn, tp: 2, 7 LR f1 score: 0.583 LR cohens kappa score: 0.567 LR average precision score: 0.774 -> test with 'GB' GB tn, fp: 288, 0 GB fn, tp: 4, 5 GB f1 score: 0.714 GB cohens kappa score: 0.708 -> test with 'KNN' KNN tn, fp: 287, 1 KNN fn, tp: 1, 8 KNN f1 score: 0.889 KNN cohens kappa score: 0.885 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1116 synthetic samples -> test with GAN.predict GAN tn, fp: 277, 11 GAN fn, tp: 0, 8 GAN f1 score: 0.593 GAN cohens kappa score: 0.576 -> test with 'LR' LR tn, fp: 273, 15 LR fn, tp: 0, 8 LR f1 score: 0.516 LR cohens kappa score: 0.496 LR average precision score: 0.684 -> test with 'GB' GB tn, fp: 286, 2 GB fn, tp: 2, 6 GB f1 score: 0.750 GB cohens kappa score: 0.743 -> test with 'KNN' KNN tn, fp: 275, 13 KNN fn, tp: 0, 8 KNN f1 score: 0.552 KNN cohens kappa score: 0.533 ====== Step 2/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 2/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 282, 6 GAN fn, tp: 2, 7 GAN f1 score: 0.636 GAN cohens kappa score: 0.623 -> test with 'LR' LR tn, fp: 276, 12 LR fn, tp: 0, 9 LR f1 score: 0.600 LR cohens kappa score: 0.582 LR average precision score: 0.710 -> test with 'GB' GB tn, fp: 288, 0 GB fn, tp: 1, 8 GB f1 score: 0.941 GB cohens kappa score: 0.939 -> test with 'KNN' KNN tn, fp: 279, 9 KNN fn, tp: 0, 9 KNN f1 score: 0.667 KNN cohens kappa score: 0.653 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 281, 7 GAN fn, tp: 7, 2 GAN f1 score: 0.222 GAN cohens kappa score: 0.198 -> test with 'LR' LR tn, fp: 272, 16 LR fn, tp: 1, 8 LR f1 score: 0.485 LR cohens kappa score: 0.461 LR average precision score: 0.348 -> test with 'GB' GB tn, fp: 283, 5 GB fn, tp: 6, 3 GB f1 score: 0.353 GB cohens kappa score: 0.334 -> test with 'KNN' KNN tn, fp: 275, 13 KNN fn, tp: 0, 9 KNN f1 score: 0.581 KNN cohens kappa score: 0.562 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 285, 3 GAN fn, tp: 3, 6 GAN f1 score: 0.667 GAN cohens kappa score: 0.656 -> test with 'LR' LR tn, fp: 281, 7 LR fn, tp: 1, 8 LR f1 score: 0.667 LR cohens kappa score: 0.654 LR average precision score: 0.758 -> test with 'GB' GB tn, fp: 286, 2 GB fn, tp: 1, 8 GB f1 score: 0.842 GB cohens kappa score: 0.837 -> test with 'KNN' KNN tn, fp: 280, 8 KNN fn, tp: 0, 9 KNN f1 score: 0.692 KNN cohens kappa score: 0.680 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 286, 2 GAN fn, tp: 2, 7 GAN f1 score: 0.778 GAN cohens kappa score: 0.771 -> test with 'LR' LR tn, fp: 274, 14 LR fn, tp: 0, 9 LR f1 score: 0.562 LR cohens kappa score: 0.543 LR average precision score: 0.870 -> test with 'GB' GB tn, fp: 285, 3 GB fn, tp: 1, 8 GB f1 score: 0.800 GB cohens kappa score: 0.793 -> test with 'KNN' KNN tn, fp: 281, 7 KNN fn, tp: 0, 9 KNN f1 score: 0.720 KNN cohens kappa score: 0.709 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1116 synthetic samples -> test with GAN.predict GAN tn, fp: 283, 5 GAN fn, tp: 4, 4 GAN f1 score: 0.471 GAN cohens kappa score: 0.455 -> test with 'LR' LR tn, fp: 279, 9 LR fn, tp: 0, 8 LR f1 score: 0.640 LR cohens kappa score: 0.626 LR average precision score: 0.597 -> test with 'GB' GB tn, fp: 286, 2 GB fn, tp: 5, 3 GB f1 score: 0.462 GB cohens kappa score: 0.450 -> test with 'KNN' KNN tn, fp: 281, 7 KNN fn, tp: 1, 7 KNN f1 score: 0.636 KNN cohens kappa score: 0.623 ====== Step 3/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 3/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 276, 12 GAN fn, tp: 2, 7 GAN f1 score: 0.500 GAN cohens kappa score: 0.479 -> test with 'LR' LR tn, fp: 272, 16 LR fn, tp: 0, 9 LR f1 score: 0.529 LR cohens kappa score: 0.507 LR average precision score: 0.702 -> test with 'GB' GB tn, fp: 287, 1 GB fn, tp: 3, 6 GB f1 score: 0.750 GB cohens kappa score: 0.743 -> test with 'KNN' KNN tn, fp: 277, 11 KNN fn, tp: 0, 9 KNN f1 score: 0.621 KNN cohens kappa score: 0.604 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 284, 4 GAN fn, tp: 2, 7 GAN f1 score: 0.700 GAN cohens kappa score: 0.690 -> test with 'LR' LR tn, fp: 275, 13 LR fn, tp: 0, 9 LR f1 score: 0.581 LR cohens kappa score: 0.562 LR average precision score: 0.708 -> test with 'GB' GB tn, fp: 285, 3 GB fn, tp: 3, 6 GB f1 score: 0.667 GB cohens kappa score: 0.656 -> test with 'KNN' KNN tn, fp: 277, 11 KNN fn, tp: 1, 8 KNN f1 score: 0.571 KNN cohens kappa score: 0.553 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 285, 3 GAN fn, tp: 4, 5 GAN f1 score: 0.588 GAN cohens kappa score: 0.576 -> test with 'LR' LR tn, fp: 282, 6 LR fn, tp: 2, 7 LR f1 score: 0.636 LR cohens kappa score: 0.623 LR average precision score: 0.813 -> test with 'GB' GB tn, fp: 288, 0 GB fn, tp: 3, 6 GB f1 score: 0.800 GB cohens kappa score: 0.795 -> test with 'KNN' KNN tn, fp: 284, 4 KNN fn, tp: 0, 9 KNN f1 score: 0.818 KNN cohens kappa score: 0.811 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 285, 3 GAN fn, tp: 3, 6 GAN f1 score: 0.667 GAN cohens kappa score: 0.656 -> test with 'LR' LR tn, fp: 279, 9 LR fn, tp: 0, 9 LR f1 score: 0.667 LR cohens kappa score: 0.653 LR average precision score: 0.748 -> test with 'GB' GB tn, fp: 288, 0 GB fn, tp: 4, 5 GB f1 score: 0.714 GB cohens kappa score: 0.708 -> test with 'KNN' KNN tn, fp: 280, 8 KNN fn, tp: 1, 8 KNN f1 score: 0.640 KNN cohens kappa score: 0.625 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1116 synthetic samples -> test with GAN.predict GAN tn, fp: 282, 6 GAN fn, tp: 7, 1 GAN f1 score: 0.133 GAN cohens kappa score: 0.111 -> test with 'LR' LR tn, fp: 275, 13 LR fn, tp: 0, 8 LR f1 score: 0.552 LR cohens kappa score: 0.533 LR average precision score: 0.332 -> test with 'GB' GB tn, fp: 284, 4 GB fn, tp: 1, 7 GB f1 score: 0.737 GB cohens kappa score: 0.728 -> test with 'KNN' KNN tn, fp: 279, 9 KNN fn, tp: 0, 8 KNN f1 score: 0.640 KNN cohens kappa score: 0.626 ====== Step 4/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 4/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 280, 8 GAN fn, tp: 3, 6 GAN f1 score: 0.522 GAN cohens kappa score: 0.503 -> test with 'LR' LR tn, fp: 276, 12 LR fn, tp: 1, 8 LR f1 score: 0.552 LR cohens kappa score: 0.532 LR average precision score: 0.753 -> test with 'GB' GB tn, fp: 286, 2 GB fn, tp: 1, 8 GB f1 score: 0.842 GB cohens kappa score: 0.837 -> test with 'KNN' KNN tn, fp: 276, 12 KNN fn, tp: 0, 9 KNN f1 score: 0.600 KNN cohens kappa score: 0.582 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 277, 11 GAN fn, tp: 3, 6 GAN f1 score: 0.462 GAN cohens kappa score: 0.439 -> test with 'LR' LR tn, fp: 271, 17 LR fn, tp: 0, 9 LR f1 score: 0.514 LR cohens kappa score: 0.491 LR average precision score: 0.628 -> test with 'GB' GB tn, fp: 286, 2 GB fn, tp: 2, 7 GB f1 score: 0.778 GB cohens kappa score: 0.771 -> test with 'KNN' KNN tn, fp: 280, 8 KNN fn, tp: 0, 9 KNN f1 score: 0.692 KNN cohens kappa score: 0.680 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 282, 6 GAN fn, tp: 3, 6 GAN f1 score: 0.571 GAN cohens kappa score: 0.556 -> test with 'LR' LR tn, fp: 280, 8 LR fn, tp: 2, 7 LR f1 score: 0.583 LR cohens kappa score: 0.567 LR average precision score: 0.597 -> test with 'GB' GB tn, fp: 283, 5 GB fn, tp: 4, 5 GB f1 score: 0.526 GB cohens kappa score: 0.511 -> test with 'KNN' KNN tn, fp: 280, 8 KNN fn, tp: 2, 7 KNN f1 score: 0.583 KNN cohens kappa score: 0.567 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 287, 1 GAN fn, tp: 6, 3 GAN f1 score: 0.462 GAN cohens kappa score: 0.451 -> test with 'LR' LR tn, fp: 280, 8 LR fn, tp: 0, 9 LR f1 score: 0.692 LR cohens kappa score: 0.680 LR average precision score: 0.696 -> test with 'GB' GB tn, fp: 288, 0 GB fn, tp: 3, 6 GB f1 score: 0.800 GB cohens kappa score: 0.795 -> test with 'KNN' KNN tn, fp: 284, 4 KNN fn, tp: 1, 8 KNN f1 score: 0.762 KNN cohens kappa score: 0.753 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1116 synthetic samples -> test with GAN.predict GAN tn, fp: 287, 1 GAN fn, tp: 2, 6 GAN f1 score: 0.800 GAN cohens kappa score: 0.795 -> test with 'LR' LR tn, fp: 276, 12 LR fn, tp: 0, 8 LR f1 score: 0.571 LR cohens kappa score: 0.554 LR average precision score: 0.669 -> test with 'GB' GB tn, fp: 286, 2 GB fn, tp: 2, 6 GB f1 score: 0.750 GB cohens kappa score: 0.743 -> test with 'KNN' KNN tn, fp: 272, 16 KNN fn, tp: 0, 8 KNN f1 score: 0.500 KNN cohens kappa score: 0.479 ====== Step 5/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 5/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 281, 7 GAN fn, tp: 0, 9 GAN f1 score: 0.720 GAN cohens kappa score: 0.709 -> test with 'LR' LR tn, fp: 273, 15 LR fn, tp: 0, 9 LR f1 score: 0.545 LR cohens kappa score: 0.524 LR average precision score: 0.724 -> test with 'GB' GB tn, fp: 285, 3 GB fn, tp: 1, 8 GB f1 score: 0.800 GB cohens kappa score: 0.793 -> test with 'KNN' KNN tn, fp: 274, 14 KNN fn, tp: 0, 9 KNN f1 score: 0.562 KNN cohens kappa score: 0.543 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 286, 2 GAN fn, tp: 5, 4 GAN f1 score: 0.533 GAN cohens kappa score: 0.522 -> test with 'LR' LR tn, fp: 280, 8 LR fn, tp: 1, 8 LR f1 score: 0.640 LR cohens kappa score: 0.625 LR average precision score: 0.796 -> test with 'GB' GB tn, fp: 288, 0 GB fn, tp: 3, 6 GB f1 score: 0.800 GB cohens kappa score: 0.795 -> test with 'KNN' KNN tn, fp: 283, 5 KNN fn, tp: 1, 8 KNN f1 score: 0.727 KNN cohens kappa score: 0.717 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 280, 8 GAN fn, tp: 3, 6 GAN f1 score: 0.522 GAN cohens kappa score: 0.503 -> test with 'LR' LR tn, fp: 278, 10 LR fn, tp: 0, 9 LR f1 score: 0.643 LR cohens kappa score: 0.628 LR average precision score: 0.738 -> test with 'GB' GB tn, fp: 287, 1 GB fn, tp: 1, 8 GB f1 score: 0.889 GB cohens kappa score: 0.885 -> test with 'KNN' KNN tn, fp: 281, 7 KNN fn, tp: 0, 9 KNN f1 score: 0.720 KNN cohens kappa score: 0.709 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1117 synthetic samples -> test with GAN.predict GAN tn, fp: 285, 3 GAN fn, tp: 7, 2 GAN f1 score: 0.286 GAN cohens kappa score: 0.270 -> test with 'LR' LR tn, fp: 280, 8 LR fn, tp: 0, 9 LR f1 score: 0.692 LR cohens kappa score: 0.680 LR average precision score: 0.577 -> test with 'GB' GB tn, fp: 287, 1 GB fn, tp: 4, 5 GB f1 score: 0.667 GB cohens kappa score: 0.658 -> test with 'KNN' KNN tn, fp: 284, 4 KNN fn, tp: 0, 9 KNN f1 score: 0.818 KNN cohens kappa score: 0.811 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1116 synthetic samples -> test with GAN.predict GAN tn, fp: 277, 11 GAN fn, tp: 3, 5 GAN f1 score: 0.417 GAN cohens kappa score: 0.395 -> test with 'LR' LR tn, fp: 275, 13 LR fn, tp: 1, 7 LR f1 score: 0.500 LR cohens kappa score: 0.480 LR average precision score: 0.396 -> test with 'GB' GB tn, fp: 282, 6 GB fn, tp: 3, 5 GB f1 score: 0.526 GB cohens kappa score: 0.511 -> test with 'KNN' KNN tn, fp: 274, 14 KNN fn, tp: 1, 7 KNN f1 score: 0.483 KNN cohens kappa score: 0.462 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 282, 17 LR fn, tp: 2, 9 LR f1 score: 0.692 LR cohens kappa score: 0.680 LR average precision score: 0.884 average: LR tn, fp: 276.6, 11.4 LR fn, tp: 0.48, 8.32 LR f1 score: 0.589 LR cohens kappa score: 0.571 LR average precision score: 0.671 minimum: LR tn, fp: 271, 6 LR fn, tp: 0, 7 LR f1 score: 0.485 LR cohens kappa score: 0.461 LR average precision score: 0.332 -----[ GB ]----- maximum: GB tn, fp: 288, 6 GB fn, tp: 6, 8 GB f1 score: 0.941 GB cohens kappa score: 0.939 average: GB tn, fp: 285.92, 2.08 GB fn, tp: 2.6, 6.2 GB f1 score: 0.723 GB cohens kappa score: 0.716 minimum: GB tn, fp: 282, 0 GB fn, tp: 1, 3 GB f1 score: 0.353 GB cohens kappa score: 0.334 -----[ KNN ]----- maximum: KNN tn, fp: 287, 16 KNN fn, tp: 2, 9 KNN f1 score: 0.889 KNN cohens kappa score: 0.885 average: KNN tn, fp: 279.0, 9.0 KNN fn, tp: 0.44, 8.36 KNN f1 score: 0.651 KNN cohens kappa score: 0.636 minimum: KNN tn, fp: 272, 1 KNN fn, tp: 0, 7 KNN f1 score: 0.483 KNN cohens kappa score: 0.462 -----[ GAN ]----- maximum: GAN tn, fp: 287, 12 GAN fn, tp: 7, 9 GAN f1 score: 0.800 GAN cohens kappa score: 0.795 average: GAN tn, fp: 282.36, 5.64 GAN fn, tp: 3.56, 5.24 GAN f1 score: 0.524 GAN cohens kappa score: 0.509 minimum: GAN tn, fp: 276, 1 GAN fn, tp: 0, 1 GAN f1 score: 0.133 GAN cohens kappa score: 0.111