/////////////////////////////////////////// // Running convGAN-majority-5 on folding_abalone9-18 /////////////////////////////////////////// Load 'data_input/folding_abalone9-18' 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 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 7s - loss: 0.4869 49/56 [=========================>....] - ETA: 0s - loss: 0.2776 56/56 [==============================] - 0s 1ms/step - loss: 0.2772 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2111 49/56 [=========================>....] - ETA: 0s - loss: 0.2653 56/56 [==============================] - 0s 1ms/step - loss: 0.2676 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1532 50/56 [=========================>....] - ETA: 0s - loss: 0.2611 56/56 [==============================] - 0s 1ms/step - loss: 0.2649 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1731 50/56 [=========================>....] - ETA: 0s - loss: 0.2623 56/56 [==============================] - 0s 1ms/step - loss: 0.2629 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2847 50/56 [=========================>....] - ETA: 0s - loss: 0.2604 56/56 [==============================] - 0s 1ms/step - loss: 0.2568 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1675 50/56 [=========================>....] - ETA: 0s - loss: 0.2485 56/56 [==============================] - 0s 1ms/step - loss: 0.2528 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1627 49/56 [=========================>....] - ETA: 0s - loss: 0.2533 56/56 [==============================] - 0s 1ms/step - loss: 0.2479 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2107 50/56 [=========================>....] - ETA: 0s - loss: 0.2452 56/56 [==============================] - 0s 1ms/step - loss: 0.2473 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2453 46/56 [=======================>......] - ETA: 0s - loss: 0.2359 56/56 [==============================] - 0s 1ms/step - loss: 0.2414 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.3505 44/56 [======================>.......] - ETA: 0s - loss: 0.2388 56/56 [==============================] - 0s 1ms/step - loss: 0.2370 -> test with GAN.predict GAN tn, fp: 122, 16 GAN fn, tp: 0, 9 GAN f1 score: 0.529 GAN cohens kappa score: 0.483 -> test with 'LR' LR tn, fp: 123, 15 LR fn, tp: 0, 9 LR f1 score: 0.545 LR cohens kappa score: 0.501 LR average precision score: 0.904 -> test with 'RF' RF tn, fp: 136, 2 RF fn, tp: 8, 1 RF f1 score: 0.167 RF cohens kappa score: 0.140 -> test with 'GB' GB tn, fp: 136, 2 GB fn, tp: 5, 4 GB f1 score: 0.533 GB cohens kappa score: 0.509 -> test with 'KNN' KNN tn, fp: 121, 17 KNN fn, tp: 4, 5 KNN f1 score: 0.323 KNN cohens kappa score: 0.258 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 7s - loss: 0.1805 49/56 [=========================>....] - ETA: 0s - loss: 0.2067 56/56 [==============================] - 0s 1ms/step - loss: 0.2039 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2280 49/56 [=========================>....] - ETA: 0s - loss: 0.1972 56/56 [==============================] - 0s 1ms/step - loss: 0.2008 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1480 49/56 [=========================>....] - ETA: 0s - loss: 0.1990 56/56 [==============================] - 0s 1ms/step - loss: 0.1996 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.2114 43/56 [======================>.......] - ETA: 0s - loss: 0.1916 56/56 [==============================] - 0s 1ms/step - loss: 0.1949 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1629 44/56 [======================>.......] - ETA: 0s - loss: 0.1947 56/56 [==============================] - 0s 1ms/step - loss: 0.1936 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1718 49/56 [=========================>....] - ETA: 0s - loss: 0.1905 56/56 [==============================] - 0s 1ms/step - loss: 0.1896 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0878 49/56 [=========================>....] - ETA: 0s - loss: 0.1811 56/56 [==============================] - 0s 1ms/step - loss: 0.1867 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2054 49/56 [=========================>....] - ETA: 0s - loss: 0.1816 56/56 [==============================] - 0s 1ms/step - loss: 0.1835 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2872 49/56 [=========================>....] - ETA: 0s - loss: 0.1843 56/56 [==============================] - 0s 1ms/step - loss: 0.1820 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2721 49/56 [=========================>....] - ETA: 0s - loss: 0.1805 56/56 [==============================] - 0s 1ms/step - loss: 0.1810 -> test with GAN.predict GAN tn, fp: 133, 5 GAN fn, tp: 4, 5 GAN f1 score: 0.526 GAN cohens kappa score: 0.494 -> test with 'LR' LR tn, fp: 131, 7 LR fn, tp: 3, 6 LR f1 score: 0.545 LR cohens kappa score: 0.510 LR average precision score: 0.542 -> test with 'RF' RF tn, fp: 135, 3 RF fn, tp: 6, 3 RF f1 score: 0.400 RF cohens kappa score: 0.369 -> test with 'GB' GB tn, fp: 135, 3 GB fn, tp: 7, 2 GB f1 score: 0.286 GB cohens kappa score: 0.253 -> test with 'KNN' KNN tn, fp: 118, 20 KNN fn, tp: 3, 6 KNN f1 score: 0.343 KNN cohens kappa score: 0.277 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.2096 48/56 [========================>.....] - ETA: 0s - loss: 0.2957 56/56 [==============================] - 0s 1ms/step - loss: 0.2953 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2847 49/56 [=========================>....] - ETA: 0s - loss: 0.2897 56/56 [==============================] - 0s 1ms/step - loss: 0.2891 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2916 49/56 [=========================>....] - ETA: 0s - loss: 0.2895 56/56 [==============================] - 0s 1ms/step - loss: 0.2882 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3154 49/56 [=========================>....] - ETA: 0s - loss: 0.2821 56/56 [==============================] - 0s 1ms/step - loss: 0.2801 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.3465 50/56 [=========================>....] - ETA: 0s - loss: 0.2631 56/56 [==============================] - 0s 1ms/step - loss: 0.2719 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.3326 49/56 [=========================>....] - ETA: 0s - loss: 0.2725 56/56 [==============================] - 0s 1ms/step - loss: 0.2714 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.3734 50/56 [=========================>....] - ETA: 0s - loss: 0.2645 56/56 [==============================] - 0s 1ms/step - loss: 0.2661 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.3035 49/56 [=========================>....] - ETA: 0s - loss: 0.2613 56/56 [==============================] - 0s 1ms/step - loss: 0.2605 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2569 49/56 [=========================>....] - ETA: 0s - loss: 0.2605 56/56 [==============================] - 0s 1ms/step - loss: 0.2582 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2691 45/56 [=======================>......] - ETA: 0s - loss: 0.2567 56/56 [==============================] - 0s 1ms/step - loss: 0.2539 -> test with GAN.predict GAN tn, fp: 129, 9 GAN fn, tp: 2, 7 GAN f1 score: 0.560 GAN cohens kappa score: 0.523 -> test with 'LR' LR tn, fp: 129, 9 LR fn, tp: 0, 9 LR f1 score: 0.667 LR cohens kappa score: 0.637 LR average precision score: 0.833 -> test with 'RF' RF tn, fp: 135, 3 RF fn, tp: 7, 2 RF f1 score: 0.286 RF cohens kappa score: 0.253 -> test with 'GB' GB tn, fp: 133, 5 GB fn, tp: 5, 4 GB f1 score: 0.444 GB cohens kappa score: 0.408 -> test with 'KNN' KNN tn, fp: 132, 6 KNN fn, tp: 4, 5 KNN f1 score: 0.500 KNN cohens kappa score: 0.464 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.1894 44/56 [======================>.......] - ETA: 0s - loss: 0.2681 56/56 [==============================] - 0s 1ms/step - loss: 0.2587 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.3740 45/56 [=======================>......] - ETA: 0s - loss: 0.2545 56/56 [==============================] - 0s 1ms/step - loss: 0.2518 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.3541 49/56 [=========================>....] - ETA: 0s - loss: 0.2506 56/56 [==============================] - 0s 1ms/step - loss: 0.2479 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3100 49/56 [=========================>....] - ETA: 0s - loss: 0.2434 56/56 [==============================] - 0s 1ms/step - loss: 0.2450 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2297 49/56 [=========================>....] - ETA: 0s - loss: 0.2524 56/56 [==============================] - 0s 1ms/step - loss: 0.2478 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1240 49/56 [=========================>....] - ETA: 0s - loss: 0.2449 56/56 [==============================] - 0s 1ms/step - loss: 0.2404 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.2424 49/56 [=========================>....] - ETA: 0s - loss: 0.2351 56/56 [==============================] - 0s 1ms/step - loss: 0.2379 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.4393 49/56 [=========================>....] - ETA: 0s - loss: 0.2471 56/56 [==============================] - 0s 1ms/step - loss: 0.2355 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.5742 49/56 [=========================>....] - ETA: 0s - loss: 0.2322 56/56 [==============================] - 0s 1ms/step - loss: 0.2319 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2757 49/56 [=========================>....] - ETA: 0s - loss: 0.2280 56/56 [==============================] - 0s 1ms/step - loss: 0.2292 -> test with GAN.predict GAN tn, fp: 128, 10 GAN fn, tp: 2, 7 GAN f1 score: 0.538 GAN cohens kappa score: 0.498 -> test with 'LR' LR tn, fp: 127, 11 LR fn, tp: 2, 7 LR f1 score: 0.519 LR cohens kappa score: 0.476 LR average precision score: 0.527 -> test with 'RF' RF tn, fp: 135, 3 RF fn, tp: 6, 3 RF f1 score: 0.400 RF cohens kappa score: 0.369 -> test with 'GB' GB tn, fp: 134, 4 GB fn, tp: 5, 4 GB f1 score: 0.471 GB cohens kappa score: 0.438 -> test with 'KNN' KNN tn, fp: 123, 15 KNN fn, tp: 2, 7 KNN f1 score: 0.452 KNN cohens kappa score: 0.399 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 516 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.1948 49/56 [=========================>....] - ETA: 0s - loss: 0.2131 56/56 [==============================] - 0s 1ms/step - loss: 0.2126 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2389 49/56 [=========================>....] - ETA: 0s - loss: 0.2137 56/56 [==============================] - 0s 1ms/step - loss: 0.2109 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1808 45/56 [=======================>......] - ETA: 0s - loss: 0.2127 56/56 [==============================] - 0s 1ms/step - loss: 0.2089 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1522 49/56 [=========================>....] - ETA: 0s - loss: 0.2062 56/56 [==============================] - 0s 1ms/step - loss: 0.2081 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1189 49/56 [=========================>....] - ETA: 0s - loss: 0.2167 56/56 [==============================] - 0s 1ms/step - loss: 0.2123 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1892 46/56 [=======================>......] - ETA: 0s - loss: 0.2048 56/56 [==============================] - 0s 1ms/step - loss: 0.2108 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0819 44/56 [======================>.......] - ETA: 0s - loss: 0.2195 56/56 [==============================] - 0s 1ms/step - loss: 0.2077 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2557 43/56 [======================>.......] - ETA: 0s - loss: 0.2074 56/56 [==============================] - 0s 1ms/step - loss: 0.2043 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2056 49/56 [=========================>....] - ETA: 0s - loss: 0.1931 56/56 [==============================] - 0s 1ms/step - loss: 0.2011 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1267 49/56 [=========================>....] - ETA: 0s - loss: 0.1935 56/56 [==============================] - 0s 1ms/step - loss: 0.2017 -> test with GAN.predict GAN tn, fp: 128, 9 GAN fn, tp: 2, 4 GAN f1 score: 0.421 GAN cohens kappa score: 0.386 -> test with 'LR' LR tn, fp: 126, 11 LR fn, tp: 1, 5 LR f1 score: 0.455 LR cohens kappa score: 0.419 LR average precision score: 0.487 -> test with 'RF' RF tn, fp: 135, 2 RF fn, tp: 4, 2 RF f1 score: 0.400 RF cohens kappa score: 0.379 -> test with 'GB' GB tn, fp: 134, 3 GB fn, tp: 4, 2 GB f1 score: 0.364 GB cohens kappa score: 0.338 -> test with 'KNN' KNN tn, fp: 127, 10 KNN fn, tp: 2, 4 KNN f1 score: 0.400 KNN cohens kappa score: 0.363 ====== Step 2/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 2/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 9s - loss: 0.2823 48/56 [========================>.....] - ETA: 0s - loss: 0.2177 56/56 [==============================] - 0s 1ms/step - loss: 0.2159 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.1172 49/56 [=========================>....] - ETA: 0s - loss: 0.2090 56/56 [==============================] - 0s 1ms/step - loss: 0.2115 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1311 49/56 [=========================>....] - ETA: 0s - loss: 0.2055 56/56 [==============================] - 0s 1ms/step - loss: 0.2058 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1218 49/56 [=========================>....] - ETA: 0s - loss: 0.2070 56/56 [==============================] - 0s 1ms/step - loss: 0.2031 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1554 49/56 [=========================>....] - ETA: 0s - loss: 0.2075 56/56 [==============================] - 0s 1ms/step - loss: 0.2047 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.2930 49/56 [=========================>....] - ETA: 0s - loss: 0.2038 56/56 [==============================] - 0s 1ms/step - loss: 0.2022 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1820 49/56 [=========================>....] - ETA: 0s - loss: 0.1926 56/56 [==============================] - 0s 1ms/step - loss: 0.2015 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1776 49/56 [=========================>....] - ETA: 0s - loss: 0.1995 56/56 [==============================] - 0s 1ms/step - loss: 0.1975 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.3999 49/56 [=========================>....] - ETA: 0s - loss: 0.1975 56/56 [==============================] - 0s 1ms/step - loss: 0.1973 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2655 49/56 [=========================>....] - ETA: 0s - loss: 0.1965 56/56 [==============================] - 0s 1ms/step - loss: 0.1990 -> test with GAN.predict GAN tn, fp: 130, 8 GAN fn, tp: 3, 6 GAN f1 score: 0.522 GAN cohens kappa score: 0.483 -> test with 'LR' LR tn, fp: 123, 15 LR fn, tp: 1, 8 LR f1 score: 0.500 LR cohens kappa score: 0.452 LR average precision score: 0.674 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 5, 4 RF f1 score: 0.571 RF cohens kappa score: 0.552 -> test with 'GB' GB tn, fp: 136, 2 GB fn, tp: 5, 4 GB f1 score: 0.533 GB cohens kappa score: 0.509 -> test with 'KNN' KNN tn, fp: 124, 14 KNN fn, tp: 4, 5 KNN f1 score: 0.357 KNN cohens kappa score: 0.299 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 7s - loss: 0.3289 48/56 [========================>.....] - ETA: 0s - loss: 0.2426 56/56 [==============================] - 0s 1ms/step - loss: 0.2478 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2444 49/56 [=========================>....] - ETA: 0s - loss: 0.2460 56/56 [==============================] - 0s 1ms/step - loss: 0.2447 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2242 48/56 [========================>.....] - ETA: 0s - loss: 0.2425 56/56 [==============================] - 0s 1ms/step - loss: 0.2376 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3313 49/56 [=========================>....] - ETA: 0s - loss: 0.2353 56/56 [==============================] - 0s 1ms/step - loss: 0.2354 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.4224 49/56 [=========================>....] - ETA: 0s - loss: 0.2338 56/56 [==============================] - 0s 1ms/step - loss: 0.2344 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.2022 49/56 [=========================>....] - ETA: 0s - loss: 0.2407 56/56 [==============================] - 0s 1ms/step - loss: 0.2324 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1955 49/56 [=========================>....] - ETA: 0s - loss: 0.2363 56/56 [==============================] - 0s 1ms/step - loss: 0.2309 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2251 49/56 [=========================>....] - ETA: 0s - loss: 0.2213 56/56 [==============================] - 0s 1ms/step - loss: 0.2246 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2772 49/56 [=========================>....] - ETA: 0s - loss: 0.2323 56/56 [==============================] - 0s 1ms/step - loss: 0.2289 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1817 49/56 [=========================>....] - ETA: 0s - loss: 0.2184 56/56 [==============================] - 0s 1ms/step - loss: 0.2211 -> test with GAN.predict GAN tn, fp: 129, 9 GAN fn, tp: 3, 6 GAN f1 score: 0.500 GAN cohens kappa score: 0.459 -> test with 'LR' LR tn, fp: 130, 8 LR fn, tp: 1, 8 LR f1 score: 0.640 LR cohens kappa score: 0.609 LR average precision score: 0.771 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 6, 3 RF f1 score: 0.462 RF cohens kappa score: 0.440 -> test with 'GB' GB tn, fp: 135, 3 GB fn, tp: 6, 3 GB f1 score: 0.400 GB cohens kappa score: 0.369 -> test with 'KNN' KNN tn, fp: 127, 11 KNN fn, tp: 4, 5 KNN f1 score: 0.400 KNN cohens kappa score: 0.349 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.2337 49/56 [=========================>....] - ETA: 0s - loss: 0.2623 56/56 [==============================] - 0s 1ms/step - loss: 0.2560 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.1773 47/56 [========================>.....] - ETA: 0s - loss: 0.2522 56/56 [==============================] - 0s 1ms/step - loss: 0.2477 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2557 47/56 [========================>.....] - ETA: 0s - loss: 0.2394 56/56 [==============================] - 0s 1ms/step - loss: 0.2453 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1866 49/56 [=========================>....] - ETA: 0s - loss: 0.2421 56/56 [==============================] - 0s 1ms/step - loss: 0.2442 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2548 49/56 [=========================>....] - ETA: 0s - loss: 0.2468 56/56 [==============================] - 0s 1ms/step - loss: 0.2376 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.2494 49/56 [=========================>....] - ETA: 0s - loss: 0.2467 56/56 [==============================] - 0s 1ms/step - loss: 0.2469 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.4434 49/56 [=========================>....] - ETA: 0s - loss: 0.2214 56/56 [==============================] - 0s 1ms/step - loss: 0.2334 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2234 49/56 [=========================>....] - ETA: 0s - loss: 0.2325 56/56 [==============================] - 0s 1ms/step - loss: 0.2364 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2813 49/56 [=========================>....] - ETA: 0s - loss: 0.2300 56/56 [==============================] - 0s 1ms/step - loss: 0.2309 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1461 49/56 [=========================>....] - ETA: 0s - loss: 0.2229 56/56 [==============================] - 0s 1ms/step - loss: 0.2237 -> test with GAN.predict GAN tn, fp: 123, 15 GAN fn, tp: 2, 7 GAN f1 score: 0.452 GAN cohens kappa score: 0.399 -> test with 'LR' LR tn, fp: 132, 6 LR fn, tp: 2, 7 LR f1 score: 0.636 LR cohens kappa score: 0.608 LR average precision score: 0.703 -> test with 'RF' RF tn, fp: 131, 7 RF fn, tp: 8, 1 RF f1 score: 0.118 RF cohens kappa score: 0.064 -> test with 'GB' GB tn, fp: 128, 10 GB fn, tp: 6, 3 GB f1 score: 0.273 GB cohens kappa score: 0.216 -> test with 'KNN' KNN tn, fp: 118, 20 KNN fn, tp: 2, 7 KNN f1 score: 0.389 KNN cohens kappa score: 0.327 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 7s - loss: 0.3131 49/56 [=========================>....] - ETA: 0s - loss: 0.2435 56/56 [==============================] - 0s 1ms/step - loss: 0.2411 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2496 50/56 [=========================>....] - ETA: 0s - loss: 0.2356 56/56 [==============================] - 0s 1ms/step - loss: 0.2349 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2542 43/56 [======================>.......] - ETA: 0s - loss: 0.2344 56/56 [==============================] - 0s 1ms/step - loss: 0.2285 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.2558 44/56 [======================>.......] - ETA: 0s - loss: 0.2301 56/56 [==============================] - 0s 1ms/step - loss: 0.2279 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0984 49/56 [=========================>....] - ETA: 0s - loss: 0.2368 56/56 [==============================] - 0s 1ms/step - loss: 0.2295 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.3452 49/56 [=========================>....] - ETA: 0s - loss: 0.2197 56/56 [==============================] - 0s 1ms/step - loss: 0.2213 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1540 49/56 [=========================>....] - ETA: 0s - loss: 0.2279 56/56 [==============================] - 0s 1ms/step - loss: 0.2198 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1208 50/56 [=========================>....] - ETA: 0s - loss: 0.2182 56/56 [==============================] - 0s 1ms/step - loss: 0.2186 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2182 49/56 [=========================>....] - ETA: 0s - loss: 0.2195 56/56 [==============================] - 0s 1ms/step - loss: 0.2135 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1164 46/56 [=======================>......] - ETA: 0s - loss: 0.2148 56/56 [==============================] - 0s 1ms/step - loss: 0.2174 -> test with GAN.predict GAN tn, fp: 122, 16 GAN fn, tp: 1, 8 GAN f1 score: 0.485 GAN cohens kappa score: 0.434 -> test with 'LR' LR tn, fp: 125, 13 LR fn, tp: 1, 8 LR f1 score: 0.533 LR cohens kappa score: 0.490 LR average precision score: 0.690 -> test with 'RF' RF tn, fp: 132, 6 RF fn, tp: 7, 2 RF f1 score: 0.235 RF cohens kappa score: 0.189 -> test with 'GB' GB tn, fp: 132, 6 GB fn, tp: 5, 4 GB f1 score: 0.421 GB cohens kappa score: 0.381 -> test with 'KNN' KNN tn, fp: 121, 17 KNN fn, tp: 3, 6 KNN f1 score: 0.375 KNN cohens kappa score: 0.315 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 516 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 7s - loss: 0.1634 45/56 [=======================>......] - ETA: 0s - loss: 0.2322 56/56 [==============================] - 0s 1ms/step - loss: 0.2320 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2844 48/56 [========================>.....] - ETA: 0s - loss: 0.2310 56/56 [==============================] - 0s 1ms/step - loss: 0.2272 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2126 49/56 [=========================>....] - ETA: 0s - loss: 0.2160 56/56 [==============================] - 0s 1ms/step - loss: 0.2242 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3932 49/56 [=========================>....] - ETA: 0s - loss: 0.2236 56/56 [==============================] - 0s 1ms/step - loss: 0.2302 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1848 49/56 [=========================>....] - ETA: 0s - loss: 0.2262 56/56 [==============================] - 0s 1ms/step - loss: 0.2250 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1495 49/56 [=========================>....] - ETA: 0s - loss: 0.2131 56/56 [==============================] - 0s 1ms/step - loss: 0.2194 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1908 49/56 [=========================>....] - ETA: 0s - loss: 0.2178 56/56 [==============================] - 0s 1ms/step - loss: 0.2171 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2610 49/56 [=========================>....] - ETA: 0s - loss: 0.2062 56/56 [==============================] - 0s 1ms/step - loss: 0.2114 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0862 46/56 [=======================>......] - ETA: 0s - loss: 0.2082 56/56 [==============================] - 0s 1ms/step - loss: 0.2107 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.3257 49/56 [=========================>....] - ETA: 0s - loss: 0.2119 56/56 [==============================] - 0s 1ms/step - loss: 0.2086 -> test with GAN.predict GAN tn, fp: 123, 14 GAN fn, tp: 2, 4 GAN f1 score: 0.333 GAN cohens kappa score: 0.289 -> test with 'LR' LR tn, fp: 128, 9 LR fn, tp: 1, 5 LR f1 score: 0.500 LR cohens kappa score: 0.469 LR average precision score: 0.569 -> test with 'RF' RF tn, fp: 134, 3 RF fn, tp: 3, 3 RF f1 score: 0.500 RF cohens kappa score: 0.478 -> test with 'GB' GB tn, fp: 129, 8 GB fn, tp: 3, 3 GB f1 score: 0.353 GB cohens kappa score: 0.316 -> test with 'KNN' KNN tn, fp: 122, 15 KNN fn, tp: 2, 4 KNN f1 score: 0.320 KNN cohens kappa score: 0.274 ====== Step 3/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 3/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.4693 48/56 [========================>.....] - ETA: 0s - loss: 0.2399 56/56 [==============================] - 0s 1ms/step - loss: 0.2309 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.3355 50/56 [=========================>....] - ETA: 0s - loss: 0.2339 56/56 [==============================] - 0s 1ms/step - loss: 0.2294 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.3396 49/56 [=========================>....] - ETA: 0s - loss: 0.2226 56/56 [==============================] - 0s 1ms/step - loss: 0.2244 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1729 49/56 [=========================>....] - ETA: 0s - loss: 0.2170 56/56 [==============================] - 0s 1ms/step - loss: 0.2238 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2593 49/56 [=========================>....] - ETA: 0s - loss: 0.2163 56/56 [==============================] - 0s 1ms/step - loss: 0.2200 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1646 49/56 [=========================>....] - ETA: 0s - loss: 0.2127 56/56 [==============================] - 0s 1ms/step - loss: 0.2185 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.2795 50/56 [=========================>....] - ETA: 0s - loss: 0.2225 56/56 [==============================] - 0s 1ms/step - loss: 0.2203 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1799 49/56 [=========================>....] - ETA: 0s - loss: 0.2155 56/56 [==============================] - 0s 1ms/step - loss: 0.2147 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2327 49/56 [=========================>....] - ETA: 0s - loss: 0.2132 56/56 [==============================] - 0s 1ms/step - loss: 0.2145 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.3673 49/56 [=========================>....] - ETA: 0s - loss: 0.2136 56/56 [==============================] - 0s 1ms/step - loss: 0.2105 -> test with GAN.predict GAN tn, fp: 121, 17 GAN fn, tp: 2, 7 GAN f1 score: 0.424 GAN cohens kappa score: 0.368 -> test with 'LR' LR tn, fp: 127, 11 LR fn, tp: 2, 7 LR f1 score: 0.519 LR cohens kappa score: 0.476 LR average precision score: 0.593 -> test with 'RF' RF tn, fp: 134, 4 RF fn, tp: 8, 1 RF f1 score: 0.143 RF cohens kappa score: 0.104 -> test with 'GB' GB tn, fp: 130, 8 GB fn, tp: 8, 1 GB f1 score: 0.111 GB cohens kappa score: 0.053 -> test with 'KNN' KNN tn, fp: 126, 12 KNN fn, tp: 4, 5 KNN f1 score: 0.385 KNN cohens kappa score: 0.331 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.3872 48/56 [========================>.....] - ETA: 0s - loss: 0.3115 56/56 [==============================] - 0s 1ms/step - loss: 0.3057 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2872 49/56 [=========================>....] - ETA: 0s - loss: 0.2962 56/56 [==============================] - 0s 1ms/step - loss: 0.3002 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.3011 49/56 [=========================>....] - ETA: 0s - loss: 0.2978 56/56 [==============================] - 0s 1ms/step - loss: 0.2950 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.2643 49/56 [=========================>....] - ETA: 0s - loss: 0.2848 56/56 [==============================] - 0s 1ms/step - loss: 0.2905 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.4135 49/56 [=========================>....] - ETA: 0s - loss: 0.2862 56/56 [==============================] - 0s 1ms/step - loss: 0.2870 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.2053 49/56 [=========================>....] - ETA: 0s - loss: 0.2873 56/56 [==============================] - 0s 1ms/step - loss: 0.2846 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.2099 49/56 [=========================>....] - ETA: 0s - loss: 0.2758 56/56 [==============================] - 0s 1ms/step - loss: 0.2770 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1818 49/56 [=========================>....] - ETA: 0s - loss: 0.2839 56/56 [==============================] - 0s 1ms/step - loss: 0.2807 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1559 49/56 [=========================>....] - ETA: 0s - loss: 0.2745 56/56 [==============================] - 0s 1ms/step - loss: 0.2734 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.3142 43/56 [======================>.......] - ETA: 0s - loss: 0.2839 56/56 [==============================] - 0s 1ms/step - loss: 0.2729 -> test with GAN.predict GAN tn, fp: 130, 8 GAN fn, tp: 0, 9 GAN f1 score: 0.692 GAN cohens kappa score: 0.666 -> test with 'LR' LR tn, fp: 131, 7 LR fn, tp: 0, 9 LR f1 score: 0.720 LR cohens kappa score: 0.696 LR average precision score: 0.906 -> test with 'RF' RF tn, fp: 136, 2 RF fn, tp: 4, 5 RF f1 score: 0.625 RF cohens kappa score: 0.604 -> test with 'GB' GB tn, fp: 132, 6 GB fn, tp: 4, 5 GB f1 score: 0.500 GB cohens kappa score: 0.464 -> test with 'KNN' KNN tn, fp: 117, 21 KNN fn, tp: 1, 8 KNN f1 score: 0.421 KNN cohens kappa score: 0.361 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 9s - loss: 0.1270 48/56 [========================>.....] - ETA: 0s - loss: 0.1764 56/56 [==============================] - 0s 1ms/step - loss: 0.1796 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.1544 50/56 [=========================>....] - ETA: 0s - loss: 0.1813 56/56 [==============================] - 0s 1ms/step - loss: 0.1778 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0878 49/56 [=========================>....] - ETA: 0s - loss: 0.1774 56/56 [==============================] - 0s 1ms/step - loss: 0.1751 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3379 49/56 [=========================>....] - ETA: 0s - loss: 0.1724 56/56 [==============================] - 0s 1ms/step - loss: 0.1702 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0882 46/56 [=======================>......] - ETA: 0s - loss: 0.1599 56/56 [==============================] - 0s 1ms/step - loss: 0.1686 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1441 45/56 [=======================>......] - ETA: 0s - loss: 0.1644 56/56 [==============================] - 0s 1ms/step - loss: 0.1666 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1865 46/56 [=======================>......] - ETA: 0s - loss: 0.1704 56/56 [==============================] - 0s 1ms/step - loss: 0.1660 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1861 49/56 [=========================>....] - ETA: 0s - loss: 0.1714 56/56 [==============================] - 0s 1ms/step - loss: 0.1630 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1590 49/56 [=========================>....] - ETA: 0s - loss: 0.1579 56/56 [==============================] - 0s 1ms/step - loss: 0.1632 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2917 49/56 [=========================>....] - ETA: 0s - loss: 0.1632 56/56 [==============================] - 0s 1ms/step - loss: 0.1592 -> test with GAN.predict GAN tn, fp: 128, 10 GAN fn, tp: 3, 6 GAN f1 score: 0.480 GAN cohens kappa score: 0.436 -> test with 'LR' LR tn, fp: 132, 6 LR fn, tp: 4, 5 LR f1 score: 0.500 LR cohens kappa score: 0.464 LR average precision score: 0.693 -> test with 'RF' RF tn, fp: 133, 5 RF fn, tp: 8, 1 RF f1 score: 0.133 RF cohens kappa score: 0.089 -> test with 'GB' GB tn, fp: 132, 6 GB fn, tp: 7, 2 GB f1 score: 0.235 GB cohens kappa score: 0.189 -> test with 'KNN' KNN tn, fp: 125, 13 KNN fn, tp: 5, 4 KNN f1 score: 0.308 KNN cohens kappa score: 0.247 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.3352 49/56 [=========================>....] - ETA: 0s - loss: 0.2552 56/56 [==============================] - 0s 1ms/step - loss: 0.2512 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2223 49/56 [=========================>....] - ETA: 0s - loss: 0.2428 56/56 [==============================] - 0s 1ms/step - loss: 0.2445 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1835 49/56 [=========================>....] - ETA: 0s - loss: 0.2377 56/56 [==============================] - 0s 1ms/step - loss: 0.2415 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1335 49/56 [=========================>....] - ETA: 0s - loss: 0.2395 56/56 [==============================] - 0s 1ms/step - loss: 0.2368 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1782 48/56 [========================>.....] - ETA: 0s - loss: 0.2319 56/56 [==============================] - 0s 1ms/step - loss: 0.2344 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1417 49/56 [=========================>....] - ETA: 0s - loss: 0.2275 56/56 [==============================] - 0s 1ms/step - loss: 0.2318 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.3927 49/56 [=========================>....] - ETA: 0s - loss: 0.2242 56/56 [==============================] - 0s 1ms/step - loss: 0.2281 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1498 49/56 [=========================>....] - ETA: 0s - loss: 0.2311 56/56 [==============================] - 0s 1ms/step - loss: 0.2242 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1754 49/56 [=========================>....] - ETA: 0s - loss: 0.2251 56/56 [==============================] - 0s 1ms/step - loss: 0.2239 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1270 49/56 [=========================>....] - ETA: 0s - loss: 0.2253 56/56 [==============================] - 0s 1ms/step - loss: 0.2248 -> test with GAN.predict GAN tn, fp: 122, 16 GAN fn, tp: 3, 6 GAN f1 score: 0.387 GAN cohens kappa score: 0.329 -> test with 'LR' LR tn, fp: 117, 21 LR fn, tp: 1, 8 LR f1 score: 0.421 LR cohens kappa score: 0.361 LR average precision score: 0.649 -> test with 'RF' RF tn, fp: 134, 4 RF fn, tp: 7, 2 RF f1 score: 0.267 RF cohens kappa score: 0.229 -> test with 'GB' GB tn, fp: 128, 10 GB fn, tp: 6, 3 GB f1 score: 0.273 GB cohens kappa score: 0.216 -> test with 'KNN' KNN tn, fp: 119, 19 KNN fn, tp: 4, 5 KNN f1 score: 0.303 KNN cohens kappa score: 0.235 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 516 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 20s - loss: 0.2082 42/56 [=====================>........] - ETA: 0s - loss: 0.2620  56/56 [==============================] - 0s 1ms/step - loss: 0.2667 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.1746 49/56 [=========================>....] - ETA: 0s - loss: 0.2582 56/56 [==============================] - 0s 1ms/step - loss: 0.2608 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2656 49/56 [=========================>....] - ETA: 0s - loss: 0.2538 56/56 [==============================] - 0s 1ms/step - loss: 0.2535 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.2269 49/56 [=========================>....] - ETA: 0s - loss: 0.2548 56/56 [==============================] - 0s 1ms/step - loss: 0.2533 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2904 49/56 [=========================>....] - ETA: 0s - loss: 0.2326 56/56 [==============================] - 0s 1ms/step - loss: 0.2451 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.4626 49/56 [=========================>....] - ETA: 0s - loss: 0.2497 56/56 [==============================] - 0s 1ms/step - loss: 0.2482 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1902 49/56 [=========================>....] - ETA: 0s - loss: 0.2396 56/56 [==============================] - 0s 1ms/step - loss: 0.2441 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1237 49/56 [=========================>....] - ETA: 0s - loss: 0.2445 56/56 [==============================] - 0s 1ms/step - loss: 0.2407 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1262 49/56 [=========================>....] - ETA: 0s - loss: 0.2377 56/56 [==============================] - 0s 1ms/step - loss: 0.2380 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1731 45/56 [=======================>......] - ETA: 0s - loss: 0.2189 56/56 [==============================] - 0s 1ms/step - loss: 0.2319 -> test with GAN.predict GAN tn, fp: 127, 10 GAN fn, tp: 2, 4 GAN f1 score: 0.400 GAN cohens kappa score: 0.363 -> test with 'LR' LR tn, fp: 124, 13 LR fn, tp: 1, 5 LR f1 score: 0.417 LR cohens kappa score: 0.377 LR average precision score: 0.553 -> test with 'RF' RF tn, fp: 133, 4 RF fn, tp: 5, 1 RF f1 score: 0.182 RF cohens kappa score: 0.149 -> test with 'GB' GB tn, fp: 133, 4 GB fn, tp: 4, 2 GB f1 score: 0.333 GB cohens kappa score: 0.304 -> test with 'KNN' KNN tn, fp: 121, 16 KNN fn, tp: 3, 3 KNN f1 score: 0.240 KNN cohens kappa score: 0.188 ====== Step 4/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 4/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 9s - loss: 0.1748 49/56 [=========================>....] - ETA: 0s - loss: 0.2386 56/56 [==============================] - 0s 1ms/step - loss: 0.2320 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.4176 49/56 [=========================>....] - ETA: 0s - loss: 0.2279 56/56 [==============================] - 0s 1ms/step - loss: 0.2251 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1040 49/56 [=========================>....] - ETA: 0s - loss: 0.2233 56/56 [==============================] - 0s 1ms/step - loss: 0.2207 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1555 49/56 [=========================>....] - ETA: 0s - loss: 0.2179 56/56 [==============================] - 0s 1ms/step - loss: 0.2177 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0934 49/56 [=========================>....] - ETA: 0s - loss: 0.2198 56/56 [==============================] - 0s 1ms/step - loss: 0.2143 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.4126 49/56 [=========================>....] - ETA: 0s - loss: 0.2097 56/56 [==============================] - 0s 1ms/step - loss: 0.2119 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.3093 49/56 [=========================>....] - ETA: 0s - loss: 0.2112 56/56 [==============================] - 0s 1ms/step - loss: 0.2100 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1753 49/56 [=========================>....] - ETA: 0s - loss: 0.2087 56/56 [==============================] - 0s 1ms/step - loss: 0.2062 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1420 49/56 [=========================>....] - ETA: 0s - loss: 0.2026 56/56 [==============================] - 0s 1ms/step - loss: 0.2059 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1921 49/56 [=========================>....] - ETA: 0s - loss: 0.1913 56/56 [==============================] - 0s 1ms/step - loss: 0.2010 -> test with GAN.predict GAN tn, fp: 127, 11 GAN fn, tp: 3, 6 GAN f1 score: 0.462 GAN cohens kappa score: 0.415 -> test with 'LR' LR tn, fp: 128, 10 LR fn, tp: 4, 5 LR f1 score: 0.417 LR cohens kappa score: 0.368 LR average precision score: 0.534 -> test with 'RF' RF tn, fp: 134, 4 RF fn, tp: 6, 3 RF f1 score: 0.375 RF cohens kappa score: 0.340 -> test with 'GB' GB tn, fp: 136, 2 GB fn, tp: 5, 4 GB f1 score: 0.533 GB cohens kappa score: 0.509 -> test with 'KNN' KNN tn, fp: 127, 11 KNN fn, tp: 4, 5 KNN f1 score: 0.400 KNN cohens kappa score: 0.349 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.2563 49/56 [=========================>....] - ETA: 0s - loss: 0.2500 56/56 [==============================] - 0s 1ms/step - loss: 0.2488 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.1577 49/56 [=========================>....] - ETA: 0s - loss: 0.2518 56/56 [==============================] - 0s 1ms/step - loss: 0.2509 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2190 49/56 [=========================>....] - ETA: 0s - loss: 0.2449 56/56 [==============================] - 0s 1ms/step - loss: 0.2471 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1673 48/56 [========================>.....] - ETA: 0s - loss: 0.2516 56/56 [==============================] - 0s 1ms/step - loss: 0.2459 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2175 49/56 [=========================>....] - ETA: 0s - loss: 0.2382 56/56 [==============================] - 0s 1ms/step - loss: 0.2369 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1866 48/56 [========================>.....] - ETA: 0s - loss: 0.2349 56/56 [==============================] - 0s 1ms/step - loss: 0.2369 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1518 49/56 [=========================>....] - ETA: 0s - loss: 0.2337 56/56 [==============================] - 0s 1ms/step - loss: 0.2367 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1820 49/56 [=========================>....] - ETA: 0s - loss: 0.2352 56/56 [==============================] - 0s 1ms/step - loss: 0.2323 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2641 49/56 [=========================>....] - ETA: 0s - loss: 0.2329 56/56 [==============================] - 0s 1ms/step - loss: 0.2324 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2426 49/56 [=========================>....] - ETA: 0s - loss: 0.2312 56/56 [==============================] - 0s 1ms/step - loss: 0.2256 -> test with GAN.predict GAN tn, fp: 126, 12 GAN fn, tp: 2, 7 GAN f1 score: 0.500 GAN cohens kappa score: 0.455 -> test with 'LR' LR tn, fp: 124, 14 LR fn, tp: 2, 7 LR f1 score: 0.467 LR cohens kappa score: 0.417 LR average precision score: 0.711 -> test with 'RF' RF tn, fp: 132, 6 RF fn, tp: 5, 4 RF f1 score: 0.421 RF cohens kappa score: 0.381 -> test with 'GB' GB tn, fp: 128, 10 GB fn, tp: 4, 5 GB f1 score: 0.417 GB cohens kappa score: 0.368 -> test with 'KNN' KNN tn, fp: 117, 21 KNN fn, tp: 2, 7 KNN f1 score: 0.378 KNN cohens kappa score: 0.315 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.3719 48/56 [========================>.....] - ETA: 0s - loss: 0.2790 56/56 [==============================] - 0s 1ms/step - loss: 0.2767 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.3228 47/56 [========================>.....] - ETA: 0s - loss: 0.2657 56/56 [==============================] - 0s 1ms/step - loss: 0.2724 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2493 43/56 [======================>.......] - ETA: 0s - loss: 0.2677 56/56 [==============================] - 0s 1ms/step - loss: 0.2698 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3515 43/56 [======================>.......] - ETA: 0s - loss: 0.2713 56/56 [==============================] - 0s 1ms/step - loss: 0.2637 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2592 49/56 [=========================>....] - ETA: 0s - loss: 0.2653 56/56 [==============================] - 0s 1ms/step - loss: 0.2577 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.3351 49/56 [=========================>....] - ETA: 0s - loss: 0.2517 56/56 [==============================] - 0s 1ms/step - loss: 0.2536 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1440 49/56 [=========================>....] - ETA: 0s - loss: 0.2460 56/56 [==============================] - 0s 1ms/step - loss: 0.2531 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1443 49/56 [=========================>....] - ETA: 0s - loss: 0.2402 56/56 [==============================] - 0s 1ms/step - loss: 0.2452 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1517 49/56 [=========================>....] - ETA: 0s - loss: 0.2463 56/56 [==============================] - 0s 1ms/step - loss: 0.2436 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.3098 49/56 [=========================>....] - ETA: 0s - loss: 0.2386 56/56 [==============================] - 0s 1ms/step - loss: 0.2384 -> test with GAN.predict GAN tn, fp: 123, 15 GAN fn, tp: 1, 8 GAN f1 score: 0.500 GAN cohens kappa score: 0.452 -> test with 'LR' LR tn, fp: 129, 9 LR fn, tp: 1, 8 LR f1 score: 0.615 LR cohens kappa score: 0.582 LR average precision score: 0.692 -> test with 'RF' RF tn, fp: 136, 2 RF fn, tp: 7, 2 RF f1 score: 0.308 RF cohens kappa score: 0.281 -> test with 'GB' GB tn, fp: 134, 4 GB fn, tp: 8, 1 GB f1 score: 0.143 GB cohens kappa score: 0.104 -> test with 'KNN' KNN tn, fp: 123, 15 KNN fn, tp: 4, 5 KNN f1 score: 0.345 KNN cohens kappa score: 0.284 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.3076 49/56 [=========================>....] - ETA: 0s - loss: 0.2925 56/56 [==============================] - 0s 1ms/step - loss: 0.2968 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2473 49/56 [=========================>....] - ETA: 0s - loss: 0.2918 56/56 [==============================] - 0s 1ms/step - loss: 0.2912 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2896 49/56 [=========================>....] - ETA: 0s - loss: 0.2946 56/56 [==============================] - 0s 1ms/step - loss: 0.2886 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3263 49/56 [=========================>....] - ETA: 0s - loss: 0.2773 56/56 [==============================] - 0s 1ms/step - loss: 0.2798 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.3581 49/56 [=========================>....] - ETA: 0s - loss: 0.2817 56/56 [==============================] - 0s 1ms/step - loss: 0.2780 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.3136 49/56 [=========================>....] - ETA: 0s - loss: 0.2775 56/56 [==============================] - 0s 1ms/step - loss: 0.2774 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1772 49/56 [=========================>....] - ETA: 0s - loss: 0.2791 56/56 [==============================] - 0s 1ms/step - loss: 0.2730 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2508 48/56 [========================>.....] - ETA: 0s - loss: 0.2722 56/56 [==============================] - 0s 1ms/step - loss: 0.2694 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1902 48/56 [========================>.....] - ETA: 0s - loss: 0.2745 56/56 [==============================] - 0s 1ms/step - loss: 0.2695 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2421 48/56 [========================>.....] - ETA: 0s - loss: 0.2658 56/56 [==============================] - 0s 1ms/step - loss: 0.2627 -> test with GAN.predict GAN tn, fp: 127, 11 GAN fn, tp: 0, 9 GAN f1 score: 0.621 GAN cohens kappa score: 0.586 -> test with 'LR' LR tn, fp: 123, 15 LR fn, tp: 0, 9 LR f1 score: 0.545 LR cohens kappa score: 0.501 LR average precision score: 0.928 -> test with 'RF' RF tn, fp: 134, 4 RF fn, tp: 7, 2 RF f1 score: 0.267 RF cohens kappa score: 0.229 -> test with 'GB' GB tn, fp: 132, 6 GB fn, tp: 5, 4 GB f1 score: 0.421 GB cohens kappa score: 0.381 -> test with 'KNN' KNN tn, fp: 113, 25 KNN fn, tp: 2, 7 KNN f1 score: 0.341 KNN cohens kappa score: 0.272 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 516 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 7s - loss: 0.1640 48/56 [========================>.....] - ETA: 0s - loss: 0.2664 56/56 [==============================] - 0s 1ms/step - loss: 0.2670 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2876 49/56 [=========================>....] - ETA: 0s - loss: 0.2699 56/56 [==============================] - 0s 1ms/step - loss: 0.2631 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1235 49/56 [=========================>....] - ETA: 0s - loss: 0.2677 56/56 [==============================] - 0s 1ms/step - loss: 0.2635 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.2784 46/56 [=======================>......] - ETA: 0s - loss: 0.2555 56/56 [==============================] - 0s 1ms/step - loss: 0.2529 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2079 43/56 [======================>.......] - ETA: 0s - loss: 0.2580 56/56 [==============================] - 0s 1ms/step - loss: 0.2511 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.3750 45/56 [=======================>......] - ETA: 0s - loss: 0.2436 56/56 [==============================] - 0s 1ms/step - loss: 0.2439 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.3445 49/56 [=========================>....] - ETA: 0s - loss: 0.2384 56/56 [==============================] - 0s 1ms/step - loss: 0.2424 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2286 49/56 [=========================>....] - ETA: 0s - loss: 0.2444 56/56 [==============================] - 0s 1ms/step - loss: 0.2391 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.3165 47/56 [========================>.....] - ETA: 0s - loss: 0.2512 56/56 [==============================] - 0s 1ms/step - loss: 0.2441 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2572 46/56 [=======================>......] - ETA: 0s - loss: 0.2332 56/56 [==============================] - 0s 1ms/step - loss: 0.2384 -> test with GAN.predict GAN tn, fp: 128, 9 GAN fn, tp: 2, 4 GAN f1 score: 0.421 GAN cohens kappa score: 0.386 -> test with 'LR' LR tn, fp: 130, 7 LR fn, tp: 1, 5 LR f1 score: 0.556 LR cohens kappa score: 0.529 LR average precision score: 0.588 -> test with 'RF' RF tn, fp: 131, 6 RF fn, tp: 4, 2 RF f1 score: 0.286 RF cohens kappa score: 0.250 -> test with 'GB' GB tn, fp: 130, 7 GB fn, tp: 4, 2 GB f1 score: 0.267 GB cohens kappa score: 0.228 -> test with 'KNN' KNN tn, fp: 124, 13 KNN fn, tp: 1, 5 KNN f1 score: 0.417 KNN cohens kappa score: 0.377 ====== Step 5/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 5/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.4624 37/56 [==================>...........] - ETA: 0s - loss: 0.2542 56/56 [==============================] - 0s 1ms/step - loss: 0.2520 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.1638 41/56 [====================>.........] - ETA: 0s - loss: 0.2497 56/56 [==============================] - 0s 1ms/step - loss: 0.2446 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.3759 41/56 [====================>.........] - ETA: 0s - loss: 0.2500 56/56 [==============================] - 0s 1ms/step - loss: 0.2417 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1845 44/56 [======================>.......] - ETA: 0s - loss: 0.2420 56/56 [==============================] - 0s 1ms/step - loss: 0.2380 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1491 45/56 [=======================>......] - ETA: 0s - loss: 0.2270 56/56 [==============================] - 0s 1ms/step - loss: 0.2329 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.2546 42/56 [=====================>........] - ETA: 0s - loss: 0.2339 56/56 [==============================] - 0s 1ms/step - loss: 0.2335 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.2552 44/56 [======================>.......] - ETA: 0s - loss: 0.2182 56/56 [==============================] - 0s 1ms/step - loss: 0.2280 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1376 43/56 [======================>.......] - ETA: 0s - loss: 0.2266 56/56 [==============================] - 0s 1ms/step - loss: 0.2263 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2556 43/56 [======================>.......] - ETA: 0s - loss: 0.2311 56/56 [==============================] - 0s 1ms/step - loss: 0.2244 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.3892 45/56 [=======================>......] - ETA: 0s - loss: 0.2190 56/56 [==============================] - 0s 1ms/step - loss: 0.2187 -> test with GAN.predict GAN tn, fp: 127, 11 GAN fn, tp: 4, 5 GAN f1 score: 0.400 GAN cohens kappa score: 0.349 -> test with 'LR' LR tn, fp: 121, 17 LR fn, tp: 1, 8 LR f1 score: 0.471 LR cohens kappa score: 0.418 LR average precision score: 0.734 -> test with 'RF' RF tn, fp: 135, 3 RF fn, tp: 8, 1 RF f1 score: 0.154 RF cohens kappa score: 0.121 -> test with 'GB' GB tn, fp: 132, 6 GB fn, tp: 7, 2 GB f1 score: 0.235 GB cohens kappa score: 0.189 -> test with 'KNN' KNN tn, fp: 123, 15 KNN fn, tp: 5, 4 KNN f1 score: 0.286 KNN cohens kappa score: 0.221 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 7s - loss: 0.3119 48/56 [========================>.....] - ETA: 0s - loss: 0.3019 56/56 [==============================] - 0s 1ms/step - loss: 0.2964 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2533 48/56 [========================>.....] - ETA: 0s - loss: 0.2877 56/56 [==============================] - 0s 1ms/step - loss: 0.2845 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2728 49/56 [=========================>....] - ETA: 0s - loss: 0.2775 56/56 [==============================] - 0s 1ms/step - loss: 0.2763 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.2631 49/56 [=========================>....] - ETA: 0s - loss: 0.2768 56/56 [==============================] - 0s 1ms/step - loss: 0.2710 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2075 49/56 [=========================>....] - ETA: 0s - loss: 0.2667 56/56 [==============================] - 0s 1ms/step - loss: 0.2649 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.2397 48/56 [========================>.....] - ETA: 0s - loss: 0.2581 56/56 [==============================] - 0s 1ms/step - loss: 0.2593 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.2151 49/56 [=========================>....] - ETA: 0s - loss: 0.2513 56/56 [==============================] - 0s 1ms/step - loss: 0.2549 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2855 49/56 [=========================>....] - ETA: 0s - loss: 0.2460 56/56 [==============================] - 0s 1ms/step - loss: 0.2449 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1682 49/56 [=========================>....] - ETA: 0s - loss: 0.2497 56/56 [==============================] - 0s 1ms/step - loss: 0.2442 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2379 49/56 [=========================>....] - ETA: 0s - loss: 0.2383 56/56 [==============================] - 0s 1ms/step - loss: 0.2402 -> test with GAN.predict GAN tn, fp: 125, 13 GAN fn, tp: 4, 5 GAN f1 score: 0.370 GAN cohens kappa score: 0.314 -> test with 'LR' LR tn, fp: 128, 10 LR fn, tp: 0, 9 LR f1 score: 0.643 LR cohens kappa score: 0.610 LR average precision score: 0.738 -> test with 'RF' RF tn, fp: 134, 4 RF fn, tp: 8, 1 RF f1 score: 0.143 RF cohens kappa score: 0.104 -> test with 'GB' GB tn, fp: 133, 5 GB fn, tp: 6, 3 GB f1 score: 0.353 GB cohens kappa score: 0.313 -> test with 'KNN' KNN tn, fp: 117, 21 KNN fn, tp: 4, 5 KNN f1 score: 0.286 KNN cohens kappa score: 0.214 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.1225 47/56 [========================>.....] - ETA: 0s - loss: 0.2280 56/56 [==============================] - 0s 1ms/step - loss: 0.2316 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2083 44/56 [======================>.......] - ETA: 0s - loss: 0.2197 56/56 [==============================] - 0s 1ms/step - loss: 0.2294 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2304 45/56 [=======================>......] - ETA: 0s - loss: 0.2169 56/56 [==============================] - 0s 1ms/step - loss: 0.2286 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3917 49/56 [=========================>....] - ETA: 0s - loss: 0.2270 56/56 [==============================] - 0s 1ms/step - loss: 0.2215 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1395 49/56 [=========================>....] - ETA: 0s - loss: 0.2137 56/56 [==============================] - 0s 1ms/step - loss: 0.2180 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.3126 43/56 [======================>.......] - ETA: 0s - loss: 0.2161 56/56 [==============================] - 0s 1ms/step - loss: 0.2137 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1918 49/56 [=========================>....] - ETA: 0s - loss: 0.2090 56/56 [==============================] - 0s 1ms/step - loss: 0.2102 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1740 47/56 [========================>.....] - ETA: 0s - loss: 0.2042 56/56 [==============================] - 0s 1ms/step - loss: 0.2083 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1764 49/56 [=========================>....] - ETA: 0s - loss: 0.2049 56/56 [==============================] - 0s 1ms/step - loss: 0.2048 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1902 49/56 [=========================>....] - ETA: 0s - loss: 0.2009 56/56 [==============================] - 0s 1ms/step - loss: 0.2031 -> test with GAN.predict GAN tn, fp: 127, 11 GAN fn, tp: 4, 5 GAN f1 score: 0.400 GAN cohens kappa score: 0.349 -> test with 'LR' LR tn, fp: 126, 12 LR fn, tp: 3, 6 LR f1 score: 0.444 LR cohens kappa score: 0.395 LR average precision score: 0.526 -> test with 'RF' RF tn, fp: 136, 2 RF fn, tp: 7, 2 RF f1 score: 0.308 RF cohens kappa score: 0.281 -> test with 'GB' GB tn, fp: 134, 4 GB fn, tp: 6, 3 GB f1 score: 0.375 GB cohens kappa score: 0.340 -> test with 'KNN' KNN tn, fp: 122, 16 KNN fn, tp: 5, 4 KNN f1 score: 0.276 KNN cohens kappa score: 0.209 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.2216 44/56 [======================>.......] - ETA: 0s - loss: 0.2332 56/56 [==============================] - 0s 1ms/step - loss: 0.2332 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.1283 48/56 [========================>.....] - ETA: 0s - loss: 0.2212 56/56 [==============================] - 0s 1ms/step - loss: 0.2267 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2455 47/56 [========================>.....] - ETA: 0s - loss: 0.2315 56/56 [==============================] - 0s 1ms/step - loss: 0.2219 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0764 49/56 [=========================>....] - ETA: 0s - loss: 0.2184 56/56 [==============================] - 0s 1ms/step - loss: 0.2197 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2308 43/56 [======================>.......] - ETA: 0s - loss: 0.2067 56/56 [==============================] - 0s 1ms/step - loss: 0.2137 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.2273 49/56 [=========================>....] - ETA: 0s - loss: 0.2126 56/56 [==============================] - 0s 1ms/step - loss: 0.2129 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1713 49/56 [=========================>....] - ETA: 0s - loss: 0.2138 56/56 [==============================] - 0s 1ms/step - loss: 0.2110 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.3789 48/56 [========================>.....] - ETA: 0s - loss: 0.2057 56/56 [==============================] - 0s 1ms/step - loss: 0.2055 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0935 48/56 [========================>.....] - ETA: 0s - loss: 0.2042 56/56 [==============================] - 0s 1ms/step - loss: 0.2066 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2695 44/56 [======================>.......] - ETA: 0s - loss: 0.2149 56/56 [==============================] - 0s 1ms/step - loss: 0.2061 -> test with GAN.predict GAN tn, fp: 121, 17 GAN fn, tp: 1, 8 GAN f1 score: 0.471 GAN cohens kappa score: 0.418 -> test with 'LR' LR tn, fp: 130, 8 LR fn, tp: 1, 8 LR f1 score: 0.640 LR cohens kappa score: 0.609 LR average precision score: 0.931 -> test with 'RF' RF tn, fp: 133, 5 RF fn, tp: 5, 4 RF f1 score: 0.444 RF cohens kappa score: 0.408 -> test with 'GB' GB tn, fp: 129, 9 GB fn, tp: 4, 5 GB f1 score: 0.435 GB cohens kappa score: 0.389 -> test with 'KNN' KNN tn, fp: 125, 13 KNN fn, tp: 3, 6 KNN f1 score: 0.429 KNN cohens kappa score: 0.377 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 516 synthetic samples -> retrain GAN for predict Epoch 1/10 1/56 [..............................] - ETA: 8s - loss: 0.2401 49/56 [=========================>....] - ETA: 0s - loss: 0.2716 56/56 [==============================] - 0s 1ms/step - loss: 0.2773 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2224 49/56 [=========================>....] - ETA: 0s - loss: 0.2789 56/56 [==============================] - 0s 1ms/step - loss: 0.2764 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.3275 49/56 [=========================>....] - ETA: 0s - loss: 0.2797 56/56 [==============================] - 0s 1ms/step - loss: 0.2727 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3167 47/56 [========================>.....] - ETA: 0s - loss: 0.2650 56/56 [==============================] - 0s 1ms/step - loss: 0.2681 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.3730 50/56 [=========================>....] - ETA: 0s - loss: 0.2665 56/56 [==============================] - 0s 1ms/step - loss: 0.2639 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1524 49/56 [=========================>....] - ETA: 0s - loss: 0.2663 56/56 [==============================] - 0s 1ms/step - loss: 0.2637 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.2568 50/56 [=========================>....] - ETA: 0s - loss: 0.2610 56/56 [==============================] - 0s 1ms/step - loss: 0.2582 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1195 49/56 [=========================>....] - ETA: 0s - loss: 0.2568 56/56 [==============================] - 0s 1ms/step - loss: 0.2580 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.3048 49/56 [=========================>....] - ETA: 0s - loss: 0.2505 56/56 [==============================] - 0s 1ms/step - loss: 0.2589 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2546 49/56 [=========================>....] - ETA: 0s - loss: 0.2617 56/56 [==============================] - 0s 1ms/step - loss: 0.2569 -> test with GAN.predict GAN tn, fp: 126, 11 GAN fn, tp: 0, 6 GAN f1 score: 0.522 GAN cohens kappa score: 0.490 -> test with 'LR' LR tn, fp: 127, 10 LR fn, tp: 0, 6 LR f1 score: 0.545 LR cohens kappa score: 0.516 LR average precision score: 0.797 -> test with 'RF' RF tn, fp: 134, 3 RF fn, tp: 3, 3 RF f1 score: 0.500 RF cohens kappa score: 0.478 -> test with 'GB' GB tn, fp: 133, 4 GB fn, tp: 3, 3 GB f1 score: 0.462 GB cohens kappa score: 0.436 -> test with 'KNN' KNN tn, fp: 125, 12 KNN fn, tp: 2, 4 KNN f1 score: 0.364 KNN cohens kappa score: 0.322 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 132, 21 LR fn, tp: 4, 9 LR f1 score: 0.720 LR cohens kappa score: 0.696 LR average precision score: 0.931 average: LR tn, fp: 126.84, 10.96 LR fn, tp: 1.32, 7.08 LR f1 score: 0.538 LR cohens kappa score: 0.500 LR average precision score: 0.691 minimum: LR tn, fp: 117, 6 LR fn, tp: 0, 5 LR f1 score: 0.417 LR cohens kappa score: 0.361 LR average precision score: 0.487 -----[ RF ]----- maximum: RF tn, fp: 137, 7 RF fn, tp: 8, 5 RF f1 score: 0.625 RF cohens kappa score: 0.604 average: RF tn, fp: 134.24, 3.56 RF fn, tp: 6.08, 2.32 RF f1 score: 0.324 RF cohens kappa score: 0.291 minimum: RF tn, fp: 131, 1 RF fn, tp: 3, 1 RF f1 score: 0.118 RF cohens kappa score: 0.064 -----[ GB ]----- maximum: GB tn, fp: 136, 10 GB fn, tp: 8, 5 GB f1 score: 0.533 GB cohens kappa score: 0.509 average: GB tn, fp: 132.32, 5.48 GB fn, tp: 5.28, 3.12 GB f1 score: 0.367 GB cohens kappa score: 0.329 minimum: GB tn, fp: 128, 2 GB fn, tp: 3, 1 GB f1 score: 0.111 GB cohens kappa score: 0.053 -----[ KNN ]----- maximum: KNN tn, fp: 132, 25 KNN fn, tp: 5, 8 KNN f1 score: 0.500 KNN cohens kappa score: 0.464 average: KNN tn, fp: 122.28, 15.52 KNN fn, tp: 3.16, 5.24 KNN f1 score: 0.361 KNN cohens kappa score: 0.305 minimum: KNN tn, fp: 113, 6 KNN fn, tp: 1, 3 KNN f1 score: 0.240 KNN cohens kappa score: 0.188 -----[ GAN ]----- maximum: GAN tn, fp: 133, 17 GAN fn, tp: 4, 9 GAN f1 score: 0.692 GAN cohens kappa score: 0.666 average: GAN tn, fp: 126.08, 11.72 GAN fn, tp: 2.08, 6.32 GAN f1 score: 0.477 GAN cohens kappa score: 0.433 minimum: GAN tn, fp: 121, 5 GAN fn, tp: 0, 4 GAN f1 score: 0.333 GAN cohens kappa score: 0.289