/////////////////////////////////////////// // Running convGAN-proximary-full 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: 0.1357 50/56 [=========================>....] - ETA: 0s - loss: 0.1623 56/56 [==============================] - 0s 1ms/step - loss: 0.1670 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.3035 51/56 [==========================>...] - ETA: 0s - loss: 0.1524 56/56 [==============================] - 0s 1ms/step - loss: 0.1527 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.3603 51/56 [==========================>...] - ETA: 0s - loss: 0.1455 56/56 [==============================] - 0s 1ms/step - loss: 0.1501 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0259 43/56 [======================>.......] - ETA: 0s - loss: 0.1546 56/56 [==============================] - 0s 1ms/step - loss: 0.1493 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1956 44/56 [======================>.......] - ETA: 0s - loss: 0.1412 56/56 [==============================] - 0s 1ms/step - loss: 0.1443 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0925 49/56 [=========================>....] - ETA: 0s - loss: 0.1529 56/56 [==============================] - 0s 1ms/step - loss: 0.1437 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.3724 49/56 [=========================>....] - ETA: 0s - loss: 0.1454 56/56 [==============================] - 0s 1ms/step - loss: 0.1451 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0483 51/56 [==========================>...] - ETA: 0s - loss: 0.1408 56/56 [==============================] - 0s 1ms/step - loss: 0.1388 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0474 48/56 [========================>.....] - ETA: 0s - loss: 0.1431 56/56 [==============================] - 0s 1ms/step - loss: 0.1436 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0903 50/56 [=========================>....] - ETA: 0s - loss: 0.1395 56/56 [==============================] - 0s 1ms/step - loss: 0.1398 -> test with GAN.predict GAN tn, fp: 133, 5 GAN fn, tp: 1, 8 GAN f1 score: 0.727 GAN cohens kappa score: 0.706 -> 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: 0.918 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 8, 1 RF f1 score: 0.182 RF cohens kappa score: 0.163 -> 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: 136, 2 KNN fn, tp: 6, 3 KNN f1 score: 0.429 KNN cohens kappa score: 0.402 ------ 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: 0.2272 48/56 [========================>.....] - ETA: 0s - loss: 0.1426 56/56 [==============================] - 0s 1ms/step - loss: 0.1330 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0479 50/56 [=========================>....] - ETA: 0s - loss: 0.0872 56/56 [==============================] - 0s 1ms/step - loss: 0.0950 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0029 50/56 [=========================>....] - ETA: 0s - loss: 0.0920 56/56 [==============================] - 0s 1ms/step - loss: 0.0926 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 6.8266e-04 50/56 [=========================>....] - ETA: 0s - loss: 0.0846  56/56 [==============================] - 0s 1ms/step - loss: 0.0862 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1586 50/56 [=========================>....] - ETA: 0s - loss: 0.0930 56/56 [==============================] - 0s 1ms/step - loss: 0.0909 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0350 50/56 [=========================>....] - ETA: 0s - loss: 0.0844 56/56 [==============================] - 0s 1ms/step - loss: 0.0790 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0136 50/56 [=========================>....] - ETA: 0s - loss: 0.0792 56/56 [==============================] - 0s 1ms/step - loss: 0.0762 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0387 50/56 [=========================>....] - ETA: 0s - loss: 0.0725 56/56 [==============================] - 0s 1ms/step - loss: 0.0739 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0482 50/56 [=========================>....] - ETA: 0s - loss: 0.0678 56/56 [==============================] - 0s 1ms/step - loss: 0.0756 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0550 50/56 [=========================>....] - ETA: 0s - loss: 0.0610 56/56 [==============================] - 0s 1ms/step - loss: 0.0716 -> test with GAN.predict GAN tn, fp: 134, 4 GAN fn, tp: 6, 3 GAN f1 score: 0.375 GAN cohens kappa score: 0.340 -> test with 'LR' LR tn, fp: 133, 5 LR fn, tp: 4, 5 LR f1 score: 0.526 LR cohens kappa score: 0.494 LR average precision score: 0.551 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 8, 1 RF f1 score: 0.182 RF cohens kappa score: 0.163 -> test with 'GB' GB tn, fp: 133, 5 GB fn, tp: 8, 1 GB f1 score: 0.133 GB cohens kappa score: 0.089 -> test with 'KNN' KNN tn, fp: 135, 3 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.032 ------ 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: 7s - loss: 8.9830e-04 44/56 [======================>.......] - ETA: 0s - loss: 0.1184  56/56 [==============================] - 0s 1ms/step - loss: 0.1184 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0150 46/56 [=======================>......] - ETA: 0s - loss: 0.1023 56/56 [==============================] - 0s 1ms/step - loss: 0.1004 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0478 50/56 [=========================>....] - ETA: 0s - loss: 0.0993 56/56 [==============================] - 0s 1ms/step - loss: 0.1054 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0735 50/56 [=========================>....] - ETA: 0s - loss: 0.0847 56/56 [==============================] - 0s 1ms/step - loss: 0.0969 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2879 50/56 [=========================>....] - ETA: 0s - loss: 0.0871 56/56 [==============================] - 0s 1ms/step - loss: 0.0897 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0549 50/56 [=========================>....] - ETA: 0s - loss: 0.0890 56/56 [==============================] - 0s 1ms/step - loss: 0.0879 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0465 50/56 [=========================>....] - ETA: 0s - loss: 0.0894 56/56 [==============================] - 0s 1ms/step - loss: 0.0874 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1090 50/56 [=========================>....] - ETA: 0s - loss: 0.0944 56/56 [==============================] - 0s 1ms/step - loss: 0.0882 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0159 49/56 [=========================>....] - ETA: 0s - loss: 0.0884 56/56 [==============================] - 0s 1ms/step - loss: 0.0895 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0175 49/56 [=========================>....] - ETA: 0s - loss: 0.0883 56/56 [==============================] - 0s 1ms/step - loss: 0.0858 -> test with GAN.predict GAN tn, fp: 136, 2 GAN fn, tp: 2, 7 GAN f1 score: 0.778 GAN cohens kappa score: 0.763 -> 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: 0.797 -> test with 'RF' RF tn, fp: 136, 2 RF fn, tp: 6, 3 RF f1 score: 0.429 RF cohens kappa score: 0.402 -> test with 'GB' GB tn, fp: 137, 1 GB fn, tp: 8, 1 GB f1 score: 0.182 GB cohens kappa score: 0.163 -> test with 'KNN' KNN tn, fp: 138, 0 KNN fn, tp: 8, 1 KNN f1 score: 0.200 KNN cohens kappa score: 0.190 ------ 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: 0.0529 45/56 [=======================>......] - ETA: 0s - loss: 0.1188 56/56 [==============================] - 0s 1ms/step - loss: 0.1220 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0490 44/56 [======================>.......] - ETA: 0s - loss: 0.1029 56/56 [==============================] - 0s 1ms/step - loss: 0.1087 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0697 45/56 [=======================>......] - ETA: 0s - loss: 0.1175 56/56 [==============================] - 0s 1ms/step - loss: 0.1169 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0102 45/56 [=======================>......] - ETA: 0s - loss: 0.1018 56/56 [==============================] - 0s 1ms/step - loss: 0.1023 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1969 45/56 [=======================>......] - ETA: 0s - loss: 0.0852 56/56 [==============================] - 0s 1ms/step - loss: 0.1058 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0093 43/56 [======================>.......] - ETA: 0s - loss: 0.1114 56/56 [==============================] - 0s 1ms/step - loss: 0.0996 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1215 45/56 [=======================>......] - ETA: 0s - loss: 0.0900 56/56 [==============================] - 0s 1ms/step - loss: 0.0923 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1337 45/56 [=======================>......] - ETA: 0s - loss: 0.0991 56/56 [==============================] - 0s 1ms/step - loss: 0.0927 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0169 43/56 [======================>.......] - ETA: 0s - loss: 0.0969 56/56 [==============================] - 0s 1ms/step - loss: 0.0933 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0014 44/56 [======================>.......] - ETA: 0s - loss: 0.0916 56/56 [==============================] - 0s 1ms/step - loss: 0.0931 -> test with GAN.predict GAN tn, fp: 134, 4 GAN fn, tp: 6, 3 GAN f1 score: 0.375 GAN cohens kappa score: 0.340 -> test with 'LR' LR tn, fp: 133, 5 LR fn, tp: 4, 5 LR f1 score: 0.526 LR cohens kappa score: 0.494 LR average precision score: 0.631 -> test with 'RF' RF tn, fp: 138, 0 RF fn, tp: 6, 3 RF f1 score: 0.500 RF cohens kappa score: 0.484 -> test with 'GB' GB tn, fp: 137, 1 GB fn, tp: 7, 2 GB f1 score: 0.333 GB cohens kappa score: 0.312 -> test with 'KNN' KNN tn, fp: 138, 0 KNN fn, tp: 8, 1 KNN f1 score: 0.200 KNN cohens kappa score: 0.190 ------ 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: 0.7218 42/56 [=====================>........] - ETA: 0s - loss: 0.1689 56/56 [==============================] - 0s 1ms/step - loss: 0.1843 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0034 43/56 [======================>.......] - ETA: 0s - loss: 0.1682 56/56 [==============================] - 0s 1ms/step - loss: 0.1560 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.3309 42/56 [=====================>........] - ETA: 0s - loss: 0.1601 56/56 [==============================] - 0s 1ms/step - loss: 0.1355 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.3636 42/56 [=====================>........] - ETA: 0s - loss: 0.1124 56/56 [==============================] - 0s 1ms/step - loss: 0.1096 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2224 43/56 [======================>.......] - ETA: 0s - loss: 0.0894 56/56 [==============================] - 0s 1ms/step - loss: 0.1044 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0064 42/56 [=====================>........] - ETA: 0s - loss: 0.0907 56/56 [==============================] - 0s 1ms/step - loss: 0.0992 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0107 42/56 [=====================>........] - ETA: 0s - loss: 0.1091 56/56 [==============================] - 0s 1ms/step - loss: 0.1021 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0049 43/56 [======================>.......] - ETA: 0s - loss: 0.0955 56/56 [==============================] - 0s 1ms/step - loss: 0.0923 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0726 41/56 [====================>.........] - ETA: 0s - loss: 0.0752 56/56 [==============================] - 0s 1ms/step - loss: 0.0904 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0051 42/56 [=====================>........] - ETA: 0s - loss: 0.0702 56/56 [==============================] - 0s 1ms/step - loss: 0.0875 -> test with GAN.predict GAN tn, fp: 136, 1 GAN fn, tp: 4, 2 GAN f1 score: 0.444 GAN cohens kappa score: 0.428 -> test with 'LR' LR tn, fp: 134, 3 LR fn, tp: 2, 4 LR f1 score: 0.615 LR cohens kappa score: 0.597 LR average precision score: 0.447 -> test with 'RF' RF tn, fp: 137, 0 RF fn, tp: 4, 2 RF f1 score: 0.500 RF cohens kappa score: 0.489 -> test with 'GB' GB tn, fp: 137, 0 GB fn, tp: 4, 2 GB f1 score: 0.500 GB cohens kappa score: 0.489 -> test with 'KNN' KNN tn, fp: 137, 0 KNN fn, tp: 5, 1 KNN f1 score: 0.286 KNN cohens kappa score: 0.277 ====== 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: 0.0047 37/56 [==================>...........] - ETA: 0s - loss: 0.1173 56/56 [==============================] - 0s 1ms/step - loss: 0.1089 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0146 40/56 [====================>.........] - ETA: 0s - loss: 0.1052 56/56 [==============================] - 0s 1ms/step - loss: 0.0916 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0040 39/56 [===================>..........] - ETA: 0s - loss: 0.0878 56/56 [==============================] - 0s 1ms/step - loss: 0.0885 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.6756 40/56 [====================>.........] - ETA: 0s - loss: 0.0883 56/56 [==============================] - 0s 1ms/step - loss: 0.0796 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0185 37/56 [==================>...........] - ETA: 0s - loss: 0.0620 56/56 [==============================] - 0s 1ms/step - loss: 0.0799 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0035 38/56 [===================>..........] - ETA: 0s - loss: 0.0786 56/56 [==============================] - 0s 2ms/step - loss: 0.0730 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0044 36/56 [==================>...........] - ETA: 0s - loss: 0.0559 56/56 [==============================] - 0s 1ms/step - loss: 0.0696 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0408 34/56 [=================>............] - ETA: 0s - loss: 0.0935 56/56 [==============================] - 0s 2ms/step - loss: 0.0716 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0777 33/56 [================>.............] - ETA: 0s - loss: 0.0665 56/56 [==============================] - 0s 2ms/step - loss: 0.0708 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0992 38/56 [===================>..........] - ETA: 0s - loss: 0.1122 56/56 [==============================] - 0s 1ms/step - loss: 0.0967 -> test with GAN.predict GAN tn, fp: 136, 2 GAN fn, tp: 6, 3 GAN f1 score: 0.429 GAN cohens kappa score: 0.402 -> test with 'LR' LR tn, fp: 131, 7 LR fn, tp: 2, 7 LR f1 score: 0.609 LR cohens kappa score: 0.577 LR average precision score: 0.626 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 7, 2 RF f1 score: 0.333 RF cohens kappa score: 0.312 -> 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: 136, 2 KNN fn, tp: 8, 1 KNN f1 score: 0.167 KNN cohens kappa score: 0.140 ------ 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: 8s - loss: 0.0089 34/56 [=================>............] - ETA: 0s - loss: 0.1064 56/56 [==============================] - 0s 1ms/step - loss: 0.1267 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0246 41/56 [====================>.........] - ETA: 0s - loss: 0.1282 56/56 [==============================] - 0s 1ms/step - loss: 0.1353 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0305 42/56 [=====================>........] - ETA: 0s - loss: 0.1166 56/56 [==============================] - 0s 1ms/step - loss: 0.1064 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0970 41/56 [====================>.........] - ETA: 0s - loss: 0.1002 56/56 [==============================] - 0s 1ms/step - loss: 0.1011 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2697 40/56 [====================>.........] - ETA: 0s - loss: 0.1071 56/56 [==============================] - 0s 1ms/step - loss: 0.0971 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0362 43/56 [======================>.......] - ETA: 0s - loss: 0.1029 56/56 [==============================] - 0s 1ms/step - loss: 0.0910 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1631 37/56 [==================>...........] - ETA: 0s - loss: 0.0763 56/56 [==============================] - 0s 1ms/step - loss: 0.0877 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0329 40/56 [====================>.........] - ETA: 0s - loss: 0.0836 56/56 [==============================] - 0s 1ms/step - loss: 0.0843 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0154 42/56 [=====================>........] - ETA: 0s - loss: 0.0934 56/56 [==============================] - 0s 1ms/step - loss: 0.0829 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0310 45/56 [=======================>......] - ETA: 0s - loss: 0.0774 56/56 [==============================] - 0s 1ms/step - loss: 0.0813 -> test with GAN.predict GAN tn, fp: 136, 2 GAN fn, tp: 3, 6 GAN f1 score: 0.706 GAN cohens kappa score: 0.688 -> 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: 0.751 -> 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: 136, 2 GB fn, tp: 6, 3 GB f1 score: 0.429 GB cohens kappa score: 0.402 -> test with 'KNN' KNN tn, fp: 137, 1 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.012 ------ 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: 10s - loss: 5.0524e-04 41/56 [====================>.........] - ETA: 0s - loss: 0.1657  56/56 [==============================] - 0s 1ms/step - loss: 0.1588 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2426 42/56 [=====================>........] - ETA: 0s - loss: 0.1364 56/56 [==============================] - 0s 1ms/step - loss: 0.1355 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.7550 43/56 [======================>.......] - ETA: 0s - loss: 0.1029 56/56 [==============================] - 0s 1ms/step - loss: 0.1058 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0024 43/56 [======================>.......] - ETA: 0s - loss: 0.1124 56/56 [==============================] - 0s 1ms/step - loss: 0.1005 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0350 42/56 [=====================>........] - ETA: 0s - loss: 0.1121 56/56 [==============================] - 0s 1ms/step - loss: 0.0969 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0303 41/56 [====================>.........] - ETA: 0s - loss: 0.1006 56/56 [==============================] - 0s 1ms/step - loss: 0.0967 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0424 42/56 [=====================>........] - ETA: 0s - loss: 0.0994 56/56 [==============================] - 0s 1ms/step - loss: 0.0934 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0348 42/56 [=====================>........] - ETA: 0s - loss: 0.0939 56/56 [==============================] - 0s 1ms/step - loss: 0.0906 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0272 43/56 [======================>.......] - ETA: 0s - loss: 0.0968 56/56 [==============================] - 0s 1ms/step - loss: 0.0862 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0159 40/56 [====================>.........] - ETA: 0s - loss: 0.0922 56/56 [==============================] - 0s 1ms/step - loss: 0.0875 -> test with GAN.predict GAN tn, fp: 136, 2 GAN fn, tp: 4, 5 GAN f1 score: 0.625 GAN cohens kappa score: 0.604 -> test with 'LR' LR tn, fp: 134, 4 LR fn, tp: 2, 7 LR f1 score: 0.700 LR cohens kappa score: 0.678 LR average precision score: 0.729 -> 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: 134, 4 GB fn, tp: 8, 1 GB f1 score: 0.143 GB cohens kappa score: 0.104 -> test with 'KNN' KNN tn, fp: 138, 0 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: 0.000 ------ 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: 0.0014 49/56 [=========================>....] - ETA: 0s - loss: 0.1190 56/56 [==============================] - 0s 1ms/step - loss: 0.1186 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2265 50/56 [=========================>....] - ETA: 0s - loss: 0.1193 56/56 [==============================] - 0s 1ms/step - loss: 0.1125 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1140 46/56 [=======================>......] - ETA: 0s - loss: 0.1171 56/56 [==============================] - 0s 1ms/step - loss: 0.1077 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0555 46/56 [=======================>......] - ETA: 0s - loss: 0.0806 56/56 [==============================] - 0s 1ms/step - loss: 0.0976 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0506 48/56 [========================>.....] - ETA: 0s - loss: 0.0915 56/56 [==============================] - 0s 1ms/step - loss: 0.0936 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.3806 49/56 [=========================>....] - ETA: 0s - loss: 0.0897 56/56 [==============================] - 0s 1ms/step - loss: 0.0954 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0241 48/56 [========================>.....] - ETA: 0s - loss: 0.0877 56/56 [==============================] - 0s 1ms/step - loss: 0.0890 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.5460 49/56 [=========================>....] - ETA: 0s - loss: 0.1312 56/56 [==============================] - 0s 1ms/step - loss: 0.1233 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2517 48/56 [========================>.....] - ETA: 0s - loss: 0.0928 56/56 [==============================] - 0s 1ms/step - loss: 0.0886 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0515 47/56 [========================>.....] - ETA: 0s - loss: 0.0767 56/56 [==============================] - 0s 1ms/step - loss: 0.0882 -> test with GAN.predict GAN tn, fp: 134, 4 GAN fn, tp: 4, 5 GAN f1 score: 0.556 GAN cohens kappa score: 0.527 -> test with 'LR' LR tn, fp: 130, 8 LR fn, tp: 2, 7 LR f1 score: 0.583 LR cohens kappa score: 0.549 LR average precision score: 0.750 -> test with 'RF' RF tn, fp: 136, 2 RF fn, tp: 6, 3 RF f1 score: 0.429 RF cohens kappa score: 0.402 -> test with 'GB' GB tn, fp: 136, 2 GB fn, tp: 6, 3 GB f1 score: 0.429 GB cohens kappa score: 0.402 -> test with 'KNN' KNN tn, fp: 137, 1 KNN fn, tp: 8, 1 KNN f1 score: 0.182 KNN cohens kappa score: 0.163 ------ 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: 8s - loss: 0.1129 49/56 [=========================>....] - ETA: 0s - loss: 0.1050 56/56 [==============================] - 0s 1ms/step - loss: 0.0998 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0088 48/56 [========================>.....] - ETA: 0s - loss: 0.0892 56/56 [==============================] - 0s 1ms/step - loss: 0.0840 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1895 47/56 [========================>.....] - ETA: 0s - loss: 0.0924 56/56 [==============================] - 0s 1ms/step - loss: 0.0825 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0346 36/56 [==================>...........] - ETA: 0s - loss: 0.0824 56/56 [==============================] - 0s 1ms/step - loss: 0.0803 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0221 42/56 [=====================>........] - ETA: 0s - loss: 0.0867 56/56 [==============================] - 0s 1ms/step - loss: 0.0827 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0417 48/56 [========================>.....] - ETA: 0s - loss: 0.0845 56/56 [==============================] - 0s 1ms/step - loss: 0.0769 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1511 43/56 [======================>.......] - ETA: 0s - loss: 0.0729 56/56 [==============================] - 0s 1ms/step - loss: 0.0744 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1631 38/56 [===================>..........] - ETA: 0s - loss: 0.0789 56/56 [==============================] - 0s 1ms/step - loss: 0.0751 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0413 38/56 [===================>..........] - ETA: 0s - loss: 0.0683 56/56 [==============================] - 0s 1ms/step - loss: 0.0780 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0380 42/56 [=====================>........] - ETA: 0s - loss: 0.0837 56/56 [==============================] - 0s 1ms/step - loss: 0.0840 -> test with GAN.predict GAN tn, fp: 134, 3 GAN fn, tp: 3, 3 GAN f1 score: 0.500 GAN cohens kappa score: 0.478 -> 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: 0.562 -> test with 'RF' RF tn, fp: 137, 0 RF fn, tp: 3, 3 RF f1 score: 0.667 RF cohens kappa score: 0.657 -> test with 'GB' GB tn, fp: 137, 0 GB fn, tp: 4, 2 GB f1 score: 0.500 GB cohens kappa score: 0.489 -> test with 'KNN' KNN tn, fp: 137, 0 KNN fn, tp: 5, 1 KNN f1 score: 0.286 KNN cohens kappa score: 0.277 ====== 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: 9s - loss: 0.1923 45/56 [=======================>......] - ETA: 0s - loss: 0.0920 56/56 [==============================] - 0s 1ms/step - loss: 0.0973 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0200 48/56 [========================>.....] - ETA: 0s - loss: 0.0913 56/56 [==============================] - 0s 1ms/step - loss: 0.0989 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0100 47/56 [========================>.....] - ETA: 0s - loss: 0.0869 56/56 [==============================] - 0s 1ms/step - loss: 0.0909 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1113 42/56 [=====================>........] - ETA: 0s - loss: 0.0721 56/56 [==============================] - 0s 1ms/step - loss: 0.0839 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0426 42/56 [=====================>........] - ETA: 0s - loss: 0.0854 56/56 [==============================] - 0s 1ms/step - loss: 0.0825 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.5961 48/56 [========================>.....] - ETA: 0s - loss: 0.0869 56/56 [==============================] - 0s 1ms/step - loss: 0.0902 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0257 49/56 [=========================>....] - ETA: 0s - loss: 0.0886 56/56 [==============================] - 0s 1ms/step - loss: 0.0839 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0456 49/56 [=========================>....] - ETA: 0s - loss: 0.0822 56/56 [==============================] - 0s 1ms/step - loss: 0.0784 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0070 49/56 [=========================>....] - ETA: 0s - loss: 0.0773 56/56 [==============================] - 0s 1ms/step - loss: 0.0767 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0067 49/56 [=========================>....] - ETA: 0s - loss: 0.0824 56/56 [==============================] - 0s 1ms/step - loss: 0.0775 -> test with GAN.predict GAN tn, fp: 134, 4 GAN fn, tp: 5, 4 GAN f1 score: 0.471 GAN cohens kappa score: 0.438 -> test with 'LR' LR tn, fp: 131, 7 LR fn, tp: 5, 4 LR f1 score: 0.400 LR cohens kappa score: 0.357 LR average precision score: 0.518 -> 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: 135, 3 GB fn, tp: 7, 2 GB f1 score: 0.286 GB cohens kappa score: 0.253 -> test with 'KNN' KNN tn, fp: 136, 2 KNN fn, tp: 8, 1 KNN f1 score: 0.167 KNN cohens kappa score: 0.140 ------ 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: 0.2894 47/56 [========================>.....] - ETA: 0s - loss: 0.1709 56/56 [==============================] - 0s 1ms/step - loss: 0.1549 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.3875 49/56 [=========================>....] - ETA: 0s - loss: 0.0979 56/56 [==============================] - 0s 1ms/step - loss: 0.1215 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0590 49/56 [=========================>....] - ETA: 0s - loss: 0.1075 56/56 [==============================] - 0s 1ms/step - loss: 0.1247 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0058 41/56 [====================>.........] - ETA: 0s - loss: 0.1290 56/56 [==============================] - 0s 1ms/step - loss: 0.1141 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0147 48/56 [========================>.....] - ETA: 0s - loss: 0.1075 56/56 [==============================] - 0s 1ms/step - loss: 0.1107 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0956 44/56 [======================>.......] - ETA: 0s - loss: 0.1038 56/56 [==============================] - 0s 1ms/step - loss: 0.1044 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.1781 41/56 [====================>.........] - ETA: 0s - loss: 0.1177 56/56 [==============================] - 0s 1ms/step - loss: 0.1039 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1046 48/56 [========================>.....] - ETA: 0s - loss: 0.1060 56/56 [==============================] - 0s 1ms/step - loss: 0.1019 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0267 50/56 [=========================>....] - ETA: 0s - loss: 0.1007 56/56 [==============================] - 0s 1ms/step - loss: 0.0969 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0409 49/56 [=========================>....] - ETA: 0s - loss: 0.1025 56/56 [==============================] - 0s 1ms/step - loss: 0.0985 -> test with GAN.predict GAN tn, fp: 136, 2 GAN fn, tp: 5, 4 GAN f1 score: 0.533 GAN cohens kappa score: 0.509 -> test with 'LR' LR tn, fp: 134, 4 LR fn, tp: 0, 9 LR f1 score: 0.818 LR cohens kappa score: 0.804 LR average precision score: 0.822 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 8, 1 RF f1 score: 0.182 RF cohens kappa score: 0.163 -> test with 'GB' GB tn, fp: 135, 3 GB fn, tp: 8, 1 GB f1 score: 0.154 GB cohens kappa score: 0.121 -> test with 'KNN' KNN tn, fp: 137, 1 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.012 ------ 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: 8s - loss: 0.1183 48/56 [========================>.....] - ETA: 0s - loss: 0.1010 56/56 [==============================] - 0s 1ms/step - loss: 0.1070 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0080 47/56 [========================>.....] - ETA: 0s - loss: 0.1070 56/56 [==============================] - 0s 1ms/step - loss: 0.0970 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.3042 48/56 [========================>.....] - ETA: 0s - loss: 0.0920 56/56 [==============================] - 0s 1ms/step - loss: 0.0877 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0893 48/56 [========================>.....] - ETA: 0s - loss: 0.0973 56/56 [==============================] - 0s 1ms/step - loss: 0.0911 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0152 50/56 [=========================>....] - ETA: 0s - loss: 0.0751 56/56 [==============================] - 0s 1ms/step - loss: 0.0892 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0806 49/56 [=========================>....] - ETA: 0s - loss: 0.1044 56/56 [==============================] - 0s 1ms/step - loss: 0.0982 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0066 49/56 [=========================>....] - ETA: 0s - loss: 0.0901 56/56 [==============================] - 0s 1ms/step - loss: 0.0925 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2340 49/56 [=========================>....] - ETA: 0s - loss: 0.0883 56/56 [==============================] - 0s 1ms/step - loss: 0.0901 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0157 49/56 [=========================>....] - ETA: 0s - loss: 0.0862 56/56 [==============================] - 0s 1ms/step - loss: 0.0871 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0439 47/56 [========================>.....] - ETA: 0s - loss: 0.0844 56/56 [==============================] - 0s 1ms/step - loss: 0.0845 -> test with GAN.predict GAN tn, fp: 137, 1 GAN fn, tp: 6, 3 GAN f1 score: 0.462 GAN cohens kappa score: 0.440 -> test with 'LR' LR tn, fp: 134, 4 LR fn, tp: 4, 5 LR f1 score: 0.556 LR cohens kappa score: 0.527 LR average precision score: 0.671 -> 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: 137, 1 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.012 ------ 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: 7s - loss: 0.2951 48/56 [========================>.....] - ETA: 0s - loss: 0.1680 56/56 [==============================] - 0s 1ms/step - loss: 0.1727 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0977 47/56 [========================>.....] - ETA: 0s - loss: 0.1860 56/56 [==============================] - 0s 1ms/step - loss: 0.1782 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0263 45/56 [=======================>......] - ETA: 0s - loss: 0.1360 56/56 [==============================] - 0s 1ms/step - loss: 0.1518 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.2003 43/56 [======================>.......] - ETA: 0s - loss: 0.1731 56/56 [==============================] - 0s 1ms/step - loss: 0.1523 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.2615 49/56 [=========================>....] - ETA: 0s - loss: 0.1519 56/56 [==============================] - 0s 1ms/step - loss: 0.1456 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0732 44/56 [======================>.......] - ETA: 0s - loss: 0.1310 56/56 [==============================] - 0s 1ms/step - loss: 0.1449 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.2108 40/56 [====================>.........] - ETA: 0s - loss: 0.1386 56/56 [==============================] - 0s 1ms/step - loss: 0.1393 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.2213 49/56 [=========================>....] - ETA: 0s - loss: 0.1402 56/56 [==============================] - 0s 1ms/step - loss: 0.1398 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0459 49/56 [=========================>....] - ETA: 0s - loss: 0.1296 56/56 [==============================] - 0s 1ms/step - loss: 0.1386 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1004 49/56 [=========================>....] - ETA: 0s - loss: 0.1407 56/56 [==============================] - 0s 1ms/step - loss: 0.1358 -> test with GAN.predict GAN tn, fp: 136, 2 GAN fn, tp: 5, 4 GAN f1 score: 0.533 GAN cohens kappa score: 0.509 -> test with 'LR' LR tn, fp: 122, 16 LR fn, tp: 2, 7 LR f1 score: 0.438 LR cohens kappa score: 0.383 LR average precision score: 0.665 -> test with 'RF' RF tn, fp: 136, 2 RF fn, tp: 6, 3 RF f1 score: 0.429 RF cohens kappa score: 0.402 -> test with 'GB' GB tn, fp: 137, 1 GB fn, tp: 6, 3 GB f1 score: 0.462 GB cohens kappa score: 0.440 -> test with 'KNN' KNN tn, fp: 138, 0 KNN fn, tp: 5, 4 KNN f1 score: 0.615 KNN cohens kappa score: 0.600 ------ 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: 8s - loss: 0.5741 47/56 [========================>.....] - ETA: 0s - loss: 0.1399 56/56 [==============================] - 0s 1ms/step - loss: 0.1324 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.1398 44/56 [======================>.......] - ETA: 0s - loss: 0.1319 56/56 [==============================] - 0s 1ms/step - loss: 0.1256 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0482 42/56 [=====================>........] - ETA: 0s - loss: 0.1076 56/56 [==============================] - 0s 1ms/step - loss: 0.1103 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0248 43/56 [======================>.......] - ETA: 0s - loss: 0.1043 56/56 [==============================] - 0s 1ms/step - loss: 0.1057 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1815 47/56 [========================>.....] - ETA: 0s - loss: 0.0988 56/56 [==============================] - 0s 1ms/step - loss: 0.1068 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0136 44/56 [======================>.......] - ETA: 0s - loss: 0.1117 56/56 [==============================] - 0s 1ms/step - loss: 0.1035 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0135 48/56 [========================>.....] - ETA: 0s - loss: 0.1144 56/56 [==============================] - 0s 1ms/step - loss: 0.1084 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0616 49/56 [=========================>....] - ETA: 0s - loss: 0.0985 56/56 [==============================] - 0s 1ms/step - loss: 0.1007 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0095 45/56 [=======================>......] - ETA: 0s - loss: 0.0919 56/56 [==============================] - 0s 1ms/step - loss: 0.0990 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0952 43/56 [======================>.......] - ETA: 0s - loss: 0.0975 56/56 [==============================] - 0s 1ms/step - loss: 0.0981 -> test with GAN.predict GAN tn, fp: 136, 1 GAN fn, tp: 4, 2 GAN f1 score: 0.444 GAN cohens kappa score: 0.428 -> test with 'LR' LR tn, fp: 131, 6 LR fn, tp: 2, 4 LR f1 score: 0.500 LR cohens kappa score: 0.472 LR average precision score: 0.533 -> test with 'RF' RF tn, fp: 136, 1 RF fn, tp: 4, 2 RF f1 score: 0.444 RF cohens kappa score: 0.428 -> 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: 136, 1 KNN fn, tp: 6, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.012 ====== 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: 8s - loss: 0.2522 48/56 [========================>.....] - ETA: 0s - loss: 0.1712 56/56 [==============================] - 0s 1ms/step - loss: 0.1557 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0027 49/56 [=========================>....] - ETA: 0s - loss: 0.1356 56/56 [==============================] - 0s 1ms/step - loss: 0.1396 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0048 49/56 [=========================>....] - ETA: 0s - loss: 0.1406 56/56 [==============================] - 0s 1ms/step - loss: 0.1307 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0112 47/56 [========================>.....] - ETA: 0s - loss: 0.1023 56/56 [==============================] - 0s 1ms/step - loss: 0.1058 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.6295 45/56 [=======================>......] - ETA: 0s - loss: 0.0991 56/56 [==============================] - 0s 1ms/step - loss: 0.1041 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0185 50/56 [=========================>....] - ETA: 0s - loss: 0.0996 56/56 [==============================] - 0s 1ms/step - loss: 0.0979 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0572 48/56 [========================>.....] - ETA: 0s - loss: 0.0930 56/56 [==============================] - 0s 1ms/step - loss: 0.0941 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0139 44/56 [======================>.......] - ETA: 0s - loss: 0.0859 56/56 [==============================] - 0s 1ms/step - loss: 0.0897 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0192 42/56 [=====================>........] - ETA: 0s - loss: 0.0973 56/56 [==============================] - 0s 1ms/step - loss: 0.0860 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0150 39/56 [===================>..........] - ETA: 0s - loss: 0.0850 56/56 [==============================] - 0s 1ms/step - loss: 0.0876 -> test with GAN.predict GAN tn, fp: 135, 3 GAN fn, tp: 4, 5 GAN f1 score: 0.588 GAN cohens kappa score: 0.563 -> test with 'LR' LR tn, fp: 130, 8 LR fn, tp: 5, 4 LR f1 score: 0.381 LR cohens kappa score: 0.334 LR average precision score: 0.530 -> test with 'RF' RF tn, fp: 136, 2 RF fn, tp: 6, 3 RF f1 score: 0.429 RF cohens kappa score: 0.402 -> 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: 137, 1 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.012 ------ 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: 9s - loss: 0.4145 44/56 [======================>.......] - ETA: 0s - loss: 0.1608 56/56 [==============================] - 0s 1ms/step - loss: 0.1470 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0501 39/56 [===================>..........] - ETA: 0s - loss: 0.1289 56/56 [==============================] - 0s 1ms/step - loss: 0.1268 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0170 42/56 [=====================>........] - ETA: 0s - loss: 0.1184 56/56 [==============================] - 0s 1ms/step - loss: 0.1203 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0676 42/56 [=====================>........] - ETA: 0s - loss: 0.1146 56/56 [==============================] - 0s 1ms/step - loss: 0.1206 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0242 40/56 [====================>.........] - ETA: 0s - loss: 0.0986 56/56 [==============================] - 0s 1ms/step - loss: 0.1024 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0031 27/56 [=============>................] - ETA: 0s - loss: 0.0787 56/56 [==============================] - 0s 2ms/step - loss: 0.1012 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0391 39/56 [===================>..........] - ETA: 0s - loss: 0.1139 56/56 [==============================] - 0s 1ms/step - loss: 0.0984 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0293 44/56 [======================>.......] - ETA: 0s - loss: 0.1003 56/56 [==============================] - 0s 1ms/step - loss: 0.0958 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0202 44/56 [======================>.......] - ETA: 0s - loss: 0.0887 56/56 [==============================] - 0s 1ms/step - loss: 0.0943 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0156 42/56 [=====================>........] - ETA: 0s - loss: 0.0918 56/56 [==============================] - 0s 1ms/step - loss: 0.0936 -> test with GAN.predict GAN tn, fp: 136, 2 GAN fn, tp: 5, 4 GAN f1 score: 0.533 GAN cohens kappa score: 0.509 -> 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: 0.712 -> 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: 130, 8 GB fn, tp: 5, 4 GB f1 score: 0.381 GB cohens kappa score: 0.334 -> test with 'KNN' KNN tn, fp: 138, 0 KNN fn, tp: 8, 1 KNN f1 score: 0.200 KNN cohens kappa score: 0.190 ------ 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: 0.0012 44/56 [======================>.......] - ETA: 0s - loss: 0.1475 56/56 [==============================] - 0s 1ms/step - loss: 0.1349 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.3369 47/56 [========================>.....] - ETA: 0s - loss: 0.1431 56/56 [==============================] - 0s 1ms/step - loss: 0.1327 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0018 46/56 [=======================>......] - ETA: 0s - loss: 0.1083 56/56 [==============================] - 0s 1ms/step - loss: 0.1091 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0029 41/56 [====================>.........] - ETA: 0s - loss: 0.0982 56/56 [==============================] - 0s 1ms/step - loss: 0.1108 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1907 40/56 [====================>.........] - ETA: 0s - loss: 0.0837 56/56 [==============================] - 0s 1ms/step - loss: 0.1035 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0211 45/56 [=======================>......] - ETA: 0s - loss: 0.0979 56/56 [==============================] - 0s 1ms/step - loss: 0.1054 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0082 47/56 [========================>.....] - ETA: 0s - loss: 0.0968 56/56 [==============================] - 0s 1ms/step - loss: 0.1011 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.1100 43/56 [======================>.......] - ETA: 0s - loss: 0.1057 56/56 [==============================] - 0s 1ms/step - loss: 0.1096 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1300 43/56 [======================>.......] - ETA: 0s - loss: 0.0876 56/56 [==============================] - 0s 1ms/step - loss: 0.0958 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.2583 44/56 [======================>.......] - ETA: 0s - loss: 0.0937 56/56 [==============================] - 0s 1ms/step - loss: 0.0952 -> test with GAN.predict GAN tn, fp: 137, 1 GAN fn, tp: 6, 3 GAN f1 score: 0.462 GAN cohens kappa score: 0.440 -> 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: 0.657 -> test with 'RF' RF tn, fp: 136, 2 RF fn, tp: 6, 3 RF f1 score: 0.429 RF cohens kappa score: 0.402 -> test with 'GB' GB tn, fp: 138, 0 GB fn, tp: 6, 3 GB f1 score: 0.500 GB cohens kappa score: 0.484 -> test with 'KNN' KNN tn, fp: 138, 0 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: 0.000 ------ 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: 9s - loss: 0.1910 46/56 [=======================>......] - ETA: 0s - loss: 0.1916 56/56 [==============================] - 0s 1ms/step - loss: 0.1728 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0783 43/56 [======================>.......] - ETA: 0s - loss: 0.1174 56/56 [==============================] - 0s 1ms/step - loss: 0.1322 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0049 42/56 [=====================>........] - ETA: 0s - loss: 0.1252 56/56 [==============================] - 0s 1ms/step - loss: 0.1164 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0069 42/56 [=====================>........] - ETA: 0s - loss: 0.1066 56/56 [==============================] - 0s 1ms/step - loss: 0.1118 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1813 41/56 [====================>.........] - ETA: 0s - loss: 0.1183 56/56 [==============================] - 0s 1ms/step - loss: 0.1067 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.1993 41/56 [====================>.........] - ETA: 0s - loss: 0.1005 56/56 [==============================] - 0s 1ms/step - loss: 0.1013 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.2239 42/56 [=====================>........] - ETA: 0s - loss: 0.0900 56/56 [==============================] - 0s 1ms/step - loss: 0.0998 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0055 41/56 [====================>.........] - ETA: 0s - loss: 0.1275 56/56 [==============================] - 0s 1ms/step - loss: 0.1149 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1471 42/56 [=====================>........] - ETA: 0s - loss: 0.0822 56/56 [==============================] - 0s 1ms/step - loss: 0.0922 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0222 40/56 [====================>.........] - ETA: 0s - loss: 0.1038 56/56 [==============================] - 0s 1ms/step - loss: 0.0967 -> test with GAN.predict GAN tn, fp: 133, 5 GAN fn, tp: 3, 6 GAN f1 score: 0.600 GAN cohens kappa score: 0.571 -> test with 'LR' LR tn, fp: 132, 6 LR fn, tp: 0, 9 LR f1 score: 0.750 LR cohens kappa score: 0.729 LR average precision score: 0.906 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 8, 1 RF f1 score: 0.182 RF cohens kappa score: 0.163 -> test with 'GB' GB tn, fp: 136, 2 GB fn, tp: 8, 1 GB f1 score: 0.167 GB cohens kappa score: 0.140 -> test with 'KNN' KNN tn, fp: 135, 3 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.032 ------ 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: 8s - loss: 0.0961 48/56 [========================>.....] - ETA: 0s - loss: 0.1677 56/56 [==============================] - 0s 1ms/step - loss: 0.1565 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.2979 48/56 [========================>.....] - ETA: 0s - loss: 0.1238 56/56 [==============================] - 0s 1ms/step - loss: 0.1422 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0236 48/56 [========================>.....] - ETA: 0s - loss: 0.1375 56/56 [==============================] - 0s 1ms/step - loss: 0.1308 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1299 45/56 [=======================>......] - ETA: 0s - loss: 0.1436 56/56 [==============================] - 0s 1ms/step - loss: 0.1321 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0366 42/56 [=====================>........] - ETA: 0s - loss: 0.1283 56/56 [==============================] - 0s 1ms/step - loss: 0.1240 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0056 42/56 [=====================>........] - ETA: 0s - loss: 0.1321 56/56 [==============================] - 0s 1ms/step - loss: 0.1255 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0895 48/56 [========================>.....] - ETA: 0s - loss: 0.1149 56/56 [==============================] - 0s 1ms/step - loss: 0.1215 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0186 48/56 [========================>.....] - ETA: 0s - loss: 0.1333 56/56 [==============================] - 0s 1ms/step - loss: 0.1278 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.2715 48/56 [========================>.....] - ETA: 0s - loss: 0.1212 56/56 [==============================] - 0s 1ms/step - loss: 0.1256 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0270 40/56 [====================>.........] - ETA: 0s - loss: 0.1169 56/56 [==============================] - 0s 1ms/step - loss: 0.1212 -> test with GAN.predict GAN tn, fp: 132, 5 GAN fn, tp: 2, 4 GAN f1 score: 0.533 GAN cohens kappa score: 0.509 -> test with 'LR' LR tn, fp: 132, 5 LR fn, tp: 2, 4 LR f1 score: 0.533 LR cohens kappa score: 0.509 LR average precision score: 0.605 -> 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: 135, 2 GB fn, tp: 4, 2 GB f1 score: 0.400 GB cohens kappa score: 0.379 -> test with 'KNN' KNN tn, fp: 136, 1 KNN fn, tp: 4, 2 KNN f1 score: 0.444 KNN cohens kappa score: 0.428 ====== 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: 9s - loss: 0.0417 44/56 [======================>.......] - ETA: 0s - loss: 0.1535 56/56 [==============================] - 0s 1ms/step - loss: 0.1375 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0689 44/56 [======================>.......] - ETA: 0s - loss: 0.1556 56/56 [==============================] - 0s 1ms/step - loss: 0.1329 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.2138 41/56 [====================>.........] - ETA: 0s - loss: 0.1403 56/56 [==============================] - 0s 1ms/step - loss: 0.1246 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1691 39/56 [===================>..........] - ETA: 0s - loss: 0.1116 56/56 [==============================] - 0s 1ms/step - loss: 0.1125 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0829 45/56 [=======================>......] - ETA: 0s - loss: 0.1158 56/56 [==============================] - 0s 1ms/step - loss: 0.1096 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.4549 46/56 [=======================>......] - ETA: 0s - loss: 0.1191 56/56 [==============================] - 0s 1ms/step - loss: 0.1105 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0021 47/56 [========================>.....] - ETA: 0s - loss: 0.0909 56/56 [==============================] - 0s 1ms/step - loss: 0.1086 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0792 38/56 [===================>..........] - ETA: 0s - loss: 0.0991 56/56 [==============================] - 0s 1ms/step - loss: 0.1026 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1227 34/56 [=================>............] - ETA: 0s - loss: 0.1093 56/56 [==============================] - 0s 2ms/step - loss: 0.0983 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1169 39/56 [===================>..........] - ETA: 0s - loss: 0.1060 56/56 [==============================] - 0s 1ms/step - loss: 0.1043 -> test with GAN.predict GAN tn, fp: 133, 5 GAN fn, tp: 3, 6 GAN f1 score: 0.600 GAN cohens kappa score: 0.571 -> test with 'LR' LR tn, fp: 129, 9 LR fn, tp: 3, 6 LR f1 score: 0.500 LR cohens kappa score: 0.459 LR average precision score: 0.673 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 8, 1 RF f1 score: 0.182 RF cohens kappa score: 0.163 -> test with 'GB' GB tn, fp: 137, 1 GB fn, tp: 9, 0 GB f1 score: 0.000 GB cohens kappa score: -0.012 -> test with 'KNN' KNN tn, fp: 136, 2 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.023 ------ 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: 9s - loss: 0.1101 47/56 [========================>.....] - ETA: 0s - loss: 0.1145 56/56 [==============================] - 0s 1ms/step - loss: 0.1199 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 6.1767e-04 48/56 [========================>.....] - ETA: 0s - loss: 0.1115  56/56 [==============================] - 0s 1ms/step - loss: 0.1153 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0036 45/56 [=======================>......] - ETA: 0s - loss: 0.1088 56/56 [==============================] - 0s 1ms/step - loss: 0.1053 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.1091 47/56 [========================>.....] - ETA: 0s - loss: 0.1036 56/56 [==============================] - 0s 1ms/step - loss: 0.1027 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0317 47/56 [========================>.....] - ETA: 0s - loss: 0.1028 56/56 [==============================] - 0s 1ms/step - loss: 0.1002 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0429 48/56 [========================>.....] - ETA: 0s - loss: 0.1066 56/56 [==============================] - 0s 1ms/step - loss: 0.0971 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0239 42/56 [=====================>........] - ETA: 0s - loss: 0.0986 56/56 [==============================] - 0s 1ms/step - loss: 0.0940 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0875 42/56 [=====================>........] - ETA: 0s - loss: 0.0913 56/56 [==============================] - 0s 1ms/step - loss: 0.0932 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.1594 48/56 [========================>.....] - ETA: 0s - loss: 0.0855 56/56 [==============================] - 0s 1ms/step - loss: 0.0914 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0490 49/56 [=========================>....] - ETA: 0s - loss: 0.0857 56/56 [==============================] - 0s 1ms/step - loss: 0.0907 -> test with GAN.predict GAN tn, fp: 137, 1 GAN fn, tp: 4, 5 GAN f1 score: 0.667 GAN cohens kappa score: 0.649 -> test with 'LR' LR tn, fp: 130, 8 LR fn, tp: 2, 7 LR f1 score: 0.583 LR cohens kappa score: 0.549 LR average precision score: 0.685 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 7, 2 RF f1 score: 0.333 RF cohens kappa score: 0.312 -> test with 'GB' GB tn, fp: 137, 1 GB fn, tp: 6, 3 GB f1 score: 0.462 GB cohens kappa score: 0.440 -> test with 'KNN' KNN tn, fp: 137, 1 KNN fn, tp: 8, 1 KNN f1 score: 0.182 KNN cohens kappa score: 0.163 ------ 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: 10s - loss: 0.0077 46/56 [=======================>......] - ETA: 0s - loss: 0.1026  56/56 [==============================] - 0s 1ms/step - loss: 0.0991 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0151 45/56 [=======================>......] - ETA: 0s - loss: 0.0844 56/56 [==============================] - 0s 1ms/step - loss: 0.0845 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.1920 46/56 [=======================>......] - ETA: 0s - loss: 0.0893 56/56 [==============================] - 0s 1ms/step - loss: 0.0875 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0223 48/56 [========================>.....] - ETA: 0s - loss: 0.0785 56/56 [==============================] - 0s 1ms/step - loss: 0.0779 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.1164 46/56 [=======================>......] - ETA: 0s - loss: 0.0847 56/56 [==============================] - 0s 1ms/step - loss: 0.0805 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0463 47/56 [========================>.....] - ETA: 0s - loss: 0.0780 56/56 [==============================] - 0s 1ms/step - loss: 0.0797 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0264 47/56 [========================>.....] - ETA: 0s - loss: 0.0849 56/56 [==============================] - 0s 1ms/step - loss: 0.0818 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.6580 47/56 [========================>.....] - ETA: 0s - loss: 0.0775 56/56 [==============================] - 0s 1ms/step - loss: 0.0808 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0053 47/56 [========================>.....] - ETA: 0s - loss: 0.0813 56/56 [==============================] - 0s 1ms/step - loss: 0.0794 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0067 48/56 [========================>.....] - ETA: 0s - loss: 0.0761 56/56 [==============================] - 0s 1ms/step - loss: 0.0783 -> test with GAN.predict GAN tn, fp: 135, 3 GAN fn, tp: 6, 3 GAN f1 score: 0.400 GAN cohens kappa score: 0.369 -> test with 'LR' LR tn, fp: 130, 8 LR fn, tp: 4, 5 LR f1 score: 0.455 LR cohens kappa score: 0.412 LR average precision score: 0.539 -> 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: 135, 3 GB fn, tp: 8, 1 GB f1 score: 0.154 GB cohens kappa score: 0.121 -> test with 'KNN' KNN tn, fp: 136, 2 KNN fn, tp: 8, 1 KNN f1 score: 0.167 KNN cohens kappa score: 0.140 ------ 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: 7s - loss: 0.0500 47/56 [========================>.....] - ETA: 0s - loss: 0.1273 56/56 [==============================] - 0s 1ms/step - loss: 0.1248 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0014 48/56 [========================>.....] - ETA: 0s - loss: 0.1137 56/56 [==============================] - 0s 1ms/step - loss: 0.1125 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0916 43/56 [======================>.......] - ETA: 0s - loss: 0.0994 56/56 [==============================] - 0s 1ms/step - loss: 0.1064 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0140 39/56 [===================>..........] - ETA: 0s - loss: 0.1118 56/56 [==============================] - 0s 1ms/step - loss: 0.0960 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0271 42/56 [=====================>........] - ETA: 0s - loss: 0.0984 56/56 [==============================] - 0s 1ms/step - loss: 0.0936 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.0046 47/56 [========================>.....] - ETA: 0s - loss: 0.1082 56/56 [==============================] - 0s 1ms/step - loss: 0.1015 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0142 47/56 [========================>.....] - ETA: 0s - loss: 0.1019 56/56 [==============================] - 0s 1ms/step - loss: 0.0894 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0077 47/56 [========================>.....] - ETA: 0s - loss: 0.0754 56/56 [==============================] - 0s 1ms/step - loss: 0.0880 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0993 46/56 [=======================>......] - ETA: 0s - loss: 0.0861 56/56 [==============================] - 0s 1ms/step - loss: 0.0894 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.1911 48/56 [========================>.....] - ETA: 0s - loss: 0.0830 56/56 [==============================] - 0s 1ms/step - loss: 0.0867 -> test with GAN.predict GAN tn, fp: 136, 2 GAN fn, tp: 3, 6 GAN f1 score: 0.706 GAN cohens kappa score: 0.688 -> test with 'LR' LR tn, fp: 132, 6 LR fn, tp: 1, 8 LR f1 score: 0.696 LR cohens kappa score: 0.671 LR average precision score: 0.908 -> test with 'RF' RF tn, fp: 137, 1 RF fn, tp: 7, 2 RF f1 score: 0.333 RF cohens kappa score: 0.312 -> test with 'GB' GB tn, fp: 137, 1 GB fn, tp: 7, 2 GB f1 score: 0.333 GB cohens kappa score: 0.312 -> test with 'KNN' KNN tn, fp: 136, 2 KNN fn, tp: 7, 2 KNN f1 score: 0.308 KNN cohens kappa score: 0.281 ------ 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: 7s - loss: 0.0067 47/56 [========================>.....] - ETA: 0s - loss: 0.1300 56/56 [==============================] - 0s 1ms/step - loss: 0.1364 Epoch 2/10 1/56 [..............................] - ETA: 0s - loss: 0.0302 48/56 [========================>.....] - ETA: 0s - loss: 0.1247 56/56 [==============================] - 0s 1ms/step - loss: 0.1246 Epoch 3/10 1/56 [..............................] - ETA: 0s - loss: 0.0013 48/56 [========================>.....] - ETA: 0s - loss: 0.1002 56/56 [==============================] - 0s 1ms/step - loss: 0.1134 Epoch 4/10 1/56 [..............................] - ETA: 0s - loss: 0.0203 47/56 [========================>.....] - ETA: 0s - loss: 0.1128 56/56 [==============================] - 0s 1ms/step - loss: 0.1088 Epoch 5/10 1/56 [..............................] - ETA: 0s - loss: 0.0516 48/56 [========================>.....] - ETA: 0s - loss: 0.0919 56/56 [==============================] - 0s 1ms/step - loss: 0.0942 Epoch 6/10 1/56 [..............................] - ETA: 0s - loss: 0.4339 48/56 [========================>.....] - ETA: 0s - loss: 0.1026 56/56 [==============================] - 0s 1ms/step - loss: 0.0920 Epoch 7/10 1/56 [..............................] - ETA: 0s - loss: 0.0532 42/56 [=====================>........] - ETA: 0s - loss: 0.0910 56/56 [==============================] - 0s 1ms/step - loss: 0.0897 Epoch 8/10 1/56 [..............................] - ETA: 0s - loss: 0.0072 48/56 [========================>.....] - ETA: 0s - loss: 0.0983 56/56 [==============================] - 0s 1ms/step - loss: 0.0921 Epoch 9/10 1/56 [..............................] - ETA: 0s - loss: 0.0026 49/56 [=========================>....] - ETA: 0s - loss: 0.0840 56/56 [==============================] - 0s 1ms/step - loss: 0.0884 Epoch 10/10 1/56 [..............................] - ETA: 0s - loss: 0.0122 48/56 [========================>.....] - ETA: 0s - loss: 0.0905 56/56 [==============================] - 0s 1ms/step - loss: 0.0899 -> test with GAN.predict GAN tn, fp: 135, 2 GAN fn, tp: 2, 4 GAN f1 score: 0.667 GAN cohens kappa score: 0.652 -> test with 'LR' LR tn, fp: 132, 5 LR fn, tp: 1, 5 LR f1 score: 0.625 LR cohens kappa score: 0.604 LR average precision score: 0.821 -> test with 'RF' RF tn, fp: 136, 1 RF fn, tp: 3, 3 RF f1 score: 0.600 RF cohens kappa score: 0.586 -> test with 'GB' GB tn, fp: 137, 0 GB fn, tp: 4, 2 GB f1 score: 0.500 GB cohens kappa score: 0.489 -> test with 'KNN' KNN tn, fp: 137, 0 KNN fn, tp: 5, 1 KNN f1 score: 0.286 KNN cohens kappa score: 0.277 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 134, 16 LR fn, tp: 5, 9 LR f1 score: 0.818 LR cohens kappa score: 0.804 LR average precision score: 0.918 average: LR tn, fp: 130.96, 6.84 LR fn, tp: 2.28, 6.12 LR f1 score: 0.574 LR cohens kappa score: 0.543 LR average precision score: 0.680 minimum: LR tn, fp: 122, 3 LR fn, tp: 0, 4 LR f1 score: 0.381 LR cohens kappa score: 0.334 LR average precision score: 0.447 -----[ RF ]----- maximum: RF tn, fp: 138, 5 RF fn, tp: 8, 4 RF f1 score: 0.667 RF cohens kappa score: 0.657 average: RF tn, fp: 136.28, 1.52 RF fn, tp: 6.24, 2.16 RF f1 score: 0.359 RF cohens kappa score: 0.337 minimum: RF tn, fp: 133, 0 RF fn, tp: 3, 1 RF f1 score: 0.154 RF cohens kappa score: 0.121 -----[ GB ]----- maximum: GB tn, fp: 138, 8 GB fn, tp: 9, 4 GB f1 score: 0.500 GB cohens kappa score: 0.489 average: GB tn, fp: 135.44, 2.36 GB fn, tp: 6.4, 2.0 GB f1 score: 0.318 GB cohens kappa score: 0.292 minimum: GB tn, fp: 130, 0 GB fn, tp: 4, 0 GB f1 score: 0.000 GB cohens kappa score: -0.012 -----[ KNN ]----- maximum: KNN tn, fp: 138, 3 KNN fn, tp: 9, 4 KNN f1 score: 0.615 KNN cohens kappa score: 0.600 average: KNN tn, fp: 136.76, 1.04 KNN fn, tp: 7.52, 0.88 KNN f1 score: 0.165 KNN cohens kappa score: 0.149 minimum: KNN tn, fp: 135, 0 KNN fn, tp: 4, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.032 -----[ GAN ]----- maximum: GAN tn, fp: 137, 5 GAN fn, tp: 6, 8 GAN f1 score: 0.778 GAN cohens kappa score: 0.763 average: GAN tn, fp: 135.08, 2.72 GAN fn, tp: 4.08, 4.32 GAN f1 score: 0.549 GAN cohens kappa score: 0.525 minimum: GAN tn, fp: 132, 1 GAN fn, tp: 1, 2 GAN f1 score: 0.375 GAN cohens kappa score: 0.340