/////////////////////////////////////////// // 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 -> test with GAN.predict GAN tn, fp: 121, 17 GAN fn, tp: 0, 9 GAN f1 score: 0.514 GAN cohens kappa score: 0.466 -> test with 'LR' LR tn, fp: 121, 17 LR fn, tp: 0, 9 LR f1 score: 0.514 LR cohens kappa score: 0.466 LR average precision score: 0.888 -> 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: 119, 19 KNN fn, tp: 1, 8 KNN f1 score: 0.444 KNN cohens kappa score: 0.388 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> 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: 3, 6 LR f1 score: 0.571 LR cohens kappa score: 0.539 LR average precision score: 0.581 -> 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: 2, 7 KNN f1 score: 0.378 KNN cohens kappa score: 0.315 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> 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: 126, 12 LR fn, tp: 1, 8 LR f1 score: 0.552 LR cohens kappa score: 0.510 LR average precision score: 0.815 -> test with 'GB' GB tn, fp: 131, 7 GB fn, tp: 7, 2 GB f1 score: 0.222 GB cohens kappa score: 0.171 -> test with 'KNN' KNN tn, fp: 129, 9 KNN fn, tp: 3, 6 KNN f1 score: 0.500 KNN cohens kappa score: 0.459 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> test with GAN.predict GAN tn, fp: 124, 14 GAN fn, tp: 2, 7 GAN f1 score: 0.467 GAN cohens kappa score: 0.417 -> test with 'LR' LR tn, fp: 129, 9 LR fn, tp: 2, 7 LR f1 score: 0.560 LR cohens kappa score: 0.523 LR average precision score: 0.600 -> 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: 120, 18 KNN fn, tp: 3, 6 KNN f1 score: 0.364 KNN cohens kappa score: 0.301 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 516 synthetic samples -> test with GAN.predict GAN tn, fp: 126, 11 GAN fn, tp: 2, 4 GAN f1 score: 0.381 GAN cohens kappa score: 0.341 -> test with 'LR' LR tn, fp: 128, 9 LR fn, tp: 2, 4 LR f1 score: 0.421 LR cohens kappa score: 0.386 LR average precision score: 0.477 -> 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: 127, 10 KNN fn, tp: 3, 3 KNN f1 score: 0.316 KNN cohens kappa score: 0.274 ====== 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 -> 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: 119, 19 LR fn, tp: 2, 7 LR f1 score: 0.400 LR cohens kappa score: 0.340 LR average precision score: 0.625 -> test with 'GB' GB tn, fp: 135, 3 GB fn, tp: 5, 4 GB f1 score: 0.500 GB cohens kappa score: 0.472 -> test with 'KNN' KNN tn, fp: 127, 11 KNN fn, tp: 5, 4 KNN f1 score: 0.333 KNN cohens kappa score: 0.278 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> test with GAN.predict GAN tn, fp: 123, 15 GAN fn, tp: 3, 6 GAN f1 score: 0.400 GAN cohens kappa score: 0.344 -> 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: 0.784 -> test with 'GB' GB tn, fp: 132, 6 GB fn, tp: 6, 3 GB f1 score: 0.333 GB cohens kappa score: 0.290 -> test with 'KNN' KNN tn, fp: 127, 11 KNN fn, tp: 3, 6 KNN f1 score: 0.462 KNN cohens kappa score: 0.415 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> 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: 131, 7 LR fn, tp: 2, 7 LR f1 score: 0.609 LR cohens kappa score: 0.577 LR average precision score: 0.731 -> test with 'GB' GB tn, fp: 131, 7 GB fn, tp: 5, 4 GB f1 score: 0.400 GB cohens kappa score: 0.357 -> test with 'KNN' KNN tn, fp: 125, 13 KNN fn, tp: 2, 7 KNN f1 score: 0.483 KNN cohens kappa score: 0.435 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> test with GAN.predict GAN tn, fp: 124, 14 GAN fn, tp: 1, 8 GAN f1 score: 0.516 GAN cohens kappa score: 0.470 -> test with 'LR' LR tn, fp: 122, 16 LR fn, tp: 1, 8 LR f1 score: 0.485 LR cohens kappa score: 0.434 LR average precision score: 0.715 -> test with 'GB' GB tn, fp: 132, 6 GB fn, tp: 6, 3 GB f1 score: 0.333 GB cohens kappa score: 0.290 -> 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 -> test with GAN.predict GAN tn, fp: 122, 15 GAN fn, tp: 2, 4 GAN f1 score: 0.320 GAN cohens kappa score: 0.274 -> test with 'LR' LR tn, fp: 125, 12 LR fn, tp: 1, 5 LR f1 score: 0.435 LR cohens kappa score: 0.397 LR average precision score: 0.579 -> test with 'GB' GB tn, fp: 128, 9 GB fn, tp: 3, 3 GB f1 score: 0.333 GB cohens kappa score: 0.294 -> test with 'KNN' KNN tn, fp: 124, 13 KNN fn, tp: 2, 4 KNN f1 score: 0.348 KNN cohens kappa score: 0.305 ====== 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 -> test with GAN.predict GAN tn, fp: 121, 17 GAN fn, tp: 3, 6 GAN f1 score: 0.375 GAN cohens kappa score: 0.315 -> 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: 0.631 -> test with 'GB' GB tn, fp: 131, 7 GB fn, tp: 8, 1 GB f1 score: 0.118 GB cohens kappa score: 0.064 -> test with 'KNN' KNN tn, fp: 128, 10 KNN fn, tp: 5, 4 KNN f1 score: 0.348 KNN cohens kappa score: 0.295 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> test with GAN.predict GAN tn, fp: 125, 13 GAN fn, tp: 0, 9 GAN f1 score: 0.581 GAN cohens kappa score: 0.541 -> 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: 0.869 -> test with 'GB' GB tn, fp: 132, 6 GB fn, tp: 3, 6 GB f1 score: 0.571 GB cohens kappa score: 0.539 -> 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 -> 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: 133, 5 LR fn, tp: 4, 5 LR f1 score: 0.526 LR cohens kappa score: 0.494 LR average precision score: 0.695 -> 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: 127, 11 KNN fn, tp: 4, 5 KNN f1 score: 0.400 KNN cohens kappa score: 0.349 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> 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: 119, 19 LR fn, tp: 2, 7 LR f1 score: 0.400 LR cohens kappa score: 0.340 LR average precision score: 0.624 -> test with 'GB' GB tn, fp: 129, 9 GB fn, tp: 7, 2 GB f1 score: 0.200 GB cohens kappa score: 0.142 -> test with 'KNN' KNN tn, fp: 119, 19 KNN fn, tp: 5, 4 KNN f1 score: 0.250 KNN cohens kappa score: 0.178 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 516 synthetic samples -> test with GAN.predict GAN tn, fp: 118, 19 GAN fn, tp: 1, 5 GAN f1 score: 0.333 GAN cohens kappa score: 0.285 -> 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: 0.549 -> test with 'GB' GB tn, fp: 131, 6 GB fn, tp: 4, 2 GB f1 score: 0.286 GB cohens kappa score: 0.250 -> test with 'KNN' KNN tn, fp: 117, 20 KNN fn, tp: 2, 4 KNN f1 score: 0.267 KNN cohens kappa score: 0.214 ====== 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 -> test with GAN.predict GAN tn, fp: 126, 12 GAN fn, tp: 3, 6 GAN f1 score: 0.444 GAN cohens kappa score: 0.395 -> 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: 0.557 -> 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: 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 -> test with GAN.predict GAN tn, fp: 120, 18 GAN fn, tp: 2, 7 GAN f1 score: 0.412 GAN cohens kappa score: 0.354 -> 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: 0.702 -> test with 'GB' GB tn, fp: 127, 11 GB fn, tp: 4, 5 GB f1 score: 0.400 GB cohens kappa score: 0.349 -> test with 'KNN' KNN tn, fp: 119, 19 KNN fn, tp: 3, 6 KNN f1 score: 0.353 KNN cohens kappa score: 0.289 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> test with GAN.predict GAN tn, fp: 120, 18 GAN fn, tp: 2, 7 GAN f1 score: 0.412 GAN cohens kappa score: 0.354 -> test with 'LR' LR tn, fp: 124, 14 LR fn, tp: 1, 8 LR f1 score: 0.516 LR cohens kappa score: 0.470 LR average precision score: 0.728 -> test with 'GB' GB tn, fp: 129, 9 GB fn, tp: 6, 3 GB f1 score: 0.286 GB cohens kappa score: 0.232 -> 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 -> test with GAN.predict GAN tn, fp: 118, 20 GAN fn, tp: 0, 9 GAN f1 score: 0.474 GAN cohens kappa score: 0.419 -> test with 'LR' LR tn, fp: 122, 16 LR fn, tp: 0, 9 LR f1 score: 0.529 LR cohens kappa score: 0.483 LR average precision score: 0.967 -> 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: 120, 18 KNN fn, tp: 2, 7 KNN f1 score: 0.412 KNN cohens kappa score: 0.354 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 516 synthetic samples -> test with GAN.predict GAN tn, fp: 131, 6 GAN fn, tp: 2, 4 GAN f1 score: 0.500 GAN cohens kappa score: 0.472 -> 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: 0.518 -> 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: 122, 15 KNN fn, tp: 2, 4 KNN f1 score: 0.320 KNN cohens kappa score: 0.274 ====== 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 -> test with GAN.predict GAN tn, fp: 123, 15 GAN fn, tp: 3, 6 GAN f1 score: 0.400 GAN cohens kappa score: 0.344 -> test with 'LR' LR tn, fp: 123, 15 LR fn, tp: 2, 7 LR f1 score: 0.452 LR cohens kappa score: 0.399 LR average precision score: 0.698 -> 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: 117, 21 KNN fn, tp: 5, 4 KNN f1 score: 0.235 KNN cohens kappa score: 0.160 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> test with GAN.predict GAN tn, fp: 121, 17 GAN fn, tp: 4, 5 GAN f1 score: 0.323 GAN cohens kappa score: 0.258 -> test with 'LR' LR tn, fp: 126, 12 LR fn, tp: 0, 9 LR f1 score: 0.600 LR cohens kappa score: 0.562 LR average precision score: 0.731 -> 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: 119, 19 KNN fn, tp: 4, 5 KNN f1 score: 0.303 KNN cohens kappa score: 0.235 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> test with GAN.predict GAN tn, fp: 126, 12 GAN fn, tp: 4, 5 GAN f1 score: 0.385 GAN cohens kappa score: 0.331 -> 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: 0.542 -> test with 'GB' GB tn, fp: 130, 8 GB fn, tp: 6, 3 GB f1 score: 0.300 GB cohens kappa score: 0.249 -> test with 'KNN' KNN tn, fp: 123, 15 KNN fn, tp: 6, 3 KNN f1 score: 0.222 KNN cohens kappa score: 0.153 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 518 synthetic samples -> test with GAN.predict GAN tn, fp: 126, 12 GAN fn, tp: 1, 8 GAN f1 score: 0.552 GAN cohens kappa score: 0.510 -> test with 'LR' LR tn, fp: 131, 7 LR fn, tp: 1, 8 LR f1 score: 0.667 LR cohens kappa score: 0.639 LR average precision score: 0.932 -> test with 'GB' GB tn, fp: 135, 3 GB fn, tp: 4, 5 GB f1 score: 0.588 GB cohens kappa score: 0.563 -> test with 'KNN' KNN tn, fp: 128, 10 KNN fn, tp: 3, 6 KNN f1 score: 0.480 KNN cohens kappa score: 0.436 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 516 synthetic samples -> test with GAN.predict GAN tn, fp: 128, 9 GAN fn, tp: 1, 5 GAN f1 score: 0.500 GAN cohens kappa score: 0.469 -> test with 'LR' LR tn, fp: 128, 9 LR fn, tp: 0, 6 LR f1 score: 0.571 LR cohens kappa score: 0.544 LR average precision score: 0.802 -> 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: 126, 11 KNN fn, tp: 2, 4 KNN f1 score: 0.381 KNN cohens kappa score: 0.341 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 133, 19 LR fn, tp: 4, 9 LR f1 score: 0.720 LR cohens kappa score: 0.696 LR average precision score: 0.967 average: LR tn, fp: 126.76, 11.04 LR fn, tp: 1.6, 6.8 LR f1 score: 0.523 LR cohens kappa score: 0.483 LR average precision score: 0.694 minimum: LR tn, fp: 119, 5 LR fn, tp: 0, 4 LR f1 score: 0.400 LR cohens kappa score: 0.340 LR average precision score: 0.477 -----[ GB ]----- maximum: GB tn, fp: 135, 11 GB fn, tp: 8, 6 GB f1 score: 0.588 GB cohens kappa score: 0.563 average: GB tn, fp: 131.48, 6.32 GB fn, tp: 5.28, 3.12 GB f1 score: 0.348 GB cohens kappa score: 0.307 minimum: GB tn, fp: 127, 3 GB fn, tp: 3, 1 GB f1 score: 0.118 GB cohens kappa score: 0.064 -----[ KNN ]----- maximum: KNN tn, fp: 129, 21 KNN fn, tp: 6, 8 KNN f1 score: 0.500 KNN cohens kappa score: 0.459 average: KNN tn, fp: 122.72, 15.08 KNN fn, tp: 3.16, 5.24 KNN f1 score: 0.366 KNN cohens kappa score: 0.310 minimum: KNN tn, fp: 117, 9 KNN fn, tp: 1, 3 KNN f1 score: 0.222 KNN cohens kappa score: 0.153 -----[ GAN ]----- maximum: GAN tn, fp: 131, 20 GAN fn, tp: 4, 9 GAN f1 score: 0.581 GAN cohens kappa score: 0.541 average: GAN tn, fp: 124.16, 13.64 GAN fn, tp: 2.16, 6.24 GAN f1 score: 0.442 GAN cohens kappa score: 0.394 minimum: GAN tn, fp: 118, 6 GAN fn, tp: 0, 4 GAN f1 score: 0.320 GAN cohens kappa score: 0.258