/////////////////////////////////////////// // Running convGAN-majority-full on imblearn_mammography /////////////////////////////////////////// Load 'data_input/imblearn_mammography' from imblearn non empty cut in data_input/imblearn_mammography! (7 points) Data loaded. -> Shuffling data ### Start exercise for synthetic point generator ====== Step 1/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 1/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2098, 87 GAN fn, tp: 6, 46 GAN f1 score: 0.497 GAN cohens kappa score: 0.480 -> test with 'LR' LR tn, fp: 1876, 309 LR fn, tp: 6, 46 LR f1 score: 0.226 LR cohens kappa score: 0.193 LR average precision score: 0.560 -> test with 'GB' GB tn, fp: 2130, 55 GB fn, tp: 15, 37 GB f1 score: 0.514 GB cohens kappa score: 0.499 -> test with 'KNN' KNN tn, fp: 2080, 105 KNN fn, tp: 6, 46 KNN f1 score: 0.453 KNN cohens kappa score: 0.434 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2125, 60 GAN fn, tp: 10, 42 GAN f1 score: 0.545 GAN cohens kappa score: 0.531 -> test with 'LR' LR tn, fp: 1911, 274 LR fn, tp: 6, 46 LR f1 score: 0.247 LR cohens kappa score: 0.216 LR average precision score: 0.479 -> test with 'GB' GB tn, fp: 2136, 49 GB fn, tp: 12, 40 GB f1 score: 0.567 GB cohens kappa score: 0.554 -> test with 'KNN' KNN tn, fp: 2094, 91 KNN fn, tp: 7, 45 KNN f1 score: 0.479 KNN cohens kappa score: 0.461 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2123, 62 GAN fn, tp: 8, 44 GAN f1 score: 0.557 GAN cohens kappa score: 0.543 -> test with 'LR' LR tn, fp: 1904, 281 LR fn, tp: 6, 46 LR f1 score: 0.243 LR cohens kappa score: 0.211 LR average precision score: 0.591 -> test with 'GB' GB tn, fp: 2154, 31 GB fn, tp: 11, 41 GB f1 score: 0.661 GB cohens kappa score: 0.652 -> test with 'KNN' KNN tn, fp: 2097, 88 KNN fn, tp: 6, 46 KNN f1 score: 0.495 KNN cohens kappa score: 0.477 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2114, 71 GAN fn, tp: 10, 42 GAN f1 score: 0.509 GAN cohens kappa score: 0.493 -> test with 'LR' LR tn, fp: 1916, 269 LR fn, tp: 7, 45 LR f1 score: 0.246 LR cohens kappa score: 0.215 LR average precision score: 0.329 -> test with 'GB' GB tn, fp: 2134, 51 GB fn, tp: 17, 35 GB f1 score: 0.507 GB cohens kappa score: 0.493 -> test with 'KNN' KNN tn, fp: 2075, 110 KNN fn, tp: 9, 43 KNN f1 score: 0.420 KNN cohens kappa score: 0.399 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8532 synthetic samples -> test with GAN.predict GAN tn, fp: 2131, 52 GAN fn, tp: 9, 43 GAN f1 score: 0.585 GAN cohens kappa score: 0.572 -> test with 'LR' LR tn, fp: 1915, 268 LR fn, tp: 6, 46 LR f1 score: 0.251 LR cohens kappa score: 0.220 LR average precision score: 0.563 -> test with 'GB' GB tn, fp: 2140, 43 GB fn, tp: 13, 39 GB f1 score: 0.582 GB cohens kappa score: 0.570 -> test with 'KNN' KNN tn, fp: 1484, 699 KNN fn, tp: 10, 42 KNN f1 score: 0.106 KNN cohens kappa score: 0.065 ====== Step 2/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 2/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2090, 95 GAN fn, tp: 11, 41 GAN f1 score: 0.436 GAN cohens kappa score: 0.417 -> test with 'LR' LR tn, fp: 1879, 306 LR fn, tp: 6, 46 LR f1 score: 0.228 LR cohens kappa score: 0.195 LR average precision score: 0.507 -> test with 'GB' GB tn, fp: 2114, 71 GB fn, tp: 12, 40 GB f1 score: 0.491 GB cohens kappa score: 0.474 -> test with 'KNN' KNN tn, fp: 2083, 102 KNN fn, tp: 8, 44 KNN f1 score: 0.444 KNN cohens kappa score: 0.425 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2104, 81 GAN fn, tp: 7, 45 GAN f1 score: 0.506 GAN cohens kappa score: 0.489 -> test with 'LR' LR tn, fp: 1883, 302 LR fn, tp: 7, 45 LR f1 score: 0.226 LR cohens kappa score: 0.193 LR average precision score: 0.419 -> test with 'GB' GB tn, fp: 2131, 54 GB fn, tp: 12, 40 GB f1 score: 0.548 GB cohens kappa score: 0.534 -> test with 'KNN' KNN tn, fp: 2067, 118 KNN fn, tp: 5, 47 KNN f1 score: 0.433 KNN cohens kappa score: 0.412 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2120, 65 GAN fn, tp: 10, 42 GAN f1 score: 0.528 GAN cohens kappa score: 0.513 -> test with 'LR' LR tn, fp: 1926, 259 LR fn, tp: 7, 45 LR f1 score: 0.253 LR cohens kappa score: 0.222 LR average precision score: 0.507 -> test with 'GB' GB tn, fp: 2144, 41 GB fn, tp: 18, 34 GB f1 score: 0.535 GB cohens kappa score: 0.522 -> test with 'KNN' KNN tn, fp: 1438, 747 KNN fn, tp: 10, 42 KNN f1 score: 0.100 KNN cohens kappa score: 0.059 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2125, 60 GAN fn, tp: 8, 44 GAN f1 score: 0.564 GAN cohens kappa score: 0.550 -> test with 'LR' LR tn, fp: 1911, 274 LR fn, tp: 5, 47 LR f1 score: 0.252 LR cohens kappa score: 0.221 LR average precision score: 0.476 -> test with 'GB' GB tn, fp: 2134, 51 GB fn, tp: 9, 43 GB f1 score: 0.589 GB cohens kappa score: 0.576 -> test with 'KNN' KNN tn, fp: 1414, 771 KNN fn, tp: 4, 48 KNN f1 score: 0.110 KNN cohens kappa score: 0.070 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8532 synthetic samples -> test with GAN.predict GAN tn, fp: 2125, 58 GAN fn, tp: 11, 41 GAN f1 score: 0.543 GAN cohens kappa score: 0.529 -> test with 'LR' LR tn, fp: 1933, 250 LR fn, tp: 8, 44 LR f1 score: 0.254 LR cohens kappa score: 0.224 LR average precision score: 0.518 -> test with 'GB' GB tn, fp: 2147, 36 GB fn, tp: 15, 37 GB f1 score: 0.592 GB cohens kappa score: 0.581 -> test with 'KNN' KNN tn, fp: 2117, 66 KNN fn, tp: 9, 43 KNN f1 score: 0.534 KNN cohens kappa score: 0.519 ====== Step 3/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 3/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2121, 64 GAN fn, tp: 8, 44 GAN f1 score: 0.550 GAN cohens kappa score: 0.535 -> test with 'LR' LR tn, fp: 1915, 270 LR fn, tp: 6, 46 LR f1 score: 0.250 LR cohens kappa score: 0.219 LR average precision score: 0.565 -> test with 'GB' GB tn, fp: 2138, 47 GB fn, tp: 10, 42 GB f1 score: 0.596 GB cohens kappa score: 0.584 -> test with 'KNN' KNN tn, fp: 2090, 95 KNN fn, tp: 6, 46 KNN f1 score: 0.477 KNN cohens kappa score: 0.458 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2099, 86 GAN fn, tp: 8, 44 GAN f1 score: 0.484 GAN cohens kappa score: 0.466 -> test with 'LR' LR tn, fp: 1917, 268 LR fn, tp: 6, 46 LR f1 score: 0.251 LR cohens kappa score: 0.220 LR average precision score: 0.465 -> test with 'GB' GB tn, fp: 2145, 40 GB fn, tp: 17, 35 GB f1 score: 0.551 GB cohens kappa score: 0.539 -> test with 'KNN' KNN tn, fp: 2105, 80 KNN fn, tp: 10, 42 KNN f1 score: 0.483 KNN cohens kappa score: 0.465 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2089, 96 GAN fn, tp: 3, 49 GAN f1 score: 0.497 GAN cohens kappa score: 0.480 -> test with 'LR' LR tn, fp: 1803, 382 LR fn, tp: 2, 50 LR f1 score: 0.207 LR cohens kappa score: 0.172 LR average precision score: 0.500 -> test with 'GB' GB tn, fp: 2128, 57 GB fn, tp: 3, 49 GB f1 score: 0.620 GB cohens kappa score: 0.608 -> test with 'KNN' KNN tn, fp: 1412, 773 KNN fn, tp: 5, 47 KNN f1 score: 0.108 KNN cohens kappa score: 0.067 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2124, 61 GAN fn, tp: 13, 39 GAN f1 score: 0.513 GAN cohens kappa score: 0.498 -> test with 'LR' LR tn, fp: 1915, 270 LR fn, tp: 9, 43 LR f1 score: 0.236 LR cohens kappa score: 0.204 LR average precision score: 0.487 -> test with 'GB' GB tn, fp: 2134, 51 GB fn, tp: 14, 38 GB f1 score: 0.539 GB cohens kappa score: 0.525 -> test with 'KNN' KNN tn, fp: 2092, 93 KNN fn, tp: 12, 40 KNN f1 score: 0.432 KNN cohens kappa score: 0.413 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8532 synthetic samples -> test with GAN.predict GAN tn, fp: 2122, 61 GAN fn, tp: 13, 39 GAN f1 score: 0.513 GAN cohens kappa score: 0.498 -> test with 'LR' LR tn, fp: 1908, 275 LR fn, tp: 7, 45 LR f1 score: 0.242 LR cohens kappa score: 0.210 LR average precision score: 0.564 -> test with 'GB' GB tn, fp: 2146, 37 GB fn, tp: 17, 35 GB f1 score: 0.565 GB cohens kappa score: 0.552 -> test with 'KNN' KNN tn, fp: 2096, 87 KNN fn, tp: 10, 42 KNN f1 score: 0.464 KNN cohens kappa score: 0.446 ====== Step 4/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 4/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2117, 68 GAN fn, tp: 9, 43 GAN f1 score: 0.528 GAN cohens kappa score: 0.512 -> test with 'LR' LR tn, fp: 1912, 273 LR fn, tp: 8, 44 LR f1 score: 0.238 LR cohens kappa score: 0.207 LR average precision score: 0.562 -> test with 'GB' GB tn, fp: 2144, 41 GB fn, tp: 20, 32 GB f1 score: 0.512 GB cohens kappa score: 0.498 -> test with 'KNN' KNN tn, fp: 2113, 72 KNN fn, tp: 11, 41 KNN f1 score: 0.497 KNN cohens kappa score: 0.480 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2118, 67 GAN fn, tp: 9, 43 GAN f1 score: 0.531 GAN cohens kappa score: 0.516 -> test with 'LR' LR tn, fp: 1895, 290 LR fn, tp: 5, 47 LR f1 score: 0.242 LR cohens kappa score: 0.210 LR average precision score: 0.412 -> test with 'GB' GB tn, fp: 2139, 46 GB fn, tp: 11, 41 GB f1 score: 0.590 GB cohens kappa score: 0.578 -> test with 'KNN' KNN tn, fp: 2104, 81 KNN fn, tp: 9, 43 KNN f1 score: 0.489 KNN cohens kappa score: 0.471 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2114, 71 GAN fn, tp: 8, 44 GAN f1 score: 0.527 GAN cohens kappa score: 0.511 -> test with 'LR' LR tn, fp: 1918, 267 LR fn, tp: 7, 45 LR f1 score: 0.247 LR cohens kappa score: 0.216 LR average precision score: 0.476 -> test with 'GB' GB tn, fp: 2130, 55 GB fn, tp: 10, 42 GB f1 score: 0.564 GB cohens kappa score: 0.550 -> test with 'KNN' KNN tn, fp: 2091, 94 KNN fn, tp: 9, 43 KNN f1 score: 0.455 KNN cohens kappa score: 0.436 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2087, 98 GAN fn, tp: 6, 46 GAN f1 score: 0.469 GAN cohens kappa score: 0.451 -> test with 'LR' LR tn, fp: 1921, 264 LR fn, tp: 9, 43 LR f1 score: 0.240 LR cohens kappa score: 0.208 LR average precision score: 0.486 -> test with 'GB' GB tn, fp: 2145, 40 GB fn, tp: 13, 39 GB f1 score: 0.595 GB cohens kappa score: 0.584 -> test with 'KNN' KNN tn, fp: 2087, 98 KNN fn, tp: 7, 45 KNN f1 score: 0.462 KNN cohens kappa score: 0.443 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8532 synthetic samples -> test with GAN.predict GAN tn, fp: 2121, 62 GAN fn, tp: 10, 42 GAN f1 score: 0.538 GAN cohens kappa score: 0.524 -> test with 'LR' LR tn, fp: 1881, 302 LR fn, tp: 1, 51 LR f1 score: 0.252 LR cohens kappa score: 0.220 LR average precision score: 0.482 -> test with 'GB' GB tn, fp: 2125, 58 GB fn, tp: 8, 44 GB f1 score: 0.571 GB cohens kappa score: 0.558 -> test with 'KNN' KNN tn, fp: 2068, 115 KNN fn, tp: 7, 45 KNN f1 score: 0.425 KNN cohens kappa score: 0.404 ====== Step 5/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 5/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2151, 34 GAN fn, tp: 12, 40 GAN f1 score: 0.635 GAN cohens kappa score: 0.625 -> test with 'LR' LR tn, fp: 1901, 284 LR fn, tp: 3, 49 LR f1 score: 0.255 LR cohens kappa score: 0.223 LR average precision score: 0.485 -> test with 'GB' GB tn, fp: 2156, 29 GB fn, tp: 9, 43 GB f1 score: 0.694 GB cohens kappa score: 0.685 -> test with 'KNN' KNN tn, fp: 2095, 90 KNN fn, tp: 7, 45 KNN f1 score: 0.481 KNN cohens kappa score: 0.463 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2081, 104 GAN fn, tp: 5, 47 GAN f1 score: 0.463 GAN cohens kappa score: 0.444 -> test with 'LR' LR tn, fp: 1903, 282 LR fn, tp: 7, 45 LR f1 score: 0.237 LR cohens kappa score: 0.206 LR average precision score: 0.437 -> test with 'GB' GB tn, fp: 2137, 48 GB fn, tp: 9, 43 GB f1 score: 0.601 GB cohens kappa score: 0.589 -> test with 'KNN' KNN tn, fp: 2069, 116 KNN fn, tp: 5, 47 KNN f1 score: 0.437 KNN cohens kappa score: 0.417 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2120, 65 GAN fn, tp: 12, 40 GAN f1 score: 0.510 GAN cohens kappa score: 0.494 -> test with 'LR' LR tn, fp: 1914, 271 LR fn, tp: 8, 44 LR f1 score: 0.240 LR cohens kappa score: 0.208 LR average precision score: 0.506 -> test with 'GB' GB tn, fp: 2137, 48 GB fn, tp: 15, 37 GB f1 score: 0.540 GB cohens kappa score: 0.526 -> test with 'KNN' KNN tn, fp: 2092, 93 KNN fn, tp: 11, 41 KNN f1 score: 0.441 KNN cohens kappa score: 0.421 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8530 synthetic samples -> test with GAN.predict GAN tn, fp: 2106, 79 GAN fn, tp: 9, 43 GAN f1 score: 0.494 GAN cohens kappa score: 0.477 -> test with 'LR' LR tn, fp: 1901, 284 LR fn, tp: 4, 48 LR f1 score: 0.250 LR cohens kappa score: 0.219 LR average precision score: 0.474 -> test with 'GB' GB tn, fp: 2134, 51 GB fn, tp: 11, 41 GB f1 score: 0.569 GB cohens kappa score: 0.556 -> test with 'KNN' KNN tn, fp: 2099, 86 KNN fn, tp: 6, 46 KNN f1 score: 0.500 KNN cohens kappa score: 0.483 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 8532 synthetic samples -> test with GAN.predict GAN tn, fp: 2076, 107 GAN fn, tp: 10, 42 GAN f1 score: 0.418 GAN cohens kappa score: 0.397 -> test with 'LR' LR tn, fp: 1930, 253 LR fn, tp: 8, 44 LR f1 score: 0.252 LR cohens kappa score: 0.221 LR average precision score: 0.572 -> test with 'GB' GB tn, fp: 2138, 45 GB fn, tp: 14, 38 GB f1 score: 0.563 GB cohens kappa score: 0.550 -> test with 'KNN' KNN tn, fp: 2085, 98 KNN fn, tp: 10, 42 KNN f1 score: 0.438 KNN cohens kappa score: 0.418 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 1933, 382 LR fn, tp: 9, 51 LR f1 score: 0.255 LR cohens kappa score: 0.224 LR average precision score: 0.591 average: LR tn, fp: 1903.52, 281.08 LR fn, tp: 6.16, 45.84 LR f1 score: 0.243 LR cohens kappa score: 0.211 LR average precision score: 0.497 minimum: LR tn, fp: 1803, 250 LR fn, tp: 1, 43 LR f1 score: 0.207 LR cohens kappa score: 0.172 LR average precision score: 0.329 -----[ GB ]----- maximum: GB tn, fp: 2156, 71 GB fn, tp: 20, 49 GB f1 score: 0.694 GB cohens kappa score: 0.685 average: GB tn, fp: 2137.6, 47.0 GB fn, tp: 12.6, 39.4 GB f1 score: 0.570 GB cohens kappa score: 0.557 minimum: GB tn, fp: 2114, 29 GB fn, tp: 3, 32 GB f1 score: 0.491 GB cohens kappa score: 0.474 -----[ KNN ]----- maximum: KNN tn, fp: 2117, 773 KNN fn, tp: 12, 48 KNN f1 score: 0.534 KNN cohens kappa score: 0.519 average: KNN tn, fp: 1985.88, 198.72 KNN fn, tp: 7.96, 44.04 KNN f1 score: 0.406 KNN cohens kappa score: 0.384 minimum: KNN tn, fp: 1412, 66 KNN fn, tp: 4, 40 KNN f1 score: 0.100 KNN cohens kappa score: 0.059 -----[ GAN ]----- maximum: GAN tn, fp: 2151, 107 GAN fn, tp: 13, 49 GAN f1 score: 0.635 GAN cohens kappa score: 0.625 average: GAN tn, fp: 2112.04, 72.56 GAN fn, tp: 9.0, 43.0 GAN f1 score: 0.518 GAN cohens kappa score: 0.502 minimum: GAN tn, fp: 2076, 34 GAN fn, tp: 3, 39 GAN f1 score: 0.418 GAN cohens kappa score: 0.397