/////////////////////////////////////////// // Running SimpleGAN on folding_car_good /////////////////////////////////////////// Load 'data_input/folding_car_good' 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 Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 211, 121 LR fn, tp: 9, 5 LR f1 score: 0.071 LR cohens kappa score: -0.002 LR average precision score: 0.045 -> test with 'GB' GB tn, fp: 328, 4 GB fn, tp: 7, 7 GB f1 score: 0.560 GB cohens kappa score: 0.544 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 12, 2 KNN f1 score: 0.250 KNN cohens kappa score: 0.242 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 325, 7 LR fn, tp: 14, 0 LR f1 score: 0.000 LR cohens kappa score: -0.028 LR average precision score: 0.051 -> test with 'GB' GB tn, fp: 332, 0 GB fn, tp: 0, 14 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 12, 2 KNN f1 score: 0.250 KNN cohens kappa score: 0.242 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 202, 130 LR fn, tp: 7, 7 LR f1 score: 0.093 LR cohens kappa score: 0.021 LR average precision score: 0.045 -> test with 'GB' GB tn, fp: 329, 3 GB fn, tp: 6, 8 GB f1 score: 0.640 GB cohens kappa score: 0.627 -> test with 'KNN' KNN tn, fp: 329, 3 KNN fn, tp: 9, 5 KNN f1 score: 0.455 KNN cohens kappa score: 0.438 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 219, 113 LR fn, tp: 8, 6 LR f1 score: 0.090 LR cohens kappa score: 0.019 LR average precision score: 0.053 -> test with 'GB' GB tn, fp: 325, 7 GB fn, tp: 8, 6 GB f1 score: 0.444 GB cohens kappa score: 0.422 -> test with 'KNN' KNN tn, fp: 328, 4 KNN fn, tp: 13, 1 KNN f1 score: 0.105 KNN cohens kappa score: 0.086 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 200, 131 LR fn, tp: 5, 8 LR f1 score: 0.105 LR cohens kappa score: 0.039 LR average precision score: 0.061 -> test with 'GB' GB tn, fp: 323, 8 GB fn, tp: 2, 11 GB f1 score: 0.688 GB cohens kappa score: 0.673 -> test with 'KNN' KNN tn, fp: 329, 2 KNN fn, tp: 10, 3 KNN f1 score: 0.333 KNN cohens kappa score: 0.319 ====== Step 2/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 2/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 205, 127 LR fn, tp: 7, 7 LR f1 score: 0.095 LR cohens kappa score: 0.023 LR average precision score: 0.047 -> test with 'GB' GB tn, fp: 329, 3 GB fn, tp: 6, 8 GB f1 score: 0.640 GB cohens kappa score: 0.627 -> test with 'KNN' KNN tn, fp: 329, 3 KNN fn, tp: 12, 2 KNN f1 score: 0.211 KNN cohens kappa score: 0.193 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 196, 136 LR fn, tp: 8, 6 LR f1 score: 0.077 LR cohens kappa score: 0.004 LR average precision score: 0.041 -> test with 'GB' GB tn, fp: 324, 8 GB fn, tp: 5, 9 GB f1 score: 0.581 GB cohens kappa score: 0.561 -> test with 'KNN' KNN tn, fp: 328, 4 KNN fn, tp: 11, 3 KNN f1 score: 0.286 KNN cohens kappa score: 0.266 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 212, 120 LR fn, tp: 5, 9 LR f1 score: 0.126 LR cohens kappa score: 0.057 LR average precision score: 0.057 -> test with 'GB' GB tn, fp: 331, 1 GB fn, tp: 9, 5 GB f1 score: 0.500 GB cohens kappa score: 0.488 -> test with 'KNN' KNN tn, fp: 331, 1 KNN fn, tp: 10, 4 KNN f1 score: 0.421 KNN cohens kappa score: 0.408 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 223, 109 LR fn, tp: 11, 3 LR f1 score: 0.048 LR cohens kappa score: -0.026 LR average precision score: 0.048 -> test with 'GB' GB tn, fp: 326, 6 GB fn, tp: 5, 9 GB f1 score: 0.621 GB cohens kappa score: 0.604 -> test with 'KNN' KNN tn, fp: 329, 3 KNN fn, tp: 14, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.014 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 211, 120 LR fn, tp: 7, 6 LR f1 score: 0.086 LR cohens kappa score: 0.019 LR average precision score: 0.047 -> test with 'GB' GB tn, fp: 325, 6 GB fn, tp: 4, 9 GB f1 score: 0.643 GB cohens kappa score: 0.628 -> test with 'KNN' KNN tn, fp: 329, 2 KNN fn, tp: 10, 3 KNN f1 score: 0.333 KNN cohens kappa score: 0.319 ====== Step 3/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 3/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 303, 29 LR fn, tp: 11, 3 LR f1 score: 0.130 LR cohens kappa score: 0.079 LR average precision score: 0.062 -> test with 'GB' GB tn, fp: 332, 0 GB fn, tp: 3, 11 GB f1 score: 0.880 GB cohens kappa score: 0.876 -> test with 'KNN' KNN tn, fp: 331, 1 KNN fn, tp: 13, 1 KNN f1 score: 0.125 KNN cohens kappa score: 0.116 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 323, 9 LR fn, tp: 13, 1 LR f1 score: 0.083 LR cohens kappa score: 0.051 LR average precision score: 0.071 -> test with 'GB' GB tn, fp: 329, 3 GB fn, tp: 1, 13 GB f1 score: 0.867 GB cohens kappa score: 0.861 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 13, 1 KNN f1 score: 0.133 KNN cohens kappa score: 0.129 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 308, 24 LR fn, tp: 14, 0 LR f1 score: 0.000 LR cohens kappa score: -0.054 LR average precision score: 0.043 -> test with 'GB' GB tn, fp: 331, 1 GB fn, tp: 9, 5 GB f1 score: 0.500 GB cohens kappa score: 0.488 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 11, 3 KNN f1 score: 0.353 KNN cohens kappa score: 0.344 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 224, 108 LR fn, tp: 7, 7 LR f1 score: 0.109 LR cohens kappa score: 0.039 LR average precision score: 0.050 -> test with 'GB' GB tn, fp: 330, 2 GB fn, tp: 6, 8 GB f1 score: 0.667 GB cohens kappa score: 0.655 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 13, 1 KNN f1 score: 0.133 KNN cohens kappa score: 0.129 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 313, 18 LR fn, tp: 11, 2 LR f1 score: 0.121 LR cohens kappa score: 0.079 LR average precision score: 0.063 -> test with 'GB' GB tn, fp: 328, 3 GB fn, tp: 2, 11 GB f1 score: 0.815 GB cohens kappa score: 0.807 -> test with 'KNN' KNN tn, fp: 330, 1 KNN fn, tp: 9, 4 KNN f1 score: 0.444 KNN cohens kappa score: 0.433 ====== Step 4/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 4/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 307, 25 LR fn, tp: 11, 3 LR f1 score: 0.143 LR cohens kappa score: 0.094 LR average precision score: 0.094 -> test with 'GB' GB tn, fp: 332, 0 GB fn, tp: 0, 14 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 12, 2 KNN f1 score: 0.250 KNN cohens kappa score: 0.242 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 201, 131 LR fn, tp: 8, 6 LR f1 score: 0.079 LR cohens kappa score: 0.007 LR average precision score: 0.041 -> test with 'GB' GB tn, fp: 327, 5 GB fn, tp: 9, 5 GB f1 score: 0.417 GB cohens kappa score: 0.396 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 11, 3 KNN f1 score: 0.353 KNN cohens kappa score: 0.344 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 318, 14 LR fn, tp: 14, 0 LR f1 score: 0.000 LR cohens kappa score: -0.042 LR average precision score: 0.047 -> test with 'GB' GB tn, fp: 331, 1 GB fn, tp: 5, 9 GB f1 score: 0.750 GB cohens kappa score: 0.741 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 11, 3 KNN f1 score: 0.353 KNN cohens kappa score: 0.344 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 202, 130 LR fn, tp: 11, 3 LR f1 score: 0.041 LR cohens kappa score: -0.035 LR average precision score: 0.040 -> test with 'GB' GB tn, fp: 328, 4 GB fn, tp: 3, 11 GB f1 score: 0.759 GB cohens kappa score: 0.748 -> test with 'KNN' KNN tn, fp: 327, 5 KNN fn, tp: 10, 4 KNN f1 score: 0.348 KNN cohens kappa score: 0.326 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 215, 116 LR fn, tp: 5, 8 LR f1 score: 0.117 LR cohens kappa score: 0.052 LR average precision score: 0.060 -> test with 'GB' GB tn, fp: 327, 4 GB fn, tp: 7, 6 GB f1 score: 0.522 GB cohens kappa score: 0.505 -> test with 'KNN' KNN tn, fp: 330, 1 KNN fn, tp: 11, 2 KNN f1 score: 0.250 KNN cohens kappa score: 0.239 ====== Step 5/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 5/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 209, 123 LR fn, tp: 10, 4 LR f1 score: 0.057 LR cohens kappa score: -0.017 LR average precision score: 0.038 -> test with 'GB' GB tn, fp: 329, 3 GB fn, tp: 10, 4 GB f1 score: 0.381 GB cohens kappa score: 0.364 -> test with 'KNN' KNN tn, fp: 330, 2 KNN fn, tp: 12, 2 KNN f1 score: 0.222 KNN cohens kappa score: 0.208 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 323, 9 LR fn, tp: 14, 0 LR f1 score: 0.000 LR cohens kappa score: -0.033 LR average precision score: 0.094 -> test with 'GB' GB tn, fp: 331, 1 GB fn, tp: 4, 10 GB f1 score: 0.800 GB cohens kappa score: 0.793 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 9, 5 KNN f1 score: 0.526 KNN cohens kappa score: 0.516 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 312, 20 LR fn, tp: 14, 0 LR f1 score: 0.000 LR cohens kappa score: -0.050 LR average precision score: 0.052 -> test with 'GB' GB tn, fp: 326, 6 GB fn, tp: 2, 12 GB f1 score: 0.750 GB cohens kappa score: 0.738 -> test with 'KNN' KNN tn, fp: 332, 0 KNN fn, tp: 10, 4 KNN f1 score: 0.444 KNN cohens kappa score: 0.434 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 216, 116 LR fn, tp: 7, 7 LR f1 score: 0.102 LR cohens kappa score: 0.032 LR average precision score: 0.062 -> test with 'GB' GB tn, fp: 328, 4 GB fn, tp: 7, 7 GB f1 score: 0.560 GB cohens kappa score: 0.544 -> test with 'KNN' KNN tn, fp: 330, 2 KNN fn, tp: 13, 1 KNN f1 score: 0.118 KNN cohens kappa score: 0.105 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 203, 128 LR fn, tp: 9, 4 LR f1 score: 0.055 LR cohens kappa score: -0.015 LR average precision score: 0.043 -> test with 'GB' GB tn, fp: 322, 9 GB fn, tp: 6, 7 GB f1 score: 0.483 GB cohens kappa score: 0.460 -> test with 'KNN' KNN tn, fp: 326, 5 KNN fn, tp: 9, 4 KNN f1 score: 0.364 KNN cohens kappa score: 0.343 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 325, 136 LR fn, tp: 14, 9 LR f1 score: 0.143 LR cohens kappa score: 0.094 LR average precision score: 0.094 average: LR tn, fp: 247.24, 84.56 LR fn, tp: 9.6, 4.2 LR f1 score: 0.073 LR cohens kappa score: 0.013 LR average precision score: 0.054 minimum: LR tn, fp: 196, 7 LR fn, tp: 5, 0 LR f1 score: 0.000 LR cohens kappa score: -0.054 LR average precision score: 0.038 -----[ GB ]----- maximum: GB tn, fp: 332, 9 GB fn, tp: 10, 14 GB f1 score: 1.000 GB cohens kappa score: 1.000 average: GB tn, fp: 328.12, 3.68 GB fn, tp: 5.04, 8.76 GB f1 score: 0.659 GB cohens kappa score: 0.646 minimum: GB tn, fp: 322, 0 GB fn, tp: 0, 4 GB f1 score: 0.381 GB cohens kappa score: 0.364 -----[ KNN ]----- maximum: KNN tn, fp: 332, 5 KNN fn, tp: 14, 5 KNN f1 score: 0.526 KNN cohens kappa score: 0.516 average: KNN tn, fp: 330.24, 1.56 KNN fn, tp: 11.2, 2.6 KNN f1 score: 0.282 KNN cohens kappa score: 0.270 minimum: KNN tn, fp: 326, 0 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.014