/////////////////////////////////////////// // Running ctGAN 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 -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 169, 163 LR fn, tp: 4, 10 LR f1 score: 0.107 LR cohens kappa score: 0.035 LR average precision score: 0.056 -> test with 'RF' RF tn, fp: 304, 28 RF fn, tp: 0, 14 RF f1 score: 0.500 RF cohens kappa score: 0.468 -> test with 'GB' GB tn, fp: 304, 28 GB fn, tp: 0, 14 GB f1 score: 0.500 GB cohens kappa score: 0.468 -> test with 'KNN' KNN tn, fp: 221, 111 KNN fn, tp: 0, 14 KNN f1 score: 0.201 KNN cohens kappa score: 0.139 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 191, 141 LR fn, tp: 3, 11 LR f1 score: 0.133 LR cohens kappa score: 0.063 LR average precision score: 0.079 -> test with 'RF' RF tn, fp: 300, 32 RF fn, tp: 0, 14 RF f1 score: 0.467 RF cohens kappa score: 0.431 -> test with 'GB' GB tn, fp: 300, 32 GB fn, tp: 0, 14 GB f1 score: 0.467 GB cohens kappa score: 0.431 -> test with 'KNN' KNN tn, fp: 229, 103 KNN fn, tp: 0, 14 KNN f1 score: 0.214 KNN cohens kappa score: 0.152 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 179, 153 LR fn, tp: 7, 7 LR f1 score: 0.080 LR cohens kappa score: 0.007 LR average precision score: 0.055 -> test with 'RF' RF tn, fp: 311, 21 RF fn, tp: 0, 14 RF f1 score: 0.571 RF cohens kappa score: 0.545 -> test with 'GB' GB tn, fp: 311, 21 GB fn, tp: 0, 14 GB f1 score: 0.571 GB cohens kappa score: 0.545 -> test with 'KNN' KNN tn, fp: 240, 92 KNN fn, tp: 0, 14 KNN f1 score: 0.233 KNN cohens kappa score: 0.174 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 149, 183 LR fn, tp: 1, 13 LR f1 score: 0.124 LR cohens kappa score: 0.052 LR average precision score: 0.086 -> test with 'RF' RF tn, fp: 311, 21 RF fn, tp: 0, 14 RF f1 score: 0.571 RF cohens kappa score: 0.545 -> test with 'GB' GB tn, fp: 311, 21 GB fn, tp: 0, 14 GB f1 score: 0.571 GB cohens kappa score: 0.545 -> test with 'KNN' KNN tn, fp: 230, 102 KNN fn, tp: 0, 14 KNN f1 score: 0.215 KNN cohens kappa score: 0.154 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 170, 161 LR fn, tp: 2, 11 LR f1 score: 0.119 LR cohens kappa score: 0.052 LR average precision score: 0.063 -> test with 'RF' RF tn, fp: 310, 21 RF fn, tp: 0, 13 RF f1 score: 0.553 RF cohens kappa score: 0.527 -> test with 'GB' GB tn, fp: 310, 21 GB fn, tp: 0, 13 GB f1 score: 0.553 GB cohens kappa score: 0.527 -> test with 'KNN' KNN tn, fp: 244, 87 KNN fn, tp: 0, 13 KNN f1 score: 0.230 KNN cohens kappa score: 0.175 ====== Step 2/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 2/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 156, 176 LR fn, tp: 4, 10 LR f1 score: 0.100 LR cohens kappa score: 0.027 LR average precision score: 0.058 -> test with 'RF' RF tn, fp: 312, 20 RF fn, tp: 0, 14 RF f1 score: 0.583 RF cohens kappa score: 0.558 -> test with 'GB' GB tn, fp: 312, 20 GB fn, tp: 0, 14 GB f1 score: 0.583 GB cohens kappa score: 0.558 -> test with 'KNN' KNN tn, fp: 235, 97 KNN fn, tp: 0, 14 KNN f1 score: 0.224 KNN cohens kappa score: 0.164 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 161, 171 LR fn, tp: 3, 11 LR f1 score: 0.112 LR cohens kappa score: 0.040 LR average precision score: 0.067 -> test with 'RF' RF tn, fp: 316, 16 RF fn, tp: 0, 14 RF f1 score: 0.636 RF cohens kappa score: 0.615 -> test with 'GB' GB tn, fp: 316, 16 GB fn, tp: 0, 14 GB f1 score: 0.636 GB cohens kappa score: 0.615 -> test with 'KNN' KNN tn, fp: 246, 86 KNN fn, tp: 0, 14 KNN f1 score: 0.246 KNN cohens kappa score: 0.188 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 186, 146 LR fn, tp: 4, 10 LR f1 score: 0.118 LR cohens kappa score: 0.047 LR average precision score: 0.067 -> test with 'RF' RF tn, fp: 306, 26 RF fn, tp: 0, 14 RF f1 score: 0.519 RF cohens kappa score: 0.488 -> test with 'GB' GB tn, fp: 306, 26 GB fn, tp: 0, 14 GB f1 score: 0.519 GB cohens kappa score: 0.488 -> test with 'KNN' KNN tn, fp: 243, 89 KNN fn, tp: 0, 14 KNN f1 score: 0.239 KNN cohens kappa score: 0.181 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 172, 160 LR fn, tp: 5, 9 LR f1 score: 0.098 LR cohens kappa score: 0.026 LR average precision score: 0.050 -> test with 'RF' RF tn, fp: 296, 36 RF fn, tp: 0, 14 RF f1 score: 0.438 RF cohens kappa score: 0.400 -> test with 'GB' GB tn, fp: 296, 36 GB fn, tp: 0, 14 GB f1 score: 0.438 GB cohens kappa score: 0.400 -> test with 'KNN' KNN tn, fp: 212, 120 KNN fn, tp: 0, 14 KNN f1 score: 0.189 KNN cohens kappa score: 0.125 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 189, 142 LR fn, tp: 3, 10 LR f1 score: 0.121 LR cohens kappa score: 0.055 LR average precision score: 0.069 -> test with 'RF' RF tn, fp: 306, 25 RF fn, tp: 0, 13 RF f1 score: 0.510 RF cohens kappa score: 0.481 -> test with 'GB' GB tn, fp: 306, 25 GB fn, tp: 0, 13 GB f1 score: 0.510 GB cohens kappa score: 0.481 -> test with 'KNN' KNN tn, fp: 239, 92 KNN fn, tp: 0, 13 KNN f1 score: 0.220 KNN cohens kappa score: 0.164 ====== Step 3/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 3/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 171, 161 LR fn, tp: 3, 11 LR f1 score: 0.118 LR cohens kappa score: 0.047 LR average precision score: 0.063 -> test with 'RF' RF tn, fp: 306, 26 RF fn, tp: 0, 14 RF f1 score: 0.519 RF cohens kappa score: 0.488 -> test with 'GB' GB tn, fp: 306, 26 GB fn, tp: 0, 14 GB f1 score: 0.519 GB cohens kappa score: 0.488 -> test with 'KNN' KNN tn, fp: 226, 106 KNN fn, tp: 0, 14 KNN f1 score: 0.209 KNN cohens kappa score: 0.147 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 192, 140 LR fn, tp: 6, 8 LR f1 score: 0.099 LR cohens kappa score: 0.027 LR average precision score: 0.067 -> test with 'RF' RF tn, fp: 312, 20 RF fn, tp: 0, 14 RF f1 score: 0.583 RF cohens kappa score: 0.558 -> test with 'GB' GB tn, fp: 312, 20 GB fn, tp: 0, 14 GB f1 score: 0.583 GB cohens kappa score: 0.558 -> test with 'KNN' KNN tn, fp: 240, 92 KNN fn, tp: 0, 14 KNN f1 score: 0.233 KNN cohens kappa score: 0.174 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 164, 168 LR fn, tp: 5, 9 LR f1 score: 0.094 LR cohens kappa score: 0.021 LR average precision score: 0.057 -> test with 'RF' RF tn, fp: 308, 24 RF fn, tp: 0, 14 RF f1 score: 0.538 RF cohens kappa score: 0.509 -> test with 'GB' GB tn, fp: 308, 24 GB fn, tp: 0, 14 GB f1 score: 0.538 GB cohens kappa score: 0.509 -> test with 'KNN' KNN tn, fp: 243, 89 KNN fn, tp: 0, 14 KNN f1 score: 0.239 KNN cohens kappa score: 0.181 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 185, 147 LR fn, tp: 3, 11 LR f1 score: 0.128 LR cohens kappa score: 0.058 LR average precision score: 0.081 -> test with 'RF' RF tn, fp: 305, 27 RF fn, tp: 0, 14 RF f1 score: 0.509 RF cohens kappa score: 0.478 -> test with 'GB' GB tn, fp: 305, 27 GB fn, tp: 0, 14 GB f1 score: 0.509 GB cohens kappa score: 0.478 -> test with 'KNN' KNN tn, fp: 244, 88 KNN fn, tp: 0, 14 KNN f1 score: 0.241 KNN cohens kappa score: 0.183 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 172, 159 LR fn, tp: 5, 8 LR f1 score: 0.089 LR cohens kappa score: 0.020 LR average precision score: 0.058 -> test with 'RF' RF tn, fp: 305, 26 RF fn, tp: 0, 13 RF f1 score: 0.500 RF cohens kappa score: 0.470 -> test with 'GB' GB tn, fp: 305, 26 GB fn, tp: 0, 13 GB f1 score: 0.500 GB cohens kappa score: 0.470 -> test with 'KNN' KNN tn, fp: 212, 119 KNN fn, tp: 0, 13 KNN f1 score: 0.179 KNN cohens kappa score: 0.119 ====== Step 4/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 4/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 195, 137 LR fn, tp: 6, 8 LR f1 score: 0.101 LR cohens kappa score: 0.029 LR average precision score: 0.079 -> test with 'RF' RF tn, fp: 315, 17 RF fn, tp: 0, 14 RF f1 score: 0.622 RF cohens kappa score: 0.600 -> test with 'GB' GB tn, fp: 315, 17 GB fn, tp: 0, 14 GB f1 score: 0.622 GB cohens kappa score: 0.600 -> test with 'KNN' KNN tn, fp: 241, 91 KNN fn, tp: 0, 14 KNN f1 score: 0.235 KNN cohens kappa score: 0.176 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 171, 161 LR fn, tp: 4, 10 LR f1 score: 0.108 LR cohens kappa score: 0.036 LR average precision score: 0.063 -> test with 'RF' RF tn, fp: 304, 28 RF fn, tp: 0, 14 RF f1 score: 0.500 RF cohens kappa score: 0.468 -> test with 'GB' GB tn, fp: 304, 28 GB fn, tp: 0, 14 GB f1 score: 0.500 GB cohens kappa score: 0.468 -> test with 'KNN' KNN tn, fp: 224, 108 KNN fn, tp: 0, 14 KNN f1 score: 0.206 KNN cohens kappa score: 0.144 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 181, 151 LR fn, tp: 3, 11 LR f1 score: 0.125 LR cohens kappa score: 0.055 LR average precision score: 0.082 -> test with 'RF' RF tn, fp: 304, 28 RF fn, tp: 0, 14 RF f1 score: 0.500 RF cohens kappa score: 0.468 -> test with 'GB' GB tn, fp: 304, 28 GB fn, tp: 0, 14 GB f1 score: 0.500 GB cohens kappa score: 0.468 -> test with 'KNN' KNN tn, fp: 233, 99 KNN fn, tp: 0, 14 KNN f1 score: 0.220 KNN cohens kappa score: 0.160 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 179, 153 LR fn, tp: 5, 9 LR f1 score: 0.102 LR cohens kappa score: 0.030 LR average precision score: 0.053 -> test with 'RF' RF tn, fp: 308, 24 RF fn, tp: 0, 14 RF f1 score: 0.538 RF cohens kappa score: 0.509 -> test with 'GB' GB tn, fp: 308, 24 GB fn, tp: 0, 14 GB f1 score: 0.538 GB cohens kappa score: 0.509 -> test with 'KNN' KNN tn, fp: 241, 91 KNN fn, tp: 0, 14 KNN f1 score: 0.235 KNN cohens kappa score: 0.176 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 178, 153 LR fn, tp: 2, 11 LR f1 score: 0.124 LR cohens kappa score: 0.058 LR average precision score: 0.094 -> test with 'RF' RF tn, fp: 305, 26 RF fn, tp: 0, 13 RF f1 score: 0.500 RF cohens kappa score: 0.470 -> test with 'GB' GB tn, fp: 305, 26 GB fn, tp: 0, 13 GB f1 score: 0.500 GB cohens kappa score: 0.470 -> test with 'KNN' KNN tn, fp: 220, 111 KNN fn, tp: 0, 13 KNN f1 score: 0.190 KNN cohens kappa score: 0.130 ====== Step 5/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 5/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 174, 158 LR fn, tp: 4, 10 LR f1 score: 0.110 LR cohens kappa score: 0.038 LR average precision score: 0.056 -> test with 'RF' RF tn, fp: 303, 29 RF fn, tp: 0, 14 RF f1 score: 0.491 RF cohens kappa score: 0.458 -> test with 'GB' GB tn, fp: 303, 29 GB fn, tp: 0, 14 GB f1 score: 0.491 GB cohens kappa score: 0.458 -> test with 'KNN' KNN tn, fp: 236, 96 KNN fn, tp: 0, 14 KNN f1 score: 0.226 KNN cohens kappa score: 0.166 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 185, 147 LR fn, tp: 4, 10 LR f1 score: 0.117 LR cohens kappa score: 0.046 LR average precision score: 0.068 -> test with 'RF' RF tn, fp: 314, 18 RF fn, tp: 0, 14 RF f1 score: 0.609 RF cohens kappa score: 0.585 -> test with 'GB' GB tn, fp: 314, 18 GB fn, tp: 0, 14 GB f1 score: 0.609 GB cohens kappa score: 0.585 -> test with 'KNN' KNN tn, fp: 238, 94 KNN fn, tp: 0, 14 KNN f1 score: 0.230 KNN cohens kappa score: 0.170 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 166, 166 LR fn, tp: 4, 10 LR f1 score: 0.105 LR cohens kappa score: 0.033 LR average precision score: 0.091 -> test with 'RF' RF tn, fp: 301, 31 RF fn, tp: 0, 14 RF f1 score: 0.475 RF cohens kappa score: 0.440 -> test with 'GB' GB tn, fp: 301, 31 GB fn, tp: 0, 14 GB f1 score: 0.475 GB cohens kappa score: 0.440 -> test with 'KNN' KNN tn, fp: 223, 109 KNN fn, tp: 0, 14 KNN f1 score: 0.204 KNN cohens kappa score: 0.142 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 179, 153 LR fn, tp: 5, 9 LR f1 score: 0.102 LR cohens kappa score: 0.030 LR average precision score: 0.063 -> test with 'RF' RF tn, fp: 309, 23 RF fn, tp: 0, 14 RF f1 score: 0.549 RF cohens kappa score: 0.521 -> test with 'GB' GB tn, fp: 309, 23 GB fn, tp: 0, 14 GB f1 score: 0.549 GB cohens kappa score: 0.521 -> test with 'KNN' KNN tn, fp: 235, 97 KNN fn, tp: 0, 14 KNN f1 score: 0.224 KNN cohens kappa score: 0.164 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1272 synthetic samples -> test with 'LR' LR tn, fp: 169, 162 LR fn, tp: 4, 9 LR f1 score: 0.098 LR cohens kappa score: 0.030 LR average precision score: 0.104 -> test with 'RF' RF tn, fp: 309, 22 RF fn, tp: 0, 13 RF f1 score: 0.542 RF cohens kappa score: 0.515 -> test with 'GB' GB tn, fp: 309, 22 GB fn, tp: 0, 13 GB f1 score: 0.542 GB cohens kappa score: 0.515 -> test with 'KNN' KNN tn, fp: 235, 96 KNN fn, tp: 0, 13 KNN f1 score: 0.213 KNN cohens kappa score: 0.156 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 195, 183 LR fn, tp: 7, 13 LR f1 score: 0.133 LR cohens kappa score: 0.063 LR average precision score: 0.104 average: LR tn, fp: 175.32, 156.48 LR fn, tp: 3.96, 9.84 LR f1 score: 0.109 LR cohens kappa score: 0.038 LR average precision score: 0.069 minimum: LR tn, fp: 149, 137 LR fn, tp: 1, 7 LR f1 score: 0.080 LR cohens kappa score: 0.007 LR average precision score: 0.050 -----[ RF ]----- maximum: RF tn, fp: 316, 36 RF fn, tp: 0, 14 RF f1 score: 0.636 RF cohens kappa score: 0.615 average: RF tn, fp: 307.2, 24.6 RF fn, tp: 0.0, 13.8 RF f1 score: 0.533 RF cohens kappa score: 0.504 minimum: RF tn, fp: 296, 16 RF fn, tp: 0, 13 RF f1 score: 0.438 RF cohens kappa score: 0.400 -----[ GB ]----- maximum: GB tn, fp: 316, 36 GB fn, tp: 0, 14 GB f1 score: 0.636 GB cohens kappa score: 0.615 average: GB tn, fp: 307.2, 24.6 GB fn, tp: 0.0, 13.8 GB f1 score: 0.533 GB cohens kappa score: 0.504 minimum: GB tn, fp: 296, 16 GB fn, tp: 0, 13 GB f1 score: 0.438 GB cohens kappa score: 0.400 -----[ KNN ]----- maximum: KNN tn, fp: 246, 120 KNN fn, tp: 0, 14 KNN f1 score: 0.246 KNN cohens kappa score: 0.188 average: KNN tn, fp: 233.2, 98.6 KNN fn, tp: 0.0, 13.8 KNN f1 score: 0.220 KNN cohens kappa score: 0.160 minimum: KNN tn, fp: 212, 86 KNN fn, tp: 0, 13 KNN f1 score: 0.179 KNN cohens kappa score: 0.119