/////////////////////////////////////////// // Running convGAN-majority-5 on imblearn_ozone_level /////////////////////////////////////////// Load 'data_input/imblearn_ozone_level' from imblearn 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 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 475, 18 GAN fn, tp: 8, 7 GAN f1 score: 0.350 GAN cohens kappa score: 0.325 -> test with 'LR' LR tn, fp: 422, 71 LR fn, tp: 2, 13 LR f1 score: 0.263 LR cohens kappa score: 0.224 LR average precision score: 0.331 -> test with 'GB' GB tn, fp: 477, 16 GB fn, tp: 8, 7 GB f1 score: 0.368 GB cohens kappa score: 0.345 -> test with 'KNN' KNN tn, fp: 405, 88 KNN fn, tp: 9, 6 KNN f1 score: 0.110 KNN cohens kappa score: 0.062 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 247, 246 GAN fn, tp: 2, 13 GAN f1 score: 0.095 GAN cohens kappa score: 0.041 -> test with 'LR' LR tn, fp: 433, 60 LR fn, tp: 5, 10 LR f1 score: 0.235 LR cohens kappa score: 0.196 LR average precision score: 0.219 -> test with 'GB' GB tn, fp: 483, 10 GB fn, tp: 8, 7 GB f1 score: 0.437 GB cohens kappa score: 0.419 -> test with 'KNN' KNN tn, fp: 407, 86 KNN fn, tp: 7, 8 KNN f1 score: 0.147 KNN cohens kappa score: 0.101 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 412, 81 GAN fn, tp: 3, 12 GAN f1 score: 0.222 GAN cohens kappa score: 0.181 -> test with 'LR' LR tn, fp: 433, 60 LR fn, tp: 4, 11 LR f1 score: 0.256 LR cohens kappa score: 0.218 LR average precision score: 0.123 -> test with 'GB' GB tn, fp: 476, 17 GB fn, tp: 8, 7 GB f1 score: 0.359 GB cohens kappa score: 0.335 -> test with 'KNN' KNN tn, fp: 426, 67 KNN fn, tp: 11, 4 KNN f1 score: 0.093 KNN cohens kappa score: 0.047 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 338, 155 GAN fn, tp: 3, 12 GAN f1 score: 0.132 GAN cohens kappa score: 0.082 -> test with 'LR' LR tn, fp: 432, 61 LR fn, tp: 5, 10 LR f1 score: 0.233 LR cohens kappa score: 0.193 LR average precision score: 0.208 -> test with 'GB' GB tn, fp: 483, 10 GB fn, tp: 10, 5 GB f1 score: 0.333 GB cohens kappa score: 0.313 -> test with 'KNN' KNN tn, fp: 406, 87 KNN fn, tp: 9, 6 KNN f1 score: 0.111 KNN cohens kappa score: 0.063 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 466, 25 GAN fn, tp: 8, 5 GAN f1 score: 0.233 GAN cohens kappa score: 0.204 -> test with 'LR' LR tn, fp: 431, 60 LR fn, tp: 3, 10 LR f1 score: 0.241 LR cohens kappa score: 0.206 LR average precision score: 0.134 -> test with 'GB' GB tn, fp: 479, 12 GB fn, tp: 10, 3 GB f1 score: 0.214 GB cohens kappa score: 0.192 -> test with 'KNN' KNN tn, fp: 382, 109 KNN fn, tp: 8, 5 KNN f1 score: 0.079 KNN cohens kappa score: 0.034 ====== Step 2/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 2/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 433, 60 GAN fn, tp: 6, 9 GAN f1 score: 0.214 GAN cohens kappa score: 0.174 -> test with 'LR' LR tn, fp: 422, 71 LR fn, tp: 5, 10 LR f1 score: 0.208 LR cohens kappa score: 0.167 LR average precision score: 0.273 -> test with 'GB' GB tn, fp: 482, 11 GB fn, tp: 12, 3 GB f1 score: 0.207 GB cohens kappa score: 0.184 -> test with 'KNN' KNN tn, fp: 402, 91 KNN fn, tp: 9, 6 KNN f1 score: 0.107 KNN cohens kappa score: 0.059 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 416, 77 GAN fn, tp: 4, 11 GAN f1 score: 0.214 GAN cohens kappa score: 0.172 -> test with 'LR' LR tn, fp: 448, 45 LR fn, tp: 5, 10 LR f1 score: 0.286 LR cohens kappa score: 0.251 LR average precision score: 0.237 -> test with 'GB' GB tn, fp: 479, 14 GB fn, tp: 8, 7 GB f1 score: 0.389 GB cohens kappa score: 0.367 -> test with 'KNN' KNN tn, fp: 366, 127 KNN fn, tp: 4, 11 KNN f1 score: 0.144 KNN cohens kappa score: 0.096 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 349, 144 GAN fn, tp: 2, 13 GAN f1 score: 0.151 GAN cohens kappa score: 0.103 -> test with 'LR' LR tn, fp: 423, 70 LR fn, tp: 1, 14 LR f1 score: 0.283 LR cohens kappa score: 0.245 LR average precision score: 0.423 -> test with 'GB' GB tn, fp: 484, 9 GB fn, tp: 7, 8 GB f1 score: 0.500 GB cohens kappa score: 0.484 -> test with 'KNN' KNN tn, fp: 435, 58 KNN fn, tp: 13, 2 KNN f1 score: 0.053 KNN cohens kappa score: 0.006 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 213, 280 GAN fn, tp: 2, 13 GAN f1 score: 0.084 GAN cohens kappa score: 0.030 -> test with 'LR' LR tn, fp: 433, 60 LR fn, tp: 5, 10 LR f1 score: 0.235 LR cohens kappa score: 0.196 LR average precision score: 0.174 -> test with 'GB' GB tn, fp: 475, 18 GB fn, tp: 9, 6 GB f1 score: 0.308 GB cohens kappa score: 0.282 -> test with 'KNN' KNN tn, fp: 414, 79 KNN fn, tp: 10, 5 KNN f1 score: 0.101 KNN cohens kappa score: 0.054 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 233, 258 GAN fn, tp: 0, 13 GAN f1 score: 0.092 GAN cohens kappa score: 0.045 -> test with 'LR' LR tn, fp: 416, 75 LR fn, tp: 3, 10 LR f1 score: 0.204 LR cohens kappa score: 0.167 LR average precision score: 0.205 -> test with 'GB' GB tn, fp: 479, 12 GB fn, tp: 7, 6 GB f1 score: 0.387 GB cohens kappa score: 0.368 -> test with 'KNN' KNN tn, fp: 431, 60 KNN fn, tp: 7, 6 KNN f1 score: 0.152 KNN cohens kappa score: 0.114 ====== Step 3/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 3/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 324, 169 GAN fn, tp: 3, 12 GAN f1 score: 0.122 GAN cohens kappa score: 0.072 -> test with 'LR' LR tn, fp: 425, 68 LR fn, tp: 3, 12 LR f1 score: 0.253 LR cohens kappa score: 0.214 LR average precision score: 0.336 -> test with 'GB' GB tn, fp: 472, 21 GB fn, tp: 9, 6 GB f1 score: 0.286 GB cohens kappa score: 0.258 -> test with 'KNN' KNN tn, fp: 418, 75 KNN fn, tp: 12, 3 KNN f1 score: 0.065 KNN cohens kappa score: 0.016 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 369, 124 GAN fn, tp: 3, 12 GAN f1 score: 0.159 GAN cohens kappa score: 0.112 -> test with 'LR' LR tn, fp: 428, 65 LR fn, tp: 3, 12 LR f1 score: 0.261 LR cohens kappa score: 0.222 LR average precision score: 0.131 -> test with 'GB' GB tn, fp: 477, 16 GB fn, tp: 7, 8 GB f1 score: 0.410 GB cohens kappa score: 0.388 -> test with 'KNN' KNN tn, fp: 413, 80 KNN fn, tp: 10, 5 KNN f1 score: 0.100 KNN cohens kappa score: 0.052 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 475, 18 GAN fn, tp: 9, 6 GAN f1 score: 0.308 GAN cohens kappa score: 0.282 -> test with 'LR' LR tn, fp: 446, 47 LR fn, tp: 4, 11 LR f1 score: 0.301 LR cohens kappa score: 0.267 LR average precision score: 0.181 -> test with 'GB' GB tn, fp: 481, 12 GB fn, tp: 8, 7 GB f1 score: 0.412 GB cohens kappa score: 0.392 -> test with 'KNN' KNN tn, fp: 396, 97 KNN fn, tp: 9, 6 KNN f1 score: 0.102 KNN cohens kappa score: 0.053 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 287, 206 GAN fn, tp: 2, 13 GAN f1 score: 0.111 GAN cohens kappa score: 0.059 -> test with 'LR' LR tn, fp: 428, 65 LR fn, tp: 5, 10 LR f1 score: 0.222 LR cohens kappa score: 0.182 LR average precision score: 0.161 -> test with 'GB' GB tn, fp: 480, 13 GB fn, tp: 8, 7 GB f1 score: 0.400 GB cohens kappa score: 0.379 -> test with 'KNN' KNN tn, fp: 400, 93 KNN fn, tp: 9, 6 KNN f1 score: 0.105 KNN cohens kappa score: 0.057 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 474, 17 GAN fn, tp: 8, 5 GAN f1 score: 0.286 GAN cohens kappa score: 0.262 -> test with 'LR' LR tn, fp: 421, 70 LR fn, tp: 3, 10 LR f1 score: 0.215 LR cohens kappa score: 0.179 LR average precision score: 0.362 -> test with 'GB' GB tn, fp: 478, 13 GB fn, tp: 8, 5 GB f1 score: 0.323 GB cohens kappa score: 0.302 -> test with 'KNN' KNN tn, fp: 425, 66 KNN fn, tp: 9, 4 KNN f1 score: 0.096 KNN cohens kappa score: 0.055 ====== Step 4/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 4/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 208, 285 GAN fn, tp: 1, 14 GAN f1 score: 0.089 GAN cohens kappa score: 0.035 -> test with 'LR' LR tn, fp: 423, 70 LR fn, tp: 4, 11 LR f1 score: 0.229 LR cohens kappa score: 0.189 LR average precision score: 0.276 -> test with 'GB' GB tn, fp: 476, 17 GB fn, tp: 9, 6 GB f1 score: 0.316 GB cohens kappa score: 0.290 -> test with 'KNN' KNN tn, fp: 417, 76 KNN fn, tp: 11, 4 KNN f1 score: 0.084 KNN cohens kappa score: 0.036 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 343, 150 GAN fn, tp: 2, 13 GAN f1 score: 0.146 GAN cohens kappa score: 0.097 -> test with 'LR' LR tn, fp: 435, 58 LR fn, tp: 3, 12 LR f1 score: 0.282 LR cohens kappa score: 0.246 LR average precision score: 0.237 -> test with 'GB' GB tn, fp: 485, 8 GB fn, tp: 10, 5 GB f1 score: 0.357 GB cohens kappa score: 0.339 -> test with 'KNN' KNN tn, fp: 444, 49 KNN fn, tp: 11, 4 KNN f1 score: 0.118 KNN cohens kappa score: 0.075 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 271, 222 GAN fn, tp: 2, 13 GAN f1 score: 0.104 GAN cohens kappa score: 0.051 -> test with 'LR' LR tn, fp: 435, 58 LR fn, tp: 3, 12 LR f1 score: 0.282 LR cohens kappa score: 0.246 LR average precision score: 0.197 -> test with 'GB' GB tn, fp: 481, 12 GB fn, tp: 8, 7 GB f1 score: 0.412 GB cohens kappa score: 0.392 -> test with 'KNN' KNN tn, fp: 424, 69 KNN fn, tp: 11, 4 KNN f1 score: 0.091 KNN cohens kappa score: 0.044 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 333, 160 GAN fn, tp: 4, 11 GAN f1 score: 0.118 GAN cohens kappa score: 0.068 -> test with 'LR' LR tn, fp: 426, 67 LR fn, tp: 3, 12 LR f1 score: 0.255 LR cohens kappa score: 0.216 LR average precision score: 0.280 -> test with 'GB' GB tn, fp: 479, 14 GB fn, tp: 7, 8 GB f1 score: 0.432 GB cohens kappa score: 0.412 -> test with 'KNN' KNN tn, fp: 383, 110 KNN fn, tp: 9, 6 KNN f1 score: 0.092 KNN cohens kappa score: 0.041 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 418, 73 GAN fn, tp: 5, 8 GAN f1 score: 0.170 GAN cohens kappa score: 0.132 -> test with 'LR' LR tn, fp: 423, 68 LR fn, tp: 4, 9 LR f1 score: 0.200 LR cohens kappa score: 0.163 LR average precision score: 0.183 -> test with 'GB' GB tn, fp: 471, 20 GB fn, tp: 7, 6 GB f1 score: 0.308 GB cohens kappa score: 0.283 -> test with 'KNN' KNN tn, fp: 385, 106 KNN fn, tp: 6, 7 KNN f1 score: 0.111 KNN cohens kappa score: 0.068 ====== Step 5/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 5/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 310, 183 GAN fn, tp: 0, 15 GAN f1 score: 0.141 GAN cohens kappa score: 0.091 -> test with 'LR' LR tn, fp: 438, 55 LR fn, tp: 2, 13 LR f1 score: 0.313 LR cohens kappa score: 0.278 LR average precision score: 0.269 -> test with 'GB' GB tn, fp: 480, 13 GB fn, tp: 5, 10 GB f1 score: 0.526 GB cohens kappa score: 0.509 -> test with 'KNN' KNN tn, fp: 398, 95 KNN fn, tp: 10, 5 KNN f1 score: 0.087 KNN cohens kappa score: 0.038 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 459, 34 GAN fn, tp: 7, 8 GAN f1 score: 0.281 GAN cohens kappa score: 0.248 -> test with 'LR' LR tn, fp: 430, 63 LR fn, tp: 3, 12 LR f1 score: 0.267 LR cohens kappa score: 0.229 LR average precision score: 0.158 -> test with 'GB' GB tn, fp: 479, 14 GB fn, tp: 10, 5 GB f1 score: 0.294 GB cohens kappa score: 0.270 -> test with 'KNN' KNN tn, fp: 401, 92 KNN fn, tp: 12, 3 KNN f1 score: 0.055 KNN cohens kappa score: 0.004 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 408, 85 GAN fn, tp: 5, 10 GAN f1 score: 0.182 GAN cohens kappa score: 0.138 -> test with 'LR' LR tn, fp: 455, 38 LR fn, tp: 7, 8 LR f1 score: 0.262 LR cohens kappa score: 0.228 LR average precision score: 0.179 -> test with 'GB' GB tn, fp: 481, 12 GB fn, tp: 11, 4 GB f1 score: 0.258 GB cohens kappa score: 0.235 -> test with 'KNN' KNN tn, fp: 374, 119 KNN fn, tp: 6, 9 KNN f1 score: 0.126 KNN cohens kappa score: 0.077 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 490, 3 GAN fn, tp: 14, 1 GAN f1 score: 0.105 GAN cohens kappa score: 0.094 -> test with 'LR' LR tn, fp: 422, 71 LR fn, tp: 2, 13 LR f1 score: 0.263 LR cohens kappa score: 0.224 LR average precision score: 0.232 -> test with 'GB' GB tn, fp: 478, 15 GB fn, tp: 7, 8 GB f1 score: 0.421 GB cohens kappa score: 0.400 -> test with 'KNN' KNN tn, fp: 432, 61 KNN fn, tp: 10, 5 KNN f1 score: 0.123 KNN cohens kappa score: 0.079 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1912 synthetic samples -> test with GAN.predict GAN tn, fp: 245, 246 GAN fn, tp: 1, 12 GAN f1 score: 0.089 GAN cohens kappa score: 0.041 -> test with 'LR' LR tn, fp: 419, 72 LR fn, tp: 2, 11 LR f1 score: 0.229 LR cohens kappa score: 0.193 LR average precision score: 0.270 -> test with 'GB' GB tn, fp: 480, 11 GB fn, tp: 8, 5 GB f1 score: 0.345 GB cohens kappa score: 0.326 -> test with 'KNN' KNN tn, fp: 369, 122 KNN fn, tp: 8, 5 KNN f1 score: 0.071 KNN cohens kappa score: 0.026 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 455, 75 LR fn, tp: 7, 14 LR f1 score: 0.313 LR cohens kappa score: 0.278 LR average precision score: 0.423 average: LR tn, fp: 429.88, 62.72 LR fn, tp: 3.56, 11.04 LR f1 score: 0.251 LR cohens kappa score: 0.214 LR average precision score: 0.231 minimum: LR tn, fp: 416, 38 LR fn, tp: 1, 8 LR f1 score: 0.200 LR cohens kappa score: 0.163 LR average precision score: 0.123 -----[ GB ]----- maximum: GB tn, fp: 485, 21 GB fn, tp: 12, 10 GB f1 score: 0.526 GB cohens kappa score: 0.509 average: GB tn, fp: 479.0, 13.6 GB fn, tp: 8.36, 6.24 GB f1 score: 0.360 GB cohens kappa score: 0.338 minimum: GB tn, fp: 471, 8 GB fn, tp: 5, 3 GB f1 score: 0.207 GB cohens kappa score: 0.184 -----[ KNN ]----- maximum: KNN tn, fp: 444, 127 KNN fn, tp: 13, 11 KNN f1 score: 0.152 KNN cohens kappa score: 0.114 average: KNN tn, fp: 406.12, 86.48 KNN fn, tp: 9.2, 5.4 KNN f1 score: 0.101 KNN cohens kappa score: 0.054 minimum: KNN tn, fp: 366, 49 KNN fn, tp: 4, 2 KNN f1 score: 0.053 KNN cohens kappa score: 0.004 -----[ GAN ]----- maximum: GAN tn, fp: 490, 285 GAN fn, tp: 14, 15 GAN f1 score: 0.350 GAN cohens kappa score: 0.325 average: GAN tn, fp: 359.84, 132.76 GAN fn, tp: 4.16, 10.44 GAN f1 score: 0.168 GAN cohens kappa score: 0.125 minimum: GAN tn, fp: 208, 3 GAN fn, tp: 0, 1 GAN f1 score: 0.084 GAN cohens kappa score: 0.030