/////////////////////////////////////////// // Running ctGAN on folding_winequality-red-4 /////////////////////////////////////////// Load 'data_input/folding_winequality-red-4' 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 1194 synthetic samples -> test with 'LR' LR tn, fp: 247, 63 LR fn, tp: 9, 2 LR f1 score: 0.053 LR cohens kappa score: -0.006 LR average precision score: 0.039 -> test with 'RF' RF tn, fp: 296, 14 RF fn, tp: 10, 1 RF f1 score: 0.077 RF cohens kappa score: 0.039 -> test with 'GB' GB tn, fp: 303, 7 GB fn, tp: 10, 1 GB f1 score: 0.105 GB cohens kappa score: 0.079 -> test with 'KNN' KNN tn, fp: 290, 20 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.046 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 286, 24 LR fn, tp: 10, 1 LR f1 score: 0.056 LR cohens kappa score: 0.008 LR average precision score: 0.043 -> test with 'RF' RF tn, fp: 300, 10 RF fn, tp: 11, 0 RF f1 score: 0.000 RF cohens kappa score: -0.034 -> test with 'GB' GB tn, fp: 301, 9 GB fn, tp: 11, 0 GB f1 score: 0.000 GB cohens kappa score: -0.032 -> test with 'KNN' KNN tn, fp: 281, 29 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.052 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 261, 49 LR fn, tp: 8, 3 LR f1 score: 0.095 LR cohens kappa score: 0.041 LR average precision score: 0.059 -> test with 'RF' RF tn, fp: 304, 6 RF fn, tp: 9, 2 RF f1 score: 0.211 RF cohens kappa score: 0.187 -> test with 'GB' GB tn, fp: 303, 7 GB fn, tp: 9, 2 GB f1 score: 0.200 GB cohens kappa score: 0.175 -> test with 'KNN' KNN tn, fp: 289, 21 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.047 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 233, 77 LR fn, tp: 9, 2 LR f1 score: 0.044 LR cohens kappa score: -0.017 LR average precision score: 0.044 -> test with 'RF' RF tn, fp: 298, 12 RF fn, tp: 8, 3 RF f1 score: 0.231 RF cohens kappa score: 0.199 -> test with 'GB' GB tn, fp: 299, 11 GB fn, tp: 9, 2 GB f1 score: 0.167 GB cohens kappa score: 0.135 -> test with 'KNN' KNN tn, fp: 278, 32 KNN fn, tp: 8, 3 KNN f1 score: 0.130 KNN cohens kappa score: 0.083 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1196 synthetic samples -> test with 'LR' LR tn, fp: 263, 43 LR fn, tp: 5, 4 LR f1 score: 0.143 LR cohens kappa score: 0.100 LR average precision score: 0.102 -> test with 'RF' RF tn, fp: 302, 4 RF fn, tp: 8, 1 RF f1 score: 0.143 RF cohens kappa score: 0.125 -> test with 'GB' GB tn, fp: 301, 5 GB fn, tp: 8, 1 GB f1 score: 0.133 GB cohens kappa score: 0.113 -> test with 'KNN' KNN tn, fp: 297, 9 KNN fn, tp: 8, 1 KNN f1 score: 0.105 KNN cohens kappa score: 0.078 ====== Step 2/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 2/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 271, 39 LR fn, tp: 8, 3 LR f1 score: 0.113 LR cohens kappa score: 0.062 LR average precision score: 0.103 -> test with 'RF' RF tn, fp: 296, 14 RF fn, tp: 10, 1 RF f1 score: 0.077 RF cohens kappa score: 0.039 -> test with 'GB' GB tn, fp: 300, 10 GB fn, tp: 10, 1 GB f1 score: 0.091 GB cohens kappa score: 0.059 -> test with 'KNN' KNN tn, fp: 288, 22 KNN fn, tp: 10, 1 KNN f1 score: 0.059 KNN cohens kappa score: 0.013 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 242, 68 LR fn, tp: 8, 3 LR f1 score: 0.073 LR cohens kappa score: 0.015 LR average precision score: 0.050 -> test with 'RF' RF tn, fp: 294, 16 RF fn, tp: 9, 2 RF f1 score: 0.138 RF cohens kappa score: 0.100 -> test with 'GB' GB tn, fp: 303, 7 GB fn, tp: 10, 1 GB f1 score: 0.105 GB cohens kappa score: 0.079 -> test with 'KNN' KNN tn, fp: 294, 16 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.042 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 255, 55 LR fn, tp: 4, 7 LR f1 score: 0.192 LR cohens kappa score: 0.142 LR average precision score: 0.148 -> test with 'RF' RF tn, fp: 303, 7 RF fn, tp: 11, 0 RF f1 score: 0.000 RF cohens kappa score: -0.027 -> test with 'GB' GB tn, fp: 306, 4 GB fn, tp: 11, 0 GB f1 score: 0.000 GB cohens kappa score: -0.019 -> test with 'KNN' KNN tn, fp: 280, 30 KNN fn, tp: 9, 2 KNN f1 score: 0.093 KNN cohens kappa score: 0.044 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 250, 60 LR fn, tp: 5, 6 LR f1 score: 0.156 LR cohens kappa score: 0.103 LR average precision score: 0.101 -> test with 'RF' RF tn, fp: 298, 12 RF fn, tp: 7, 4 RF f1 score: 0.296 RF cohens kappa score: 0.267 -> test with 'GB' GB tn, fp: 301, 9 GB fn, tp: 8, 3 GB f1 score: 0.261 GB cohens kappa score: 0.233 -> test with 'KNN' KNN tn, fp: 290, 20 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.046 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1196 synthetic samples -> test with 'LR' LR tn, fp: 240, 66 LR fn, tp: 5, 4 LR f1 score: 0.101 LR cohens kappa score: 0.053 LR average precision score: 0.045 -> test with 'RF' RF tn, fp: 289, 17 RF fn, tp: 8, 1 RF f1 score: 0.074 RF cohens kappa score: 0.037 -> test with 'GB' GB tn, fp: 299, 7 GB fn, tp: 8, 1 GB f1 score: 0.118 GB cohens kappa score: 0.093 -> test with 'KNN' KNN tn, fp: 273, 33 KNN fn, tp: 8, 1 KNN f1 score: 0.047 KNN cohens kappa score: 0.001 ====== Step 3/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 3/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 248, 62 LR fn, tp: 11, 0 LR f1 score: 0.000 LR cohens kappa score: -0.062 LR average precision score: 0.026 -> test with 'RF' RF tn, fp: 304, 6 RF fn, tp: 11, 0 RF f1 score: 0.000 RF cohens kappa score: -0.025 -> test with 'GB' GB tn, fp: 308, 2 GB fn, tp: 11, 0 GB f1 score: 0.000 GB cohens kappa score: -0.011 -> test with 'KNN' KNN tn, fp: 295, 15 KNN fn, tp: 10, 1 KNN f1 score: 0.074 KNN cohens kappa score: 0.035 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 237, 73 LR fn, tp: 3, 8 LR f1 score: 0.174 LR cohens kappa score: 0.121 LR average precision score: 0.104 -> test with 'RF' RF tn, fp: 297, 13 RF fn, tp: 9, 2 RF f1 score: 0.154 RF cohens kappa score: 0.119 -> test with 'GB' GB tn, fp: 301, 9 GB fn, tp: 9, 2 GB f1 score: 0.182 GB cohens kappa score: 0.153 -> test with 'KNN' KNN tn, fp: 286, 24 KNN fn, tp: 9, 2 KNN f1 score: 0.108 KNN cohens kappa score: 0.063 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 219, 91 LR fn, tp: 9, 2 LR f1 score: 0.038 LR cohens kappa score: -0.024 LR average precision score: 0.037 -> test with 'RF' RF tn, fp: 299, 11 RF fn, tp: 10, 1 RF f1 score: 0.087 RF cohens kappa score: 0.053 -> test with 'GB' GB tn, fp: 300, 10 GB fn, tp: 11, 0 GB f1 score: 0.000 GB cohens kappa score: -0.034 -> test with 'KNN' KNN tn, fp: 287, 23 KNN fn, tp: 9, 2 KNN f1 score: 0.111 KNN cohens kappa score: 0.067 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 263, 47 LR fn, tp: 7, 4 LR f1 score: 0.129 LR cohens kappa score: 0.077 LR average precision score: 0.111 -> test with 'RF' RF tn, fp: 303, 7 RF fn, tp: 10, 1 RF f1 score: 0.105 RF cohens kappa score: 0.079 -> test with 'GB' GB tn, fp: 303, 7 GB fn, tp: 10, 1 GB f1 score: 0.105 GB cohens kappa score: 0.079 -> test with 'KNN' KNN tn, fp: 284, 26 KNN fn, tp: 10, 1 KNN f1 score: 0.053 KNN cohens kappa score: 0.004 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1196 synthetic samples -> test with 'LR' LR tn, fp: 215, 91 LR fn, tp: 3, 6 LR f1 score: 0.113 LR cohens kappa score: 0.064 LR average precision score: 0.085 -> test with 'RF' RF tn, fp: 301, 5 RF fn, tp: 7, 2 RF f1 score: 0.250 RF cohens kappa score: 0.231 -> test with 'GB' GB tn, fp: 300, 6 GB fn, tp: 8, 1 GB f1 score: 0.125 GB cohens kappa score: 0.103 -> test with 'KNN' KNN tn, fp: 285, 21 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.042 ====== Step 4/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 4/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 300, 10 LR fn, tp: 7, 4 LR f1 score: 0.320 LR cohens kappa score: 0.293 LR average precision score: 0.305 -> test with 'RF' RF tn, fp: 306, 4 RF fn, tp: 9, 2 RF f1 score: 0.235 RF cohens kappa score: 0.216 -> test with 'GB' GB tn, fp: 306, 4 GB fn, tp: 10, 1 GB f1 score: 0.125 GB cohens kappa score: 0.106 -> test with 'KNN' KNN tn, fp: 279, 31 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.053 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 267, 43 LR fn, tp: 8, 3 LR f1 score: 0.105 LR cohens kappa score: 0.053 LR average precision score: 0.061 -> test with 'RF' RF tn, fp: 306, 4 RF fn, tp: 11, 0 RF f1 score: 0.000 RF cohens kappa score: -0.019 -> test with 'GB' GB tn, fp: 303, 7 GB fn, tp: 9, 2 GB f1 score: 0.200 GB cohens kappa score: 0.175 -> test with 'KNN' KNN tn, fp: 286, 24 KNN fn, tp: 9, 2 KNN f1 score: 0.108 KNN cohens kappa score: 0.063 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 300, 10 LR fn, tp: 10, 1 LR f1 score: 0.091 LR cohens kappa score: 0.059 LR average precision score: 0.168 -> test with 'RF' RF tn, fp: 303, 7 RF fn, tp: 9, 2 RF f1 score: 0.200 RF cohens kappa score: 0.175 -> test with 'GB' GB tn, fp: 302, 8 GB fn, tp: 9, 2 GB f1 score: 0.190 GB cohens kappa score: 0.163 -> test with 'KNN' KNN tn, fp: 290, 20 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.046 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 240, 70 LR fn, tp: 3, 8 LR f1 score: 0.180 LR cohens kappa score: 0.127 LR average precision score: 0.146 -> test with 'RF' RF tn, fp: 295, 15 RF fn, tp: 9, 2 RF f1 score: 0.143 RF cohens kappa score: 0.106 -> test with 'GB' GB tn, fp: 294, 16 GB fn, tp: 10, 1 GB f1 score: 0.071 GB cohens kappa score: 0.031 -> test with 'KNN' KNN tn, fp: 295, 15 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.041 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1196 synthetic samples -> test with 'LR' LR tn, fp: 267, 39 LR fn, tp: 7, 2 LR f1 score: 0.080 LR cohens kappa score: 0.035 LR average precision score: 0.060 -> test with 'RF' RF tn, fp: 287, 19 RF fn, tp: 7, 2 RF f1 score: 0.133 RF cohens kappa score: 0.097 -> test with 'GB' GB tn, fp: 289, 17 GB fn, tp: 8, 1 GB f1 score: 0.074 GB cohens kappa score: 0.037 -> test with 'KNN' KNN tn, fp: 282, 24 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.043 ====== Step 5/5 ======= -> Shuffling data -> Spliting data to slices ------ Step 5/5: Slice 1/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 270, 40 LR fn, tp: 8, 3 LR f1 score: 0.111 LR cohens kappa score: 0.060 LR average precision score: 0.164 -> test with 'RF' RF tn, fp: 295, 15 RF fn, tp: 10, 1 RF f1 score: 0.074 RF cohens kappa score: 0.035 -> test with 'GB' GB tn, fp: 303, 7 GB fn, tp: 10, 1 GB f1 score: 0.105 GB cohens kappa score: 0.079 -> test with 'KNN' KNN tn, fp: 293, 17 KNN fn, tp: 9, 2 KNN f1 score: 0.133 KNN cohens kappa score: 0.094 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 291, 19 LR fn, tp: 11, 0 LR f1 score: 0.000 LR cohens kappa score: -0.045 LR average precision score: 0.060 -> test with 'RF' RF tn, fp: 301, 9 RF fn, tp: 10, 1 RF f1 score: 0.095 RF cohens kappa score: 0.065 -> test with 'GB' GB tn, fp: 306, 4 GB fn, tp: 10, 1 GB f1 score: 0.125 GB cohens kappa score: 0.106 -> test with 'KNN' KNN tn, fp: 292, 18 KNN fn, tp: 9, 2 KNN f1 score: 0.129 KNN cohens kappa score: 0.089 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 267, 43 LR fn, tp: 10, 1 LR f1 score: 0.036 LR cohens kappa score: -0.020 LR average precision score: 0.057 -> test with 'RF' RF tn, fp: 294, 16 RF fn, tp: 8, 3 RF f1 score: 0.200 RF cohens kappa score: 0.164 -> test with 'GB' GB tn, fp: 301, 9 GB fn, tp: 10, 1 GB f1 score: 0.095 GB cohens kappa score: 0.065 -> test with 'KNN' KNN tn, fp: 288, 22 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.048 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1194 synthetic samples -> test with 'LR' LR tn, fp: 270, 40 LR fn, tp: 8, 3 LR f1 score: 0.111 LR cohens kappa score: 0.060 LR average precision score: 0.076 -> test with 'RF' RF tn, fp: 294, 16 RF fn, tp: 7, 4 RF f1 score: 0.258 RF cohens kappa score: 0.224 -> test with 'GB' GB tn, fp: 298, 12 GB fn, tp: 8, 3 GB f1 score: 0.231 GB cohens kappa score: 0.199 -> test with 'KNN' KNN tn, fp: 288, 22 KNN fn, tp: 11, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.048 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples -> create 1196 synthetic samples -> test with 'LR' LR tn, fp: 290, 16 LR fn, tp: 6, 3 LR f1 score: 0.214 LR cohens kappa score: 0.183 LR average precision score: 0.134 -> test with 'RF' RF tn, fp: 299, 7 RF fn, tp: 8, 1 RF f1 score: 0.118 RF cohens kappa score: 0.093 -> test with 'GB' GB tn, fp: 302, 4 GB fn, tp: 9, 0 GB f1 score: 0.000 GB cohens kappa score: -0.018 -> test with 'KNN' KNN tn, fp: 291, 15 KNN fn, tp: 9, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.037 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 300, 91 LR fn, tp: 11, 8 LR f1 score: 0.320 LR cohens kappa score: 0.293 LR average precision score: 0.305 average: LR tn, fp: 259.68, 49.52 LR fn, tp: 7.28, 3.32 LR f1 score: 0.109 LR cohens kappa score: 0.059 LR average precision score: 0.093 minimum: LR tn, fp: 215, 10 LR fn, tp: 3, 0 LR f1 score: 0.000 LR cohens kappa score: -0.062 LR average precision score: 0.026 -----[ RF ]----- maximum: RF tn, fp: 306, 19 RF fn, tp: 11, 4 RF f1 score: 0.296 RF cohens kappa score: 0.267 average: RF tn, fp: 298.56, 10.64 RF fn, tp: 9.04, 1.56 RF f1 score: 0.132 RF cohens kappa score: 0.102 minimum: RF tn, fp: 287, 4 RF fn, tp: 7, 0 RF f1 score: 0.000 RF cohens kappa score: -0.034 -----[ GB ]----- maximum: GB tn, fp: 308, 17 GB fn, tp: 11, 3 GB f1 score: 0.261 GB cohens kappa score: 0.233 average: GB tn, fp: 301.28, 7.92 GB fn, tp: 9.44, 1.16 GB f1 score: 0.112 GB cohens kappa score: 0.086 minimum: GB tn, fp: 289, 2 GB fn, tp: 8, 0 GB f1 score: 0.000 GB cohens kappa score: -0.034 -----[ KNN ]----- maximum: KNN tn, fp: 297, 33 KNN fn, tp: 11, 3 KNN f1 score: 0.133 KNN cohens kappa score: 0.094 average: KNN tn, fp: 287.24, 21.96 KNN fn, tp: 9.8, 0.8 KNN f1 score: 0.046 KNN cohens kappa score: 0.002 minimum: KNN tn, fp: 273, 9 KNN fn, tp: 8, 0 KNN f1 score: 0.000 KNN cohens kappa score: -0.053