/////////////////////////////////////////// // Running SimpleGAN on folding_kr-vs-k-three_vs_eleven /////////////////////////////////////////// Load 'data_input/folding_kr-vs-k-three_vs_eleven' 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 2219 synthetic samples -> test with 'LR' LR tn, fp: 570, 1 LR fn, tp: 0, 17 LR f1 score: 0.971 LR cohens kappa score: 0.971 LR average precision score: 0.997 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 1, 16 KNN f1 score: 0.970 KNN cohens kappa score: 0.969 ------ Step 1/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 571, 0 LR fn, tp: 1, 16 LR f1 score: 0.970 LR cohens kappa score: 0.969 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 1, 16 KNN f1 score: 0.970 KNN cohens kappa score: 0.969 ------ Step 1/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 571, 0 LR fn, tp: 0, 17 LR f1 score: 1.000 LR cohens kappa score: 1.000 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 1, 16 KNN f1 score: 0.970 KNN cohens kappa score: 0.969 ------ Step 1/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 568, 3 LR fn, tp: 1, 16 LR f1 score: 0.889 LR cohens kappa score: 0.885 LR average precision score: 0.964 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 2, 15 KNN f1 score: 0.938 KNN cohens kappa score: 0.936 ------ Step 1/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2216 synthetic samples -> test with 'LR' LR tn, fp: 566, 4 LR fn, tp: 0, 13 LR f1 score: 0.867 LR cohens kappa score: 0.863 LR average precision score: 0.867 -> test with 'GB' GB tn, fp: 570, 0 GB fn, tp: 0, 13 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 568, 2 KNN fn, tp: 2, 11 KNN f1 score: 0.846 KNN cohens kappa score: 0.843 ====== 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 2219 synthetic samples -> test with 'LR' LR tn, fp: 571, 0 LR fn, tp: 0, 17 LR f1 score: 1.000 LR cohens kappa score: 1.000 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 2, 15 KNN f1 score: 0.938 KNN cohens kappa score: 0.936 ------ Step 2/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 569, 2 LR fn, tp: 2, 15 LR f1 score: 0.882 LR cohens kappa score: 0.879 LR average precision score: 0.982 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 0, 17 KNN f1 score: 1.000 KNN cohens kappa score: 1.000 ------ Step 2/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 570, 1 LR fn, tp: 2, 15 LR f1 score: 0.909 LR cohens kappa score: 0.906 LR average precision score: 0.979 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 3, 14 KNN f1 score: 0.903 KNN cohens kappa score: 0.901 ------ Step 2/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 571, 0 LR fn, tp: 0, 17 LR f1 score: 1.000 LR cohens kappa score: 1.000 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 3, 14 KNN f1 score: 0.903 KNN cohens kappa score: 0.901 ------ Step 2/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2216 synthetic samples -> test with 'LR' LR tn, fp: 567, 3 LR fn, tp: 1, 12 LR f1 score: 0.857 LR cohens kappa score: 0.854 LR average precision score: 0.979 -> test with 'GB' GB tn, fp: 570, 0 GB fn, tp: 0, 13 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 569, 1 KNN fn, tp: 0, 13 KNN f1 score: 0.963 KNN cohens kappa score: 0.962 ====== 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 2219 synthetic samples -> test with 'LR' LR tn, fp: 570, 1 LR fn, tp: 0, 17 LR f1 score: 0.971 LR cohens kappa score: 0.971 LR average precision score: 0.993 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 0, 17 KNN f1 score: 1.000 KNN cohens kappa score: 1.000 ------ Step 3/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 569, 2 LR fn, tp: 1, 16 LR f1 score: 0.914 LR cohens kappa score: 0.912 LR average precision score: 0.983 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 3, 14 KNN f1 score: 0.903 KNN cohens kappa score: 0.901 ------ Step 3/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 569, 2 LR fn, tp: 1, 16 LR f1 score: 0.914 LR cohens kappa score: 0.912 LR average precision score: 0.994 -> test with 'GB' GB tn, fp: 570, 1 GB fn, tp: 0, 17 GB f1 score: 0.971 GB cohens kappa score: 0.971 -> test with 'KNN' KNN tn, fp: 570, 1 KNN fn, tp: 0, 17 KNN f1 score: 0.971 KNN cohens kappa score: 0.971 ------ Step 3/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 570, 1 LR fn, tp: 0, 17 LR f1 score: 0.971 LR cohens kappa score: 0.971 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 1, 16 KNN f1 score: 0.970 KNN cohens kappa score: 0.969 ------ Step 3/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2216 synthetic samples -> test with 'LR' LR tn, fp: 570, 0 LR fn, tp: 2, 11 LR f1 score: 0.917 LR cohens kappa score: 0.915 LR average precision score: 0.984 -> test with 'GB' GB tn, fp: 570, 0 GB fn, tp: 0, 13 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 570, 0 KNN fn, tp: 3, 10 KNN f1 score: 0.870 KNN cohens kappa score: 0.867 ====== 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 2219 synthetic samples -> test with 'LR' LR tn, fp: 569, 2 LR fn, tp: 1, 16 LR f1 score: 0.914 LR cohens kappa score: 0.912 LR average precision score: 0.987 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 2, 15 KNN f1 score: 0.938 KNN cohens kappa score: 0.936 ------ Step 4/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 571, 0 LR fn, tp: 1, 16 LR f1 score: 0.970 LR cohens kappa score: 0.969 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 3, 14 KNN f1 score: 0.903 KNN cohens kappa score: 0.901 ------ Step 4/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 571, 0 LR fn, tp: 0, 17 LR f1 score: 1.000 LR cohens kappa score: 1.000 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 0, 17 KNN f1 score: 1.000 KNN cohens kappa score: 1.000 ------ Step 4/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 568, 3 LR fn, tp: 0, 17 LR f1 score: 0.919 LR cohens kappa score: 0.916 LR average precision score: 0.936 -> test with 'GB' GB tn, fp: 569, 2 GB fn, tp: 0, 17 GB f1 score: 0.944 GB cohens kappa score: 0.943 -> test with 'KNN' KNN tn, fp: 570, 1 KNN fn, tp: 0, 17 KNN f1 score: 0.971 KNN cohens kappa score: 0.971 ------ Step 4/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2216 synthetic samples -> test with 'LR' LR tn, fp: 569, 1 LR fn, tp: 1, 12 LR f1 score: 0.923 LR cohens kappa score: 0.921 LR average precision score: 0.982 -> test with 'GB' GB tn, fp: 570, 0 GB fn, tp: 0, 13 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 570, 0 KNN fn, tp: 2, 11 KNN f1 score: 0.917 KNN cohens kappa score: 0.915 ====== 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 2219 synthetic samples -> test with 'LR' LR tn, fp: 567, 4 LR fn, tp: 0, 17 LR f1 score: 0.895 LR cohens kappa score: 0.891 LR average precision score: 0.965 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 569, 2 KNN fn, tp: 2, 15 KNN f1 score: 0.882 KNN cohens kappa score: 0.879 ------ Step 5/5: Slice 2/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 570, 1 LR fn, tp: 0, 17 LR f1 score: 0.971 LR cohens kappa score: 0.971 LR average precision score: 0.990 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 3, 14 KNN f1 score: 0.903 KNN cohens kappa score: 0.901 ------ Step 5/5: Slice 3/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 571, 0 LR fn, tp: 1, 16 LR f1 score: 0.970 LR cohens kappa score: 0.969 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 571, 0 KNN fn, tp: 1, 16 KNN f1 score: 0.970 KNN cohens kappa score: 0.969 ------ Step 5/5: Slice 4/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2219 synthetic samples -> test with 'LR' LR tn, fp: 571, 0 LR fn, tp: 1, 16 LR f1 score: 0.970 LR cohens kappa score: 0.969 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 571, 0 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 570, 1 KNN fn, tp: 1, 16 KNN f1 score: 0.941 KNN cohens kappa score: 0.939 ------ Step 5/5: Slice 5/5 ------- -> Reset the GAN -> Train generator for synthetic samples Epoch 1/3 Epoch 2/3 Epoch 3/3 -> create 2216 synthetic samples -> test with 'LR' LR tn, fp: 570, 0 LR fn, tp: 0, 13 LR f1 score: 1.000 LR cohens kappa score: 1.000 LR average precision score: 1.000 -> test with 'GB' GB tn, fp: 570, 0 GB fn, tp: 0, 13 GB f1 score: 1.000 GB cohens kappa score: 1.000 -> test with 'KNN' KNN tn, fp: 570, 0 KNN fn, tp: 1, 12 KNN f1 score: 0.960 KNN cohens kappa score: 0.959 ### Exercise is done. -----[ LR ]----- maximum: LR tn, fp: 571, 4 LR fn, tp: 2, 17 LR f1 score: 1.000 LR cohens kappa score: 1.000 LR average precision score: 1.000 average: LR tn, fp: 569.56, 1.24 LR fn, tp: 0.64, 15.56 LR f1 score: 0.943 LR cohens kappa score: 0.941 LR average precision score: 0.983 minimum: LR tn, fp: 566, 0 LR fn, tp: 0, 11 LR f1 score: 0.857 LR cohens kappa score: 0.854 LR average precision score: 0.867 -----[ GB ]----- maximum: GB tn, fp: 571, 2 GB fn, tp: 0, 17 GB f1 score: 1.000 GB cohens kappa score: 1.000 average: GB tn, fp: 570.68, 0.12 GB fn, tp: 0.0, 16.2 GB f1 score: 0.997 GB cohens kappa score: 0.997 minimum: GB tn, fp: 569, 0 GB fn, tp: 0, 13 GB f1 score: 0.944 GB cohens kappa score: 0.943 -----[ KNN ]----- maximum: KNN tn, fp: 571, 2 KNN fn, tp: 3, 17 KNN f1 score: 1.000 KNN cohens kappa score: 1.000 average: KNN tn, fp: 570.48, 0.32 KNN fn, tp: 1.48, 14.72 KNN f1 score: 0.940 KNN cohens kappa score: 0.938 minimum: KNN tn, fp: 568, 0 KNN fn, tp: 0, 10 KNN f1 score: 0.846 KNN cohens kappa score: 0.843