{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "scrolled": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Acyclic\n", "\n", "--- This is a regression problem ---\n", "\n", "\n", "1. Loading dataset from file...\n", "\n", "2. Calculating gram matrices. This could take a while...\n", "\n", " None edge weight specified. Set all weight to 1.\n", "\n", "getting sp graphs: 183it [00:00, 5345.48it/s]\n", "calculating kernels: 16836it [00:01, 16066.90it/s]\n", "\n", " --- shortest path kernel matrix of size 183 built in 1.2855160236358643 seconds ---\n", "\n", "the gram matrix with parameters {'node_kernels': {'symb': , 'nsymb': , 'mix': functools.partial(, , )}, 'n_jobs': 8} is: \n", "\n", "\n", "\n", "1 gram matrices are calculated, 0 of which are ignored.\n", "\n", "3. Fitting and predicting using nested cross validation. This could really take a while...\n", "cross validation: 30it [00:03, 8.63it/s]\n", "\n", "4. Getting final performance...\n", "best_params_out: [{'node_kernels': {'symb': , 'nsymb': , 'mix': functools.partial(, , )}, 'n_jobs': 8}]\n", "best_params_in: [{'alpha': 0.0001}]\n", "\n", "best_val_perf: 9.674788994813262\n", "best_val_std: 0.6229031522274688\n", "final_performance: [9.590999824754439]\n", "final_confidence: [2.911796096257332]\n", "train_performance: [6.16594412531739]\n", "train_std: [0.2739093211154806]\n", "\n", "time to calculate gram matrix with different hyper-params: 1.29±nans\n", "time to calculate best gram matrix: 1.29±nans\n", "total training time with all hyper-param choices: 5.15s\n", "\n", "\n", "\n", "Alkane\n", "\n", "--- This is a regression problem ---\n", "\n", "\n", "1. Loading dataset from file...\n", "\n", "2. Calculating gram matrices. This could take a while...\n", "\n", " None edge weight specified. Set all weight to 1.\n", "\n", "\n", " 1 graphs are removed as they don't contain edges.\n", "\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/usr/local/lib/python3.6/dist-packages/numpy/core/_methods.py:140: RuntimeWarning: Degrees of freedom <= 0 for slice\n", " keepdims=keepdims)\n", "/usr/local/lib/python3.6/dist-packages/numpy/core/_methods.py:132: RuntimeWarning: invalid value encountered in double_scalars\n", " ret = ret.dtype.type(ret / rcount)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "getting sp graphs: 149it [00:00, 6510.18it/s]\n", "calculating kernels: 11175it [00:00, 18881.68it/s]\n", "\n", " --- shortest path kernel matrix of size 149 built in 0.8007419109344482 seconds ---\n", "\n", "the gram matrix with parameters {'node_kernels': {'symb': , 'nsymb': , 'mix': functools.partial(, , )}, 'n_jobs': 8} is: \n", "\n", "\n", "\n", "1 gram matrices are calculated, 0 of which are ignored.\n", "\n", "3. Fitting and predicting using nested cross validation. This could really take a while...\n", "cross validation: 30it [00:02, 10.52it/s]\n", "\n", "4. Getting final performance...\n", "best_params_out: [{'node_kernels': {'symb': , 'nsymb': , 'mix': functools.partial(, , )}, 'n_jobs': 8}]\n", "best_params_in: [{'alpha': 3.162277660168379e-07}]\n", "\n", "best_val_perf: 8.784264102873752\n", "best_val_std: 0.2656887278835053\n", "final_performance: [8.059911355753659]\n", "final_confidence: [1.9620843656589473]\n", "train_performance: [7.8406202266920575]\n", "train_std: [0.2177862360087283]\n", "\n", "time to calculate gram matrix with different hyper-params: 0.80±nans\n", "time to calculate best gram matrix: 0.80±nans\n", "total training time with all hyper-param choices: 4.02s\n", "\n", "\n", "\n", "MAO\n", "\n", "--- This is a classification problem ---\n", "\n", "\n", "1. Loading dataset from file...\n", "\n", "2. Calculating gram matrices. This could take a while...\n", "\n", " None edge weight specified. Set all weight to 1.\n", "\n", "getting sp graphs: 68it [00:00, 1095.77it/s]\n", "calculating kernels: 2346it [00:02, 813.63it/s]\n", "\n", " --- shortest path kernel matrix of size 68 built in 3.110588550567627 seconds ---\n", "\n", "the gram matrix with parameters {'node_kernels': {'symb': , 'nsymb': , 'mix': functools.partial(, , )}, 'n_jobs': 8} is: \n", "\n", "\n", "\n", "1 gram matrices are calculated, 0 of which are ignored.\n", "\n", "3. Fitting and predicting using nested cross validation. This could really take a while...\n", "cross validation: 30it [00:02, 10.97it/s]\n", "\n", "4. Getting final performance...\n", "best_params_out: [{'node_kernels': {'symb': , 'nsymb': , 'mix': functools.partial(, , )}, 'n_jobs': 8}]\n", "best_params_in: [{'C': 3162.2776601683795}]\n", "\n", "best_val_perf: 0.8798412698412699\n", "best_val_std: 0.02062186442241262\n", "final_performance: [0.9042857142857144]\n", "final_confidence: [0.07343487734322982]\n", "train_performance: [0.9709180695847363]\n", "train_std: [0.005927396388634032]\n", "\n", "time to calculate gram matrix with different hyper-params: 3.11±nans\n", "time to calculate best gram matrix: 3.11±nans\n", "total training time with all hyper-param choices: 6.21s\n", "\n", "\n", "\n", "PAH\n", "\n", "--- This is a classification problem ---\n", "\n", "\n", "1. Loading dataset from file...\n", "\n", "2. Calculating gram matrices. This could take a while...\n", "\n", " None edge weight specified. Set all weight to 1.\n", "\n", "getting sp graphs: 94it [00:00, 2190.46it/s]\n", "calculating kernels: 4465it [00:05, 763.81it/s]\n", "\n", " --- shortest path kernel matrix of size 94 built in 6.083932399749756 seconds ---\n", "\n", "the gram matrix with parameters {'node_kernels': {'symb': , 'nsymb': , 'mix': functools.partial(, , )}, 'n_jobs': 8} is: \n", "\n", "\n", "\n", "1 gram matrices are calculated, 0 of which are ignored.\n", "\n", "3. Fitting and predicting using nested cross validation. This could really take a while...\n", "cross validation: 0it [00:00, ?it/s]" ] } ], "source": [ "import functools\n", "from libs import *\n", "import multiprocessing\n", "\n", "from pygraph.kernels.spKernel import spkernel\n", "from pygraph.utils.kernels import deltakernel, gaussiankernel, kernelproduct\n", "#from pygraph.utils.model_selection_precomputed import trial_do\n", "\n", "# datasets\n", "dslist = [\n", " {'name': 'Acyclic', 'dataset': '../datasets/acyclic/dataset_bps.ds',\n", " 'task': 'regression'}, # node symb\n", " {'name': 'Alkane', 'dataset': '../datasets/Alkane/dataset.ds', 'task': 'regression',\n", " 'dataset_y': '../datasets/Alkane/dataset_boiling_point_names.txt', }, \n", " # contains single node graph, node symb\n", " {'name': 'MAO', 'dataset': '../datasets/MAO/dataset.ds', }, # node/edge symb\n", " {'name': 'PAH', 'dataset': '../datasets/PAH/dataset.ds', }, # unlabeled\n", " {'name': 'MUTAG', 'dataset': '../datasets/MUTAG/MUTAG.mat',\n", " 'extra_params': {'am_sp_al_nl_el': [0, 0, 3, 1, 2]}}, # node/edge symb\n", " {'name': 'Letter-med', 'dataset': '../datasets/Letter-med/Letter-med_A.txt'},\n", " # node nsymb\n", " {'name': 'ENZYMES', 'dataset': '../datasets/ENZYMES_txt/ENZYMES_A_sparse.txt'},\n", " # node symb/nsymb\n", "\n", "# {'name': 'Mutagenicity', 'dataset': '../datasets/Mutagenicity/Mutagenicity_A.txt'},\n", "# # node/edge symb\n", "# {'name': 'D&D', 'dataset': '../datasets/D&D/DD.mat',\n", "# 'extra_params': {'am_sp_al_nl_el': [0, 1, 2, 1, -1]}}, # node symb\n", "#\n", "# {'name': 'COIL-DEL', 'dataset': '../datasets/COIL-DEL/COIL-DEL_A.txt'}, # edge symb, node nsymb\n", "# {'name': 'BZR', 'dataset': '../datasets/BZR_txt/BZR_A_sparse.txt'}, # node symb/nsymb\n", "# {'name': 'COX2', 'dataset': '../datasets/COX2_txt/COX2_A_sparse.txt'}, # node symb/nsymb\n", "# {'name': 'Fingerprint', 'dataset': '../datasets/Fingerprint/Fingerprint_A.txt'},\n", "# {'name': 'DHFR', 'dataset': '../datasets/DHFR_txt/DHFR_A_sparse.txt'}, # node symb/nsymb\n", "# {'name': 'SYNTHETIC', 'dataset': '../datasets/SYNTHETIC_txt/SYNTHETIC_A_sparse.txt'}, # node symb/nsymb\n", "# {'name': 'MSRC9', 'dataset': '../datasets/MSRC_9_txt/MSRC_9_A.txt'}, # node symb\n", "# {'name': 'MSRC21', 'dataset': '../datasets/MSRC_21_txt/MSRC_21_A.txt'}, # node symb\n", "# {'name': 'FIRSTMM_DB', 'dataset': '../datasets/FIRSTMM_DB/FIRSTMM_DB_A.txt'}, # node symb/nsymb ,edge nsymb\n", "#\n", "# {'name': 'PROTEINS', 'dataset': '../datasets/PROTEINS_txt/PROTEINS_A_sparse.txt'}, # node symb/nsymb\n", "# {'name': 'PROTEINS_full', 'dataset': '../datasets/PROTEINS_full_txt/PROTEINS_full_A_sparse.txt'}, # node symb/nsymb\n", "# {'name': 'AIDS', 'dataset': '../datasets/AIDS/AIDS_A.txt'}, # node symb/nsymb, edge symb\n", "# {'name': 'NCI1', 'dataset': '../datasets/NCI1/NCI1.mat',\n", "# 'extra_params': {'am_sp_al_nl_el': [1, 1, 2, 0, -1]}}, # node symb\n", "# {'name': 'NCI109', 'dataset': '../datasets/NCI109/NCI109.mat',\n", "# 'extra_params': {'am_sp_al_nl_el': [1, 1, 2, 0, -1]}}, # node symb\n", "# {'name': 'NCI-HIV', 'dataset': '../datasets/NCI-HIV/AIDO99SD.sdf',\n", "# 'dataset_y': '../datasets/NCI-HIV/aids_conc_may04.txt',}, # node/edge symb\n", "\n", " # # not working below\n", " # {'name': 'PTC_FM', 'dataset': '../datasets/PTC/Train/FM.ds',},\n", " # {'name': 'PTC_FR', 'dataset': '../datasets/PTC/Train/FR.ds',},\n", " # {'name': 'PTC_MM', 'dataset': '../datasets/PTC/Train/MM.ds',},\n", " # {'name': 'PTC_MR', 'dataset': '../datasets/PTC/Train/MR.ds',},\n", "]\n", "estimator = spkernel\n", "# hyper-parameters\n", "mixkernel = functools.partial(kernelproduct, deltakernel, gaussiankernel)\n", "param_grid_precomputed = {'node_kernels': [\n", " {'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}]}\n", "param_grid = [{'C': np.logspace(-10, 10, num=41, base=10)},\n", " {'alpha': np.logspace(-10, 10, num=41, base=10)}]\n", "\n", "# for each dataset, do model selection.\n", "for ds in dslist:\n", " print()\n", " print(ds['name'])\n", " model_selection_for_precomputed_kernel(\n", " ds['dataset'],\n", " estimator,\n", " param_grid_precomputed,\n", " (param_grid[1] if ('task' in ds and ds['task']\n", " == 'regression') else param_grid[0]),\n", " (ds['task'] if 'task' in ds else 'classification'),\n", " NUM_TRIALS=30,\n", " datafile_y=(ds['dataset_y'] if 'dataset_y' in ds else None),\n", " extra_params=(ds['extra_params'] if 'extra_params' in ds else None),\n", " ds_name=ds['name'],\n", " n_jobs=multiprocessing.cpu_count(),\n", " read_gm_from_file=False)\n", " print()" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.7" } }, "nbformat": 4, "nbformat_minor": 2 }