graphkit-learn/notebooks/run_randomwalkkernel.ipynb

{
 "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",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 5067.96it/s]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "../pygraph/kernels/randomWalkKernel.py:104: UserWarning: All labels are ignored.\n",
      "  warnings.warn('All labels are ignored.')\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "calculating kernels: 16836it [00:00, 76328.32it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.38956499099731445 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 0.1, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      " None edge weight specified. Set all weight to 1.\n",
      "\n",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 5928.69it/s]\n",
      "calculating kernels: 16836it [00:00, 76159.65it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.3680381774902344 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 0.01, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      " None edge weight specified. Set all weight to 1.\n",
      "\n",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 5599.99it/s]\n",
      "calculating kernels: 16836it [00:00, 68122.63it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.37236690521240234 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 0.001, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      " None edge weight specified. Set all weight to 1.\n",
      "\n",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 5444.75it/s]\n",
      "calculating kernels: 16836it [00:00, 65554.92it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.37699007987976074 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 0.0001, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      " None edge weight specified. Set all weight to 1.\n",
      "\n",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 4451.65it/s]\n",
      "calculating kernels: 16836it [00:00, 64227.38it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.40868353843688965 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-05, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      " None edge weight specified. Set all weight to 1.\n",
      "\n",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 5455.55it/s]\n",
      "calculating kernels: 16836it [00:00, 69253.03it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.4017300605773926 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-06, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      " None edge weight specified. Set all weight to 1.\n",
      "\n",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 5691.60it/s]\n",
      "calculating kernels: 16836it [00:00, 67461.93it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.3712270259857178 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-07, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      " None edge weight specified. Set all weight to 1.\n",
      "\n",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 5229.98it/s]\n",
      "calculating kernels: 16836it [00:00, 70363.33it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.37551283836364746 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-08, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      " None edge weight specified. Set all weight to 1.\n",
      "\n",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 5023.84it/s]\n",
      "calculating kernels: 16836it [00:00, 71457.21it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.39424848556518555 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-09, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      " None edge weight specified. Set all weight to 1.\n",
      "\n",
      "compute adjacency matrices: 100%|██████████| 183/183 [00:00<00:00, 5359.14it/s]\n",
      "calculating kernels: 16836it [00:00, 73095.73it/s]\n",
      "\n",
      " --- kernel matrix of random walk kernel of size 183 built in 0.37821507453918457 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-10, 'n_jobs': 8} is: \n",
      "\n",
      "\n",
      "\n",
      "10 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 [00:33,  1.10s/it]\n",
      "\n",
      "4. Getting final performance...\n",
      "best_params_out:  [{'compute_method': 'sylvester', 'weight': 0.01, 'n_jobs': 8}]\n",
      "best_params_in:  [{'alpha': 3.1622776601683795e-10}]\n",
      "\n",
      "best_val_perf:  31.894498817348637\n",
      "best_val_std:  0.5235865101548381\n",
      "final_performance:  [32.04579601256704]\n",
      "final_confidence:  [3.9737533137212138]\n",
      "train_performance: [30.830572265896325]\n",
      "train_std:  [0.44072573889937117]\n",
      "\n",
      "time to calculate gram matrix with different hyper-params: 0.38±0.01s\n",
      "time to calculate best gram matrix: 0.37±nans\n",
      "total training time with all hyper-param choices: 40.27s\n",
      "\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",
      "reindex vertices: 100%|██████████| 183/183 [00:00<00:00, 26008.32it/s]\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": [
      "calculating kernels: 12501it [00:01, 6173.52it/s]"
     ]
    }
   ],
   "source": [
    "# %load_ext line_profiler\n",
    "# %matplotlib inline\n",
    "import functools\n",
    "from libs import *\n",
    "import multiprocessing\n",
    "\n",
    "from pygraph.kernels.randomWalkKernel import randomwalkkernel\n",
    "from pygraph.utils.kernels import deltakernel, gaussiankernel, kernelproduct\n",
    "\n",
    "import numpy as np\n",
    "\n",
    "\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",
    "#    {'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",
    "    #\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, missing values\n",
    "#    {'name': 'MSRC21', 'dataset': '../datasets/MSRC_21_txt/MSRC_21_A.txt'}, # node symb, missing values\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 = randomwalkkernel\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 ds in dslist:\n",
    "    print()\n",
    "    print(ds['name'])\n",
    "    for compute_method in ['sylvester', 'conjugate', 'fp', 'spectral']:\n",
    "        if compute_method == 'sylvester':\n",
    "            param_grid_precomputed = {'compute_method': ['sylvester'],\n",
    "#                          'weight': np.linspace(0.01, 0.10, 10)}\n",
    "                          'weight': np.logspace(-1, -10, num=10, base=10)}\n",
    "        elif compute_method == 'conjugate':\n",
    "            mixkernel = functools.partial(kernelproduct, deltakernel, gaussiankernel)\n",
    "            param_grid_precomputed = {'compute_method': ['conjugate'], \n",
    "                          'node_kernels': \n",
    "                          [{'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}],\n",
    "                          'edge_kernels': \n",
    "                          [{'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}],\n",
    "                          'weight': np.logspace(-1, -10, num=10, base=10)}\n",
    "        elif compute_method == 'fp':\n",
    "            mixkernel = functools.partial(kernelproduct, deltakernel, gaussiankernel)\n",
    "            param_grid_precomputed = {'compute_method': ['fp'], \n",
    "                          'node_kernels': \n",
    "                          [{'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}],\n",
    "                          'edge_kernels': \n",
    "                          [{'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}],\n",
    "                          'weight': np.logspace(-3, -10, num=8, base=10)}\n",
    "        elif compute_method == 'spectral':\n",
    "            param_grid_precomputed = {'compute_method': ['spectral'],\n",
    "                          'weight': np.logspace(-1, -10, num=10, base=10),\n",
    "                          'sub_kernel': ['geo', 'exp']}\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
}