wangwei
/
graphkit-learn

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "ENZYMES\n",
      "\n",
      "--- This is a classification problem ---\n",
      "\n",
      "\n",
      "I. 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: 100%|██████████| 600/600 [00:01<00:00, 387.62it/s]\n",
      "calculating kernels:   0%|          | 116/180300.0 [00:36<13:08:20,  3.81it/s]"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-1-90cefd800f5f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     59\u001b[0m         \u001b[0mdatafile_y\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mds\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'dataset_y'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;34m'dataset_y'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mds\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     60\u001b[0m         \u001b[0mextra_params\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mds\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'extra_params'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;34m'extra_params'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mds\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 61\u001b[0;31m         ds_name=ds['name'])\n\u001b[0m\u001b[1;32m     62\u001b[0m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/media/ljia/DATA/research-repo/codes/Linlin/py-graph/pygraph/utils/model_selection_precomputed.py\u001b[0m in \u001b[0;36mmodel_selection_for_precomputed_kernel\u001b[0;34m(datafile, estimator, param_grid_precomputed, param_grid, model_type, NUM_TRIALS, datafile_y, extra_params, ds_name)\u001b[0m\n\u001b[1;32m    101\u001b[0m         \u001b[0mnb_gm_ignore\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0\u001b[0m \u001b[0;31m# the number of gram matrices those should not be considered, as they may contain elements that are not numbers (NaN)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    102\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0midx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams_out\u001b[0m \u001b[0;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparam_list_precomputed\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 103\u001b[0;31m             \u001b[0mrtn_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mestimator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mparams_out\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    104\u001b[0m             \u001b[0mKmatrix\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrtn_data\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    105\u001b[0m             \u001b[0mcurrent_run_time\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrtn_data\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/media/ljia/DATA/research-repo/codes/Linlin/py-graph/pygraph/kernels/spKernel.py\u001b[0m in \u001b[0;36mspkernel\u001b[0;34m(node_label, edge_weight, node_kernels, *args)\u001b[0m\n\u001b[1;32m     93\u001b[0m                     \u001b[0;32mfor\u001b[0m \u001b[0mj\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mGn\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     94\u001b[0m                         \u001b[0;32mfor\u001b[0m \u001b[0me1\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mGn\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0medges\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 95\u001b[0;31m                             \u001b[0;32mfor\u001b[0m \u001b[0me2\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mGn\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mj\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0medges\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     96\u001b[0m                                 \u001b[0;32mif\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'cost'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0me2\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'cost'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     97\u001b[0m                                     \u001b[0mkn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnode_kernels\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'mix'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "%load_ext line_profiler\n",
    "%matplotlib inline\n",
    "import functools\n",
    "from libs import *\n",
    "from pygraph.kernels.spKernel import spkernel\n",
    "from pygraph.utils.kernels import deltakernel, kernelsum\n",
    "from sklearn.metrics.pairwise import rbf_kernel\n",
    "\n",
    "dslist = [   \n",
    "#     {'name': 'Acyclic', 'dataset': '../datasets/acyclic/dataset_bps.ds', 'task': 'regression'}, # node symb\n",
    "#     {'name': 'COIL-DEL', 'dataset': '../datasets/COIL-DEL/COIL-DEL_A.txt'}, # edge symb, node nsymb\n",
    "#     {'name': 'PAH', 'dataset': '../datasets/PAH/dataset.ds',}, # unlabeled\n",
    "#     {'name': 'Mutagenicity', 'dataset': '../datasets/Mutagenicity/Mutagenicity_A.txt'}, # node/edge symb\n",
    "#     {'name': 'MAO', 'dataset': '../datasets/MAO/dataset.ds',}, # node/edge symb\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': 'Alkane', 'dataset': '../datasets/Alkane/dataset.ds', 'task': 'regression', \n",
    "#         'dataset_y': '../datasets/Alkane/dataset_boiling_point_names.txt',}, # contains single node graph, node symb\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': 'ENZYMES', 'dataset': '../datasets/ENZYMES_txt/ENZYMES_A_sparse.txt'}, # node symb/nsymb\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': 'D&D', 'dataset': '../datasets/D&D/DD.mat',\n",
    "#      'extra_params': {'am_sp_al_nl_el': [0, 1, 2, 1, -1]}}, # node symb\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",
    "mixkernel = functools.partial(kernelsum, deltakernel, rbf_kernel)\n",
    "param_grid_precomputed = {'node_kernels': [{'symb': deltakernel, 'nsymb': rbf_kernel, '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 ds in dslist:\n",
    "    print()\n",
    "    print(ds['name'])\n",
    "    model_selection_for_precomputed_kernel(\n",
    "        ds['dataset'], estimator, param_grid_precomputed, \n",
    "        (param_grid[1] if ('task' in ds and ds['task'] == 'regression') else param_grid[0]), \n",
    "        (ds['task'] if 'task' in ds else 'classification'), 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",
    "    print()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "--- This is a regression problem ---\n",
      "\n",
      "1. Loading dataset from file...\n",
      "\n",
      "2. Calculating gram matrices. This could take a while...\n",
      "--- shortest path kernel matrix of size 183 built in 13.54222846031189 seconds ---\n",
      "\n",
      "gram matrix with parameters {} is: \n",
      "[[1.         0.23570226 1.         ... 0.07784989 0.07784989 0.07784989]\n",
      " [0.23570226 1.         0.23570226 ... 0.         0.         0.16514456]\n",
      " [1.         0.23570226 1.         ... 0.07784989 0.07784989 0.07784989]\n",
      " ...\n",
      " [0.07784989 0.         0.07784989 ... 1.         0.38181818 0.12727273]\n",
      " [0.07784989 0.         0.07784989 ... 0.38181818 1.         0.12727273]\n",
      " [0.07784989 0.16514456 0.07784989 ... 0.12727273 0.12727273 1.        ]]\n"
     ]
    },
    {
     "data": {