wangwei
/
graphkit-learn

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Acyclic\n",
      "\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",
      "\n",
      "gram matrix with parameters {'p_quit': 0.10000000000000001, 'itr': 20} is: \n",
      "removing tottering: 100%|██████████| 183/183 [00:00<00:00, 1678.94it/s]\n",
      "calculating kernels:   8%|▊         | 1318/16836.0 [02:48<28:58,  8.93it/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-c8ad7685a8b8>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     58\u001b[0m         \u001b[0;34m(\u001b[0m\u001b[0mds\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'task'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;34m'task'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mds\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;34m'classification'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNUM_TRIALS\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m30\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\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[0;32m---> 60\u001b[0;31m         extra_params=(ds['extra_params'] if 'extra_params' in ds else None))\n\u001b[0m\u001b[1;32m     61\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)\u001b[0m\n\u001b[1;32m     99\u001b[0m             \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'gram matrix with parameters'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams_out\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'is: '\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    100\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 101\u001b[0;31m         \u001b[0mKmatrix\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcurrent_run_time\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    102\u001b[0m         \u001b[0mKmatrix_diag\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mKmatrix\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdiagonal\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    103\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/media/ljia/DATA/research-repo/codes/Linlin/py-graph/pygraph/kernels/marginalizedKernel.py\u001b[0m in \u001b[0;36mmarginalizedkernel\u001b[0;34m(node_label, edge_label, p_quit, itr, remove_totters, *args)\u001b[0m\n\u001b[1;32m     83\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     84\u001b[0m             Kmatrix[i][j] = _marginalizedkernel_do(Gn[i], Gn[j], node_label,\n\u001b[0;32m---> 85\u001b[0;31m                                                    edge_label, p_quit, itr)\n\u001b[0m\u001b[1;32m     86\u001b[0m             \u001b[0mKmatrix\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mj\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mKmatrix\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mj\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     87\u001b[0m             \u001b[0mpbar\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\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/marginalizedKernel.py\u001b[0m in \u001b[0;36m_marginalizedkernel_do\u001b[0;34m(G1, G2, node_label, edge_label, p_quit, itr)\u001b[0m\n\u001b[1;32m    147\u001b[0m                     \u001b[0;32mfor\u001b[0m \u001b[0mneighbor2\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mneighbor_n2\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    148\u001b[0m                         \u001b[0mt\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mp_trans_n1\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mp_trans_n2\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 149\u001b[0;31m                             \u001b[0mdeltakernel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mG1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnode\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mneighbor1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mnode_label\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mG2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnode\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mneighbor2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mnode_label\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    150\u001b[0m                             \u001b[0mdeltakernel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mneighbor_n1\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mneighbor1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0medge_label\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mneighbor_n2\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mneighbor2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0medge_label\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    151\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.5/dist-packages/networkx/classes/graph.py\u001b[0m in \u001b[0;36mnodes\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    717\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    718\u001b[0m         \"\"\"\n\u001b[0;32m--> 719\u001b[0;31m         \u001b[0mnodes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mNodeView\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    720\u001b[0m         \u001b[0;31m# Lazy View creation: overload the (class) property on the instance\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    721\u001b[0m         \u001b[0;31m# Then future G.nodes use the existing View\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.5/dist-packages/networkx/classes/reportviews.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, graph)\u001b[0m\n\u001b[1;32m    165\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_nodes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstate\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'_nodes'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    166\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 167\u001b[0;31m     \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgraph\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    168\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_nodes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgraph\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_node\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    169\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 numpy as np\n",
    "import sys\n",
    "sys.path.insert(0, \"../\")\n",
    "from pygraph.utils.model_selection_precomputed import model_selection_for_precomputed_kernel\n",
    "from pygraph.kernels.marginalizedKernel import marginalizedkernel\n",
    "\n",
    "dslist = [   \n",
    "    {'name': 'Acyclic', 'dataset': '../datasets/acyclic/dataset_bps.ds', 'task': 'regression'}, # node_labeled\n",
    "#     {'name': 'COIL-DEL', 'dataset': '../datasets/COIL-DEL/COIL-DEL_A.txt'}, # edge_labeled\n",
    "#     {'name': 'PAH', 'dataset': '../datasets/PAH/dataset.ds',}, # unlabeled\n",
    "#     {'name': 'Mutagenicity', 'dataset': '../datasets/Mutagenicity/Mutagenicity_A.txt'}, # fully_labeled\n",
    "#     {'name': 'MAO', 'dataset': '../datasets/MAO/dataset.ds',},\n",
    "\n",
    "#     {'name': 'MUTAG', 'dataset': '../datasets/MUTAG/MUTAG.mat',\n",
    "#         'extra_params': {'am_sp_al_nl_el': [0, 0, 3, 1, 2]}},\n",
    "#     {'name': 'Alkane', 'dataset': '../datasets/Alkane/dataset.ds', 'task': 'regression', \n",
    "#         'dataset_y': '../datasets/Alkane/dataset_boiling_point_names.txt',},\n",
    "#     {'name': 'BZR', 'dataset': '../datasets/BZR_txt/BZR_A_sparse.txt'},\n",
    "#     {'name': 'COX2', 'dataset': '../datasets/COX2_txt/COX2_A_sparse.txt'},    \n",
    "    {'name': 'ENZYMES', 'dataset': '../datasets/ENZYMES_txt/ENZYMES_A_sparse.txt'},\n",
    "#     {'name': 'DHFR', 'dataset': '../datasets/DHFR_txt/DHFR_A_sparse.txt'},\n",
    "#     {'name': 'SYNTHETIC', 'dataset': '../datasets/SYNTHETIC_txt/SYNTHETIC_A_sparse.txt'},\n",
    "#     {'name': 'MSRC9', 'dataset': '../datasets/MSRC_9_txt/MSRC_9_A.txt'},\n",
    "#     {'name': 'MSRC21', 'dataset': '../datasets/MSRC_21_txt/MSRC_21_A.txt'},\n",
    "#     {'name': 'FIRSTMM_DB', 'dataset': '../datasets/FIRSTMM_DB/FIRSTMM_DB_A.txt'},\n",
    "\n",
    "#     {'name': 'PROTEINS', 'dataset': '../datasets/PROTEINS_txt/PROTEINS_A_sparse.txt'},\n",
    "#     {'name': 'PROTEINS_full', 'dataset': '../datasets/PROTEINS_full_txt/PROTEINS_full_A_sparse.txt'},\n",
    "#     {'name': 'D&D', 'dataset': '../datasets/D&D/DD.mat',\n",
    "#      'extra_params': {'am_sp_al_nl_el': [0, 1, 2, 1, -1]}},\n",
    "#     {'name': 'AIDS', 'dataset': '../datasets/AIDS/AIDS_A.txt'},\n",
    "#     {'name': 'NCI1', 'dataset': '../datasets/NCI1/NCI1.mat',\n",
    "#         'extra_params': {'am_sp_al_nl_el': [1, 1, 2, 0, -1]}},\n",
    "#     {'name': 'NCI109', 'dataset': '../datasets/NCI109/NCI109.mat',\n",
    "#         'extra_params': {'am_sp_al_nl_el': [1, 1, 2, 0, -1]}},\n",
    "#     {'name': 'NCI-HIV', 'dataset': '../datasets/NCI-HIV/AIDO99SD.sdf',\n",
    "#         'dataset_y': '../datasets/NCI-HIV/aids_conc_may04.txt',},\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 = marginalizedkernel\n",
    "param_grid_precomputed = {'p_quit': np.linspace(0.1, 0.9, 9), 'itr': [20]}\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",
    "    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",
      "\n",
      "gram matrix with parameters {'p_quit': 0.10000000000000001} is: \n",
      "calculate kernels: 100%|██████████| 16836/16836.0 [1:46:28<00:00,  1.48it/s]\n",
      " --- marginalized kernel matrix of size 183 built in 6388.502187728882 seconds ---\n",
      "[[ 1.          0.64549125  0.1238602  ...,  0.18744115  0.18784508\n",
      "   0.18052003]\n",
      " [ 0.64549125  1.          0.13569668 ...,  0.20535363  0.20579615\n",
      "   0.19777109]\n",
      " [ 0.1238602   0.13569668  1.         ...,  0.27603195  0.27457716\n",
      "   0.29886586]\n",
      " ..., \n",
      " [ 0.18744115  0.20535363  0.27603195 ...,  1.          0.99990821\n",
      "   0.99626713]\n",
      " [ 0.18784508  0.20579615  0.27457716 ...,  0.99990821  1.          0.99550561]\n",
      " [ 0.18052003  0.19777109  0.29886586 ...,  0.99626713  0.99550561  1.        ]]\n"
     ]
    },
    {
     "data": {