wangwei
/
graphkit-learn

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=8)]: Using backend LokyBackend with 8 concurrent workers.\n",
      "[Parallel(n_jobs=8)]: Done   2 out of   9 | elapsed:  2.8min remaining:  9.9min\n",
      "[Parallel(n_jobs=8)]: Done   3 out of   9 | elapsed:  3.2min remaining:  6.4min\n",
      "[Parallel(n_jobs=8)]: Done   4 out of   9 | elapsed:  4.0min remaining:  5.0min\n",
      "[Parallel(n_jobs=8)]: Done   5 out of   9 | elapsed:  7.9min remaining:  6.3min\n",
      "[Parallel(n_jobs=8)]: Done   6 out of   9 | elapsed: 147.0min remaining: 73.5min\n",
      "[Parallel(n_jobs=8)]: Done   7 out of   9 | elapsed: 397.8min remaining: 113.7min\n",
      "[Parallel(n_jobs=8)]: Done   9 out of   9 | elapsed: 1098.6min remaining:    0.0s\n"
     ]
    },
    {
     "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-ba0f5fe728f1>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     81\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[1;32m     82\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 83\u001b[0;31m \u001b[0mParallel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mnum_cores\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdelayed\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcompute_ds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mds\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mds\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdslist\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/usr/local/lib/python3.5/dist-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m    960\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    961\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mretrieval_context\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[0;32m--> 962\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mretrieve\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    963\u001b[0m             \u001b[0;31m# Make sure that we get a last message telling us we are done\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    964\u001b[0m             \u001b[0melapsed_time\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_start_time\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.5/dist-packages/joblib/parallel.py\u001b[0m in \u001b[0;36mretrieve\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    863\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    864\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'supports_timeout'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 865\u001b[0;31m                     \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_output\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtimeout\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    866\u001b[0m                 \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    867\u001b[0m                     \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_output\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\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[0;32m/usr/local/lib/python3.5/dist-packages/joblib/_parallel_backends.py\u001b[0m in \u001b[0;36mwrap_future_result\u001b[0;34m(future, timeout)\u001b[0m\n\u001b[1;32m    513\u001b[0m         AsyncResults.get from multiprocessing.\"\"\"\n\u001b[1;32m    514\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 515\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfuture\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    516\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mLokyTimeoutError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    517\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mTimeoutError\u001b[0m\u001b[0;34m(\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/joblib/externals/loky/_base.py\u001b[0m in \u001b[0;36mresult\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    424\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__get_result\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    425\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 426\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_condition\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    427\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    428\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_state\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mCANCELLED\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mCANCELLED_AND_NOTIFIED\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/lib/python3.5/threading.py\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    291\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m    \u001b[0;31m# restore state no matter what (e.g., KeyboardInterrupt)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    292\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mtimeout\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 293\u001b[0;31m                 \u001b[0mwaiter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0macquire\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    294\u001b[0m                 \u001b[0mgotit\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    295\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "# # test parallel computing\n",
    "# import psutil\n",
    "# # logical=True counts threads, but we are interested in cores\n",
    "# psutil.()# .cpu_count(logical=False)\n",
    "%load_ext line_profiler\n",
    "%matplotlib inline\n",
    "import functools\n",
    "from libs import *\n",
    "from sklearn.metrics.pairwise import rbf_kernel\n",
    "from joblib import Parallel, delayed\n",
    "import multiprocessing\n",
    "\n",
    "from pygraph.kernels.spKernel import spkernel\n",
    "from pygraph.utils.kernels import deltakernel, kernelsum\n",
    "\n",
    "num_cores = multiprocessing.cpu_count()\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': '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': 'Mutagenicity', 'dataset': '../datasets/Mutagenicity/Mutagenicity_A.txt'}, # node/edge symb\n",
    "    {'name': 'ENZYMES', 'dataset': '../datasets/ENZYMES_txt/ENZYMES_A_sparse.txt'}, # node symb/nsymb\n",
    "#     {'name': 'Fingerprint', 'dataset': '../datasets/Fingerprint/Fingerprint_A.txt'},\n",
    "    {'name': 'Letter-med', 'dataset': '../datasets/Letter-med/Letter-med_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': '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",
    "def compute_ds(ds):\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",
    "    \n",
    "#     %lprun -f spkernel \\\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()\n",
    "    \n",
    "Parallel(n_jobs=num_cores, verbose=10)(delayed(compute_ds)(ds) for ds in dslist)"
   ]
  },
  {
   "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",
      "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",
      "\n",
      " --- shortest path kernel matrix of size 183 built in 3.4878082275390625 seconds ---\n",
      "\n",
      "the gram matrix with parameters {'n_jobs': 8, 'node_kernels': {'mix': functools.partial(<function kernelsum at 0x7f8e59cb7048>, <function deltakernel at 0x7f8e59ddf048>, <function rbf_kernel at 0x7f8e5d3560d0>), 'symb': <function deltakernel at 0x7f8e59ddf048>, 'nsymb': <function rbf_kernel at 0x7f8e5d3560d0>}} is: \n",
      "[[1.         0.47140452 0.33333333 ... 0.30151134 0.30512858 0.27852425]\n",
      " [0.47140452 1.         0.         ... 0.14213381 0.11986583 0.17232809]\n",
      " [0.33333333 0.         1.         ... 0.36851387 0.37293493 0.34815531]\n",
      " ...\n",
      " [0.30151134 0.14213381 0.36851387 ... 1.         0.96429344 0.95175317]\n",
      " [0.30512858 0.11986583 0.37293493 ... 0.96429344 1.         0.96671243]\n",
      " [0.27852425 0.17232809 0.34815531 ... 0.95175317 0.96671243 1.        ]]\n"
     ]
    },
    {
     "data": {