OpenI
/
graphkit-learn
Not watched
1
0
Fork 0
Code
Releases 2 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
Browse Source

New translations run_randomwalkkernel.ipynb (Chinese Simplified)

l10n_v0.2.x
linlin 4 years ago
parent
b58dbd4f12
commit
33cd745bd3
1 changed files with 333 additions and 0 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +333
    -0
      lang/zh/notebooks/run_randomwalkkernel.ipynb

+ 333
- 0
lang/zh/notebooks/run_randomwalkkernel.ipynb View File

@@ -0,0 +1,333 @@
{
"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, 5308.25it/s]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"../gklearn/kernels/randomWalkKernel.py:108: UserWarning: All labels are ignored.\n",
" warnings.warn('All labels are ignored.')\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"calculating kernels: 16836it [00:00, 65408.89it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.4157981872558594 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 0.1, 'n_jobs': 8, 'verbose': True} 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, 5205.09it/s]\n",
"calculating kernels: 16836it [00:00, 73715.56it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.36714887619018555 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 0.01, 'n_jobs': 8, 'verbose': True} 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, 5344.96it/s]\n",
"calculating kernels: 16836it [00:00, 68817.65it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.3666379451751709 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 0.001, 'n_jobs': 8, 'verbose': True} 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, 5295.73it/s]\n",
"calculating kernels: 16836it [00:00, 74865.49it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.36979222297668457 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 0.0001, 'n_jobs': 8, 'verbose': True} 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, 5040.80it/s]\n",
"calculating kernels: 16836it [00:00, 70923.54it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.3692610263824463 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-05, 'n_jobs': 8, 'verbose': True} 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, 5326.60it/s]\n",
"calculating kernels: 16836it [00:00, 73697.55it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.37317800521850586 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-06, 'n_jobs': 8, 'verbose': True} 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, 5705.98it/s]\n",
"calculating kernels: 16836it [00:00, 64238.65it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.36565732955932617 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-07, 'n_jobs': 8, 'verbose': True} 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, 4833.15it/s]\n",
"calculating kernels: 16836it [00:00, 69971.77it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.37798523902893066 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-08, 'n_jobs': 8, 'verbose': True} 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, 4170.94it/s]\n",
"calculating kernels: 16836it [00:00, 64187.38it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.39433860778808594 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-09, 'n_jobs': 8, 'verbose': True} 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, 5273.43it/s]\n",
"calculating kernels: 16836it [00:00, 69555.28it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 0.3833920955657959 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'sylvester', 'weight': 1e-10, 'n_jobs': 8, 'verbose': True} 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, 1.11s/it]\n",
"\n",
"4. Getting final performance...\n",
"best_params_out: [{'compute_method': 'sylvester', 'weight': 0.01, 'n_jobs': 8, 'verbose': True}]\n",
"best_params_in: [{'alpha': 1e-10}]\n",
"\n",
"best_val_perf: 31.76835551233969\n",
"best_val_std: 0.43269972907929183\n",
"final_performance: [32.391882524496765]\n",
"final_confidence: [2.6542337929023336]\n",
"train_performance: [30.70127313658435]\n",
"train_std: [0.31861204198126475]\n",
"\n",
"time to calculate gram matrix with different hyper-params: 0.38±0.02s\n",
"time to calculate best gram matrix: 0.37±0.00s\n",
"total training time with all hyper-param choices: 40.53s\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, 28950.24it/s]\n",
"calculating kernels: 16836it [00:02, 6540.43it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 2.6675093173980713 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'conjugate', 'edge_kernels': {'symb': <function deltakernel at 0x7fe9b0a2d730>, 'nsymb': <function gaussiankernel at 0x7fe9b0a2d7b8>, 'mix': functools.partial(<function kernelproduct at 0x7fe9b0a2d8c8>, <function deltakernel at 0x7fe9b0a2d730>, <function gaussiankernel at 0x7fe9b0a2d7b8>)}, 'node_kernels': {'symb': <function deltakernel at 0x7fe9b0a2d730>, 'nsymb': <function gaussiankernel at 0x7fe9b0a2d7b8>, 'mix': functools.partial(<function kernelproduct at 0x7fe9b0a2d8c8>, <function deltakernel at 0x7fe9b0a2d730>, <function gaussiankernel at 0x7fe9b0a2d7b8>)}, 'weight': 0.1, 'n_jobs': 8, 'verbose': True} is: \n",
"\n",
"\n",
"\n",
" None edge weight specified. Set all weight to 1.\n",
"\n",
"reindex vertices: 100%|██████████| 183/183 [00:00<00:00, 28019.19it/s]\n",
"calculating kernels: 16836it [00:02, 7963.48it/s]\n",
"\n",
" --- kernel matrix of random walk kernel of size 183 built in 2.2675061225891113 seconds ---\n",
"\n",
"the gram matrix with parameters {'compute_method': 'conjugate', 'edge_kernels': {'symb': <function deltakernel at 0x7fe9b0a2d730>, 'nsymb': <function gaussiankernel at 0x7fe9b0a2d7b8>, 'mix': functools.partial(<function kernelproduct at 0x7fe9b0a2d8c8>, <function deltakernel at 0x7fe9b0a2d730>, <function gaussiankernel at 0x7fe9b0a2d7b8>)}, 'node_kernels': {'symb': <function deltakernel at 0x7fe9b0a2d730>, 'nsymb': <function gaussiankernel at 0x7fe9b0a2d7b8>, 'mix': functools.partial(<function kernelproduct at 0x7fe9b0a2d8c8>, <function deltakernel at 0x7fe9b0a2d730>, <function gaussiankernel at 0x7fe9b0a2d7b8>)}, 'weight': 0.01, 'n_jobs': 8, 'verbose': True} is: \n",
"\n",
"\n",
"\n",
" None edge weight specified. Set all weight to 1.\n",
"\n",
"reindex vertices: 100%|██████████| 183/183 [00:00<00:00, 23036.63it/s]\n",
"calculating kernels: 12801it [00:01, 8043.11it/s]"
]
}
],
"source": [
"# %load_ext line_profiler\n",
"# %matplotlib inline\n",
"import functools\n",
"from libs import *\n",
"import multiprocessing\n",
"\n",
"from gklearn.kernels.randomWalkKernel import randomwalkkernel\n",
"from gklearn.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_A.txt'}, # 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/DD/DD_A.txt'}, # 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",
" verbose=True)\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
}

Write Preview
Loading…
Cancel
Save