wangwei
/
graphkit-learn
Not watched
1
0
Fork 0
Code
Releases 2 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
70 Commits
4 Branches
345 MB
0 Download
Tree: 06b32cdf8a
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '06b32cdf8a'
${ noResults }
graphkit-learn/notebooks/run_spkernel.ipynb

run_spkernel.ipynb 180 kB
Raw Normal View History

Plus de choses sont changées...
7 years ago
​
1. add parallel computing scheme to spkernel and model_selection_precomputed. 2. modify model_selection_precomputed so that all results are written into memory and then to a file at last section of code, in case that on cpu/disk seperated systems the IO takes too much time. 3. correct utils.floyd_warshall_numpy function. DONNOT use the last version.
7 years ago
​
​
1. upgrate spkernel, now supporting symbolic and non-symbolic node labels, directed and undirected graphs, and allowing user-defined node kernels. 2. model_selection_precomputed can now save all results as human readable text. 3. modify pygraph.utils.utils.floydTransformation and pygraph.utils.graphdataset.get_dataset_attributes.
7 years ago
​
​
Plus de choses sont changées...
7 years ago
​
​
​
​
​
1. apply multiprocessing.Pool.imap_unordered method instead of the map method, so that tqdm could be applied to track progress. 2. apply part of the Fast Computation of Shortest Path Kernel (FCSP) to speed up the sp kernel.
7 years ago
1. add parallel computing scheme to spkernel and model_selection_precomputed. 2. modify model_selection_precomputed so that all results are written into memory and then to a file at last section of code, in case that on cpu/disk seperated systems the IO takes too much time. 3. correct utils.floyd_warshall_numpy function. DONNOT use the last version.
7 years ago
​
​
​
1. apply multiprocessing.Pool.imap_unordered method instead of the map method, so that tqdm could be applied to track progress. 2. apply part of the Fast Computation of Shortest Path Kernel (FCSP) to speed up the sp kernel.
7 years ago
1. add parallel computing scheme to spkernel and model_selection_precomputed. 2. modify model_selection_precomputed so that all results are written into memory and then to a file at last section of code, in case that on cpu/disk seperated systems the IO takes too much time. 3. correct utils.floyd_warshall_numpy function. DONNOT use the last version.
7 years ago
​
​
​
​
​
1. apply multiprocessing.Pool.imap_unordered method instead of the map method, so that tqdm could be applied to track progress. 2. apply part of the Fast Computation of Shortest Path Kernel (FCSP) to speed up the sp kernel.
7 years ago
1. add parallel computing scheme to spkernel and model_selection_precomputed. 2. modify model_selection_precomputed so that all results are written into memory and then to a file at last section of code, in case that on cpu/disk seperated systems the IO takes too much time. 3. correct utils.floyd_warshall_numpy function. DONNOT use the last version.
7 years ago
1. apply multiprocessing.Pool.imap_unordered method instead of the map method, so that tqdm could be applied to track progress. 2. apply part of the Fast Computation of Shortest Path Kernel (FCSP) to speed up the sp kernel.
7 years ago
​
1. add parallel computing scheme to spkernel and model_selection_precomputed. 2. modify model_selection_precomputed so that all results are written into memory and then to a file at last section of code, in case that on cpu/disk seperated systems the IO takes too much time. 3. correct utils.floyd_warshall_numpy function. DONNOT use the last version.
7 years ago
1. apply multiprocessing.Pool.imap_unordered method instead of the map method, so that tqdm could be applied to track progress. 2. apply part of the Fast Computation of Shortest Path Kernel (FCSP) to speed up the sp kernel.
7 years ago
1. add parallel computing scheme to spkernel and model_selection_precomputed. 2. modify model_selection_precomputed so that all results are written into memory and then to a file at last section of code, in case that on cpu/disk seperated systems the IO takes too much time. 3. correct utils.floyd_warshall_numpy function. DONNOT use the last version.
7 years ago
1. apply multiprocessing.Pool.imap_unordered method instead of the map method, so that tqdm could be applied to track progress. 2. apply part of the Fast Computation of Shortest Path Kernel (FCSP) to speed up the sp kernel.
7 years ago
​
​
​
1. add parallel computing scheme to spkernel and model_selection_precomputed. 2. modify model_selection_precomputed so that all results are written into memory and then to a file at last section of code, in case that on cpu/disk seperated systems the IO takes too much time. 3. correct utils.floyd_warshall_numpy function. DONNOT use the last version.
7 years ago
1. apply multiprocessing.Pool.imap_unordered method instead of the map method, so that tqdm could be applied to track progress. 2. apply part of the Fast Computation of Shortest Path Kernel (FCSP) to speed up the sp kernel.
7 years ago
​
​
1. add parallel computing scheme to spkernel and model_selection_precomputed. 2. modify model_selection_precomputed so that all results are written into memory and then to a file at last section of code, in case that on cpu/disk seperated systems the IO takes too much time. 3. correct utils.floyd_warshall_numpy function. DONNOT use the last version.
7 years ago
​
​
​
 123456789101112131415161718192021222324252627282930313233343536373839404142434445 
  1. {

  2.  "cells": [

  3.   {

  4.    "cell_type": "code",

  5.    "execution_count": null,

  6.    "metadata": {

  7.     "scrolled": false

  8.    },

  9.    "outputs": [

  10.     {

  11.      "name": "stdout",

  12.      "output_type": "stream",

  13.      "text": [

  14.       "\n",

  15.       "Letter-med\n",

  16.       "\n",

  17.       "--- This is a classification problem ---\n",

  18.       "\n",

  19.       "\n",

  20.       "I. Loading dataset from file...\n",

  21.       "\n",

  22.       "2. Calculating gram matrices. This could take a while...\n",

  23.       "\n",

  24.       " None edge weight specified. Set all weight to 1.\n",

  25.       "\n",

  26.       "\n",

  27.       " 9 graphs are removed as they don't contain edges.\n",

  28.       "\n",

  29.       "getting sp graphs: 2241it [00:01, 2167.27it/s]\n",

  30.       "calculating kernels: 2512161it [35:21, 1183.88it/s]\n",

  31.       "\n",

  32.       " --- shortest path kernel matrix of size 2241 built in 2123.1229825019836 seconds ---\n",

  33.       "\n",

  34.       "the gram matrix with parameters {'n_jobs': 8, 'node_kernels': {'symb': <function deltakernel at 0x7ff7faecad08>, 'mix': functools.partial(<function kernelsum at 0x7ff7fae8a0d0>, <function deltakernel at 0x7ff7faecad08>, <function rbf_kernel at 0x7ff7fe535158>), 'nsymb': <function rbf_kernel at 0x7ff7fe535158>}} is: \n",

  35.       "[[1.         0.12737447 0.24414863 ... 0.08575717 0.24779506 0.13389497]\n",

  36.       " [0.12737447 1.         0.26175695 ... 0.45546182 0.49016833 0.67892735]\n",

  37.       " [0.24414863 0.26175695 1.         ... 0.3161496  0.27686542 0.26213761]\n",

  38.       " ...\n",

  39.       " [0.08575717 0.45546182 0.3161496  ... 1.         0.47821266 0.36507203]\n",

  40.       " [0.24779506 0.49016833 0.27686542 ... 0.47821266 1.         0.58909   ]\n",

  41.       " [0.13389497 0.67892735 0.26213761 ... 0.36507203 0.58909    1.        ]]\n"

  42.      ]

  43.     },

  44.     {

  45.      "data": {

A Python package for graph kernels, graph edit distances and graph pre-image problem.