Skip to content

Commit

Permalink
dgl 0.4.2 with ZINC-full
Browse files Browse the repository at this point in the history
  • Loading branch information
@vijaydwivedi75
vijaydwivedi75 committed Nov 2, 2020
1 parent 03da731 commit c57794a
Show file tree
Hide file tree
Showing 14 changed files with 1,254 additions and 404 deletions.
6 changes: 6 additions & 0 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,12 @@

## Updates

**Nov 2, 2020**
* This branch of the project is compatible with DGL 0.4.2.
* Added [ZINC-full](./data/script_download_molecules.sh) dataset (249K molecular graphs) with [scripts](./scripts/ZINC-full/).



**Jun 11, 2020**
* Second release of the project. Major updates :
+ Added experimental pipeline for Weisfeiler-Lehman-GNNs operating on dense rank-2 tensors.
Expand Down
199 changes: 2 additions & 197 deletions data/SBMs/generate_SBM_CLUSTER.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -208,9 +208,7 @@
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"scrolled": false
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -392,199 +390,6 @@
"print('Time (sec):',time.time() - start) # 190s\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Convert to DGL format and save with pickle"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/Users/xbresson/Documents/Dropbox/06_NTU_2017_now/03_my_codes/34_benchmark20/GITHUB_benchmark_project/benchmarking-gnn\n"
]
}
],
"source": [
"import os\n",
"os.chdir('../../') # go to root folder of the project\n",
"print(os.getcwd())\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"\n",
"import pickle\n",
"\n",
"%load_ext autoreload\n",
"%autoreload 2\n",
"\n",
"from data.SBMs import SBMsDatasetDGL \n",
"\n",
"from data.data import LoadData\n",
"from torch.utils.data import DataLoader\n",
"from data.SBMs import SBMsDataset\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[I] Loading data ...\n",
"preparing 10000 graphs for the TRAIN set...\n",
"preparing 1000 graphs for the TEST set...\n",
"preparing 1000 graphs for the VAL set...\n",
"[I] Finished loading.\n",
"[I] Data load time: 3983.7924s\n",
"Time (sec): 3983.794214248657\n"
]
}
],
"source": [
"DATASET_NAME = 'SBM_CLUSTER'\n",
"dataset = SBMsDatasetDGL(DATASET_NAME) #3983s\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"10000\n",
"1000\n",
"1000\n",
"(DGLGraph(num_nodes=117, num_edges=4104,\n",
" ndata_schemes={'feat': Scheme(shape=(), dtype=torch.int64)}\n",
" edata_schemes={'feat': Scheme(shape=(1,), dtype=torch.float32)}), tensor([0, 3, 3, 0, 4, 3, 0, 2, 0, 0, 0, 2, 2, 0, 1, 5, 3, 0, 2, 4, 2, 3, 2, 4,\n",
" 3, 1, 3, 5, 2, 3, 0, 0, 3, 5, 2, 5, 3, 2, 0, 3, 0, 3, 3, 3, 0, 3, 2, 0,\n",
" 3, 5, 2, 4, 1, 1, 3, 4, 4, 3, 3, 3, 0, 5, 2, 4, 3, 0, 0, 4, 3, 0, 0, 1,\n",
" 4, 2, 3, 2, 0, 0, 0, 4, 2, 2, 3, 3, 3, 0, 0, 2, 2, 5, 4, 0, 2, 5, 4, 0,\n",
" 0, 2, 0, 0, 0, 3, 3, 2, 2, 1, 2, 0, 0, 0, 5, 3, 1, 4, 3, 3, 5],\n",
" dtype=torch.int16))\n",
"(DGLGraph(num_nodes=90, num_edges=2396,\n",
" ndata_schemes={'feat': Scheme(shape=(), dtype=torch.int64)}\n",
" edata_schemes={'feat': Scheme(shape=(1,), dtype=torch.float32)}), tensor([1, 0, 0, 4, 4, 0, 5, 3, 4, 0, 3, 1, 0, 5, 5, 5, 1, 3, 3, 4, 1, 2, 5, 4,\n",
" 5, 5, 2, 0, 5, 3, 2, 5, 5, 5, 5, 0, 3, 3, 0, 2, 3, 3, 3, 3, 5, 3, 1, 1,\n",
" 5, 2, 5, 1, 1, 4, 5, 2, 0, 4, 4, 0, 3, 4, 0, 0, 2, 3, 5, 3, 3, 4, 0, 5,\n",
" 1, 0, 0, 0, 0, 2, 4, 0, 5, 0, 3, 0, 5, 3, 4, 3, 0, 5],\n",
" dtype=torch.int16))\n",
"(DGLGraph(num_nodes=134, num_edges=5570,\n",
" ndata_schemes={'feat': Scheme(shape=(), dtype=torch.int64)}\n",
" edata_schemes={'feat': Scheme(shape=(1,), dtype=torch.float32)}), tensor([2, 5, 4, 4, 4, 5, 2, 1, 5, 0, 0, 1, 5, 5, 4, 2, 5, 5, 0, 0, 3, 0, 1, 2,\n",
" 2, 5, 0, 2, 0, 5, 1, 5, 5, 1, 0, 0, 5, 2, 2, 5, 5, 1, 4, 0, 0, 5, 1, 0,\n",
" 3, 0, 5, 1, 5, 4, 0, 4, 5, 1, 5, 4, 4, 0, 2, 5, 2, 5, 0, 1, 0, 1, 2, 0,\n",
" 2, 2, 0, 3, 2, 4, 0, 5, 2, 0, 2, 2, 5, 4, 2, 0, 4, 0, 0, 5, 1, 0, 5, 3,\n",
" 2, 3, 5, 0, 1, 5, 2, 0, 1, 4, 0, 3, 2, 1, 0, 2, 1, 4, 2, 5, 2, 0, 5, 2,\n",
" 5, 5, 0, 1, 5, 4, 2, 2, 2, 0, 1, 0, 2, 1], dtype=torch.int16))\n"
]
}
],
"source": [
"print(len(dataset.train))\n",
"print(len(dataset.val))\n",
"print(len(dataset.test))\n",
"\n",
"print(dataset.train[0])\n",
"print(dataset.val[0])\n",
"print(dataset.test[0])\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Time (sec): 15.637878656387329\n"
]
}
],
"source": [
"start = time.time()\n",
"\n",
"with open('data/SBMs/SBM_CLUSTER.pkl','wb') as f:\n",
" pickle.dump([dataset.train,dataset.val,dataset.test],f)\n",
" \n",
"print('Time (sec):',time.time() - start)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Test load function"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[I] Loading dataset SBM_CLUSTER...\n",
"train, test, val sizes : 10000 1000 1000\n",
"[I] Finished loading.\n",
"[I] Data load time: 29.6175s\n"
]
}
],
"source": [
"DATASET_NAME = 'SBM_CLUSTER'\n",
"dataset = LoadData(DATASET_NAME) # 29s\n",
"trainset, valset, testset = dataset.train, dataset.val, dataset.test\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'data.SBMs.SBMsDataset'>\n",
"Time (sec): 0.002402067184448242\n"
]
}
],
"source": [
"start = time.time()\n",
"\n",
"batch_size = 10\n",
"collate = SBMsDataset.collate\n",
"print(SBMsDataset)\n",
"train_loader = DataLoader(trainset, batch_size=batch_size, shuffle=True, collate_fn=collate)\n",
"\n",
"print('Time (sec):',time.time() - start) #0.002s\n"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down Expand Up @@ -620,5 +425,5 @@
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}
Loading

0 comments on commit c57794a

Please sign in to comment.