Created
July 16, 2024 03:59
-
-
Save pakkinlau/aa07123a7b02dae73a70d16f1a3242ec to your computer and use it in GitHub Desktop.
print_pytorch_geometric_data_info.ipynb aims to print out PyTorch Graph Data flexibly
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"Nodes:\n", | |
" document:\n", | |
" x=torch.Size([10050, 34])\n", | |
" year=torch.Size([10050])\n", | |
" language=torch.Size([10050])\n", | |
" context:\n", | |
" x=torch.Size([903, 1])\n", | |
" year=torch.Size([903])\n", | |
" region=torch.Size([903])\n", | |
" prediction_target:\n", | |
" popularity=torch.Size([301, 3])\n", | |
" sentiment=torch.Size([301, 3])\n", | |
"\n", | |
"Edges:\n", | |
" ('document', 'semantic', 'document'):\n", | |
" edge_index=torch.Size([2, 30029])\n", | |
" edge_type=torch.Size([30029])\n", | |
" ('document', 'bridging', 'context'):\n", | |
" edge_index=torch.Size([2, 20168])\n", | |
" ('context', 'temporal', 'context'):\n", | |
" edge_index=torch.Size([2, 900])\n" | |
] | |
} | |
], | |
"source": [ | |
"import torch\n", | |
"from torch_geometric.data import HeteroData\n", | |
"\n", | |
"def print_data_size_info(file_path):\n", | |
" data = torch.load(file_path)\n", | |
" \n", | |
" if not isinstance(data, HeteroData):\n", | |
" print(\"The loaded data is not a HeteroData object.\")\n", | |
" return\n", | |
" \n", | |
" print(\"Nodes:\")\n", | |
" for node_type in data.node_types:\n", | |
" print(f\" {node_type}:\")\n", | |
" for attr, tensor in data[node_type].items():\n", | |
" print(f\" {attr}={tensor.size()}\")\n", | |
" \n", | |
" print(\"\\nEdges:\")\n", | |
" for edge_type in data.edge_types:\n", | |
" print(f\" {edge_type}:\")\n", | |
" for attr, tensor in data[edge_type].items():\n", | |
" print(f\" {attr}={tensor.size()}\")\n", | |
"\n", | |
"# Example usage\n", | |
"file_path = 'eurochinaGNN_dataset_revised_bridging_edges.pt'\n", | |
"print_data_size_info(file_path)" | |
] | |
} | |
], | |
"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": "3.12.3" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment