synthetic-graph-benchmarks 0.1.0__py3-none-any.whl

synthetic_graph_benchmarks/utils.py

@@ -0,0 +1,56 @@
+import os
+import requests
+
+def download_file(url: str, folder: str) -> str:
+    """
+    Download a file from the given URL and save it to the specified folder.
+    
+    Args:
+        url (str): The URL of the file to download.
+        folder (str): The folder where the file will be saved.
+    
+    Returns:
+        str: The path to the downloaded file.
+    """
+    os.makedirs(folder, exist_ok=True)
+    filename = url.split("/")[-1]
+    filepath = f"{folder}/{filename}"
+    if os.path.exists(filepath):
+        print(f"File {filename} already exists in {folder}. Skipping download.")
+        return filepath
+    response = requests.get(url)
+    response.raise_for_status()  # Raise an error for bad responses
+    
+    with open(filepath, "wb") as file:
+        file.write(response.content)
+    
+    return filepath
+
+
+def available_cpu_count():
+    # 1. Slurm-aware (allocated CPUs)
+    slurm_cpus = os.environ.get("SLURM_CPUS_ON_NODE") or os.environ.get(
+        "SLURM_CPUS_PER_TASK"
+    )
+    if slurm_cpus:
+        return int(slurm_cpus)
+
+    # 2. Respect CPU affinity if psutil is available
+    try:
+        process = psutil.Process()
+        if hasattr(process, "cpu_affinity"):
+            # psutil.cpu_count() returns the number of logical CPUs
+            # cpu_affinity() returns the CPUs that the process is allowed to run on
+            # We return the length of the CPU affinity list
+            affinity = process.cpu_affinity()
+            if affinity:
+                return len(affinity)
+    except Exception:
+        pass
+
+    # 3. Try Python 3.9+'s os.sched_getaffinity (Linux only)
+    if hasattr(os, "sched_getaffinity"):
+        return len(os.sched_getaffinity(0))
+
+    # 4. Fall back to all visible CPUs (may overcount on clusters)
+    return os.cpu_count() or 1  # fallback to 1 if os.cpu_count() returns None

synthetic_graph_benchmarks-0.1.0.dist-info/METADATA

@@ -0,0 +1,227 @@
+Metadata-Version: 2.4
+Name: synthetic-graph-benchmarks
+Version: 0.1.0
+Summary: Standardized benchmarks for evaluating synthetic graph generation methods
+Project-URL: Homepage, https://github.com/peteole/synthetic_graph_benchmarks
+Project-URL: Repository, https://github.com/peteole/synthetic_graph_benchmarks
+Project-URL: Documentation, https://github.com/peteole/synthetic_graph_benchmarks#readme
+Project-URL: Bug Tracker, https://github.com/peteole/synthetic_graph_benchmarks/issues
+Author-email: Ole Petersen <peteole2707@gmail.com>
+Maintainer-email: Ole Petersen <peteole2707@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: benchmarks,evaluation-metrics,graph-generation,graph-neural-networks,machine-learning,networkx,synthetic-graphs
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Mathematics
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Requires-Dist: networkx>=3.4.2
+Requires-Dist: numpy>=2.2.6
+Requires-Dist: orca-graphlets>=0.1.4
+Requires-Dist: pygsp>=0.5.1
+Requires-Dist: requests>=2.32.4
+Requires-Dist: scikit-learn>=1.7.1
+Requires-Dist: scipy>=1.15.3
+Requires-Dist: torch>=2.3.0
+Description-Content-Type: text/markdown
+
+# Synthetic Graph Benchmarks
+
+[![PyPI version](https://badge.fury.io/py/synthetic-graph-benchmarks.svg)](https://badge.fury.io/py/synthetic-graph-benchmarks)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+A Python package implementing standardized benchmarks for evaluating synthetic graph generation methods, based on the evaluation frameworks introduced in:
+
+- [**SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators**](https://arxiv.org/pdf/2204.01613) (ICML 2022)
+- [**Efficient and Scalable Graph Generation through Iterative Local Expansion**](https://arxiv.org/html/2312.11529v4) (2023)
+
+This package provides a unified interface for benchmarking graph generation algorithms against established datasets and metrics used in the graph generation literature.
+
+## Features
+
+- **Standardized Datasets**: Access to benchmark datasets including Stochastic Block Model (SBM), Planar graphs, and Tree graphs
+- **Comprehensive Metrics**: Implementation of key evaluation metrics including:
+  - Degree distribution comparison (MMD)
+  - Clustering coefficient analysis  
+  - Orbit count statistics (using ORCA)
+  - Spectral properties analysis
+  - Wavelet coefficient comparison
+- **Validation Metrics**: Graph-type specific validation (planarity, tree properties, SBM likelihood)
+- **Reproducible Evaluation**: Consistent benchmarking across different graph generation methods
+- **Easy Integration**: Simple API for evaluating your own graph generation algorithms
+
+## Installation
+
+### From PyPI (recommended)
+
+```bash
+pip install synthetic-graph-benchmarks
+```
+
+### From Source
+
+```bash
+git clone https://github.com/peteole/synthetic_graph_benchmarks.git
+cd synthetic_graph_benchmarks
+pip install -e .
+```
+
+## Quick Start
+
+```python
+import networkx as nx
+from synthetic_graph_benchmarks import (
+    benchmark_planar_results,
+    benchmark_sbm_results, 
+    benchmark_tree_results
+)
+
+# Generate some example graphs (replace with your graph generation method)
+generated_graphs = [nx.erdos_renyi_graph(64, 0.1) for _ in range(20)]
+
+# Benchmark against planar graph dataset
+results = benchmark_planar_results(generated_graphs)
+print(f"Planar accuracy: {results['planar_acc']:.3f}")
+print(f"Average metric ratio: {results['average_ratio']:.3f}")
+
+# Benchmark against SBM dataset  
+sbm_results = benchmark_sbm_results(generated_graphs)
+print(f"SBM accuracy: {sbm_results['sbm_acc']:.3f}")
+
+# Benchmark against tree dataset
+tree_results = benchmark_tree_results(generated_graphs)
+print(f"Tree accuracy: {tree_results['planar_acc']:.3f}")
+```
+
+## Datasets
+
+The package provides access to three standard benchmark datasets:
+
+### Stochastic Block Model (SBM)
+- **Size**: 200 graphs
+- **Properties**: 2-5 communities, 20-40 nodes per community
+- **Edge probabilities**: 0.3 intra-community, 0.05 inter-community
+
+### Planar Graphs  
+- **Size**: 200 graphs with 64 nodes each
+- **Generation**: Delaunay triangulation on random points in unit square
+- **Properties**: Guaranteed planarity
+
+### Tree Graphs
+- **Size**: 200 graphs with 64 nodes each  
+- **Properties**: Connected acyclic graphs (trees)
+
+## Evaluation Metrics
+
+### Graph Statistics
+- **Degree Distribution**: Maximum Mean Discrepancy (MMD) between degree histograms
+- **Clustering Coefficient**: Local clustering coefficient comparison
+- **Orbit Counts**: 4-node orbit statistics using ORCA package
+- **Spectral Properties**: Laplacian eigenvalue distribution analysis
+- **Wavelet Coefficients**: Graph wavelet signature comparison
+
+### Validity Metrics
+- **Planar Accuracy**: Fraction of generated graphs that are planar
+- **Tree Accuracy**: Fraction of generated graphs that are trees (acyclic)
+- **SBM Accuracy**: Likelihood of graphs under fitted SBM parameters
+
+### Quality Scores
+- **Uniqueness**: Fraction of non-isomorphic graphs in generated set
+- **Novelty**: Fraction of generated graphs not isomorphic to training graphs
+- **Validity-Uniqueness-Novelty (VUN)**: Combined score for overall quality
+
+## Advanced Usage
+
+### Custom Evaluation
+
+```python
+from synthetic_graph_benchmarks.dataset import Dataset
+from synthetic_graph_benchmarks.spectre_utils import PlanarSamplingMetrics
+
+# Load dataset manually
+dataset = Dataset.load_planar()
+print(f"Training graphs: {len(dataset.train_graphs)}")
+print(f"Validation graphs: {len(dataset.val_graphs)}")
+
+# Use metrics directly
+metrics = PlanarSamplingMetrics(dataset)
+test_metrics = metrics.forward(dataset.train_graphs, test=True)
+results = metrics.forward(generated_graphs, ref_metrics={"test": test_metrics}, test=True)
+```
+
+### Accessing Individual Metrics
+
+```python
+# Get detailed breakdown of all metrics
+results = benchmark_planar_results(generated_graphs)
+
+# Individual metric values
+print(f"Degree MMD: {results['degree']:.6f}")
+print(f"Clustering MMD: {results['clustering']:.6f}")  
+print(f"Orbit MMD: {results['orbit']:.6f}")
+print(f"Spectral MMD: {results['spectre']:.6f}")
+print(f"Wavelet MMD: {results['wavelet']:.6f}")
+
+# Ratios compared to training set
+print(f"Degree ratio: {results['degree_ratio']:.3f}")
+print(f"Average ratio: {results['average_ratio']:.3f}")
+```
+
+## Citing
+
+If you use this package in your research, please cite the original papers:
+
+```bibtex
+@inproceedings{martinkus2022spectre,
+  title={SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators},
+  author={Martinkus, Karolis and Loukas, Andreas and Perraudin, Nathanaël and Wattenhofer, Roger},
+  booktitle={International Conference on Machine Learning},
+  pages={15159--15202},
+  year={2022},
+  organization={PMLR}
+}
+
+@article{bergmeister2023efficient,
+  title={Efficient and Scalable Graph Generation through Iterative Local Expansion},
+  author={Bergmeister, Andreas and Martinkus, Karolis and Perraudin, Nathanaël and Wattenhofer, Roger},
+  journal={arXiv preprint arXiv:2312.11529},
+  year={2023}
+}
+```
+
+## Dependencies
+
+- Python ≥ 3.10
+- NetworkX ≥ 3.4.2
+- NumPy ≥ 2.2.6  
+- SciPy ≥ 1.15.3
+- PyGSP ≥ 0.5.1
+- scikit-learn ≥ 1.7.1
+- ORCA-graphlets ≥ 0.1.4
+- PyTorch ≥ 2.3.0
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Acknowledgments
+
+This package is based on evaluation frameworks developed by:
+- Karolis Martinkus (SPECTRE paper)
+- Andreas Bergmeister (Iterative Local Expansion paper)
+- The original GRAN evaluation codebase
+- NetworkX and PyGSP communities

synthetic_graph_benchmarks-0.1.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+synthetic_graph_benchmarks/__init__.py,sha256=pMEdpnJXD8laVjCG4zd8d555chyqXv3-2WGxnrKFAQg,660
+synthetic_graph_benchmarks/benchmarks.py,sha256=jWDaVrAwe4uYaKl1EnUIVqavDz5ZeuxcSOcHyMwUPBc,2707
+synthetic_graph_benchmarks/dataset.py,sha256=Yca2fNPvRu7cOFyjjixkyqttboC07iPDgUXZWvvweN0,1515
+synthetic_graph_benchmarks/dist_helper.py,sha256=rwtpP_IaIe8DcS5OvrSkYdF8xl7VBHaGoM3jv_Yeeos,7001
+synthetic_graph_benchmarks/spectre_utils.py,sha256=CuOQdTlznar9_FIM66qoYk5zg1OEfa4M8be4WwHsFKA,41734
+synthetic_graph_benchmarks/utils.py,sha256=Y5QTRmGjr79p1Y6h54c6k9kXz-jDveoj0ZjpAMKml50,1835
+synthetic_graph_benchmarks-0.1.0.dist-info/METADATA,sha256=7zz-Yd3WXLVNjax5UPbkmPWO0n2uMRTD9w531tuqc3I,8484
+synthetic_graph_benchmarks-0.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+synthetic_graph_benchmarks-0.1.0.dist-info/entry_points.txt,sha256=KvCdlYfIhAw2srO-7H9XG0jTaAIENxGXprw0B4aClco,79
+synthetic_graph_benchmarks-0.1.0.dist-info/licenses/LICENSE,sha256=VDqzZZ7UjLMPLrsbgpHsMCW-H4msljYwm9z61rQSIsc,1069
+synthetic_graph_benchmarks-0.1.0.dist-info/RECORD,,

synthetic_graph_benchmarks-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.27.0
+Root-Is-Purelib: true
+Tag: py3-none-any

synthetic_graph_benchmarks-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+synthetic-graph-benchmarks = synthetic_graph_benchmarks:main

synthetic_graph_benchmarks-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Ole Petersen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.