{"success":true,"data":{"author":"ohlstrom (Hugging Face); structures from the Crystallography Open Database","bucketAccessType":"public","bucketName":"ohlstrom/Crystallography-Open-Database-XRD-Patterns","bucketPrefix":"","category":"Chemistry & Materials","cloudProvider":"huggingface","createdAt":"2026-11-22T01:09:20.731Z","description":"Simulated powder X-ray diffraction (PXRD) patterns for every CIF crystal structure in the Crystallography Open Database (COD): 436,196 diffractograms spanning metals, minerals, organic molecular crystals and metal-organic frameworks. Each pattern was computed with the pymatgen XRDCalculator for Cu K-alpha radiation (1.54184 angstrom) over 2-theta 0 to 90 degrees at a 0.02 degree step, giving a 4,500-point intensity vector min-max scaled to [0, 1]. Files are PyTorch .pt dictionaries holding a patterns tensor of shape (N, 4500) and the matching COD CIF filenames, so each pattern links back to its structure at crystallography.net by COD ID. The full set ships with random subsets of 1,000, 10,000, 50,000 and 100,000 patterns for prototyping. No measured diffractograms are included. Use it to train phase identification, crystal system and space group classifiers, or diffraction-to-structure models; load with torch.load. License CC0 1.0, the same as COD. Cite Grazulis et al., Crystallography Open Database, J. Appl. Cryst. 42, 726 (2009), and pymatgen (Ong et al. 2013).","displayTitle":"COD Synthetic Powder X-Ray Diffraction (XRD) Patterns: 436,196 Simulated Diffractograms from the Crystallography Open Database","huggingFaceUrl":"https://huggingface.co/datasets/ohlstrom/Crystallography-Open-Database-XRD-Patterns","id":"e6dda98d-9170-5c52-9b09-9c07b62e4b83","license":"CC0-1.0","licenseEvidenceUrl":"https://huggingface.co/datasets/ohlstrom/Crystallography-Open-Database-XRD-Patterns","objectCountEstimate":7,"probeStatus":"ok","referenceUrl":"https://www.crystallography.net/cod/","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"ohlstrom/Crystallography-Open-Database-XRD-Patterns\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"ohlstrom/Crystallography-Open-Database-XRD-Patterns\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=ohlstrom, license:cc0-1.0, size_categories:100K<n<1M, downloads=370"],"format":"mixed","generatedAt":"2026-11-22T01:10:20.277Z","layout":{"example":"COD_xrd_patterns_1000.pt","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"COD_xrd_patterns_1000.pt","truncatedAt":512}],"sampleObjects":["COD_xrd_patterns_1000.pt","COD_xrd_patterns_10000.pt","COD_xrd_patterns_100000.pt","COD_xrd_patterns_50000.pt","COD_xrd_patterns_and_ID.pt"],"sidecars":[{"bytes":"\n---\nlicense: cc0-1.0\ntask_categories:\n  - other\ntags:\n  - chemistry\n  - crystallography\n  - xrd\n  - materials-science\npretty_name: COD XRD Patterns\nsize_categories:\n  - 100K<n<1M\n---\n\n# Crystallography Open Database — Synthetic XRD Patterns\n\n436,196 synthetic powder X-ray diffraction (XRD) patterns generated from every CIF file in the [Crystallography Open Database](https://www.crystallography.net/cod/) (COD).\n\n## What's in the dataset\n\nEach pattern is a simulated powder diffractogram computed from a published crystal structure. The dataset covers the full chemical and structural diversity of COD: metals, minerals, organics, MOFs, and everything in between. No measured (experimental) patterns are included — these are purely computational.\n\n## Files and subsets\n\n| File | Patterns | Purpose |\n|---|---|---|\n| `COD_xrd_patterns_1000.pt` | 1,000 | Quick prototyping |\n| `COD_xrd_patterns_10000.pt` | 10,000 | Development / hyperparameter tuning |\n| `COD_xrd_patterns_50000.pt` | 50,000 | Development / hyperparameter tuning |\n| `COD_xrd_patterns_100000.pt` | 100,000 | Development / hyperparameter tuning |\n| `COD_xrd_patterns.pt` | 436,196 | Full dataset |\n\nThe smaller subsets are random samples drawn from the full set.\n\n## Data format\n\nEach `.pt` file is a Python dictionary saved with `torch.save()`. Load it with:\n\n```python\nimport torch\n\ndata = torch.load(\"COD_xrd_patterns.pt\")\n\npatterns = data[\"patterns\"]    # torch.Tensor, shape (N, 4500)\nfilenames = data[\"filenames\"]  # list[str], length N\n```\n\n- **`patterns`**: A float tensor where each row is a 4,500-point XRD intensity vector.\n- **`filenames`**: The corresponding COD CIF filenames (e.g. `\"4326570.cif\"`).\n\n## Generation parameters\n\n| Parameter | Value |\n|---|---|\n| Software | pymatgen `XRDCalculator` |\n| Radiation | Cu K-alpha (lambda = 1.54184 angstrom) |\n| 2-theta range | 0 to 90 degrees |\n| Step size | 0.02 degrees |\n| Points per pattern | 4,500 |\n| Normalisation | Min-max scaled to [0, 1] |\n\nPatterns were generated by reading each CIF file, computing the theoretical diffraction peak positions and intensities, and interpolating onto the uniform 2-theta grid. Regions with no diffraction peaks are zero-padded.\n\n## Finding the original CIF files\n\nEvery filename maps directly to a COD entry. Strip the `.cif` extension to get the COD ID, then download the structure file:\n\n```\nFilename:  4326570.cif\nCOD ID:    4326570\nURL:       https://www.crystallography.net/cod/4326570.cif\n```\n\n## License\n\nCC0 1.0 Universal — same as the Crystallography Open Database itself.\n\n## Citation\n\nIf you use this dataset, please cite:\n\n**COD:**\nGrazulis, S. et al. \"Crystallography Open Database — an open-access collection of crystal structures.\" *Journal of Applied Crystallography*, 42(4), 726–729, 2009.\n\n**pymatgen:**\nOng, S. P. et al. \"Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis.\" *Computational Materials Science*, 68, 314–319, 2013.\n","encoding":"utf8","key":"README.md","name":"README.md","size":2977,"truncated":false}],"sourceObjectKey":"COD_xrd_patterns_1000.pt","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"ohlstrom/Crystallography-Open-Database-XRD-Patterns\", filename=\"COD_xrd_patterns_1000.pt\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"COD_xrd_patterns_1000.pt","totalObjects":7},"summary":"Simulated powder X-ray diffraction (PXRD) patterns for every CIF crystal structure in the Crystallography Open Database (COD): 436,196 diffractograms spanning metals, minerals,…","title":"COD Synthetic Powder X-Ray Diffraction (XRD) Patterns: 436,196 Simulated Diffractograms from the Crystallography Open Database","updatedAt":"2026-11-22T03:41:52.375Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/ohlstrom/Crystallography-Open-Database-XRD-Patterns"}}