3,571 inorganic crystal compounds with experimental bandgap values. Each entry includes Crystallographic Information File (CIF) structures and is characterized by Magpie and X-ray diffraction (XRD) features. The dataset is provided with ready-made splits for machine learning tasks.
Use Cases
- Predict electronic bandgap values based on Magpie and XRD feature vectors.
- Train crystal structure property models using the provided CIF files.
- Benchmark material discovery algorithms using the pre-defined dataset splits.
Strengths
- Contains 3,571 distinct inorganic crystal compounds.
- Includes CIF structure files, Magpie features, and XRD features for each compound.
- Provides ready-made data splits, which may reduce preprocessing effort.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Last update date is unknown; freshness unverified.
- Row count is known, but the specific source and collection methodology are not detailed.
Provenance
- Source
- Kaggle
- Collection Method
- Likely compiled from experimental materials science databases.