Compositional and Structural Fingerprints of Materials Project Time Split Data for use with Generative Materials Benchmarking Metrics

This is a supporting dataset for <em><strong>matbench-genmetrics</strong></em> [docs] [repo], a set of generative materials benchmarking metrics. The compositional (Magpie) and structural (CrystalNN) fingerprints* are produced in fingerprint_snapshot.py using <em><strong>mp-time-split</strong></em> data [docs] [repo] [figshare] and are given in <em>comp_fingerprints.csv</em> (132 features) and <em>struct_fingerprints.csv</em> (61 features), respectively. Each has an additional column in the first position, <em>material_id,</em> which contains the Materials Project <em>material_id</em>. So, in total there are 133 and 62 columns, respectively. There are 40476 entries, plus a header row with labels, so 40477 rows in total. The primary purpose of these datasets is to avoid repeating lengthy calculations each time a <em>matbench-genmetrics</em> benchmark is computed; thus, only the generated structures need to be featurized. The total runtime for the compositional and structural fingerprinting using 6 physical cores (12 virtual cores as determined by <em>multiprocessing.cpu_count()</em>) is approximately 50 minutes and 140 min, respectively. The benchmarks can be used with materials generative models such as <em>xtal2png</em><em>+</em><em>Imagen</em>. <br> *The use of Magpie and CrystalNN featurizers are based on the coverage metric from CDVAE [repo] [paper].