JARVIS-ML CFID Descriptors for 84K Materials Project Crystals: Formation Energies (NIST JARVIS, figshare), ColabFit Conversion
- Provider
- Materials Project (Jain et al.) and Kamal Choudhary (NIST JARVIS); ColabFit conversion
- License
- CC-BY-4.0 (source)
- Size
- 4 files
- Format
- Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/colabfit/JARVIS_Materials_Project_84K)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.6084/m9.figshare.13054247
- Category
- Chemistry & Materials
- Source
- https://doi.org/10.1063/1.4812323
About this dataset
Crystal structures of about 84,000 inorganic materials from the Materials Project DFT database, packaged by NIST's JARVIS (Joint Automated Repository for Various Integrated Simulations) team together with classical force-field inspired descriptors (CFID) and target properties for machine learning. CFID turns each crystal into a fixed-length feature vector for training machine-learning models of formation energy and related properties. ColabFit's card counts 83,416 configurations and about 2.34 million atoms over 89 elements, labelled with formation energy; the repository is about 1.4 GB. Files are the ColabFit Exchange conversion: Parquet files under co/ hold one row per configuration (atomic numbers, positions, cell, computed properties and metadata), ds.parquet holds dataset-level information, and cs/ groups configurations into named sets where defined; read them with pyarrow, pandas, polars or Hugging Face datasets. The JARVIS-ML-CFID-MP figshare deposit (DOI 10.6084/m9.figshare.13054247) is released under CC BY 4.0. Cite Jain et al., APL Materials 1, 011002 (2013) for the Materials Project and Choudhary et al., Physical Review Materials 2, 083801 (2018) for CFID.
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("colabfit/JARVIS_Materials_Project_84K")
print(ds)Data structure
File types in sampled files: Parquet
Files
Example file: co/co_0.parquet
Analyze this dataset without downloading it
On Scigantic, JARVIS-ML CFID Descriptors for 84K Materials Project Crystals: Formation Energies (NIST JARVIS, figshare), ColabFit Conversion opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Chemistry & Materials datasets
- Open Catalyst 2022 (OC22) S2EF Training Set, ColabFit Conversion
- Alexandria PBE 1D Crystal Geometry Optimization Paths, ColabFit Conversion
- GNPS community spectral libraries: 581,722 reference MS/MS spectra from 65 directly contributed libraries, as MGF and Parquet
- Materials Project JCESR Electrolyte Genome Molecules (2024-11-14 Release)
- Oxygen Vacancies in Jahn-Teller Distorted LaMnO3: Strained DFT+U Structures (Ricca, Niederhauser and Aschauer 2020, Materials Cloud), ColabFit Conversion
- Minerals as Calcium-Ion Battery Electrodes: DFT Structures of Pyroxenes, Garnets and Carbonates, ColabFit Conversion
- MP-ALOE: r2SCAN Active-Learning Dataset for Universal Interatomic Potentials, ColabFit Conversion
- Halide Double Perovskite Octahedral Tilting