# JARVIS-ML CFID Descriptors for 84K Materials Project Crystals: Formation Energies (NIST JARVIS, figshare), ColabFit Conversion

## Facts

- Provider: Materials Project (Jain et al.) and Kamal Choudhary (NIST JARVIS); ColabFit conversion
- License: CC-BY-4.0 (https://api.figshare.com/v2/articles/13054247)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/JARVIS_Materials_Project_84K
- Access: public, readable without an account
- DOI: https://doi.org/10.6084/m9.figshare.13054247
- Category: Chemistry & Materials
- Source: https://doi.org/10.1063/1.4812323
- Page: https://scigantic.com/archive/f187dbbe-6446-5abb-9a11-54681635e6e6
- Keywords: Chemistry & Materials, DFT, Parquet, Hugging Face

## About

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.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/JARVIS_Materials_Project_84K")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `co/co_0.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/f187dbbe-6446-5abb-9a11-54681635e6e6
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/f187dbbe-6446-5abb-9a11-54681635e6e6
- Over MCP: `get_schema_card` with id `f187dbbe-6446-5abb-9a11-54681635e6e6` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Chemistry & Materials datasets](https://scigantic.com/topics/chemistry-and-materials)
- [DFT datasets](https://scigantic.com/topics/dft)
