JARVIS-ML-CFID-descriptors and material properties

Classical force-field inspired descriptors (CFID) for more than 35000 materials and their material properties such as bandgap, formation energies, modulus of elasticity etc.<br>See JARVIS-ML:https://www.ctcms.nist.gov/jarvisml/<br>https://jarvis.nist.gov/<br><br>########################################Example:import os,jsonimport pandas as pdf = open(os.path.join(os.getcwd(),'jml_3d-4-26-2020.json'),'r')dataml=json.load(f)f.close()df=pd.DataFrame(dataml) <br><pre>typical_data_ranges = {'formation_energy_peratom': [-5, 5], 'optb88vdw_bandgap': [0, 10], 'mbj_bandgap': [0, 10], 'bulk_modulus_kv': [0, 250], 'shear_modulus_gv': [0, 250], 'epsx': [0, 60], 'epsy': [0, 60], 'epsz': [0, 60], 'mepsx': [0, 60], 'mepsy': [0, 60], 'mepsz': [0, 60], 'n-Seebeck': [-600, 10], 'n-powerfact': [0, 5000], 'p-Seebeck': [-10, 600], 'p-powerfact': [0, 5000], 'slme': [0, 40], 'spillage': [0, 4], 'encut': [0, 2000], 'kpoint_length_unit': [0, 200], 'dfpt_piezo_max_dielectric': [0, 100], 'dfpt_piezo_max_dij': [0, 3000], 'dfpt_piezo_max_eij': [0, 10], 'ehull': [0, 1], 'electron_avg_effective_masses_300K': [0, 3], 'hole_avg_effective_masses_300K': [0, 3], 'exfoliation_energy': [0, 1000], 'magmom_oszicar': [0, 10], 'max_ir_mode': [0, 4000], 'total_energy_per_atom': [-10, 3]}</pre><br>import numpy as np%matplotlib inlineimport matplotlib.pyplot as pltval=np.array(df['formation_energy_peratom'].replace('na',np.nan).dropna().values,dtype='float')plt.hist(val,bins=np.arange(-4,4,.5))<br>#########################################For more details about using the dataset, use the jupyter-notebooks:https://github.com/usnistgov/jarvis