In [ ]:

    

from mpcontribs.client import Client
from pandas import read_excel
from pymatgen import MPRester
import numpy as np
from time import sleep


    

In [ ]:

    

project = 'defect_genome_pcfc_materials'
client = Client('your-api-key-here')
mpr = MPRester()


    

In [ ]:

    

client.projects.get_entry(pk=project).result()


    

In [ ]:

    

client.projects.update_entry(pk=project, project={
    'long_title': 'Defect Genome of Cubic Perovskites for Fuel Cells'
}).result()


    

In [ ]:

    

df = read_excel('DefectGenome_JPCC-data_MP.xlsx')
df.columns = ['A', 'B', 'a', 'Eᶠ|ABO₃', 'Eᶠ|Yᴮ', 'Eᶠ|Vᴼ', 'Eᶠ|Hᵢ', 'ΔEᵢ|Yᴮ−Hᵢ']
units = {'A': '', 'B': '', 'a': 'Å'}
df


    

In [ ]:

    

contributions = []
for idx, row in df.iterrows():
    A, B = row[df.columns[0]], row[df.columns[1]]
    formula = f'{A}{B}O3'
    data = mpr.get_data(formula, prop="volume")

    if len(data) > 1:
        volume = row[df.columns[2]]**3
        for d in data:
            d['dV'] = abs(d['volume']-volume)
        data = sorted(data, key=lambda item: item['dV'])
    elif not data:
        print(formula, 'not found on MP')
        continue

    identifier = data[0]['material_id']
    print(idx, formula, identifier)
    
    contrib = {'project': project, 'identifier': identifier, 'data': {}}
    for col in df.columns:
        unit = units.get(col, 'eV')
        contrib['data'][col] = f'{row[col]} {unit}' if unit else row[col]
    
    contributions.append(contrib)
    
len(contributions)


    

In [ ]:

    

# clean up
has_more = True
while has_more:
    resp = client.contributions.delete_entries(project=project, _limit=250).result()    
    print(resp['count'], 'contributions deleted')
    has_more = resp['has_more']
    
# submit
created = client.contributions.create_entries(contributions=contributions).result()
print(created['count'], 'contributions created')


    

In [ ]:

    

client.contributions.update_entries(
    project=project, is_public=False, contributions={'is_public': True}
).result()