获取特定化学组成的数据 Pymatgen

导入所需模块

import numpy as np
from matminer.datasets import load_dataset
import matplotlib.pyplot as plt 
from pymatgen.core import Composition
import numpy as np
import pandas as pd
import pymatgen as mg
import itertools
import random
from pymatgen.core.composition import Composition
from pymatgen.core.molecular_orbitals import MolecularOrbitals
from matminer.featurizers.conversions import StrToComposition
from matminer.featurizers.composition import ElementProperty, ValenceOrbital, CohesiveEnergy
from matminer.featurizers.base import BaseFeaturizer

all_symbols = ["Y", "Lu", "Gd","Tb", "La", "Ca", "Al", "Ga", "Sc", "Si", "Sb", "In", "Mg", "Mn", "Ge", "Ba","Li",'Na','K','Rb','Cs','Ba','Sr']
complx = list(itertools.combinations(all_symbols, 3)) 
complex_picked = random.sample(complx,1771)
system = list(map(lambda x: complex_picked[x][0] + '-' + complex_picked[x][1]+ '-' + complex_picked[x][2]+'-' +'O',np.arange(len(complex_picked))))

def que(x):
    a = MPRester('KEY')
    data = a.query(criteria=x,properties=["band_gap","pretty_formula","spacegroup",'structure'])
    return data

data=[]
valid_num=[]
for i in system:
    res=que(i)
    if res !=[]:
        data.extend(res)
        valid_num.append(system.index(i))
        print(len(res),"hello，jojo!",system.index(i))

from pymatgen.ext.matproj import MPRester
data=[]
valid_num=[]
for i in system:
    res = que(i)
    if res != []:
        data.extend(res)
        valid_num.append(system.index(i))
        print("len(res):",len(res),"  system.index(i):",system.index(i),"  res:",res)

result=pd.DataFrame(data)

计算描述符

def mat_descriptor_calculation(material):
    mat=mg.Composition(material)
    fraction_list=list(map(lambda x: mat.get_atomic_fraction(x), mat))
    sort_frac=fraction_list.sort(reverse=True)
    if sort_frac is not None:
        fraction=sort_frac[0]/sort_frac[1]
    else:
        fraction=1
    atomic_number=list(map(lambda x: x.Z, mat))
    electronegativity=list(map(lambda x: x.X, mat))
    element_group=list(map(lambda x: x.group, mat))
    descriptor=atomic_number+electronegativity+element_group
    descriptor.append(fraction)
    return descriptor

mat_descriptor=list(map(lambda x:mat_descriptor_calculation(data[x['pretty_formula']),length))