Python MPRester.get_data方法代码示例

# 需要导入模块: from pymatgen import MPRester [as 别名]
# 或者: from pymatgen.MPRester import get_data [as 别名]
class CompositionToStructureFromMP(ConversionFeaturizer):
    """
    Featurizer to get a Structure object from Materials Project using the
    composition alone. The most stable entry from Materials Project is selected,
    or NaN if no entry is found in the Materials Project.

    Args:
        target_col_id (str or None): The column in which the converted data will
            be written. If the column already exists then an error will be
            thrown unless `overwrite_data` is set to `True`. If `target_col_id`
            begins with an underscore the data will be written to the column:
            `"{}_{}".format(col_id, target_col_id[1:])`, where `col_id` is the
            column being featurized. If `target_col_id` is set to None then
            the data will be written "in place" to the `col_id` column (this
            will only work if `overwrite_data=True`).
        overwrite_data (bool): Overwrite any data in `target_column` if it
            exists.
        map_key (str): Materials API key

    """

    def __init__(self, target_col_id='structure', overwrite_data=False,
                 mapi_key=None):
        super().__init__(target_col_id, overwrite_data)
        self.mpr = MPRester(mapi_key)

    def featurize(self, comp):
        """
        Get the most stable structure from Materials Project
        Args:
            comp (`pymatgen.core.composition.Composition`): A composition.

        Returns:
            (`pymatgen.core.structure.Structure`): A Structure object.
        """

        entries = self.mpr.get_data(comp.reduced_formula, prop="energy_per_atom")
        if len(entries) > 0:
            most_stable_entry = \
            sorted(entries, key=lambda e: e['energy_per_atom'])[0]
            s = self.mpr.get_structure_by_material_id(
                most_stable_entry["material_id"])
            return[s]
        
        return [float("nan")]

    def citations(self):
        return [
            "@article{doi:10.1063/1.4812323, author = {Jain,Anubhav and Ong,"
            "Shyue Ping  and Hautier,Geoffroy and Chen,Wei and Richards, "
            "William Davidson  and Dacek,Stephen and Cholia,Shreyas "
            "and Gunter,Dan  and Skinner,David and Ceder,Gerbrand "
            "and Persson,Kristin A. }, title = {Commentary: The Materials "
            "Project: A materials genome approach to accelerating materials "
            "innovation}, journal = {APL Materials}, volume = {1}, number = "
            "{1}, pages = {011002}, year = {2013}, doi = {10.1063/1.4812323}, "
            "URL = {https://doi.org/10.1063/1.4812323}, "
            "eprint = {https://doi.org/10.1063/1.4812323}}",
            "@article{Ong2015, author = {Ong, Shyue Ping and Cholia, "
            "Shreyas and Jain, Anubhav and Brafman, Miriam and Gunter, Dan "
            "and Ceder, Gerbrand and Persson, Kristin a.}, doi = "
            "{10.1016/j.commatsci.2014.10.037}, issn = {09270256}, "
            "journal = {Computational Materials Science}, month = {feb}, "
            "pages = {209--215}, publisher = {Elsevier B.V.}, title = "
            "{{The Materials Application Programming Interface (API): A simple, "
            "flexible and efficient API for materials data based on "
            "REpresentational State Transfer (REST) principles}}, "
            "url = {http://linkinghub.elsevier.com/retrieve/pii/S0927025614007113}, "
            "volume = {97}, year = {2015} } "]

    def implementors(self):
        return ["Anubhav Jain"]

# 需要导入模块: from pymatgen import MPRester [as 别名]
# 或者: from pymatgen.MPRester import get_data [as 别名]
import pandas as pd
import matplotlib.pyplot as plt
import itertools

df = pd.DataFrame()
allBinaries = itertools.combinations(periodic_table.all_symbols(), 2)  # Create list of all binary systems

API_KEY = None  # Enter your key received from Materials Project

if API_KEY is None:
    m = MPRester()
else:
    m = MPRester(API_KEY)

for system in allBinaries:
    results = m.get_data(system[0] + '-' + system[1], data_type='vasp')  # Download DFT data for each binary system
    for material in results:  # We will receive many compounds within each binary system
        if material['e_above_hull'] < 1e-6:  # Check if this compound is thermodynamically stable
            dat = [material['pretty_formula'], material['band_gap'], material['formation_energy_per_atom'],
                   material['density']]
            df = df.append(pd.Series(dat), ignore_index=True)

df.columns = ['materials', 'bandgaps', 'formenergies', 'densities']
print df[0:2]
print df.columns

MAX_Z = 100  # maximum length of vector to hold naive feature set


def naive_vectorize(composition):
    """