class mp_query():
def __init__(self, api_key):
self.mpr = MPRester(api_key)
def find_access_strings(self, search):
data = self.mpr.get_data(search)
material_ids = [datum['material_id'] for datum in data]
return material_ids
def mp_structure(self, material_id):
struct = self.mpr.get_structure_by_material_id(material_id)
struct = SpacegroupAnalyzer(
struct).get_conventional_standard_structure()
return struct
def make_structures(self, search):
material_ids = self.find_access_strings(search)
structures = []
for ID in material_ids:
struct = self.mp_structure(ID)
structures.append(struct)
return structures
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
df_2d = pd.read_csv('C:/Users/Subrat.Subedi/Downloads/2D.csv')
for index, row in df_2d.iterrows():
baseurl = 'https://www.materialsproject.org/rest/v2/materials/%s' % (
row['mpid'])
output = {}
try:
response = requests.get(baseurl + '/doc',
headers={
'x-api-key': API_KEY,
'User-Agent': USER_AGENT
}).json()
mp_json = response['response']
except KeyError:
m = MPRester(API_KEY)
data = m.get_data(row['mpid'])
mp_json = to_dict(data)
try:
output['name'] = mp_json["exp"]["tags"][0]
except:
try:
output['name'] = mp_json["pretty_formula"]
except:
continue
with open(
'C:/Users/Subrat.Subedi/Downloads/Data Collections/rex_stanford_xls/'
+ row['mpid'] + '.json',
'w',
encoding='utf-8') as rex:
json.dump(mp_json, rex)
output['authors'] = ["Materials Project"]
class CompoundEntries(object):
def __init__(self, materialsprojectKey, compoundFomulaList):
self.rester = MPRester(materialsprojectKey)
self.materialFormulaList = compoundFomulaList
# self.features = ['element1','element2', 'formation_energy_per_atom' ]
#self.featureSize=len(self.features)
self.grepped_entry_list = [None] * len(self.materialFormulaList)
self.compoundFeatureMatrix = np.array([])
self.compoundFeatures = [
'nsites', 'density', 'energy_per_atom', 'point_group'
]
def dataPretreatment(self, data_stable_phase):
data_stable_phase.update(
data_stable_phase['spacegroup']
) # Add sub-dictionary to the main-dictionary.
del data_stable_phase['spacegroup'] # Remove sub-dictionary.
# remove 'cif' and 'icsd_ids' from dictionaries for they are too long.
del data_stable_phase['cif']
del data_stable_phase['icsd_ids']
return data_stable_phase
def grep(self,
formula): # Give me one formula at a time. return one directory.
try:
data = self.rester.get_data(
formula) # data is list of directories.
except pymatgen.ext.matproj.MPRestError:
data = []
j = 0
if data == []: # No data on MaterialsProject for this compound
return []
stable_phase_found = False
while j < len(data):
if data[j]['e_above_hull'] == 0:
stable_phase_found = True
data_stable_phase = data[j]
break
elif j == len(data) - 1 and stable_phase_found == False:
return []
print("No 'e_above_hull'==0 for " + materialFormula)
j += 1
treated_data_stable_phase = self.dataPretreatment(data_stable_phase)
treated_data_stable_phase = entryToFloat.entryToFloat(
treated_data_stable_phase)
return treated_data_stable_phase
def grepCompoundFeatureMatrix(self):
index = 0
for formula in self.materialFormulaList:
print(formula)
stablePhaseEntry = self.grep(formula)
singleCompoundFeature = []
if stablePhaseEntry != []:
for feature in self.compoundFeatures:
try:
singleCompoundFeature = np.append(
singleCompoundFeature,
stablePhaseEntry[feature]) # a list
except KeyError:
singleCompoundFeature = np.append(
singleCompoundFeature, 0)
if index == 0:
self.compoundFeatureMatrix = singleCompoundFeature
else:
self.compoundFeatureMatrix = np.vstack(
[self.compoundFeatureMatrix, singleCompoundFeature])
elif stablePhaseEntry == []: # retrived data is []. Add zeros.
if index == 0:
self.compoundFeatureMatrix = np.zeros(
len(self.compoundFeatures))
else:
self.compoundFeatureMatrix = np.vstack([
self.compoundFeatureMatrix,
np.zeros(len(self.compoundFeatures))
])
index += 1
return
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)
self.set_n_jobs(1)
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"]
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"]
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):
"""
from pymatgen.io.cif import CifWriter
import csv
import os
import json
import math
if __name__ == "__main__":
MAPI_KEY = "h9GBsMfA1JvXbC7n" # You must change this to your Materials API key! (or set MAPI_KEY env variable)
QUERY = "mp-1180346" # change this to the mp-id of your compound of interest
# QUERY = "TiO" # change this to a formula of interest
# QUERY = "Ti-O" # change this to a chemical system of interest
mpr = MPRester(MAPI_KEY) # object for connecting to MP Rest interface
# all information 2+2 warning label
result = mpr.get_data("mp-9272")
print(result)
print()
result = mpr.get_data("mp-571420")
print(result)
print()
result = mpr.get_data("mp-1094115")
print(result)
print()
result = mpr.get_data("mp-1180226")
print(result)
print()
# structures = mpr.get_structures(QUERY)
# for s in structures:
# print(s)
