Skip to content

Update-2 #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
manishrana7 wants to merge 1 commit into
base: updated
Choose a base branch
from
Open

Update-2 #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 17 additions & 12 deletions analysis/crystal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,11 +8,13 @@
import pandas as pd
from ase.visualize import view
from pymatgen.analysis.defects.generators import VacancyGenerator
from pymatgen.analysis.local_env import CrystalNN, VoronoiNN
from pymatgen.analysis.local_env import CrystalNN, VoronoiNN, CutOffDictNN
from pymatgen.core import Species, Structure
from pymatgen.io.ase import AseAtomsAdaptor
from pymatgen.analysis.bond_valence import BVAnalyzer, calculate_bv_sum
from pymatgen.io.vasp import Poscar
from collections import Counter


EB_DICT = {"filepath": "../data/features/Eb.csv", "column_name": "Eb", "comparison": "os"}
VR_DICT = {"filepath": "../data/features/Vr.csv", "column_name": "Vr", "comparison": "n"}
Expand Down Expand Up @@ -90,11 +92,12 @@ def __init__(
poscar_string: Optional[str] = None,
pymatgen_structure: Optional[Structure] = None,
nn_finder_type: str = 'crystalnn', # crystalnn or voronoinn
cut_off_dict: Optional[dict] = None,
use_weights: Optional[bool] = False,
species_symbol: Optional[str] = "O",
n: Optional[int] = None, # attempt to allow for pre-emptive indexing
oxi_states_override = None,
):
):

"""
Initializes the Crystal object.
Expand All @@ -113,8 +116,10 @@ def __init__(
"""
if filepath:
self.structure = Structure.from_file(filepath)
if filepath.endswith(".txt"): # Assuming your POSCAR files have a .txt extension
self.structure.add_oxidation_state_by_guess()
## -------> Commented by Manish
# if filepath.endswith(".txt"): # Assuming your POSCAR files have a .txt extension
# self.structure.add_oxidation_state_by_guess()
## <------- I think the guessed oxidation states will be replaced, which make the guessing redundant here
elif poscar_string:
self.structure = Structure.from_str(poscar_string, fmt="poscar") #giving nan for binding energies, fix
elif pymatgen_structure:
Expand All @@ -126,9 +131,10 @@ def __init__(

if nn_finder_type.lower() == 'voronoinn':
self.nn_finder = VoronoiNN()
elif nn_finder_type.lower == 'cutoffdictnn':
self.nn_finder = CutOffDictNN(cut_off_dict=cut_off_dict)
else: # default to crystalnn
self.nn_finder = CrystalNN()

self.nn_finder = CrystalNN()


self.use_weights = use_weights
Expand Down Expand Up @@ -163,12 +169,11 @@ def guess_oxidation_states(self, oxi_states_override=None):
self.structure.add_oxidation_state_by_guess()

if not all(element.oxi_state != 0 for element in self.structure.species):
self.structure = self.structure.add_charges_from_oxi_state_guesses(
oxi_states_override=oxi_states_override,
target_charge=0,
all_oxi_states=False,
max_sites=None
)
self.structure = self.structure.add_charges_from_oxi_state_guesses(oxi_states_override=oxi_states_override,
target_charge=0,
all_oxi_states=False,
max_sites=None
)
# potential specification to decide which method to use
if not all(element.oxi_state != 0 for element in self.structure.species): # alternative method 2
raise ValueError("Oxidation states could not be guessed for all elements in the structure.")
Expand Down
81 changes: 81 additions & 0 deletions analysis/test_CCTM/CCTM_species.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,81 @@
from pymatgen.io.cif import CifParser, CifWriter
from pymatgen.core.structure import Structure
from pathlib import Path
import sys
sys.path.append(str(Path(__file__).parent.parent.parent))
from analysis.crystal import Crystal
import numpy as np
import pandas as pd
import math
import os
from datetime import datetime

# date_str = datetime.now().strftime("%y%m%d") # 20241223
# date_str = datetime.now().strftime("%y%b%d") # 2024Dec23
date_str = datetime.now().strftime("%y-%b-%d") # 2024-Dec-23

M = 0
N = 18

st = Structure.from_file(f"/Users/manish/PycharmProjects/Proj_CCTM4STCH/2_DFT/1_data/"
f"M{M}_N{N}/2_vacancy/0_bulk_structure/CONTCAR_bulk_M{M}_N{N}")

test_cif = f"./junk_{date_str}.cif"


def get_unique_values_from_dicts(dict_list, key):
seen_pairs = set()
values = []
for d in dict_list:
if key in d:
pair = (key, d[key])

if pair not in seen_pairs:
seen_pairs.add(pair)
values.append(d[key])
return values

def get_species_data():
print()
unique_values = {}
Mn_OS = [2, 3, 4]
Ce_OS = [3, 4]
species_data = []
save_file = f"species_data_{date_str}.csv"

if os.path.exists(save_file):
df = pd.read_csv(save_file)
dff = df.drop_duplicates()
print(dff)
return dff

oxi_state_base = {"Ca": 2, "Ti": 4, "O": -2}
species_template = {"Ca": "Ca{}+", "Ce": "Ce{}+", "Ti": "Ti{}+", "Mn": "Mn{}+"}

for ceos, mnos in [(ce, mn) for ce in Ce_OS for mn in Mn_OS]:
print(f"Ce{ceos}, Mn{mnos}")
oxi_state_override = {**oxi_state_base, "Ce": ceos, "Mn": mnos}
# print(oxi_state_override)
st.add_oxidation_state_by_element(oxi_state_override)
crystal = Crystal(pymatgen_structure=st, nn_finder_type="voronoinn")
eb = crystal.bond_dissociation_enthalpies
vr = crystal.reduction_potentials

for elem in ["Ca", "Ce", "Ti", "Mn"]:
specie = species_template[elem].format(oxi_state_override[elem])
try:
eb_value = next(val for val in get_unique_values_from_dicts(eb, specie))
vr_value = next(val for val in get_unique_values_from_dicts(vr, specie))
species_data.append([specie, eb_value, vr_value])
print(specie)
except (StopIteration, IndexError):
print(f"Warning: Data not found for {specie}")

df = pd.DataFrame(species_data, columns=["species", "eb", "vr"]).sort_values(by="species").drop_duplicates()
print(df)
# df.to_csv(save_file, index=False)
return df

get_species_data()
# print(df)
# get_all()
16 changes: 16 additions & 0 deletions analysis/test_CCTM/features_sumEb_and_maxVr.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
nCa,nCe,nTi,nMn,env,sigma_eb,max_vr,max_vr_ion
4,0,2,0,0-0,13.958139994832159,-1.9122077365342869,Ti4+
4,0,1,1,0-1,12.90561958532208,-0.433744681701679,Mn4+
4,0,0,2,0-2,11.853099175812002,-0.433744681701679,Mn4+
3,1,2,0,1-0,15.045808865468798,-1.9122077365342869,Ti4+
3,1,1,1,1-1,13.99328845595872,-0.433744681701679,Mn4+
3,1,0,2,1-2,12.940768046448643,-0.433744681701679,Mn4+
2,2,2,0,2-0,16.133477736105437,-1.9122077365342869,Ti4+
2,2,1,1,2-1,15.080957326595358,-0.433744681701679,Mn4+
2,2,0,2,2-2,14.02843691708528,-0.433744681701679,Mn4+
1,3,2,0,3-0,17.221146606742074,-1.9122077365342869,Ti4+
1,3,1,1,3-1,16.168626197231998,-0.433744681701679,Mn4+
1,3,0,2,3-2,15.116105787721917,-0.433744681701679,Mn4+
0,4,2,0,4-0,18.308815477378715,-1.9122077365342869,Ti4+
0,4,1,1,4-1,17.256295067868635,-0.433744681701679,Mn4+
0,4,0,2,4-2,16.203774658358558,-0.433744681701679,Mn4+
165 changes: 165 additions & 0 deletions analysis/test_CCTM/script_CCTM.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,165 @@
from pymatgen.io.cif import CifParser, CifWriter
from pymatgen.core.structure import Structure
from pathlib import Path
import sys
sys.path.append(str(Path(__file__).parent.parent.parent))
from analysis.crystal import Crystal
import numpy as np
import pandas as pd
import math
import os
from datetime import datetime

# date_str = datetime.now().strftime("%y%m%d") # 20241222
# date_str = datetime.now().strftime("%y%b%d") # 2024Dec22
date_str = datetime.now().strftime("%y-%b-%d") # 2024-Dec-22

M = 0
N = 18

st = Structure.from_file(f"/Users/manish/PycharmProjects/Proj_CCTM4STCH/2_DFT/1_data/"
f"M{M}_N{N}/2_vacancy/0_bulk_structure/CONTCAR_bulk_M{M}_N{N}")

cif_junk = f"./test_{date_str}.cif"
def get_all():
oxi_state_override = {"Ca": 2, "Ce": 3, "Ti": 4, "Mn": 4, "O": -2,}
st.add_oxidation_state_by_element(oxi_state_override)

cif_writer = CifWriter(st)
cif_writer.write_file(cif_junk)
# cif_file_path = Path(__file__).parent / f"../manish/{cif_junk}"
cif_file_path = Path(__file__).parent / f"{cif_junk}"
print(cif_file_path)
cif_file_path = cif_file_path.resolve()
if not cif_file_path.is_file():
raise FileNotFoundError(f"The CIF file does not exist: {cif_file_path}")

structure = CifParser(cif_file_path).parse_structures(primitive=True)[0]

crystal = Crystal(pymatgen_structure=structure, nn_finder_type="voronoinn")

cn = crystal.cn_dicts
for cdict in cn:
cdict.pop("O2-", None)

eb = crystal.bond_dissociation_enthalpies
for edict in eb:
edict.pop("O2-", None)

vr = crystal.reduction_potentials
for vdict in vr:
vdict.pop("O2-", None)


Ce_ox = oxi_state_override["Ce"]
Ce_specie = f"Ce{Ce_ox}+"
Mn_ox = oxi_state_override["Mn"]
Mn_specie = f"Mn{Mn_ox}+"

print("Type of eb:", type(eb))


print("Type of vr:", type(vr), len(vr))
# print("Contents of vr:", vr)

features = []
for index, dict in enumerate(cn):
nCa = dict.get("Ca2+", 4 - dict.get(Ce_specie, 0))
nCe = dict.get(Ce_specie, 4 - dict.get("Ca2+", 0))
nTi = dict.get("Ti4+", 2 - dict.get(Mn_specie, 0))
nMn = dict.get(Mn_specie, 2 - dict.get("Ti4+", 0))

env = f"{nCe}-{nMn}"

eb_d = eb[index]
vr_d = vr[index]
sigma_eb = (nCa * eb_d.get("Ca2+", 0) + nCe * eb_d.get(Ce_specie, 0) +
nTi * eb_d.get("Ti4+", 0) + nMn * eb_d.get(Mn_specie, 0))

max_vr = max(vr_d.values())
max_vr_species = max(vr_d, key=vr_d.get)

features.append([nCa, nCe, nTi, nMn, env, sigma_eb, max_vr, max_vr_species])

dfff = pd.DataFrame(features, columns=["nCa", "nCe", "nTi", "nMn", "env", "sigma_eb", "max_vr", "max_vr_ion"])
ddff = dfff.drop_duplicates().sort_values(by="env", ascending=True)
ddff.to_csv(f"features_sumEb_and_maxVr.csv", index=False)

print(ddff)


def get_unique_values_from_dicts(dict_list, key):
seen_pairs = set()
values = []
for d in dict_list:
if key in d:
pair = (key, d[key])

if pair not in seen_pairs:
seen_pairs.add(pair)
values.append(d[key])
return values

def get_species_data():
print()
unique_values = {}
Mn_OS = [2, 3, 4]
Ce_OS = [3, 4]
species_data = []
# save_file = "species_data.csv"
# cif_junk = "./junk.cif"

# test on Dec 23, 2024
save_file = "species_data_2024Dec23.csv"
# cif_junk = "./junk_2025May20.cif"
if not os.path.exists(save_file):
for ceos, mnos in zip(Ce_OS, Mn_OS):
print(f"Ce{ceos}, Mn{mnos}")
oxi_state_override = {"Ca": 2, "Ce": ceos, "Ti": 4, "Mn": mnos, "O": -2, }
st.add_oxidation_state_by_element(oxi_state_override)

cif_writer = CifWriter(st)
cif_writer.write_file(cif_junk)
# cif_file_path = Path(__file__).parent / f"../manish/{cif_junk}"
cif_file_path = Path(__file__).parent / f"{cif_junk}"
cif_file_path = cif_file_path.resolve()
if not cif_file_path.is_file():
raise FileNotFoundError(f"The CIF file does not exist: {cif_file_path}")

structure = CifParser(cif_file_path).parse_structures(primitive=True)[0]

crystal = Crystal(pymatgen_structure=structure, nn_finder_type="voronoinn")

eb = crystal.bond_dissociation_enthalpies
vr = crystal.reduction_potentials

Ca_ox = oxi_state_override["Ca"]
Ca_specie = f"Ca{Ca_ox}+"
Ce_ox = oxi_state_override["Ce"]
Ce_specie = f"Ce{Ce_ox}+"
Ti_ox = oxi_state_override["Ti"]
Ti_specie = f"Ti{Ti_ox}+"
Mn_ox = oxi_state_override["Mn"]
Mn_specie = f"Mn{Mn_ox}+"

species_list = [Ca_specie, Ce_specie, Ti_specie, Mn_specie]
for species in species_list:
eb_value = get_unique_values_from_dicts(eb, species)[0]
vr_value = get_unique_values_from_dicts(vr, species)[0]
species_data.append([species, eb_value, vr_value])

print(species_data)
df = pd.DataFrame(species_data, columns=["species", "eb", "vr"])
dff = df.drop_duplicates()
print(dff)
# dff.to_csv(save_file, index=False)

else:
df = pd.read_csv(save_file)
dff = df.drop_duplicates()
print(dff)
# dff.to_csv(save_file, index=False)

return dff

df = get_species_data()
Loading