Merge branch 'master' of https://github.com/materialsproject/pymatgen

CHANGES.rst

@@ -1,6 +1,13 @@
 Change log
 ==========
 
+v2022.0.11
+----------
+* New features to handle Grüneisen parameters (@JaGeo, @ab5424, @gpetretto, #2190)
+* New option to return SymmetrizedStructure in CifParser (@mkhorton, 0d9a455)
+* Fix for SubstrateAnalyzer (@shyamd, #2198)
+* Fix for BandFillingCorrection (@kavanase, #2193)
+
 v2022.0.10
 ----------
 * Add spin-dependent eigenvalue band properties (@arosen93, #2187)

pymatgen/analysis/interfaces/substrate_analyzer.py

@@ -64,16 +64,24 @@ def from_zsl(
         else:
             elastic_energy = 0
 
-        match_dict = match.as_dict()
-
-        cls(
+        return cls(
             film_miller=film_miller,
             substrate_miller=substrate_miller,
             strain=strain,
             von_mises_strain=von_mises_strain,
             elastic_energy=elastic_energy,
             ground_state_energy=ground_state_energy,
-            **{k: match_dict[k] for k in match_dict.keys() if not k.startswith("@")},
+            **{
+                k: getattr(match, k)
+                for k in [
+                    "film_sl_vectors",
+                    "substrate_sl_vectors",
+                    "film_vectors",
+                    "substrate_vectors",
+                    "film_transformation",
+                    "substrate_transformation",
+                ]
+            },
         )
 
     @property
@@ -183,6 +191,7 @@ def calculate(
             substrate_miller,
         ] in surface_vector_sets:
             for match in self(film_vectors, substrate_vectors, lowest):
+
                 sub_match = SubstrateMatch.from_zsl(
                     match=match,
                     film=film,

pymatgen/analysis/interfaces/tests/test_substrate_analyzer.py

@@ -35,6 +35,9 @@ def test_init(self):
 
         matches = list(s.calculate(film, substrate, film_elac))
         self.assertEqual(len(matches), 192)
+        for match in matches:
+            assert match is not None
+            assert isinstance(match.match_area, float)
 
 
 if __name__ == "__main__":

pymatgen/analysis/interfaces/tests/test_zsl.py

@@ -60,6 +60,10 @@ def test_bidirectional(self):
         matches = list(z(self.substrate.lattice.matrix[:2], self.film.lattice.matrix[:2]))
         self.assertEqual(len(matches), 48)
 
+        for match in matches:
+            assert match is not None
+            assert isinstance(match.match_area, float)
+
 
 if __name__ == "__main__":
     unittest.main()

pymatgen/analysis/interfaces/zsl.py

@@ -6,7 +6,7 @@
 This module implements the Zur and McGill lattice matching algorithm
 """
 
-from typing import Iterator
+from typing import Iterator, List
 
 from dataclasses import dataclass
 from itertools import product
@@ -24,17 +24,17 @@ class ZSLMatch(MSONable):
     the appropriate transformation matrix
     """
 
-    film_sl_vectors: np.ndarray
-    substrate_sl_vectors: np.ndarray
-    film_vectors: np.ndarray
-    substrate_vectors: np.ndarray
-    film_transformation: np.ndarray
-    substrate_transformation: np.ndarray
+    film_sl_vectors: List
+    substrate_sl_vectors: List
+    film_vectors: List
+    substrate_vectors: List
+    film_transformation: List
+    substrate_transformation: List
 
     @property
     def match_area(self):
         """The area of the match between the substrate and film super lattice vectors"""
-        return vec_area(*self.film_sl_vectors.tolist())
+        return vec_area(*self.film_sl_vectors)
 
     @property
     def match_transformation(self):

pymatgen/core/__init__.py

@@ -30,7 +30,7 @@
 __email__ = "pymatgen@googlegroups.com"
 __maintainer__ = "Shyue Ping Ong"
 __maintainer_email__ = "shyuep@gmail.com"
-__version__ = "2022.0.10"
+__version__ = "2022.0.11"
 
 
 SETTINGS_FILE = os.path.join(os.path.expanduser("~"), ".pmgrc.yaml")

pymatgen/entries/compatibility.py

@@ -851,8 +851,8 @@ def __init__(
         References:
             Wang, A., Kingsbury, R., McDermott, M., Horton, M., Jain. A., Ong, S.P.,
                 Dwaraknath, S., Persson, K. A framework for quantifying uncertainty
-                in DFT energy corrections. ChemRxiv. Preprint.
-                https://doi.org/10.26434/chemrxiv.14593476.v1
+                in DFT energy corrections. Scientific Reports 11: 15496, 2021.
+                https://doi.org/10.1038/s41598-021-94550-5
 
             Jain, A. et al. Formation enthalpies by mixing GGA and GGA + U calculations.
                 Phys. Rev. B - Condens. Matter Mater. Phys. 84, 1–10 (2011).

pymatgen/io/cif.py

@@ -28,9 +28,10 @@
 from pymatgen.core.periodic_table import DummySpecies, Element, Species, get_el_sp
 from pymatgen.core.structure import Structure
 from pymatgen.electronic_structure.core import Magmom
-from pymatgen.symmetry.analyzer import SpacegroupAnalyzer
+from pymatgen.symmetry.analyzer import SpacegroupAnalyzer, SpacegroupOperations
 from pymatgen.symmetry.groups import SYMM_DATA, SpaceGroup
 from pymatgen.symmetry.maggroups import MagneticSpaceGroup
+from pymatgen.symmetry.structure import SymmetrizedStructure
 from pymatgen.util.coord import find_in_coord_list_pbc, in_coord_list_pbc
 
 __author__ = "Shyue Ping Ong, Will Richards, Matthew Horton"
@@ -911,7 +912,7 @@ def _parse_symbol(self, sym):
 
         return parsed_sym
 
-    def _get_structure(self, data, primitive):
+    def _get_structure(self, data, primitive, symmetrized):
         """
         Generate structure from part of the cif.
         """
@@ -951,6 +952,7 @@ def get_matching_coord(coord):
             return False
 
         for i in range(len(data["_atom_site_label"])):
+
             try:
                 # If site type symbol exists, use it. Otherwise, we use the
                 # label.
@@ -1021,6 +1023,7 @@ def get_matching_coord(coord):
         allcoords = []
         allmagmoms = []
         allhydrogens = []
+        equivalent_indices = []
 
         # check to see if magCIF file is disordered
         if self.feature_flags["magcif"]:
@@ -1034,9 +1037,11 @@ def get_matching_coord(coord):
                     raise NotImplementedError("Disordered magnetic structures not currently supported.")
 
         if coord_to_species.items():
-            for comp, group in groupby(
-                sorted(list(coord_to_species.items()), key=lambda x: x[1]),
-                key=lambda x: x[1],
+            for idx, (comp, group) in enumerate(
+                groupby(
+                    sorted(list(coord_to_species.items()), key=lambda x: x[1]),
+                    key=lambda x: x[1],
+                )
             ):
                 tmp_coords = [site[0] for site in group]
                 tmp_magmom = [coord_to_magmoms[tmp_coord] for tmp_coord in tmp_coords]
@@ -1054,6 +1059,17 @@ def get_matching_coord(coord):
                     im_h = 0
                     species = comp
 
+                # The following might be a more natural representation of equivalent indicies,
+                # but is not in the format expect by SymmetrizedStructure:
+                #   equivalent_indices.append(list(range(len(allcoords), len(coords)+len(allcoords))))
+                # The above gives a list like:
+                #   [[0, 1, 2, 3], [4, 5, 6, 7, 8, 9, 10, 11]] where the
+                # integers are site indices, whereas the version used below will give a version like:
+                #   [0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1]
+                # which is a list in the same order as the sites, but where if a site has the same integer
+                # it is equivalent.
+                equivalent_indices += len(coords) * [idx]
+
                 allhydrogens.extend(len(coords) * [im_h])
                 allcoords.extend(coords)
                 allspecies.extend(len(coords) * [species])
@@ -1079,6 +1095,19 @@ def get_matching_coord(coord):
 
             struct = Structure(lattice, allspecies, allcoords, site_properties=site_properties)
 
+            if symmetrized:
+
+                # Wyckoff labels not currently parsed, note that not all CIFs will contain Wyckoff labels
+                # TODO: extract Wyckoff labels (or other CIF attributes) and include as site_properties
+                wyckoffs = ["Not Parsed"] * len(struct)
+
+                # Names of space groups are likewise not parsed (again, not all CIFs will contain this information)
+                # What is stored are the lists of symmetry operations used to generate the structure
+                # TODO: ensure space group labels are stored if present
+                sg = SpacegroupOperations("Not Parsed", -1, self.symmetry_operations)
+
+                return SymmetrizedStructure(struct, sg, equivalent_indices, wyckoffs)
+
             struct = struct.get_sorted_structure()
 
             if primitive and self.feature_flags["magcif"]:
@@ -1089,7 +1118,7 @@ def get_matching_coord(coord):
 
             return struct
 
-    def get_structures(self, primitive=True):
+    def get_structures(self, primitive=True, symmetrized=False):
         """
         Return list of structures in CIF file. primitive boolean sets whether a
         conventional cell structure or primitive cell structure is returned.
@@ -1098,14 +1127,29 @@ def get_structures(self, primitive=True):
             primitive (bool): Set to False to return conventional unit cells.
                 Defaults to True. With magnetic CIF files, will return primitive
                 magnetic cell which may be larger than nuclear primitive cell.
+            symmetrized (bool): If True, return a SymmetrizedStructure which will
+                include the equivalent indices and symmetry operations used to
+                create the Structure as provided by the CIF (if explicit symmetry
+                operations are included in the CIF) or generated from information
+                in the CIF (if only space group labels are provided). Note that
+                currently Wyckoff labels and space group labels or numbers are
+                not included in the generated SymmetrizedStructure, these will be
+                notated as "Not Parsed" or -1 respectively.
 
         Returns:
             List of Structures.
         """
+
+        if primitive and symmetrized:
+            raise ValueError(
+                "Using both 'primitive' and 'symmetrized' arguments is not currently supported "
+                "since unexpected behavior might result."
+            )
+
         structures = []
         for i, d in enumerate(self._cif.data.values()):
             try:
-                s = self._get_structure(d, primitive)
+                s = self._get_structure(d, primitive, symmetrized)
                 if s:
                     structures.append(s)
             except (KeyError, ValueError) as exc:

pymatgen/io/tests/test_cif.py

@@ -14,6 +14,7 @@
 from pymatgen.core.structure import Structure
 from pymatgen.analysis.structure_matcher import StructureMatcher
 from pymatgen.electronic_structure.core import Magmom
+from pymatgen.symmetry.structure import SymmetrizedStructure
 from pymatgen.io.cif import CifBlock, CifParser, CifWriter
 from pymatgen.io.vasp.inputs import Poscar
 from pymatgen.util.testing import PymatgenTest
@@ -291,6 +292,14 @@ def test_CifParser(self):
         self.assertEqual(len(parser.get_structures(primitive=False)[0]), 2)
         self.assertFalse(parser.has_errors)
 
+    def test_get_symmetrized_structure(self):
+        parser = CifParser(self.TEST_FILES_DIR / "Li2O.cif")
+        sym_structure = parser.get_structures(primitive=False, symmetrized=True)[0]
+        structure = parser.get_structures(primitive=False, symmetrized=False)[0]
+        self.assertIsInstance(sym_structure, SymmetrizedStructure)
+        self.assertEqual(structure, sym_structure)
+        self.assertEqual(sym_structure.equivalent_indices, [[0, 1, 2, 3], [4, 5, 6, 7, 8, 9, 10, 11]])
+
     def test_site_symbol_preference(self):
         parser = CifParser(self.TEST_FILES_DIR / "site_type_symbol_test.cif")
         self.assertEqual(parser.get_structures()[0].formula, "Ge0.4 Sb0.4 Te1")

requirements-dev.txt

@@ -4,9 +4,9 @@ sphinx_rtd_theme
 pytest==6.2.4
 pytest-cov==2.12.1
 coverage==5.5
-coveralls==3.1.0
+coveralls==3.2.0
 mypy==0.910
 pydocstyle==6.1.1
 flake8==3.9.2
-pylint==2.9.3
-black==21.6b0
+pylint==2.9.6
+black==21.7b0

requirements-optional.txt

@@ -1,5 +1,5 @@
 pybtex==0.24.0
-tqdm==4.61.2
+tqdm==4.62.0
 ase==3.19.0
 chemview==0.6
 netCDF4==1.5.3

requirements.txt

@@ -8,7 +8,7 @@ tabulate==0.8.9
 matplotlib==3.3.4
 palettable==3.3.0
 spglib==1.16.1
-pandas==1.2.5
+pandas==1.3.0
 networkx==2.5.1
 plotly==4.14.3
 beautifulsoup4==4.9.3

setup.py

@@ -97,7 +97,7 @@ def finalize_options(self):
         include=["pymatgen.*", "pymatgen.analysis.*", "pymatgen.io.*", "pymatgen.ext.*"],
         exclude=["pymatgen.*.tests", "pymatgen.*.*.tests", "pymatgen.*.*.*.tests"],
     ),
-    version="2022.0.10",
+    version="2022.0.11",
     cmdclass={"build_ext": build_ext},
     python_requires=">=3.7",
     install_requires=[