Merge branch 'materialsproject:master' into master

Author: esoteric-ephemera

.github/dependabot.yml

@@ -27,7 +27,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Setup Pages
         uses: actions/configure-pages@v3
       - name: Build with Jekyll

.github/workflows/jekyll-gh-pages.yml

@@ -87,10 +87,10 @@ If you use `pymatgen` in your research, please consider citing the following wor
 
 In addition, some of `pymatgen`'s functionality is based on scientific advances/principles developed by the computational materials scientists in our team. Please refer to the [`pymatgen` docs] on how to cite them.
 
-### Soliciting contributions to an updated pymatgen paper
+### Soliciting contributions to 2nd `pymatgen` paper
 
 If you are a long-standing `pymatgen` contributor and would like to be involved in working on an updated `pymatgen` publication,
-please contact the maintainers [@shyuep, @mkhorton and @janosh](mailto:ongsp@ucsd.edu,m.k.horton@gmail.com,janosh@lbl.gov?subject=Contributing%20to%20updated%20pymatgen%20paper).
+please fill out this [co-author registration form](https://docs.google.com/forms/d/e/1FAIpQLSecIhD2YjdPGldrRTM8Go3VxVg_vjKjZAOXtIKDG7qckHLYaQ/viewform) or contact [@shyuep, @mkhorton and @janosh](mailto:ongsp@ucsd.edu,m.k.horton@gmail.com,janosh@lbl.gov?subject=Contributing%20to%20updated%20pymatgen%20paper) with questions.
 
 ## License
 

README.md

@@ -91,8 +91,7 @@ class Algo:
         if len(cg.algorithms) != 1:
             raise ValueError("Multiple algorithms !")
         cg._algorithms = [ExplicitPermutationsAlgorithm(permutations=explicit_permutations)]
-        newgeom_dir = "new_geometry_files"
-        if not os.path.exists(newgeom_dir):
-            os.makedirs(newgeom_dir)
-        with open(f"{newgeom_dir}/{cg_symbol}.json", "w") as f:
+        new_geom_dir = "new_geometry_files"
+        os.makedirs(new_geom_dir, exist_ok=True)
+        with open(f"{new_geom_dir}/{cg_symbol}.json", "w") as f:
             json.dump(cg.as_dict(), f)

dev_scripts/chemenv/explicit_permutations.py

@@ -431,7 +431,6 @@ def random_permutations_iterator(initial_permutation, n_permutations):
         )
         if test == "y":
             new_geom_dir = "new_geometry_files"
-            if not os.path.exists(new_geom_dir):
-                os.makedirs(new_geom_dir)
+            os.makedirs(new_geom_dir, exist_ok=True)
             with open(f"{new_geom_dir}/{cg_symbol}.json", "w") as file:
                 json.dump(cg.as_dict(), file)

dev_scripts/chemenv/get_plane_permutations_optimized.py

@@ -143,8 +143,7 @@ def setup_potcars(potcar_dirs: list[str]):
             if len(filenames) > 0:
                 try:
                     base_dir = os.path.join(target_dir, basename)
-                    if not os.path.exists(base_dir):
-                        os.makedirs(base_dir)
+                    os.makedirs(base_dir, exist_ok=True)
                     fname = filenames[0]
                     dest = os.path.join(base_dir, os.path.basename(fname))
                     shutil.copy(fname, dest)

docs/index.md

@@ -111,8 +111,8 @@ def __init__(self, input_script):
         self._stdout = stdout
         self._stderr = stderr
 
-        cpreport = loadfn("cpreport.json") if os.path.exists("cpreport.json") else None
-        self._cpreport = cpreport
+        cp_report = loadfn("cpreport.json") if os.path.exists("cpreport.json") else None
+        self._cp_report = cp_report
 
         yt = loadfn("yt.json") if os.path.exists("yt.json") else None
         self._yt = yt
@@ -240,7 +240,7 @@ def from_chgcar(
                 structure,
                 stdout=caller._stdout,
                 stderr=caller._stderr,
-                cpreport=caller._cpreport,
+                cpreport=caller._cp_report,
                 yt=caller._yt,
                 zpsp=zpsp,
             )

pymatgen/cli/pmg_config.py

@@ -545,18 +545,19 @@ def run(
         if convergence and not write_input:
             raise ValueError("Convergence mode requires write_input to be true")
 
-        if self.run_type in ("BANDS", "DOS", "FERMI"):
+        run_type = self.run_type
+        if run_type in ("BANDS", "DOS", "FERMI"):
             convergence = False
             if self.lpfac > max_lpfac:
                 max_lpfac = self.lpfac
 
-        if self.run_type == "BANDS" and self.bs.is_spin_polarized:
+        if run_type == "BANDS" and self.bs.is_spin_polarized:
             print(
-                f"Reminder: for run_type {self.run_type}, spin component are not separated! "
+                f"Reminder: for {run_type=}, spin component are not separated! "
                 "(you have a spin polarized band structure)"
             )
 
-        if self.run_type in ("FERMI", "DOS") and self.spin is None:
+        if run_type in ("FERMI", "DOS") and self.spin is None:
             if self.bs.is_spin_polarized:
                 raise BoltztrapError("Spin parameter must be specified for spin polarized band structures!")
             self.spin = 1
@@ -568,9 +569,8 @@ def run(
         else:
             path_dir = os.path.abspath(os.path.join(path_dir, dir_bz_name))
 
-        if not os.path.exists(path_dir):
-            os.mkdir(path_dir)
-        elif clear_dir:
+        os.mkdir(path_dir, exist_ok=True)
+        if clear_dir:
             for c in os.listdir(path_dir):
                 os.remove(os.path.join(path_dir, c))
 

pymatgen/command_line/critic2_caller.py

@@ -16,9 +16,6 @@
 from pymatgen.util.due import Doi, due
 from pymatgen.util.provenance import StructureNL
 
-# from retrying import retry
-
-
 # TODO: importing optimade-python-tool's data structures will make more sense
 Provider = namedtuple("Provider", ["name", "base_url", "description", "homepage", "prefix"])
 
@@ -46,7 +43,9 @@ class OptimadeRester:
     # these aliases are provided as a convenient shortcut for users of the OptimadeRester class
     aliases = {
         "aflow": "http://aflow.org/API/optimade/",
+        "alexandria": "https://alexandria.odbx.science",
         "cod": "https://www.crystallography.net/cod/optimade",
+        "cmr": "https://cmr-optimade.fysik.dtu.dk",
         "mcloud.mc3d": "https://aiida.materialscloud.org/mc3d/optimade",
         "mcloud.mc2d": "https://aiida.materialscloud.org/mc2d/optimade",
         "mcloud.2dtopo": "https://aiida.materialscloud.org/2dtopo/optimade",
@@ -58,6 +57,7 @@ class OptimadeRester:
         "mcloud.tin-antimony-sulfoiodide": "https://aiida.materialscloud.org/tin-antimony-sulfoiodide/optimade",
         "mcloud.optimade-sample": "https://aiida.materialscloud.org/optimade-sample/optimade",
         "mp": "https://optimade.materialsproject.org",
+        "mpdd": "http://mpddoptimade.phaseslab.org",
         "mpds": "https://api.mpds.io",
         "nmd": "https://nomad-lab.eu/prod/rae/optimade/",
         "odbx": "https://optimade.odbx.science",
@@ -154,11 +154,8 @@ def describe(self):
         provider_text = "\n".join(map(str, (provider for provider in self._providers.values() if provider)))
         return f"OptimadeRester connected to:\n{provider_text}"
 
-    # @retry(stop_max_attempt_number=3, wait_random_min=1000, wait_random_max=2000)
     def _get_json(self, url):
-        """Retrieves JSON, will attempt to (politely) try again on failure subject to a
-        random delay and a maximum number of attempts.
-        """
+        """Retrieves and returns JSON resource from given url."""
         return self.session.get(url, timeout=self._timeout).json()
 
     @staticmethod
@@ -215,8 +212,11 @@ def get_structures(
             elements: List of elements
             nelements: Number of elements, e.g. 4 or [2, 5] for the range >=2 and <=5
             nsites: Number of sites, e.g. 4 or [2, 5] for the range >=2 and <=5
-            chemical_formula_anonymous: Anonymous chemical formula
-            chemical_formula_hill: Chemical formula following Hill convention
+            chemical_formula_anonymous: The desired chemical formula in OPTIMADE anonymous formula format
+            (NB. The ordering is reversed from the pymatgen format, e.g., pymatgen "ABC2" should become "A2BC").
+            chemical_formula_hill: The desired chemical formula in the OPTIMADE take on the Hill formula format.
+            (NB. Again, this is different from the pymatgen format, as the OPTIMADE version is a reduced chemical
+            formula simply using the IUPAC/Hill ordering.)
 
         Returns:
             dict[str, Structure]: keyed by that database provider's id system
@@ -253,8 +253,11 @@ def get_snls(
             elements: List of elements
             nelements: Number of elements, e.g. 4 or [2, 5] for the range >=2 and <=5
             nsites: Number of sites, e.g. 4 or [2, 5] for the range >=2 and <=5
-            chemical_formula_anonymous: Anonymous chemical formula
-            chemical_formula_hill: Chemical formula following Hill convention
+            chemical_formula_anonymous: The desired chemical formula in OPTIMADE anonymous formula format
+            (NB. The ordering is reversed from the pymatgen format, e.g., pymatgen "ABC2" should become "A2BC").
+            chemical_formula_hill: The desired chemical formula in the OPTIMADE take on the Hill formula format.
+            (NB. Again, this is different from the pymatgen format, as the OPTIMADE version is a reduced chemical
+            formula simply using the IUPAC/Hill ordering.)
             additional_response_fields: Any additional fields desired from the OPTIMADE API,
             these will be stored under the `'_optimade'` key in each `StructureNL.data` dictionary.
 

pymatgen/electronic_structure/boltztrap.py

@@ -614,8 +614,7 @@ def __str__(self):
     def write(self, filepath="run.abi"):
         """Write the input file to file to filepath."""
         dirname = os.path.dirname(os.path.abspath(filepath))
-        if not os.path.exists(dirname):
-            os.makedirs(dirname)
+        os.makedirs(dirname, exist_ok=True)
 
         # Write the input file.
         with open(filepath, "w") as fh:

pymatgen/ext/optimade.py

@@ -507,11 +507,10 @@ def match_elecs(x):
                     break
 
             if basis is None:
-                if basis_and_potential.get(el, {}).get("basis"):
-                    warnings.warn(f"Unable to validate basis for {el}. Exact name provided will be put in input file.")
-                    basis = basis_and_potential[el].get("basis")
-                else:
-                    raise ValueError("No explicit basis found and matching has failed.")
+                if not basis_and_potential.get(el, {}).get("basis"):
+                    raise ValueError(f"No explicit basis found for {el} and matching has failed.")
+                warnings.warn(f"Unable to validate basis for {el}. Exact name provided will be put in input file.")
+                basis = basis_and_potential[el].get("basis")
 
             if aux_basis is None and basis_and_potential.get(el, {}).get("aux_basis"):
                 warnings.warn(
@@ -528,7 +527,7 @@ def match_elecs(x):
                 else:
                     raise ValueError("No explicit potential found and matching has failed.")
 
-            if basis.filename:
+            if hasattr(basis, "filename"):
                 data["basis_filenames"].append(basis.filename)
             pfn1 = data.get("potential_filename")
             pfn2 = potential.filename
@@ -539,11 +538,7 @@ def match_elecs(x):
                 )
             data["potential_filename"] = pfn2
 
-            data[el] = {
-                "basis": basis,
-                "aux_basis": aux_basis,
-                "potential": potential,
-            }
+            data[el] = {"basis": basis, "aux_basis": aux_basis, "potential": potential}
         return data
 
     @staticmethod

pymatgen/io/abinit/inputs.py

@@ -91,8 +91,8 @@ def write_input(self, output_dir=".", make_dir_if_not_present=True):
             make_dir_if_not_present: Set to True if you want the directory (
                 and the whole path) to be created if it is not present.
         """
-        if make_dir_if_not_present and not os.path.exists(output_dir):
-            os.makedirs(output_dir)
+        if make_dir_if_not_present:
+            os.makedirs(output_dir, exist_ok=True)
 
         feff = self.all_input()
 
@@ -282,27 +282,27 @@ def __str__(self):
         output.append("")
         return "\n".join(output)
 
-    @staticmethod
-    def from_directory(input_dir):
+    @classmethod
+    def from_directory(cls, input_dir):
         """
         Read in a set of FEFF input files from a directory, which is
         useful when existing FEFF input needs some adjustment.
         """
         sub_d = {}
         for fname, ftype in [("HEADER", Header), ("PARAMETERS", Tags)]:
-            fullzpath = zpath(os.path.join(input_dir, fname))
-            sub_d[fname.lower()] = ftype.from_file(fullzpath)
+            full_zpath = zpath(os.path.join(input_dir, fname))
+            sub_d[fname.lower()] = ftype.from_file(full_zpath)
 
         # Generation of FEFFDict set requires absorbing atom, need to search
         # the index of absorption atom in the structure according to the
         # distance matrix and shell species information contained in feff.inp
 
         absorber_index = []
         radius = None
-        feffinp = zpath(f"{input_dir}/feff.inp")
+        feff_inp = zpath(f"{input_dir}/feff.inp")
 
         if "RECIPROCAL" not in sub_d["parameters"]:
-            input_atoms = Atoms.cluster_from_file(feffinp)
+            input_atoms = Atoms.cluster_from_file(feff_inp)
             shell_species = np.array([x.species_string for x in input_atoms])
 
             # First row of distance matrix represents the distance from the absorber to
@@ -313,12 +313,7 @@ def from_directory(input_dir):
             from math import ceil
 
             radius = int(
-                ceil(
-                    input_atoms.get_distance(
-                        input_atoms.index(input_atoms[0]),
-                        input_atoms.index(input_atoms[-1]),
-                    )
-                )
+                ceil(input_atoms.get_distance(input_atoms.index(input_atoms[0]), input_atoms.index(input_atoms[-1])))
             )
 
             for site_index, site in enumerate(sub_d["header"].struct):
@@ -342,7 +337,7 @@ def from_directory(input_dir):
             CONFIG = loadfn(f"{MODULE_DIR}/MPXANESSet.yaml")
             if radius is None:
                 radius = 10
-            return FEFFDictSet(
+            return cls(
                 absorber_index[0],
                 sub_d["header"].struct,
                 radius=radius,

pymatgen/io/cp2k/sets.py

@@ -1077,8 +1077,8 @@ def write_lammps_inputs(
     variables = {} if settings is None else settings
     template = Template(script_template)
     input_script = template.safe_substitute(**variables)
-    if make_dir_if_not_present and not os.path.exists(output_dir):
-        os.makedirs(output_dir)
+    if make_dir_if_not_present:
+        os.makedirs(output_dir, exist_ok=True)
     with open(os.path.join(output_dir, script_filename), "w") as f:
         f.write(input_script)
     read_data = re.search(r"read_data\s+(.*)\n", input_script)