Fix: ignore UP031 (deepmodeling#762)

.pre-commit-config.yaml

@@ -21,7 +21,7 @@ repos:
 # Python
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.7.4
+    rev: v0.8.1
     hooks:
     - id: ruff
       args: ["--fix"]

docs/conf.py

@@ -24,7 +24,7 @@
 # -- Project information -----------------------------------------------------
 
 project = "dpdata"
-copyright = "2019-%d, DeepModeling " % date.today().year
+copyright = "2019-%d, DeepModeling " % date.today().year  # noqa: UP031
 author = "Han Wang"
 
 # The short X.Y version

dpdata/abacus/md.py

@@ -68,7 +68,7 @@ def get_coords_from_dump(dumplines, natoms):
     else:
         nframes_dump = int(nlines / (total_natoms + 9))
     assert nframes_dump > 0, (
-        "Number of lines in MD_dump file = %d. Number of atoms = %d. The MD_dump file is incomplete."
+        "Number of lines in MD_dump file = %d. Number of atoms = %d. The MD_dump file is incomplete."  # noqa: UP031
         % (nlines, total_natoms)
     )
     cells = np.zeros([nframes_dump, 3, 3])
@@ -125,7 +125,7 @@ def get_coords_from_dump(dumplines, natoms):
                     )
             iframe += 1
     assert iframe == nframes_dump, (
-        "iframe=%d, nframe_dump=%d. Number of frames does not match number of lines in MD_dump."
+        "iframe=%d, nframe_dump=%d. Number of frames does not match number of lines in MD_dump."  # noqa: UP031
         % (iframe, nframes_dump)
     )
     stresses *= kbar2evperang3
@@ -145,7 +145,7 @@ def get_energy(outlines, ndump, dump_freq):
                 energy.append(np.nan)
             nenergy += 1
     assert ndump == len(energy), (
-        "Number of total energies in running_md.log = %d. Number of frames in MD_dump = %d. Please check."
+        "Number of total energies in running_md.log = %d. Number of frames in MD_dump = %d. Please check."  # noqa: UP031
         % (len(energy), ndump)
     )
     energy = np.array(energy)
@@ -191,7 +191,7 @@ def get_frame(fname):
             force = np.delete(force, i - ndump, axis=0)
             stress = np.delete(stress, i - ndump, axis=0)
             energy = np.delete(energy, i - ndump, axis=0)
-            unconv_stru += "%d " % i
+            unconv_stru += "%d " % i  # noqa: UP031
     ndump = len(energy)
     if unconv_stru != "":
         warnings.warn(f"Structure {unconv_stru} are unconverged and not collected!")

dpdata/abacus/relax.py

@@ -47,7 +47,7 @@ def get_coords_from_log(loglines, natoms):
             natoms_log += int(line.split()[-1])
 
     assert natoms_log > 0 and natoms_log == natoms, (
-        "ERROR: detected atom number in log file is %d" % natoms
+        "ERROR: detected atom number in log file is %d" % natoms  # noqa: UP031
     )
 
     energy = []
@@ -76,7 +76,7 @@ def get_coords_from_log(loglines, natoms):
                         list(map(lambda x: float(x) * a0, loglines[i + k].split()[1:4]))
                     )
             else:
-                assert False, "Unrecongnized coordinate type, %s, line:%d" % (
+                assert False, "Unrecongnized coordinate type, %s, line:%d" % (  # noqa: UP031
                     loglines[i].split()[0],
                     i,
                 )

dpdata/data_type.py

@@ -122,7 +122,7 @@ def check(self, system: System):
                 elif isinstance(data, list):
                     if len(shape) and shape[0] != len(data):
                         raise DataError(
-                            "Length of %s is %d, but expected %d"
+                            "Length of %s is %d, but expected %d"  # noqa: UP031
                             % (self.name, len(data), shape[0])
                         )
                 else:

dpdata/deepmd/comp.py

@@ -119,7 +119,7 @@ def dump(folder, data, set_size=5000, comp_prec=np.float32, remove_sets=True):
     for ii in range(nsets):
         set_stt = ii * set_size
         set_end = (ii + 1) * set_size
-        set_folder = os.path.join(folder, "set.%03d" % ii)
+        set_folder = os.path.join(folder, "set.%03d" % ii)  # noqa: UP031
         os.makedirs(set_folder)
     try:
         os.remove(os.path.join(folder, "nopbc"))
@@ -158,5 +158,5 @@ def dump(folder, data, set_size=5000, comp_prec=np.float32, remove_sets=True):
         for ii in range(nsets):
             set_stt = ii * set_size
             set_end = (ii + 1) * set_size
-            set_folder = os.path.join(folder, "set.%03d" % ii)
+            set_folder = os.path.join(folder, "set.%03d" % ii)  # noqa: UP031
             np.save(os.path.join(set_folder, dtype.deepmd_name), ddata[set_stt:set_end])

dpdata/deepmd/hdf5.py

@@ -59,7 +59,7 @@ def to_system_data(
     else:
         my_type_map = []
         for ii in range(ntypes):
-            my_type_map.append("Type_%d" % ii)
+            my_type_map.append("Type_%d" % ii)  # noqa: UP031
     assert len(my_type_map) >= len(data["atom_numbs"])
     for ii in range(len(data["atom_numbs"])):
         data["atom_names"].append(my_type_map[ii])
@@ -217,7 +217,7 @@ def dump(
     for ii in range(nsets):
         set_stt = ii * set_size
         set_end = (ii + 1) * set_size
-        set_folder = g.create_group("set.%03d" % ii)
+        set_folder = g.create_group("set.%03d" % ii)  # noqa: UP031
         for dt, prop in data_types.items():
             if dt in reshaped_data:
                 set_folder.create_dataset(

dpdata/deepmd/raw.py

@@ -27,7 +27,7 @@ def load_type(folder, type_map=None):
     else:
         my_type_map = []
         for ii in range(ntypes):
-            my_type_map.append("Type_%d" % ii)
+            my_type_map.append("Type_%d" % ii)  # noqa: UP031
     data["atom_names"] = my_type_map
     data["atom_numbs"] = []
     for ii, _ in enumerate(data["atom_names"]):

dpdata/gaussian/gjf.py

@@ -186,8 +186,8 @@ def make_gaussian_input(
             mult_frags.append(detect_multiplicity(np.array(symbols)[idx]))
         if use_fragment_guesses:
             multiplicity = sum(mult_frags) - frag_numb + 1 - charge % 2
-            chargekeywords_frag = "%d %d" % (charge, multiplicity) + "".join(
-                [" %d %d" % (charge, mult_frag) for mult_frag in mult_frags]
+            chargekeywords_frag = "%d %d" % (charge, multiplicity) + "".join(  # noqa: UP031
+                [" %d %d" % (charge, mult_frag) for mult_frag in mult_frags]  # noqa: UP031
             )
         else:
             multi_frags = np.array(mult_frags)
@@ -239,10 +239,10 @@ def make_gaussian_input(
     for ii, (symbol, coordinate) in enumerate(zip(symbols, coordinates)):
         if use_fragment_guesses:
             buff.append(
-                "%s(Fragment=%d) %f %f %f" % (symbol, frag_index[ii] + 1, *coordinate)
+                "%s(Fragment=%d) %f %f %f" % (symbol, frag_index[ii] + 1, *coordinate)  # noqa: UP031
             )
         else:
-            buff.append("{} {:f} {:f} {:f}".format(symbol, *coordinate))
+            buff.append("{} {:f} {:f} {:f}".format(symbol, *coordinate))  # noqa: UP031
     if not sys_data.get("nopbc", False):
         # PBC condition
         cell = sys_data["cells"][0]

dpdata/lammps/dump.py

@@ -289,7 +289,7 @@ def system_data(
     system["atom_names"] = []
     if type_map is None:
         for ii in range(len(system["atom_numbs"])):
-            system["atom_names"].append("TYPE_%d" % ii)
+            system["atom_names"].append("TYPE_%d" % ii)  # noqa: UP031
     else:
         assert len(type_map) >= len(system["atom_numbs"])
         for ii in range(len(system["atom_numbs"])):

dpdata/lammps/lmp.py

@@ -167,7 +167,7 @@ def system_data(lines, type_map=None, type_idx_zero=True):
     system["atom_names"] = []
     if type_map is None:
         for ii in range(len(system["atom_numbs"])):
-            system["atom_names"].append("Type_%d" % ii)
+            system["atom_names"].append("Type_%d" % ii)  # noqa: UP031
     else:
         assert len(type_map) >= len(system["atom_numbs"])
         for ii in range(len(system["atom_numbs"])):
@@ -198,27 +198,27 @@ def from_system_data(system, f_idx=0):
     ret += "\n"
     natoms = sum(system["atom_numbs"])
     ntypes = len(system["atom_numbs"])
-    ret += "%d atoms\n" % natoms
-    ret += "%d atom types\n" % ntypes
+    ret += "%d atoms\n" % natoms  # noqa: UP031
+    ret += "%d atom types\n" % ntypes  # noqa: UP031
     ret += (ptr_float_fmt + " " + ptr_float_fmt + " xlo xhi\n") % (
         0,
         system["cells"][f_idx][0][0],
-    )
+    )  # noqa: UP031
     ret += (ptr_float_fmt + " " + ptr_float_fmt + " ylo yhi\n") % (
         0,
         system["cells"][f_idx][1][1],
-    )
+    )  # noqa: UP031
     ret += (ptr_float_fmt + " " + ptr_float_fmt + " zlo zhi\n") % (
         0,
         system["cells"][f_idx][2][2],
-    )
+    )  # noqa: UP031
     ret += (
         ptr_float_fmt + " " + ptr_float_fmt + " " + ptr_float_fmt + " xy xz yz\n"
     ) % (
         system["cells"][f_idx][1][0],
         system["cells"][f_idx][2][0],
         system["cells"][f_idx][2][1],
-    )
+    )  # noqa: UP031
     ret += "\n"
     ret += "Atoms # atomic\n"
     ret += "\n"
@@ -233,7 +233,7 @@ def from_system_data(system, f_idx=0):
         + " "
         + ptr_float_fmt
         + "\n"
-    )
+    )  # noqa: UP031
 
     if "spins" in system:
         coord_fmt = (
@@ -247,7 +247,7 @@ def from_system_data(system, f_idx=0):
             + " "
             + ptr_float_fmt
             + "\n"
-        )
+        )  # noqa: UP031
         spins_norm = np.linalg.norm(system["spins"][f_idx], axis=1)
     for ii in range(natoms):
         if "spins" in system:
@@ -262,7 +262,7 @@ def from_system_data(system, f_idx=0):
                     system["spins"][f_idx][ii][1] / spins_norm[ii],
                     system["spins"][f_idx][ii][2] / spins_norm[ii],
                     spins_norm[ii],
-                )
+                )  # noqa: UP031
             else:
                 ret += coord_fmt % (
                     ii + 1,
@@ -274,15 +274,15 @@ def from_system_data(system, f_idx=0):
                     system["spins"][f_idx][ii][1],
                     system["spins"][f_idx][ii][2] + 1,
                     spins_norm[ii],
-                )
+                )  # noqa: UP031
         else:
             ret += coord_fmt % (
                 ii + 1,
                 system["atom_types"][ii] + 1,
                 system["coords"][f_idx][ii][0] - system["orig"][0],
                 system["coords"][f_idx][ii][1] - system["orig"][1],
                 system["coords"][f_idx][ii][2] - system["orig"][2],
-            )
+            )  # noqa: UP031
     return ret
 
 

dpdata/plugins/amber.py

@@ -136,8 +136,8 @@ def label(self, data: dict) -> dict:
         labeled_system = dpdata.LabeledSystem()
         with tempfile.TemporaryDirectory() as d:
             for ii, ss in enumerate(ori_system):
-                inp_fn = os.path.join(d, "%d.in" % ii)
-                out_fn = os.path.join(d, "%d.out" % ii)
+                inp_fn = os.path.join(d, "%d.in" % ii)  # noqa: UP031
+                out_fn = os.path.join(d, "%d.out" % ii)  # noqa: UP031
                 ss.to("sqm/in", inp_fn, **self.kwargs)
                 try:
                     sp.check_output(

dpdata/plugins/gaussian.py

@@ -109,8 +109,8 @@ def label(self, data: dict) -> dict:
         labeled_system = dpdata.LabeledSystem()
         with tempfile.TemporaryDirectory() as d:
             for ii, ss in enumerate(ori_system):
-                inp_fn = os.path.join(d, "%d.gjf" % ii)
-                out_fn = os.path.join(d, "%d.log" % ii)
+                inp_fn = os.path.join(d, "%d.gjf" % ii)  # noqa: UP031
+                out_fn = os.path.join(d, "%d.log" % ii)  # noqa: UP031
                 ss.to("gaussian/gjf", inp_fn, **self.kwargs)
                 try:
                     sp.check_output([*self.gaussian_exec.split(), inp_fn])

dpdata/pwmat/atomconfig.py

@@ -54,7 +54,7 @@ def to_system_data(lines):
 def from_system_data(system, f_idx=0, skip_zeros=True):
     ret = ""
     natoms = sum(system["atom_numbs"])
-    ret += "%d" % natoms
+    ret += "%d" % natoms  # noqa: UP031
     ret += "\n"
     ret += "LATTICE"
     ret += "\n"
@@ -83,7 +83,7 @@ def from_system_data(system, f_idx=0, skip_zeros=True):
     posi_list = []
     for jj, ii in zip(atomic_numbers, posis):
         ii = np.matmul(ii, np.linalg.inv(system["cells"][0]))
-        posi_list.append("%d %15.10f %15.10f %15.10f 1 1 1" % (jj, ii[0], ii[1], ii[2]))
+        posi_list.append("%d %15.10f %15.10f %15.10f 1 1 1" % (jj, ii[0], ii[1], ii[2]))  # noqa: UP031
     for kk in range(len(posi_list)):
         min = kk
         for jj in range(kk, len(posi_list)):

dpdata/qe/traj.py

@@ -78,7 +78,7 @@ def load_atom_names(lines, ntypes):
 def load_celldm(lines):
     celldm = np.zeros(6)
     for ii in range(6):
-        key = "celldm(%d)" % (ii + 1)
+        key = "celldm(%d)" % (ii + 1)  # noqa: UP031
         val = load_key(lines, key)
         if val is not None:
             celldm[ii] = float(val)
@@ -169,7 +169,7 @@ def load_energy(fname, begin=0, step=1):
     data = np.loadtxt(fname)
     steps = []
     for ii in data[begin::step, 0]:
-        steps.append("%d" % ii)
+        steps.append("%d" % ii)  # noqa: UP031
     with open_file(fname) as fp:
         while True:
             line = fp.readline()

dpdata/rdkit/sanitize.py

@@ -367,10 +367,10 @@ def sanitize_mol(mol, verbose=False):
 # copy from FEprep
 def mol_edit_log(mol, i, j):
     if not mol.HasProp("edit"):
-        mol.SetProp("edit", "%d_%d" % (i, j))
+        mol.SetProp("edit", "%d_%d" % (i, j))  # noqa: UP031
     else:
         edited = mol.GetProp("edit")
-        mol.SetProp("edit", edited + ",%d_%d" % (i, j))
+        mol.SetProp("edit", edited + ",%d_%d" % (i, j))  # noqa: UP031
 
 
 def kekulize_aromatic_heterocycles(mol_in, assign_formal_charge=True, sanitize=True):

dpdata/system.py

@@ -226,7 +226,7 @@ def check_data(self):
             dd.check(self)
         if sum(self.get_atom_numbs()) != self.get_natoms():
             raise DataError(
-                "Sum of atom_numbs (%d) is not equal to natoms (%d)."
+                "Sum of atom_numbs (%d) is not equal to natoms (%d)."  # noqa: UP031
                 % (sum(self.get_atom_numbs()), self.get_natoms())
             )
 
@@ -281,8 +281,8 @@ def __str__(self):
         ret = "Data Summary"
         ret += "\nUnlabeled System"
         ret += "\n-------------------"
-        ret += "\nFrame Numbers     : %d" % self.get_nframes()
-        ret += "\nAtom Numbers      : %d" % self.get_natoms()
+        ret += "\nFrame Numbers     : %d" % self.get_nframes()  # noqa: UP031
+        ret += "\nAtom Numbers      : %d" % self.get_natoms()  # noqa: UP031
         ret += "\nElement List      :"
         ret += "\n-------------------"
         ret += "\n" + "  ".join(map(str, self.get_atom_names()))
@@ -1243,8 +1243,8 @@ def __str__(self):
         ret = "Data Summary"
         ret += "\nLabeled System"
         ret += "\n-------------------"
-        ret += "\nFrame Numbers      : %d" % self.get_nframes()
-        ret += "\nAtom Numbers       : %d" % self.get_natoms()
+        ret += "\nFrame Numbers      : %d" % self.get_nframes()  # noqa: UP031
+        ret += "\nAtom Numbers       : %d" % self.get_natoms()  # noqa: UP031
         status = "Yes" if self.has_virial() else "No"
         ret += f"\nIncluding Virials  : {status}"
         ret += "\nElement List       :"

dpdata/vasp/poscar.py

@@ -79,7 +79,7 @@ def from_system_data(system, f_idx=0, skip_zeros=True):
     for ii, name in zip(system["atom_numbs"], system["atom_names"]):
         if ii == 0:
             continue
-        ret += "%s%d " % (name, ii)
+        ret += "%s%d " % (name, ii)  # noqa: UP031
     ret += "\n"
     ret += "1.0\n"
     for ii in system["cells"][f_idx]:
@@ -94,7 +94,7 @@ def from_system_data(system, f_idx=0, skip_zeros=True):
     for ii in system["atom_numbs"]:
         if ii == 0:
             continue
-        ret += "%d " % ii
+        ret += "%d " % ii  # noqa: UP031
     ret += "\n"
     move = system.get("move", None)
     if move is not None and len(move) > 0:

dpdata/vasp/xml.py

@@ -58,7 +58,7 @@ def formulate_config(eles, types, posi, cell, ener, forc, strs_):
     natoms = len(types)
     ntypes = len(eles)
     ret = ""
-    ret += "#N %d %d\n" % (natoms, ntypes - 1)
+    ret += "#N %d %d\n" % (natoms, ntypes - 1)  # noqa: UP031
     ret += "#C "
     for ii in eles:
         ret += " " + ii
@@ -73,7 +73,7 @@ def formulate_config(eles, types, posi, cell, ener, forc, strs_):
     ret += "#F\n"
     for ii in range(natoms):
         sp = np.matmul(cell.T, posi[ii])
-        ret += "%d" % (types[ii] - 1)
+        ret += "%d" % (types[ii] - 1)  # noqa: UP031
         ret += f" {sp[0]:12.6f} {sp[1]:12.6f} {sp[2]:12.6f}"
         ret += f" {forc[ii][0]:12.6f} {forc[ii][1]:12.6f} {forc[ii][2]:12.6f}"
         ret += "\n"

tests/poscars/poscar_ref_oh.py

@@ -32,7 +32,7 @@ def test_cell(self):
                     self.system.data["cells"][0][ii][jj],
                     ovito_cell[ii][jj],
                     places=6,
-                    msg="cell[%d][%d] failed" % (ii, jj),
+                    msg="cell[%d][%d] failed" % (ii, jj),  # noqa: UP031
                 )
 
     def test_frame(self):
@@ -48,5 +48,5 @@ def test_frame(self):
                     self.system.data["coords"][0][ii][jj],
                     ovito_posis[ii][jj],
                     places=6,
-                    msg="posis[%d][%d] failed" % (ii, jj),
+                    msg="posis[%d][%d] failed" % (ii, jj),  # noqa: UP031
                 )