fix doc and indentation

pyxtal/db.py

@@ -86,7 +86,8 @@ def dftb_opt_single(id, xtal, skf_dir, steps, symmetrize, criteria, kresol=0.05)
                 scc_iter=100,
             )
             s, eng = my.run(mode="vc-relax", step=int(steps / 2))
-            my = DFTB(s, skf_dir, kresol=kresol, folder=".", scc_error=1e-4, scc_iter=100)
+            my = DFTB(s, skf_dir, kresol=kresol, folder=".",
+                      scc_error=1e-4, scc_iter=100)
             s, eng = my.run(mode="vc-relax", step=int(steps / 2))
             s = my.struc
     except CalculationFailed:
@@ -109,7 +110,8 @@ def dftb_opt_single(id, xtal, skf_dir, steps, symmetrize, criteria, kresol=0.05)
         else:
             eng /= len(s)
 
-        status = xtal.check_validity(criteria) if criteria is not None else True
+        status = xtal.check_validity(
+            criteria) if criteria is not None else True
 
         header = f"{id:4d}"
         dicts = {"validity": status, "energy": eng}
@@ -167,7 +169,8 @@ def gulp_opt_single(id, xtal, ff, path, criteria):
     )
     status = False
     if not error:
-        status = xtal.check_validity(criteria) if criteria is not None else True
+        status = xtal.check_validity(
+            criteria) if criteria is not None else True
     if status:
         header = f"{id:4d}"
         dicts = {"validity": status, "energy": eng}
@@ -325,7 +328,7 @@ def get_all_codes(self, group=None):
                 print("find duplicate! remove", row.id, row.csd_code)
                 self.db.delete([row.id])
         return codes
-        #self.codes = codes
+        # self.codes = codes
 
     def add(self, entry):
         (atom, kvp, data) = entry
@@ -515,7 +518,8 @@ def __init__(self, db_name, ltol=0.05, stol=0.05, atol=3):
             "dftb_energy",
             "dftb_relaxed",
         ]
-        self.matcher = sm.StructureMatcher(ltol=ltol, stol=stol, angle_tol=atol)
+        self.matcher = sm.StructureMatcher(
+            ltol=ltol, stol=stol, angle_tol=atol)
 
     def vacuum(self):
         self.db.vacuum()
@@ -538,7 +542,8 @@ def get_pyxtal(self, id, use_relaxed=None):
             if hasattr(row, use_relaxed):
                 xtal_str = getattr(row, use_relaxed)
             else:
-                raise ValueError("No ff or vasp relaxed attributes for structure", id)
+                raise ValueError(
+                    "No ff or vasp relaxed attributes for structure", id)
 
             pmg = Structure.from_str(xtal_str, fmt="cif")
 
@@ -620,7 +625,8 @@ def add_strucs_from_db(self, db_file, check=False, tol=0.1, freq=50):
                             elif key == "dof":
                                 kvp[key] = xtal.get_dof()
                             elif key == "wps":
-                                kvp[key] == str(s.wp.get_label() for s in xtal.atom_sites)
+                                kvp[key] == str(s.wp.get_label()
+                                                for s in xtal.atom_sites)
                             elif key == "pearson_symbol":
                                 kvp[key] = xtal.get_Pearson_Symbol()
 
@@ -695,7 +701,8 @@ def clean_structures_spg_topology(self, dim=None):
                         )
                     )
                 else:
-                    unique_rows.append((row.natoms, row.space_group_number, row.wps, None))
+                    unique_rows.append(
+                        (row.natoms, row.space_group_number, row.wps, None))
             else:
                 to_delete.append(row.id)
         print(len(to_delete), "structures were deleted", to_delete)
@@ -733,7 +740,8 @@ def clean_structures(self, ids=(None, None), dtol=2e-3, etol=1e-3, criteria=None
                     )
 
                 if unique and (
-                    "MAX_energy" in criteria and hasattr(row, "ff_energy") and row.ff_energy > criteria["MAX_energy"]
+                    "MAX_energy" in criteria and hasattr(
+                        row, "ff_energy") and row.ff_energy > criteria["MAX_energy"]
                 ):
                     unique = False
                     print(
@@ -807,7 +815,8 @@ def clean_structures(self, ids=(None, None), dtol=2e-3, etol=1e-3, criteria=None
                         )
                     )
                 else:
-                    unique_rows.append((row.natoms, row.space_group_number, row.wps, row.density, None))
+                    unique_rows.append(
+                        (row.natoms, row.space_group_number, row.wps, row.density, None))
             else:
                 to_delete.append(row.id)
         print(len(to_delete), "structures were deleted", to_delete)
@@ -857,7 +866,8 @@ def clean_structures_pmg(self, ids=(None, None), min_id=None, dtol=5e-2, criteri
                     )
 
                 if unique and (
-                    "MAX_energy" in criteria and hasattr(row, "ff_energy") and row.ff_energy > criteria["MAX_energy"]
+                    "MAX_energy" in criteria and hasattr(
+                        row, "ff_energy") and row.ff_energy > criteria["MAX_energy"]
                 ):
                     unique = False
                     print(
@@ -913,7 +923,8 @@ def clean_structures_pmg(self, ids=(None, None), min_id=None, dtol=5e-2, criteri
                     if abs(den - row.density) < dtol:
                         ref_pmg = xtal.to_pymatgen()
                         s_pmg = ase2pymatgen(self.db.get_atoms(id=rowid))
-                        if self.matcher.fit(s_pmg, ref_pmg):  # , symmetric=True):
+                        # , symmetric=True):
+                        if self.matcher.fit(s_pmg, ref_pmg):
                             print(
                                 "Found duplicate",
                                 row.id,
@@ -1009,7 +1020,8 @@ def update_row_ff_energy(
                 if len(ids) < ncpu:
                     ncpu = len(ids)
                 N_cycle = int(np.ceil(len(ids) / ncpu))
-                print("\n# Parallel GULP optimizations", ncpu, N_cycle, len(ids))
+                print("\n# Parallel GULP optimizations",
+                      ncpu, N_cycle, len(ids))
 
                 args_list = []
                 # Partition to ensure that each proc get the a similar load for the sorted structures
@@ -1021,10 +1033,12 @@ def update_row_ff_energy(
                         if _id < len(ids):
                             par_ids.append(ids[_id])
                             par_xtals.append(xtals[_id])
-                    args_list.append((par_ids, par_xtals, ff, calc_folder, criteria))
+                    args_list.append(
+                        (par_ids, par_xtals, ff, calc_folder, criteria))
 
                 with ProcessPoolExecutor(max_workers=ncpu) as executor:
-                    results = [executor.submit(gulp_opt_par, *p) for p in args_list]
+                    results = [executor.submit(gulp_opt_par, *p)
+                               for p in args_list]
                     for result in results:
                         gulp_results.extend(result.result())
                 print("Finish Parallel GULP optimizations", len(gulp_results))
@@ -1048,7 +1062,8 @@ def _update_db_gulp(self, gulp_results, ff):
             for gulp_result in gulp_results:
                 (id, xtal, eng) = gulp_result
                 if xtal is not None:
-                    self.db.update(id, ff_energy=eng, ff_lib=ff, ff_relaxed=xtal.to_file())
+                    self.db.update(id, ff_energy=eng, ff_lib=ff,
+                                   ff_relaxed=xtal.to_file())
                     print('update_db_gulp', id)
 
     def update_row_dftb_energy(
@@ -1080,15 +1095,17 @@ def update_row_dftb_energy(
         os.makedirs(calc_folder, exist_ok=True)
         use_relaxed = "ff_relaxed" if use_ff else None
 
-        ids, xtals = self.select_xtals(ids, overwrite, "dftb_energy", use_relaxed)
+        ids, xtals = self.select_xtals(
+            ids, overwrite, "dftb_energy", use_relaxed)
 
         dftb_results = []
         os.chdir(calc_folder)
 
         # Serial or Parallel computation
         if ncpu == 1:
             for id, xtal in zip(ids, xtals):
-                res = dftb_opt_single(id, xtal, skf_dir, steps, symmetrize, criteria)
+                res = dftb_opt_single(
+                    id, xtal, skf_dir, steps, symmetrize, criteria)
                 (xtal, eng, status) = res
                 if status:
                     dftb_results.append((id, xtal, eng))
@@ -1118,7 +1135,8 @@ def update_row_dftb_energy(
                 )
 
             with ProcessPoolExecutor(max_workers=ncpu) as executor:
-                results = [executor.submit(dftb_opt_par, *p) for p in args_list]
+                results = [executor.submit(dftb_opt_par, *p)
+                           for p in args_list]
                 for result in results:
                     dftb_results.extend(result.result())
 
@@ -1139,7 +1157,8 @@ def update_row_topology(self, StructureType="Auto", overwrite=True, prefix=None)
         try:
             import juliacall
         except:
-            raise RuntimeError("Cannot load JuliaCall, Plz enable it before running")
+            raise RuntimeError(
+                "Cannot load JuliaCall, Plz enable it before running")
 
         def parse_topology(topology_info):
             """
@@ -1154,7 +1173,8 @@ def parse_topology(topology_info):
                     dim = d
                 tmp = n.split(",")[0]
                 if tmp.startswith("UNKNOWN"):
-                    detail = tmp[7:]  # tuple(int(num) for num in tmp[7:].split())
+                    # tuple(int(num) for num in tmp[7:].split())
+                    detail = tmp[7:]
                     tmp = "aaa"
                 elif tmp.startswith("unstable"):
                     tmp = "unstable"
@@ -1209,7 +1229,8 @@ def parse_topology(topology_info):
                     detail[:10],
                 )
                 # Unknown will be labeled as aaa
-                self.db.update(row.id, topology=name, dimension=dim, topology_detail=detail)
+                self.db.update(row.id, topology=name,
+                               dimension=dim, topology_detail=detail)
             else:
                 print("Existing Topology", row.topology)
 
@@ -1288,11 +1309,15 @@ def export_structures(
             den = row.density
             dof = row.dof
             ps = row.pearson_symbol
-            sim = float(row.similarity) if hasattr(row, "similarity") and row.similarity is not None else None
+            sim = float(row.similarity) if hasattr(
+                row, "similarity") and row.similarity is not None else None
             top = row.topology if hasattr(row, "topology") else None
-            ff_eng = float(row.ff_energy) if hasattr(row, "ff_energy") else None
-            vasp_eng = float(row.vasp_energy) if hasattr(row, "vasp_energy") else None
-            properties.append([row.id, ps, spg, den, dof, sim, ff_eng, vasp_eng, top])
+            ff_eng = float(row.ff_energy) if hasattr(
+                row, "ff_energy") else None
+            vasp_eng = float(row.vasp_energy) if hasattr(
+                row, "vasp_energy") else None
+            properties.append([row.id, ps, spg, den, dof,
+                              sim, ff_eng, vasp_eng, top])
 
         dicts = {}
         for i, key in enumerate(keys):
@@ -1325,7 +1350,8 @@ def export_structures(
             # if True:
             try:
                 xtal = self.get_pyxtal(id, use_relaxed)
-                number, symbol = xtal.group.number, xtal.group.symbol.replace("/", "")
+                number, symbol = xtal.group.number, xtal.group.symbol.replace(
+                    "/", "")
                 # convert to the desired subgroup representation if needed
                 if number != spg:
                     paths = xtal.group.path_to_subgroup(spg)
@@ -1340,7 +1366,8 @@ def export_structures(
                     f"{id:d}-{xtal.get_Pearson_Symbol():s}-{number:d}-{symbol:s}",
                 )
 
-                status = xtal.check_validity(criteria, True) if criteria is not None else True
+                status = xtal.check_validity(
+                    criteria, True) if criteria is not None else True
             except:
                 status = False
                 label = "Error"
@@ -1353,7 +1380,8 @@ def export_structures(
                         _l, _sp, _cn = s.wp.get_label(), s.specie, s.coordination
                         label += f"-{_l:s}-{_sp:s}{_cn:d}"
                     label += f"-S{sim:.3f}"
-                    if len(label) > 40: label = label[:40]
+                    if len(label) > 40:
+                        label = label[:40]
                 except:
                     print("Problem in setting site coordination")
 
@@ -1447,7 +1475,8 @@ def check_overlap(self, reference_db, etol=2e-3, verbose=True):
         ref_data = []
         for row in db_ref.db.select():
             if hasattr(row, "topology") and hasattr(row, "ff_energy"):
-                ref_data.append((row.topology, row.topology_detail, row.ff_energy))
+                ref_data.append(
+                    (row.topology, row.topology_detail, row.ff_energy))
 
         overlaps = []
         for row in self.db.select():
@@ -1538,7 +1567,8 @@ def print_info(self, excluded_ids=None, cutoff=100):
         os.environ["ASE_DFTB_COMMAND"] = "/Users/qzhu8/opt/dftb+/bin/dftb+ > PREFIX.out"
         skf_dir = "/Users/qzhu8/GitHub/MOF-Builder/3ob-3-1/"
         # db.update_row_dftb_energy(skf_dir, ncpu=1, ids=(0, 2), overwrite=True)
-        db.update_row_dftb_energy(skf_dir, ncpu=1, ids=(17, 17), overwrite=True)
+        db.update_row_dftb_energy(
+            skf_dir, ncpu=1, ids=(17, 17), overwrite=True)
 
     db = database_topology("total.db")
     db.get_db_unique()