add gaussian log support

README.md

@@ -59,6 +59,7 @@ The `System` or `LabeledSystem` can be constructed from the following file forma
 | lammps  | lmp    | False        | False   | System        | 'lammps/lmp'  |
 | lammps  | dump   | True         | False   | System        | 'lammps/dump' |
 | deepmd  | raw    | True         | True    | LabeledSystem | 'deepmd/raw'  |
+| gaussian| log    | False        | True    | LabeledSystem | 'gaussian/log'|
 
 
 

dpdata/gaussian/log.py

@@ -0,0 +1,60 @@
+import numpy as np
+
+
+hartree2ev = 27.211386018
+bohr2ang = 0.52917721067
+
+length_convert = bohr2ang
+energy_convert = hartree2ev
+force_convert = energy_convert / length_convert
+
+symbols = ['X', 'H', 'He', 'Li', 'Be', 'B', 'C', 'N', 'O', 'F', 'Ne', 'Na', 'Mg', 'Al', 'Si', 'P', 'S', 'Cl', 'Ar', 'K', 'Ca', 'Sc', 'Ti', 'V', 'Cr', 'Mn', 'Fe', 'Co', 'Ni', 'Cu', 'Zn', 'Ga', 'Ge', 'As', 'Se', 'Br', 'Kr', 'Rb', 'Sr', 'Y', 'Zr', 'Nb', 'Mo', 'Tc', 'Ru', 'Rh', 'Pd', 'Ag', 'Cd', 'In', 'Sn', 'Sb', 'Te', 'I', 'Xe', 'Cs', 'Ba', 'La', 'Ce', 'Pr', 'Nd', 'Pm', 'Sm', 'Eu', 'Gd', 'Tb', 'Dy', 'Ho', 'Er', 'Tm', 'Yb', 'Lu', 'Hf', 'Ta', 'W', 'Re', 'Os', 'Ir', 'Pt', 'Au', 'Hg', 'Tl', 'Pb', 'Bi', 'Po', 'At', 'Rn', 'Fr', 'Ra', 'Ac', 'Th', 'Pa', 'U', 'Np', 'Pu', 'Am', 'Cm', 'Bk', 'Cf', 'Es', 'Fm', 'Md', 'No', 'Lr', 'Rf', 'Db', 'Sg', 'Bh', 'Hs', 'Mt', 'Ds', 'Rg', 'Cn', 'Nh', 'Fl', 'Mc', 'Lv', 'Ts', 'Og']
+
+def to_system_data(file_name):
+    data = {}
+    # read from log lines
+    flag = 0
+    energy = 0
+    coords = []
+    atom_symbols = []
+    forces = []
+
+    with open(file_name) as fp:
+        for line in fp:
+            if line.startswith(" SCF Done"):
+                # energies
+                energy = float(line.split()[4])
+            elif line.startswith(" Center     Atomic                   Forces (Hartrees/Bohr)"):
+                flag = 1
+            elif line.startswith("                          Input orientation:"):
+                flag = 5
+
+            if 1 <= flag <= 3 or 5 <= flag <= 9:
+                flag += 1
+            elif flag == 4:
+                # forces
+                if line.startswith(" -------"):
+                    flag = 0
+                else:
+                    s = line.split()
+                    forces.append([float(x) for x in s[2:5]])
+            elif flag == 10:
+                # atom_symbols and coords
+                if line.startswith(" -------"):
+                    flag = 0
+                else:
+                    s = line.split()
+                    coords.append([float(x) for x in s[3:6]])
+                    atom_symbols.append(symbols[int(s[1])])
+
+    assert(coords), "cannot find coords"
+    assert(energy), "cannot find energies"
+    assert(forces), "cannot find forces"
+
+    atom_names, data['atom_types'], atom_numbs = np.unique(atom_symbols, return_inverse=True, return_counts=True)
+    data['atom_names'] = list(atom_names)
+    data['atom_numbs'] = list(atom_numbs)
+    data['forces'] = np.array([forces]) * force_convert
+    data['energies'] = np.array([energy]) * energy_convert
+    data['coords'] = np.array([coords])
+    return data

dpdata/system.py

@@ -9,6 +9,7 @@
 import dpdata.deepmd.comp
 import dpdata.pwscf.traj
 import dpdata.md.pbc
+import dpdata.gaussian.log
 
 class System (object) :
     '''
@@ -282,6 +283,7 @@ def __init__ (self,
                 - ``deepmd/raw``: deepmd-kit raw
                 - ``deepmd/npy``: deepmd-kit compressed format (numpy binary)
                 - ``pwscf/traj``: pwscf trajectory files. should have: file_name+'.in', file_name+'.pos', file_name+'.evp' and file_name+'.for'
+                - ``gaussian/log``: gaussian logs
 
         type_map : list of str
             Needed by formats deepmd/raw and deepmd/npy. Maps atom type to name. The atom with type `ii` is mapped to `type_map[ii]`.
@@ -308,6 +310,8 @@ def __init__ (self,
             self.from_deepmd_comp(file_name, type_map = type_map)
         elif fmt == 'pwscf/traj':
             self.from_pwscf_traj(file_name, begin = begin, step = step)
+        elif fmt == 'gaussian/log':
+            self.from_gaussian_log(file_name)
         else :
             raise RuntimeError('unknow data format ' + fmt)
 
@@ -433,6 +437,12 @@ def from_pwscf_traj(self, prefix, begin = 0, step = 1) :
         self.rot_lower_triangular()
 
 
+    def from_gaussian_log(self, file_name):
+        self.data = dpdata.gaussian.log.to_system_data(file_name)
+        self.data['cells'] = np.array([[[100., 0., 0.], [0., 100., 0.], [0., 0., 100.]]])
+        self.data['virials'] = []
+
+
     def sub_system(self, f_idx) :
         """
         Construct a subsystem from the system