Merge pull request #110 from amcadmus/master

merge devel into master

.gitignore

@@ -20,3 +20,4 @@ dist
 dpdata.egg-info
 _version.py
 !tests/cp2k/aimd/cp2k.log
+__pycache__

README.md

@@ -71,6 +71,8 @@ The `System` or `LabeledSystem` can be constructed from the following file forma
 | QE      | log    | False        | True    | LabeledSystem | 'qe/pw/scf'   |
 | QE      | log    | True         | False   | System        | 'qe/cp/traj'  |
 | QE      | log    | True         | True    | LabeledSystem | 'qe/cp/traj'  |
+| Fhi-aims| output | True         | True    | LabeledSystem | 'fhi_aims/md'  |
+| Fhi-aims| output | False        | True    | LabeledSystem | 'fhi_aims/scf'  |
 |quip/gap|xyz|True|True|MultiSystems|'quip/gap/xyz'|
 | PWmat   | atom.config | False        | False   | System        | 'pwmat/atom.config'  |
 | PWmat   | movement    | True         | True    | LabeledSystem | 'pwmat/movement'     |
@@ -112,6 +114,27 @@ xyz_multi_systems.systems['B1C9'].to_deepmd_raw('./my_work_dir/B1C9_raw')
 xyz_multi_systems.to_deepmd_raw('./my_deepmd_data/')
 ```
 
+You may also use the following code to parse muti-system:
+```
+from dpdata import LabeledSystem,MultiSystems
+from glob import glob
+"""
+process multi systems
+"""
+fs=glob('./*/OUTCAR')  # remeber to change here !!!
+ms=MultiSystems()
+for f in fs:
+    try:
+        ls=LabeledSystem(f)
+    except:
+        print(f)
+    if len(ls)>0:
+        ms.append(ls)
+
+ms.to_deepmd_raw('deepmd')
+ms.to_deepmd_npy('deepmd')
+```
+
 ## Access data
 These properties stored in `System` and `LabeledSystem` can be accessed by operator `[]` with the key of the property supplied, for example
 ```python

dpdata/cp2k/output.py

@@ -20,7 +20,7 @@
 
 class Cp2kSystems(object):
     """
-    deal with cp2k outputfile 
+    deal with cp2k outputfile
     """
     def __init__(self, log_file_name, xyz_file_name):
         self.log_file_object = open(log_file_name, 'r')
@@ -69,7 +69,7 @@ def get_log_block_generator(self):
                 break
         if delimiter_flag is True:
             raise RuntimeError('This file lacks some content, please check')
-    
+
     def get_xyz_block_generator(self):
         p3 = re.compile(r'^\s*(\d+)\s*')
         while True:
@@ -116,7 +116,7 @@ def handle_single_log_frame(self, lines):
             if cell_length_pattern.match(line):
                 cell_A = float(cell_length_pattern.match(line).groupdict()['A']) * AU_TO_ANG
                 cell_B = float(cell_length_pattern.match(line).groupdict()['B']) * AU_TO_ANG
-                cell_C = float(cell_length_pattern.match(line).groupdict()['C']) * AU_TO_ANG 
+                cell_C = float(cell_length_pattern.match(line).groupdict()['C']) * AU_TO_ANG
                 cell_flag+=1
             if cell_angle_pattern.match(line):
                 cell_alpha = np.deg2rad(float(cell_angle_pattern.match(line).groupdict()['alpha']))
@@ -148,10 +148,10 @@ def handle_single_log_frame(self, lines):
                 element_index +=1
                 element_dict[line_list[2]]=[element_index,1]
             atom_types_list.append(element_dict[line_list[2]][0])
-            forces_list.append([float(line_list[3])*AU_TO_EV_EVERY_ANG, 
-                float(line_list[4])*AU_TO_EV_EVERY_ANG, 
+            forces_list.append([float(line_list[3])*AU_TO_EV_EVERY_ANG,
+                float(line_list[4])*AU_TO_EV_EVERY_ANG,
                 float(line_list[5])*AU_TO_EV_EVERY_ANG])
-        
+
         atom_names=list(element_dict.keys())
         atom_numbs=[]
         for ii in atom_names:
@@ -190,8 +190,8 @@ def handle_single_xyz_frame(self, lines):
                 element_index +=1
                 element_dict[line_list[0]]=[element_index,1]
             atom_types_list.append(element_dict[line_list[0]][0])
-            coords_list.append([float(line_list[1])*AU_TO_ANG, 
-                float(line_list[2])*AU_TO_ANG, 
+            coords_list.append([float(line_list[1])*AU_TO_ANG,
+                float(line_list[2])*AU_TO_ANG,
                 float(line_list[3])*AU_TO_ANG])
         atom_names=list(element_dict.keys())
         atom_numbs=[]
@@ -203,29 +203,30 @@ def handle_single_xyz_frame(self, lines):
         info_dict['coords'] = np.asarray([coords_list]).astype('float32')
         info_dict['energies'] = np.array([energy]).astype('float32')
         info_dict['orig']=[0,0,0]
-        return info_dict        
+        return info_dict
 
 #%%
 
 def get_frames (fname) :
     coord_flag = False
     force_flag = False
     eV = 2.72113838565563E+01 # hatree to eV
-    angstrom = 5.29177208590000E-01 # Bohrto Angstrom 
+    angstrom = 5.29177208590000E-01 # Bohrto Angstrom
     fp = open(fname)
     atom_symbol_list = []
     cell = []
     coord = []
     force = []
-
+    coord_count = 0
     for idx, ii in enumerate(fp) :
         if 'CELL| Vector' in ii :
             cell.append(ii.split()[4:7])
         if 'Atom  Kind  Element' in ii :
             coord_flag = True
             coord_idx = idx
+            coord_count += 1
         # get the coord block info
-        if coord_flag :
+        if coord_flag and (coord_count == 1):
             if (idx > coord_idx + 1) :
                 if (ii == '\n') :
                     coord_flag = False

dpdata/deepmd/comp.py

@@ -22,7 +22,7 @@ def to_system_data(folder,
     # data is empty
     data = load_type(folder, type_map = type_map)
     data['orig'] = np.zeros([3])
-    sets = glob.glob(os.path.join(folder, 'set.*'))
+    sets = sorted(glob.glob(os.path.join(folder, 'set.*')))
     all_cells = []
     all_coords = []
     all_eners = []
@@ -36,11 +36,11 @@ def to_system_data(folder,
         if eners is not None:
             eners = np.reshape(eners, [nframes])
         if labels:
-            if eners is not None and len(eners) > 0:
+            if eners is not None and eners.size > 0:
                 all_eners.append(np.reshape(eners, [nframes]))
-            if forces is not None and len(forces) > 0:
+            if forces is not None and forces.size > 0:
                 all_forces.append(np.reshape(forces, [nframes,-1,3]))
-            if virs is not None and len(virs) > 0:
+            if virs is not None and virs.size > 0:
                 all_virs.append(np.reshape(virs, [nframes,3,3]))
     data['cells'] = np.concatenate(all_cells, axis = 0)
     data['coords'] = np.concatenate(all_coords, axis = 0)    
@@ -61,7 +61,7 @@ def dump(folder,
          comp_prec = np.float32,
          remove_sets = True) :
     os.makedirs(folder, exist_ok = True)
-    sets = glob.glob(os.path.join(folder, 'set.*'))
+    sets = sorted(glob.glob(os.path.join(folder, 'set.*')))
     if len(sets) > 0:
         if remove_sets :
             for ii in sets :

dpdata/fhi_aims/output.py

@@ -8,6 +8,7 @@
 eng_patt="Total energy uncorrected.*([-]?[0-9]{1,}[.][0-9]*[E][+-][0-9]{1,})\s+eV"
 #atom_numb_patt="Number of atoms.*([0-9]{1,})"
 
+debug = False
 def get_info (lines, type_idx_zero = False) :
 
     atom_types = []
@@ -31,26 +32,23 @@ def get_info (lines, type_idx_zero = False) :
         v_str=ii.split('|')[1].split()
         vect=[float(kk) for kk in v_str]
         cell.append(vect)
-   # print(cell)
-    #atom name
+
     _tmp=re.findall(pos_patt_first,contents)
     for ii in _tmp:
         _atom_names.append(ii[0])
     atom_names=[]
     for ii in _atom_names:
         if not ii in atom_names:
            atom_names.append(ii)
-    #atom number
-    #_atom_numb_patt=re.compile(atom_numb_patt)
+
     atom_numbs =[_atom_names.count(ii) for ii in atom_names] 
+    if type_idx_zero :
+       type_map=dict(zip(atom_names,range(len(atom_names)))) 
+    else:
+       type_map=dict(zip(atom_names,range(1,len(atom_names)+1))) 
+    atom_types=list(map(lambda  k: type_map[k], _atom_names)) 
     assert(atom_numbs is not None), "cannot find ion type info in aims output"
-
-    for idx,ii in enumerate(atom_numbs) :
-        for jj in range(ii) :
-            if type_idx_zero :
-                atom_types.append(idx)
-            else :
-                atom_types.append(idx+1)
+
 
     return [cell, atom_numbs, atom_names, atom_types ]
 
@@ -81,8 +79,9 @@ def get_frames (fname, md=True, begin = 0, step = 1) :
 
     cc = 0
     while len(blk) > 0 :
-     #   with open(str(cc),'w') as f:
-     #        f.write('\n'.join(blk))
+        if debug:
+           with open(str(cc),'w') as f:
+                f.write('\n'.join(blk))
         if cc >= begin and (cc - begin) % step == 0 :
             if cc==0:
                 coord, _cell, energy, force, virial, is_converge = analyze_block(blk, first_blk=True, md=md)

dpdata/lammps/dump.py

@@ -83,9 +83,9 @@ def get_posi_frac(lines) :
     posis = np.array(posis)     
     return posis[:,1:4]
 
-def safe_get_posi(lines, cell):
+def safe_get_posi(lines, cell, orig = np.zeros(3)):
     try:
-        posis = get_posi(lines)
+        posis = get_posi(lines) - orig
     except ValueError:
         fposis = get_posi_frac(lines)
         posis = fposis @ cell
@@ -173,12 +173,12 @@ def system_data(lines, type_map = None, type_idx_zero = True) :
     system['cells'] = [np.array(cell)]
     natoms = sum(system['atom_numbs'])
     system['atom_types'] = get_atype(lines, type_idx_zero = type_idx_zero)
-    system['coords'] = [safe_get_posi(lines, cell) - np.array(orig)]
+    system['coords'] = [safe_get_posi(lines, cell, np.array(orig))]
     for ii in range(1, len(array_lines)) :
         bounds, tilt = get_dumpbox(array_lines[ii])
         orig, cell = dumpbox2box(bounds, tilt)
         system['cells'].append(cell)
-        system['coords'].append(safe_get_posi(array_lines[ii], cell) - np.array(orig))
+        system['coords'].append(safe_get_posi(array_lines[ii], cell, np.array(orig)))
     system['cells'] = np.array(system['cells'])
     system['coords'] = np.array(system['coords'])
     return system