[BUG] LabeledSystem from OUTCAR not working

[hoba87]

Summary

The generation of a LabeledSystem from an OUTCAR file is not working (anymore, since version 0.2.6).

Running on CentOS 8 with python 3.7.9.

Steps to Reproduce

dsys = dpdata.LabeledSystem('OUTCAR.out', fmt='vasp/outcar')

Command works until version 0.2.5, with >=0.2.6 getting an error, here evaluated for version 0.2.8:

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-2-d285c09cc64a> in <module>
----> 1 dsys = dpdata.LabeledSystem('OUTCAR.out', fmt='vasp/outcar')

/opt/python/python-3.7.9/lib/python3.7/site-packages/dpdata/system.py in __init__(self, file_name, fmt, type_map, begin, step, data, **kwargs)
    225         if file_name is None :
    226             return
--> 227         self.from_fmt(file_name, fmt, type_map=type_map, begin= begin, step=step, **kwargs)
    228 
    229         if type_map is not None:

/opt/python/python-3.7.9/lib/python3.7/site-packages/dpdata/system.py in from_fmt(self, file_name, fmt, **kwargs)
    251         if fmt == 'auto':
    252             fmt = os.path.basename(file_name).split('.')[-1].lower()
--> 253         return self.from_fmt_obj(load_format(fmt), file_name, **kwargs)
    254 
    255     def from_fmt_obj(self, fmtobj, file_name, **kwargs):

/opt/python/python-3.7.9/lib/python3.7/site-packages/dpdata/system.py in from_fmt_obj(self, fmtobj, file_name, **kwargs)
   1011 
   1012     def from_fmt_obj(self, fmtobj, file_name, **kwargs):
-> 1013         data = fmtobj.from_labeled_system(file_name, **kwargs)
   1014         if data:
   1015             if isinstance(data, (list, tuple)):

/opt/python/python-3.7.9/lib/python3.7/site-packages/dpdata/plugins/vasp.py in from_labeled_system(self, file_name, begin, step, **kwargs)
     75                 vol = np.linalg.det(np.reshape(data['cells'][ii], [3, 3]))
     76                 data['virials'][ii] *= v_pref * vol
---> 77         data = uniq_atom_names(data)
     78         return data
     79 

/opt/python/python-3.7.9/lib/python3.7/site-packages/dpdata/utils.py in uniq_atom_names(data)
     87     data['atom_names'] = unames
     88     tmp_type = list(data['atom_types']).copy()
---> 89     data['atom_types'] = np.array([uidxmap[jj] for jj in tmp_type], dtype=int)
     90     data['atom_numbs'] = [sum( ii == data['atom_types'] ) for ii in range(len(data['atom_names'])) ]
     91     return data

/opt/python/python-3.7.9/lib/python3.7/site-packages/dpdata/utils.py in <listcomp>(.0)
     87     data['atom_names'] = unames
     88     tmp_type = list(data['atom_types']).copy()
---> 89     data['atom_types'] = np.array([uidxmap[jj] for jj in tmp_type], dtype=int)
     90     data['atom_numbs'] = [sum( ii == data['atom_types'] ) for ii in range(len(data['atom_names'])) ]
     91     return data

IndexError: list index out of range

[njzjz]

Please provide your file.

[hoba87]

OUTCAR.zip

[HuangJiameng]

https://github.com/deepmodeling/dpdata/blob/master/dpdata/vasp/outcar.py#L10

There is no "TITLE" in this OUTCAR.out, so atoms are failed to be extracted...

[Chensons]

data = dpdata.LabeledSystem("OUTCAR") Traceback (most recent call last): File "", line 1, in File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/system.py", line 183, in init self.from_fmt( File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/system.py", line 220, in from_fmt return self.from_fmt_obj(load_format(fmt), file_name, **kwargs) File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/system.py", line 1113, in from_fmt_obj data = fmtobj.from_labeled_system(file_name, **kwargs) File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/plugins/vasp.py", line 94, in from_labeled_system data = uniq_atom_names(data) File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/utils.py", line 97, in uniq_atom_names data["atom_types"] = np.array([uidxmap[jj] for jj in tmp_type], dtype=int) File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/utils.py", line 97, in data["atom_types"] = np.array([uidxmap[jj] for jj in tmp_type], dtype=int) IndexError: list index out of range data = dpdata.LabeledSystem("OUTCAR") Traceback (most recent call last): File "", line 1, in File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/system.py", line 183, in init self.from_fmt( File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/system.py", line 220, in from_fmt return self.from_fmt_obj(load_format(fmt), file_name, **kwargs) File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/system.py", line 1113, in from_fmt_obj data = fmtobj.from_labeled_system(file_name, **kwargs) File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/plugins/vasp.py", line 94, in from_labeled_system data = uniq_atom_names(data) File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/utils.py", line 97, in uniq_atom_names data["atom_types"] = np.array([uidxmap[jj] for jj in tmp_type], dtype=int) File "/vol01/homes/hy38185/miniconda3/lib/python3.10/site-packages/dpdata/utils.py", line 97, in data["atom_types"] = np.array([uidxmap[jj] for jj in tmp_type], dtype=int) IndexError: list index out of range

[Chensons]

OUTCAR.zip

[Chensons]

This is useful ! =(https://github.com/deepmodeling/dpdata/pull/361)