Fix the bug when type_map has only one element

[marian-code]

Numpy has a bit odd behavior I ran into. The method ndarray.loadtxt() when loading from array file of length 1 outputs only the array element, not array of length=1.

import numpy as np

np.__version__
"1.20.3"

!cat array.raw
A

np.loadtxt("array.raw").tolist()
"A"

This breaks code in this place:

deepmd-kit/deepmd/utils/data.py

Line 62 in 5a84796

atom_type_ = [type_map.index(self.type_map[ii]) for ii in self.atom_type]

the list comprehension will try to iterate through characters in string and fail.

[codecov-commenter]

Codecov Report

Merging #1196 (8dbb492) into master (5a84796) will not change coverage.
The diff coverage is 100.00%.

@@           Coverage Diff           @@
##           master    #1196   +/-   ##
=======================================
  Coverage   76.04%   76.04%           
=======================================
  Files          91       91           
  Lines        7258     7258           
=======================================
  Hits         5519     5519           
  Misses       1739     1739           

Impacted Files	Coverage Δ
deepmd/utils/data.py	91.31% <100.00%> (ø)

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 5a84796...8dbb492. Read the comment docs.