failure while preprocess in demo-abacus

[yixiuzju]

Hello PhD.Li, I am a beginner in DeepH.
When I tried to replicate the “demo: train the DeepH model using the Abacus interface” , I encountered the failure when I run step2-preprocess, the command line display:
User config name: ['preprocess.ini']
Found 3 directories to preprocess
^MPreprocessing No. 1/3 [08:00:00<?]...Output subdirectories: OUT.ABACUS
Traceback (most recent call last):
File "/public3/home/scg8978/.conda/envs/python39/bin/deeph-preprocess", line 33, in
sys.exit(load_entry_point('deeph==0.2.2', 'console_scripts', 'deeph-preprocess')())
File "/public3/home/scg8978/.conda/envs/python39/lib/python3.9/site-packages/deeph/scripts/preprocess.py", line 147, in main
worker(index)
File "/public3/home/scg8978/.conda/envs/python39/lib/python3.9/site-packages/deeph/scripts/preprocess.py", line 118, in worker
abacus_parse(abspath, os.path.abspath(relpath), 'OUT.' + abacus_suffix)
File "/public3/home/scg8978/.conda/envs/python39/lib/python3.9/site-packages/deeph/preprocess/abacus_get_data.py", line 160, in abacus_parse
assert line is not None, 'Cannot find "NSPIN" in log file'
AssertionError: Cannot find "NSPIN" in log file
My preprocess.ini is
[basic]
raw_dir =./dataset_3_graphene
processed_dir =./preprocessed_3_graphene
target = hamiltonian
interface = abacus

[interpreter]
julia_interpreter = julia

[graph]
radius = -1
create_from_DFT = True
Although I have been success in master the process of deeph using the demo_abacus in the bohrium platform, I am still a beginner,I can't success in run the demo in our supercomputer, I want to ask how I can solve this problem. looking forward to your reply.
best wishes.

[mzjb]

Hi,

Please provide the OUT.ABACUS file generated by your ABACUS calculation. It should be located at ./dataset_3_graphene/xxx/OUT.ABACUS. Additionally, please let me know the version of ABACUS you are using.

[yixiuzju]

Hello PhD.Li
Thanks for your reply! I have been provided the OUT.ABACUS file in 0 file by your email "[email protected]. Meanwhile, the using ABACUS version is the latest version ABACUS3.3.3.

[mzjb]

It seems that the recent update to ABACUS has caused a change in the output format, making it incompatible with the DeepH-pack. To resolve this issue temporarily, you can modify the code by following these steps:

1. Navigate to the /public3/home/scg8978/.conda/envs/python39/lib/python3.9/site-packages/deeph/preprocess/abacus_get_data.py file.

2. Delete lines 156 to 175, which contain the following content:

        if only_S:
            spinful = False
        else:
            line = find_target_line(f, "NSPIN")
            assert line is not None, 'Cannot find "NSPIN" in log file'
            if "NSPIN == 1" in line:
                spinful = False
            elif "NSPIN == 4" in line:
                spinful = True
            else:
                raise ValueError(f'{line} is not supported')

        if only_S:
            fermi_level = 0.0
        else:
            line = find_target_line(f, "EFERMI")
            assert line is not None, 'Cannot find "EFERMI" in log file'
            assert "eV" in line
            fermi_level = float(line.split()[2])
            assert find_target_line(f, "EFERMI") is None, "There is more than one EFERMI in log file"

3. After deleting those lines, replace them with the following content:

        if only_S:
            fermi_level = 0.0
        else:
            line = find_target_line(f, "EFERMI")
            assert line is not None, 'Cannot find "EFERMI" in log file'
            assert "eV" in line
            fermi_level = float(line.split()[2])
            # assert find_target_line(f, "EFERMI") is None, "There is more than one EFERMI in log file"

        if only_S:
            spinful = False
        else:
            line = find_target_line(f, "NSPIN")
            assert line is not None, 'Cannot find "NSPIN" in log file'
            if "NSPIN == 1" in line:
                spinful = False
            elif "NSPIN == 4" in line:
                spinful = True
            else:
                raise ValueError(f'{line} is not supported')

I have tested this modification on the 0 file you provided, and it correctly parses the data.

[yixiuzju]

Hello PhD.Li
Thanks for very much your detailed reply! I have been modified the code as your suggestion, but unfortunately, I encountered the same problem, the command line display as follows，I want to ask should I continue modifying the code or make changes the version of abacus，If necessary, which version of Abacus should I switch， looking forward you reply as your busy schedule.
User config name: ['preprocess.ini']
Found 3 directories to preprocess
^MPreprocessing No. 1/3 [08:00:00<?]...Output subdirectories: OUT.ABACUS
Traceback (most recent call last):
File "/public3/home/scg8978/.conda/envs/python39/bin/deeph-preprocess", line 33, in
sys.exit(load_entry_point('deeph==0.2.2', 'console_scripts', 'deeph-preprocess')())
File "/public3/home/scg8978/.conda/envs/python39/lib/python3.9/site-packages/deeph/scripts/preprocess.py", line 147, in main
worker(index)
File "/public3/home/scg8978/.conda/envs/python39/lib/python3.9/site-packages/deeph/scripts/preprocess.py", line 118, in worker
abacus_parse(abspath, os.path.abspath(relpath), 'OUT.' + abacus_suffix)
File "/public3/home/scg8978/.conda/envs/python39/lib/python3.9/site-packages/deeph/preprocess/abacus_get_data.py", line 160, in abacus_parse
assert line is not None, 'Cannot find "EFERMI" in log file'
AssertionError: Cannot find "EFERMI" in log file

[mzjb]

Please confirm which specific data corresponds to the abacus file that is causing the error, as I attempted to process the 0 file you provided without encountering any errors. To verify, please follow these steps:

1. Delete the two folders other than 0 from the ./dataset_3_graphene directory.
2. Run deeph-preprocess and check whether it still produces an error.

[yixiuzju]

Hi PhD.Li
I successfully run deep-preprocess when I only use 0 file. when I recalculate the 1 and 2 file in the configulation using abacus , the two files also could run deep-preprocess, I guess the original 1 and 2 file calculated by abacus has some problems. Thanks for very much your help!