Several path problems

[franksyng]

1. Hi, a path problem occurred when I was trying to run the ZINC preprocessing. It seems the repo is missing the directory 'data/ZINC/random':

[2022-10-13 11:10:17,120 INFO] Extracting features...
Traceback (most recent call last):
File "/content/PROTAC-RL/preprocess.py", line 232, in
main()
File "/content/PROTAC-RL/preprocess.py", line 211, in main
src_nfeats = inputters.get_num_features(
File "/content/PROTAC-RL/onmt/inputters/inputter.py", line 119, in get_num_features
return TextDataset.get_num_features(corpus_file, side)
File "/content/PROTAC-RL/onmt/inputters/text_dataset.py", line 281, in get_num_features
with codecs.open(corpus_file, "r", "utf-8") as cf:
File "/usr/local/lib/python3.9/codecs.py", line 905, in open
file = builtins.open(filename, mode, buffering)
FileNotFoundError: [Errno 2] No such file or directory: 'data/ZINC/random/src-train'

2. Meanwhile, when training.sh was run, another file not found problem occur that indicates the missing of dataset:

training.sh: line 7: [: missing `]'
mkdir: cannot create directory ‘checkpoints/PROTAC/random’: No such file or directory
Traceback (most recent call last):
File "/content/PROTAC-RL/train.py", line 118, in
main(opt)
File "/content/PROTAC-RL/train.py", line 51, in main
single_main(opt, 0)
File "/content/PROTAC-RL/onmt/train_single.py", line 100, in main
first_dataset = next(lazily_load_dataset("train", opt))
File "/content/PROTAC-RL/onmt/inputters/inputter.py", line 547, in lazily_load_dataset
yield _lazy_dataset_loader(pt, corpus_type)
File "/content/PROTAC-RL/onmt/inputters/inputter.py", line 537, in _lazy_dataset_loader
dataset = torch.load(pt_file)
File "/usr/local/lib/python3.9/site-packages/torch/serialization.py", line 592, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/usr/local/lib/python3.9/site-packages/torch/serialization.py", line 848, in _load
data_file = io.BytesIO(zip_file.get_record(pickle_file))
RuntimeError: [enforce fail at inline_container.cc:222] . file not found: archive/data.pkl