error message occuied “zipfile.BadZipFile: File is not a zip file” about allennlp

[Hoyyyaard]

Traceback (most recent call last):
File "debug.py", line 15, in
predictor = Predictor.from_path('/mnt/cephfs/home/zhihongyan/VLN/DUET/datasets/elmo')
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/allennlp/predictors/predictor.py", line 364, in from_path
plugins.import_plugins()
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/allennlp/common/plugins.py", line 79, in import_plugins
import_module_and_submodules(
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/allennlp/common/util.py", line 362, in import_module_and_submodules
import_module_and_submodules(subpackage, exclude=exclude)
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/allennlp/common/util.py", line 351, in import_module_and_submodules
module = importlib.import_module(package_name)
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1014, in _gcd_import
File "", line 991, in _find_and_load
File "", line 975, in _find_and_load_unlocked
File "", line 671, in _load_unlocked
File "", line 843, in exec_module
File "", line 219, in _call_with_frames_removed
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/allennlp/commands/init.py", line 32, in
from allennlp.commands.checklist import CheckList
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/allennlp/commands/checklist.py", line 22, in
from allennlp.confidence_checks.task_checklists.task_suite import TaskSuite
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/allennlp/confidence_checks/task_checklists/init.py", line 4, in
from allennlp.confidence_checks.task_checklists.task_suite import TaskSuite
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/allennlp/confidence_checks/task_checklists/task_suite.py", line 9, in
from checklist.perturb import Perturb
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/checklist/perturb.py", line 7, in
from pattern.en import tenses
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/pattern/text/en/init.py", line 61, in
from pattern.text.en.inflect import (
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/pattern/text/en/init.py", line 80, in
from pattern.text.en import wordnet
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/pattern/text/en/wordnet/init.py", line 57, in
nltk.data.find("corpora/" + token)
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/nltk/data.py", line 555, in find
return find(modified_name, paths)
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/nltk/data.py", line 542, in find
return ZipFilePathPointer(p, zipentry)
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/nltk/compat.py", line 41, in _decorator
return init_func(*args, **kwargs)
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/nltk/data.py", line 394, in init
zipfile = OpenOnDemandZipFile(os.path.abspath(zipfile))
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/nltk/compat.py", line 41, in _decorator
return init_func(*args, **kwargs)
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/site-packages/nltk/data.py", line 935, in init
zipfile.ZipFile.init(self, filename)
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/zipfile.py", line 1269, in init
self._RealGetContents()
File "/mnt/cephfs/home/zhihongyan/anaconda3/envs/vlnduet_probe/lib/python3.8/zipfile.py", line 1336, in _RealGetContents
raise BadZipFile("File is not a zip file")
zipfile.BadZipFile: File is not a zip file

[epwalsh]

I believe we've encountered this before. It's an issue with race conditions in NLTK when it tries to download the same corpora from two processes at the same time. You end up with a corrupted download. Try this:

# Remove existing corrupted NLTK downloads
rm -rf ~/nltk_data
# Re-download everything
python -c 'import nltk; [nltk.download(p) for p in ("wordnet", "wordnet_ic", "sentiwordnet", "omw", "omw-1.4")]'

[github-actions]

This issue is being closed due to lack of activity. If you think it still needs to be addressed, please comment on this thread 👇