- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I've installed autosklearn locally using:
pip install auto-sklearn
But I get the following error whenever I try and use the fit function:
import autosklearn
import autosklearn.classification
#define the model
automl = autosklearn.classification.AutoSklearnClassifier(time_left_for_this_task=1200, n_jobs=1)
#train the model
automl.fit(features_train, target_train)
This is the error:
[ERROR] [2022-12-05 14:38:09,724:Client-AutoML(1):63847a06-74ed-11ed-b04d-5dc3c51ac30b] (' Dummy prediction failed with run state StatusType.CRASHED and additional output: {\'traceback\': \'Traceback (most recent call last):\\n File "/home/u157922/.local/lib/python3.9/site-packages/autosklearn/evaluation/__init__.py", line 397, in run\\n obj(**obj_kwargs)\\n File "/home/u157922/.local/lib/python3.9/site-packages/pynisher/limit_function_call.py", line 302, in __call__\\n tmp_dir.cleanup()\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/tempfile.py", line 834, in cleanup\\n self._rmtree(self.name)\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/tempfile.py", line 816, in _rmtree\\n _shutil.rmtree(name, onerror=onerror)\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/shutil.py", line 740, in rmtree\\n onerror(os.rmdir, path, sys.exc_info())\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/shutil.py", line 738, in rmtree\\n os.rmdir(path)\\nOSError: [Errno 39] Directory not empty: \\\'/home/u157922/tmp/tmpl7sxjn6a\\\'\\n\', \'error\': "OSError(39, \'Directory not empty\')"}.',)
[ERROR] [2022-12-05 14:38:09,724:Client-AutoML(1):63847a06-74ed-11ed-b04d-5dc3c51ac30b] (' Dummy prediction failed with run state StatusType.CRASHED and additional output: {\'traceback\': \'Traceback (most recent call last):\\n File "/home/u157922/.local/lib/python3.9/site-packages/autosklearn/evaluation/__init__.py", line 397, in run\\n obj(**obj_kwargs)\\n File "/home/u157922/.local/lib/python3.9/site-packages/pynisher/limit_function_call.py", line 302, in __call__\\n tmp_dir.cleanup()\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/tempfile.py", line 834, in cleanup\\n self._rmtree(self.name)\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/tempfile.py", line 816, in _rmtree\\n _shutil.rmtree(name, onerror=onerror)\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/shutil.py", line 740, in rmtree\\n onerror(os.rmdir, path, sys.exc_info())\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/shutil.py", line 738, in rmtree\\n os.rmdir(path)\\nOSError: [Errno 39] Directory not empty: \\\'/home/u157922/tmp/tmpl7sxjn6a\\\'\\n\', \'error\': "OSError(39, \'Directory not empty\')"}.',)
Traceback (most recent call last):
File "/home/u157922/.local/lib/python3.9/site-packages/autosklearn/automl.py", line 765, in fit
self._do_dummy_prediction()
File "/home/u157922/.local/lib/python3.9/site-packages/autosklearn/automl.py", line 489, in _do_dummy_prediction
raise ValueError(msg)
ValueError: (' Dummy prediction failed with run state StatusType.CRASHED and additional output: {\'traceback\': \'Traceback (most recent call last):\\n File "/home/u157922/.local/lib/python3.9/site-packages/autosklearn/evaluation/__init__.py", line 397, in run\\n obj(**obj_kwargs)\\n File "/home/u157922/.local/lib/python3.9/site-packages/pynisher/limit_function_call.py", line 302, in __call__\\n tmp_dir.cleanup()\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/tempfile.py", line 834, in cleanup\\n self._rmtree(self.name)\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/tempfile.py", line 816, in _rmtree\\n _shutil.rmtree(name, onerror=onerror)\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/shutil.py", line 740, in rmtree\\n onerror(os.rmdir, path, sys.exc_info())\\n File "/opt/intel/inteloneapi/intelpython/latest/lib/python3.9/shutil.py", line 738, in rmtree\\n os.rmdir(path)\\nOSError: [Errno 39] Directory not empty: \\\'/home/u157922/tmp/tmpl7sxjn6a\\\'\\n\', \'error\': "OSError(39, \'Directory not empty\')"}.',)
I've tried clearing out the 'tmp' directory -- but that does not resolve or change the error.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Thank you for posting in Intel Communities.
We were able to reproduce your issue from our end, we are working on this internally and get back to you with an update.
Thanks,
Jaideep
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thanks Jaideep. I appreciate the quick response.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Looks like something was modified in my environment because auto-sklearn was working today. I then tried to add PipelineProfiler:
pip install PipelineProfiler
And now auto-sklearn is broken again.
Ideally, both would be available by default. But at a minimum, I'd like to understand the steps to install and use them successfully.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Sorry for the delay. We are going to contact you privately via mail. Have a great day ahead.
Regards,
Jaideep

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page