openml-labs/gama

Multiprocessing-related issue

chclam opened this issue · 2 comments

After applying fix #148 on a local copy of GAMA I get a multiprocessing-related error when running it on some OpenML data sets. I tried running the following code:

import openml
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from gama import GamaClassifier

dataset = openml.datasets.get_dataset(10)
X, y, categorical_indicator, attribute_names = dataset.get_data(
    target=dataset.default_target_attribute, dataset_format="dataframe"
    )   

y = LabelEncoder().fit_transform(y)
X_train , X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

automl = GamaClassifier(max_total_time=180, store="nothing")
print("GAMA is fitting.")
automl.fit(X_train, y_train)

And this is the error I get, for multiple OpenML data sets.

Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 116, in spawn_main
    exitcode = _main(fd, parent_sentinel)
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 125, in _main
    prepare(preparation_data)
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 236, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 287, in _fixup_main_from_path
    main_content = runpy.run_path(main_path,
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 268, in run_path
    return _run_module_code(code, init_globals, run_name,
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 97, in _run_module_code
    _run_code(code, mod_globals, init_globals,
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/Users/chris/Documents/graduation-project/issues/gama/test.py", line 17, in <module>
    automl.fit(X_train, y_train)
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/GamaClassifier.py", line 134, in fit
    super().fit(x, y, *args, **kwargs)
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/gama.py", line 523, in fit
    self._search_phase(warm_start, timeout=fit_time)
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/gama.py", line 581, in _search_phase
    self._search_method.search(self._operator_set, start_candidates=pop)
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/search_methods/async_ea.py", line 66, in search
    self.output = async_ea(
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/search_methods/async_ea.py", line 112, in async_ea
    with AsyncEvaluator() as async_:
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/utilities/generic/async_evaluator.py", line 108, in __init__
    self._queue_manager = multiprocessing.Manager()
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 57, in Manager
    m.start()
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/managers.py", line 554, in start
    self._process.start()
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/process.py", line 121, in start
    self._popen = self._Popen(self)
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 284, in _Popen
    return Popen(process_obj)
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_fork.py", line 19, in __init__
    self._launch(process_obj)
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 154, in get_preparation_data
    _check_not_importing_main()
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 134, in _check_not_importing_main
    raise RuntimeError('''
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
Traceback (most recent call last):
  File "/Users/chris/Documents/graduation-project/issues/gama/./test.py", line 17, in <module>
    automl.fit(X_train, y_train)
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/GamaClassifier.py", line 134, in fit
    super().fit(x, y, *args, **kwargs)
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/gama.py", line 523, in fit
    self._search_phase(warm_start, timeout=fit_time)
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/gama.py", line 581, in _search_phase
    self._search_method.search(self._operator_set, start_candidates=pop)
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/search_methods/async_ea.py", line 66, in search
    self.output = async_ea(
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/search_methods/async_ea.py", line 112, in async_ea
    with AsyncEvaluator() as async_:
  File "/Users/chris/Documents/graduation-project/issues/gama/env/lib/python3.9/site-packages/gama/utilities/generic/async_evaluator.py", line 108, in __init__
    self._queue_manager = multiprocessing.Manager()
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 57, in Manager
    m.start()
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/managers.py", line 558, in start
    self._address = reader.recv()
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/connection.py", line 255, in recv
    buf = self._recv_bytes()
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/connection.py", line 419, in _recv_bytes
    buf = self._recv(4)
  File "/usr/local/Cellar/python@3.9/3.9.10/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/connection.py", line 388, in _recv
    raise EOFError
EOFError

This problem can easily be fixed by putting the code under if __name__ == "__main__":. My bad!

No problem :) it's not related to the change, it's a python multiprocessing on Windows thing