from sklearn.model_selection import GridSearchCV
from sklearn.tree import DecisionTreeClassifier
max_depth = [3,4,5,6]
params1 = {'base_estimator__max_depth':max_depth}
base_model = GridSearchCV(estimator = ensemble.AdaBoostClassifier(base_estimator = DecisionTreeClassifier()),param_grid=params1,
scoring='roc_auc',cv=5,n_jobs=4,verbose=1)
**base_model.fit(X_train[predictors],y_train)**
#返回参数的最佳组合和对应的AUC值
base_model.best_params_,base_mode.best_score_
错误原因：
Fitting 5 folds for each of 4 candidates, totalling 20 fits
---------------------------------------------------------------------------
_RemoteTraceback Traceback (most recent call last)
_RemoteTraceback:
"""
Traceback (most recent call last):
File "D:\lib\site-packages\joblib\externals\loky\backend\queues.py", line 153, in _feed
obj_ = dumps(obj, reducers=reducers)
File "D:\lib\site-packages\joblib\externals\loky\backend\reduction.py", line 271, in dumps
dump(obj, buf, reducers=reducers, protocol=protocol)
File "D:\lib\site-packages\joblib\externals\loky\backend\reduction.py", line 264, in dump
_LokyPickler(file, reducers=reducers, protocol=protocol).dump(obj)
File "D:\lib\site-packages\joblib\externals\cloudpickle\cloudpickle_fast.py", line 602, in dump
return Pickler.dump(self, obj)
File "D:\lib\site-packages\joblib\_memmapping_reducer.py", line 427, in __call__
resource_tracker.register(filename, "file")
File "D:\lib\site-packages\joblib\externals\loky\backend\resource_tracker.py", line 190, in register
self.ensure_running()
File "D:\lib\site-packages\joblib\externals\loky\backend\resource_tracker.py", line 102, in ensure_running
if self._check_alive():
File "D:\lib\site-packages\joblib\externals\loky\backend\resource_tracker.py", line 182, in _check_alive
self._send('PROBE', '', '')
File "D:\lib\site-packages\joblib\externals\loky\backend\resource_tracker.py", line 209, in _send
nbytes = os.write(self._fd, msg)
OSError: [Errno 22] Invalid argument
"""
The above exception was the direct cause of the following exception:
PicklingError Traceback (most recent call last)
File D:\lib\site-packages\joblib\parallel.py:935, in Parallel.retrieve(self)
934 if getattr(self._backend, 'supports_timeout', False):
--> 935 self._output.extend(job.get(timeout=self.timeout))
936 else:
File D:\lib\site-packages\joblib\_parallel_backends.py:542, in LokyBackend.wrap_future_result(future, timeout)
541 try:
--> 542 return future.result(timeout=timeout)
543 except CfTimeoutError as e:
File D:\lib\concurrent\futures\_base.py:446, in Future.result(self, timeout)
445 elif self._state == FINISHED:
--> 446 return self.__get_result()
447 else:
File D:\lib\concurrent\futures\_base.py:391, in Future.__get_result(self)
390 try:
--> 391 raise self._exception
392 finally:
393 # Break a reference cycle with the exception in self._exception
PicklingError: Could not pickle the task to send it to the workers.
During handling of the above exception, another exception occurred:
OSError Traceback (most recent call last)
Input In [15], in <cell line: 5>()
2 params1 = {'base_estimator__max_depth':max_depth}
3 base_model = GridSearchCV(estimator = ensemble.AdaBoostClassifier(base_estimator = DecisionTreeClassifier()),param_grid=params1,
4 scoring='roc_auc',cv=5,n_jobs=4,verbose=1)
----> 5 base_model.fit(X_train[predictors],y_train)
6 #返回参数的最佳组合和对应的AUC值
7 base_model.best_params_,base_mode.best_score_
File D:\lib\site-packages\sklearn\model_selection\_search.py:891, in BaseSearchCV.fit(self, X, y, groups, **fit_params)
885 results = self._format_results(
886 all_candidate_params, n_splits, all_out, all_more_results
887 )
889 return results
--> 891 self._run_search(evaluate_candidates)
893 # multimetric is determined here because in the case of a callable
894 # self.scoring the return type is only known after calling
895 first_test_score = all_out[0]["test_scores"]
File D:\lib\site-packages\sklearn\model_selection\_search.py:1392, in GridSearchCV._run_search(self, evaluate_candidates)
1390 def _run_search(self, evaluate_candidates):
1391 """Search all candidates in param_grid"""
-> 1392 evaluate_candidates(ParameterGrid(self.param_grid))
File D:\lib\site-packages\sklearn\model_selection\_search.py:838, in BaseSearchCV.fit.<locals>.evaluate_candidates(candidate_params, cv, more_results)
830 if self.verbose > 0:
831 print(
832 "Fitting {0} folds for each of {1} candidates,"
833 " totalling {2} fits".format(
834 n_splits, n_candidates, n_candidates * n_splits
835 )
836 )
--> 838 out = parallel(
839 delayed(_fit_and_score)(
840 clone(base_estimator),
841 X,
842 y,
843 train=train,
844 test=test,
845 parameters=parameters,
846 split_progress=(split_idx, n_splits),
847 candidate_progress=(cand_idx, n_candidates),
848 **fit_and_score_kwargs,
849 )
850 for (cand_idx, parameters), (split_idx, (train, test)) in product(
851 enumerate(candidate_params), enumerate(cv.split(X, y, groups))
852 )
853 )
855 if len(out) < 1:
856 raise ValueError(
857 "No fits were performed. "
858 "Was the CV iterator empty? "
859 "Were there no candidates?"
860 )
File D:\lib\site-packages\joblib\parallel.py:1056, in Parallel.__call__(self, iterable)
1053 self._iterating = False
1055 with self._backend.retrieval_context():
-> 1056 self.retrieve()
1057 # Make sure that we get a last message telling us we are done
1058 elapsed_time = time.time() - self._start_time
File D:\lib\site-packages\joblib\parallel.py:957, in Parallel.retrieve(self)
951 if (backend is not None and
952 hasattr(backend, 'abort_everything')):
953 # If the backend is managed externally we need to make sure
954 # to leave it in a working state to allow for future jobs
955 # scheduling.
956 ensure_ready = self._managed_backend
--> 957 backend.abort_everything(ensure_ready=ensure_ready)
958 raise
File D:\lib\site-packages\joblib\_parallel_backends.py:565, in LokyBackend.abort_everything(self, ensure_ready)
562 self._workers = None
564 if ensure_ready:
--> 565 self.configure(n_jobs=self.parallel.n_jobs, parallel=self.parallel)
File D:\lib\site-packages\joblib\_parallel_backends.py:494, in LokyBackend.configure(self, n_jobs, parallel, prefer, require, idle_worker_timeout, **memmappingexecutor_args)
490 if n_jobs == 1:
491 raise FallbackToBackend(
492 SequentialBackend(nesting_level=self.nesting_level))
--> 494 self._workers = get_memmapping_executor(
495 n_jobs, timeout=idle_worker_timeout,
496 env=self._prepare_worker_env(n_jobs=n_jobs),
497 context_id=parallel._id, **memmappingexecutor_args)
498 self.parallel = parallel
499 return n_jobs
File D:\lib\site-packages\joblib\executor.py:20, in get_memmapping_executor(n_jobs, **kwargs)
19 def get_memmapping_executor(n_jobs, **kwargs):
---> 20 return MemmappingExecutor.get_memmapping_executor(n_jobs, **kwargs)
File D:\lib\site-packages\joblib\executor.py:42, in MemmappingExecutor.get_memmapping_executor(cls, n_jobs, timeout, initializer, initargs, env, temp_folder, context_id, **backend_args)
39 reuse = _executor_args is None or _executor_args == executor_args
40 _executor_args = executor_args
---> 42 manager = TemporaryResourcesManager(temp_folder)
44 # reducers access the temporary folder in which to store temporary
45 # pickles through a call to manager.resolve_temp_folder_name. resolving
46 # the folder name dynamically is useful to use different folders across
47 # calls of a same reusable executor
48 job_reducers, result_reducers = get_memmapping_reducers(
49 unlink_on_gc_collect=True,
50 temp_folder_resolver=manager.resolve_temp_folder_name,
51 **backend_args)
File D:\lib\site-packages\joblib\_memmapping_reducer.py:531, in TemporaryResourcesManager.__init__(self, temp_folder_root, context_id)
525 if context_id is None:
526 # It would be safer to not assign a default context id (less silent
527 # bugs), but doing this while maintaining backward compatibility
528 # with the previous, context-unaware version get_memmaping_executor
529 # exposes exposes too many low-level details.
530 context_id = uuid4().hex
--> 531 self.set_current_context(context_id)
File D:\lib\site-packages\joblib\_memmapping_reducer.py:535, in TemporaryResourcesManager.set_current_context(self, context_id)
533 def set_current_context(self, context_id):
534 self._current_context_id = context_id
--> 535 self.register_new_context(context_id)
File D:\lib\site-packages\joblib\_memmapping_reducer.py:560, in TemporaryResourcesManager.register_new_context(self, context_id)
553 new_folder_name = (
554 "joblib_memmapping_folder_{}_{}_{}".format(
555 os.getpid(), self._id, context_id)
556 )
557 new_folder_path, _ = _get_temp_dir(
558 new_folder_name, self._temp_folder_root
559 )
--> 560 self.register_folder_finalizer(new_folder_path, context_id)
561 self._cached_temp_folders[context_id] = new_folder_path
File D:\lib\site-packages\joblib\_memmapping_reducer.py:590, in TemporaryResourcesManager.register_folder_finalizer(self, pool_subfolder, context_id)
583 def register_folder_finalizer(self, pool_subfolder, context_id):
584 # Register the garbage collector at program exit in case caller forgets
585 # to call terminate explicitly: note we do not pass any reference to
586 # ensure that this callback won't prevent garbage collection of
587 # parallel instance and related file handler resources such as POSIX
588 # semaphores and pipes
589 pool_module_name = whichmodule(delete_folder, 'delete_folder')
--> 590 resource_tracker.register(pool_subfolder, "folder")
592 def _cleanup():
593 # In some cases the Python runtime seems to set delete_folder to
594 # None just before exiting when accessing the delete_folder
(...)
599 # because joblib should only use relative imports to allow
600 # easy vendoring.
601 delete_folder = __import__(
602 pool_module_name, fromlist=['delete_folder']).delete_folder
File D:\lib\site-packages\joblib\externals\loky\backend\resource_tracker.py:190, in ResourceTracker.register(self, name, rtype)
188 def register(self, name, rtype):
189 '''Register a named resource, and increment its refcount.'''
--> 190 self.ensure_running()
191 self._send('REGISTER', name, rtype)
File D:\lib\site-packages\joblib\externals\loky\backend\resource_tracker.py:102, in ResourceTracker.ensure_running(self)
99 with self._lock:
100 if self._fd is not None:
101 # resource tracker was launched before, is it still running?
--> 102 if self._check_alive():
103 # => still alive
104 return
105 # => dead, launch it again
File D:\lib\site-packages\joblib\externals\loky\backend\resource_tracker.py:182, in ResourceTracker._check_alive(self)
180 '''Check for the existence of the resource tracker process.'''
181 try:
--> 182 self._send('PROBE', '', '')
183 except BrokenPipeError:
184 return False
File D:\lib\site-packages\joblib\externals\loky\backend\resource_tracker.py:209, in ResourceTracker._send(self, cmd, name, rtype)
205 if len(name) > 512:
206 # posix guarantees that writes to a pipe of less than PIPE_BUF
207 # bytes are atomic, and that PIPE_BUF >= 512
208 raise ValueError('name too long')
--> 209 nbytes = os.write(self._fd, msg)
210 assert nbytes == len(msg)
OSError: [Errno 22] Invalid argument