sklearn.model_selection.GridSearchCV - unable to use n_jobs>1 on MacOS Sierra python 2.7
Hi, I was able to run this with n_jobs=-1, and the activity monitor does show all 8 CPUs engaged, but the jobs start to die out one by one. I tried with n_jobs=2, same story. The only option that works is n_jobs=1. I played around with 'pre_dispatch' a bit - unclear what that does. GRID = GridSearchCV(LogisticRegression(), param_grid, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=10, verbose=0, error_score=0, return_train_score=False) GRID.fit(trainDocumentV,trainLabelV) How can I sustain at least 3-4 parallel jobs? thanks, Sumeet
What do you mean by "the jobs start to die out one by one"? Surely the jobs should finish and die out one by one...? On 8 January 2018 at 06:35, Sumeet Sandhu <sumeet.k.sandhu@gmail.com> wrote:
Hi,
I was able to run this with n_jobs=-1, and the activity monitor does show all 8 CPUs engaged, but the jobs start to die out one by one. I tried with n_jobs=2, same story. The only option that works is n_jobs=1. I played around with 'pre_dispatch' a bit - unclear what that does.
GRID = GridSearchCV(LogisticRegression(), param_grid, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=10, verbose=0, error_score=0, return_train_score=False) GRID.fit(trainDocumentV,trainLabelV)
How can I sustain at least 3-4 parallel jobs?
thanks, Sumeet
_______________________________________________ scikit-learn mailing list scikit-learn@python.org https://mail.python.org/mailman/listinfo/scikit-learn
What interval between dying, vs. how long is the run overall? Obviously you want that ratio to be 'small enough'. On 1/7/18 3:35 PM, Joel Nothman wrote:
What do you mean by "the jobs start to die out one by one"? Surely the jobs should finish and die out one by one...?
On 8 January 2018 at 06:35, Sumeet Sandhu <sumeet.k.sandhu@gmail.com <mailto:sumeet.k.sandhu@gmail.com>> wrote:
Hi,
I was able to run this with n_jobs=-1, and the activity monitor does show all 8 CPUs engaged, but the jobs start to die out one by one. I tried with n_jobs=2, same story. The only option that works is n_jobs=1. I played around with 'pre_dispatch' a bit - unclear what that does.
GRID = GridSearchCV(LogisticRegression(), param_grid, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=10, verbose=0, error_score=0, return_train_score=False) GRID.fit(trainDocumentV,trainLabelV)
How can I sustain at least 3-4 parallel jobs?
thanks, Sumeet
_______________________________________________ scikit-learn mailing list scikit-learn@python.org <mailto:scikit-learn@python.org> https://mail.python.org/mailman/listinfo/scikit-learn <https://mail.python.org/mailman/listinfo/scikit-learn>
_______________________________________________ scikit-learn mailing list scikit-learn@python.org https://mail.python.org/mailman/listinfo/scikit-learn
participants (3)
-
Bill Ross -
Joel Nothman -
Sumeet Sandhu