I am trying to run a stacked regression when the n_jobs is 1 it runs fine however, whenever I set the n_jobs to 2 it crashes with the error below. I looked into similar issues but none actually solved my error.
The code:
from civismlext.stacking import StackedRegressor
from civismlext.nonnegative import NonNegativeLinearRegression
def create_model():
model = Sequential()
model.add(Dense(150, activation='softmax', kernel_initializer='VarianceScaling', input_dim=456, name='HL1'))
model.add(Dropout(0.25, name="Dropout1"))
model.add(Dense(150, kernel_initializer='VarianceScaling', activation='softmax', name='HL2'))
model.add(Dropout(0.25, name="Dropout2"))
model.add(Dense(1, name='Output_Layer'))
model.compile(optimizer='adam', loss='mae', metrics=['mae', 'mean_squared_error'])
return model
mlp_model = KerasRegressor(build_fn=create_model, epochs=50, batch_size=75, validation_split=0.2, verbose=True)
super_learner = StackedRegressor([
('pipe_mlp', mlp_model),
('rf', rf),
('xgb', gb),
('meta', NonNegativeLinearRegression())
], cv=5, n_jobs=2, verbose=5)
the error:
MaybeEncodingError Traceback (most recent call last)
<ipython-input-7-1d4b04377633> in <module>()
1 # fitting the model
----> 2 super_learner.fit(X_train[:50], y_train[:50])
~/anaconda3/lib/python3.6/site-packages/civismlext/stacking.py in fit(self, X, y, **fit_params)
163 self.meta_estimator.fit(Xmeta, ymeta, **meta_params)
164 # Now fit base estimators again, this time on full training set
--> 165 self._base_est_fit(X, y, **fit_params)
166
167 return self
~/anaconda3/lib/python3.6/site-packages/civismlext/stacking.py in _base_est_fit(self, X, y, **fit_params)
220 n_jobs=self.n_jobs,
221 verbose=self.verbose,
--> 222 pre_dispatch=self.pre_dispatch)(_jobs)
223
224 for name, _ in self.estimator_list[:-1]:
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
787 # consumption.
788 self._iterating = False
--> 789 self.retrieve()
790 # Make sure that we get a last message telling us we are done
791 elapsed_time = time.time() - self._start_time
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in retrieve(self)
697 try:
698 if getattr(self._backend, 'supports_timeout', False):
--> 699 self._output.extend(job.get(timeout=self.timeout))
700 else:
701 self._output.extend(job.get())
~/anaconda3/lib/python3.6/multiprocessing/pool.py in get(self, timeout)
642 return self._value
643 else:
--> 644 raise self._value
645
646 def _set(self, i, obj):
MaybeEncodingError: Error sending result: '[<keras.callbacks.History object at 0x7f93fe43c7b8>]'. Reason: 'TypeError("can't pickle _thread.lock objects",)'
It's because the Keras scikit-learn wrappers don't exactly follow the scikit-learn API.
In scikit-learn, calling fit() on an estimator returns a fitted estimator. In the Keras wrapper, the fit() call returns a callbacks.History object.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.