How to make TPOT work on numpy sparse matrices or array.

ValueError Traceback (most recent call last)
in
4 pipeline_optimizer = TPOTClassifier(generations=5, population_size=20, cv=5,
5 random_state=42, verbosity=2)
----> 6 pipeline_optimizer.fit(X_train, y_train)
7 print(pipeline_optimizer.score(X_test, y_test))

~/anaconda3/envs/dmda/lib/python3.6/site-packages/tpot/base.py in fit(self, features, target, sample_weight, groups)
663 """
664 self._fit_init()
--> 665 features, target = self._check_dataset(features, target, sample_weight)
666
667

~/anaconda3/envs/dmda/lib/python3.6/site-packages/tpot/base.py in _check_dataset(self, features, target, sample_weight)
1171 raise ValueError(
1172 'Not all operators in {} supports sparse matrix. '
-> 1173 'Please use \"TPOT sparse\" for sparse matrix.'.format(self.config_dict)
1174 )
1175 elif self.config_dict != "TPOT sparse":

ValueError: Not all operators in None supports sparse matrix. Please use "TPOT sparse" for sparse matrix.