TypeError: Cannot clone object '<keras.engine.sequential.Sequential

[aloysiusunikl]

I am trying to run the code: PNN_Solar_model.py
(version used: python 3.6, tensorflow 1.15.0, scikit-learn 0.20.1)
The code runs at all important sections, except at end.
I am getting an error at the last section for tuning the ANN (message shown below)
I have tried a few versions of scikit-learn, down from 0.21.2
Which version of scikit-learn is used successfully?
Thank you

Error message
File "/home/mfihvac/.config/spyder-py3/temp.py", line 147, in
grid_result = grid_search.fit(X_train, np.argmax(y_train, axis=1))
File "/home/mfihvac/anaconda3/envs/fddtest2/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 677, in fit
base_estimator = clone(self.estimator)
File "/home/mfihvac/anaconda3/envs/fddtest2/lib/python3.6/site-packages/sklearn/base.py", line 58, in clone
% (repr(estimator), type(estimator)))
TypeError: Cannot clone object '<keras.engine.sequential.Sequential object at 0x7f0cb83ebe48>' (type <class 'keras.engine.sequential.Sequential'>): it does not seem to be a scikit-learn estimator as it does not implement a 'get_params' methods.