Closed salihgunduz closed 4 years ago
Dear Lago, Nord Pool data has some errors at daylight change times because of the data format. For example 45,77 was recorded like 45770.
trials_filename must start the same like 'DNN_hyperparametersnl' in _dnn_hyperopt.py and _dnn.py.
'batch_normalization' key is not 'BN' self.model = DNNModel(neurons=neurons, n_features=Xtrain.shape[-1], dropout=self.best_hyperparameters['dropout
Thanks a lot for this. I have fixed it.
The problem is that the original code had keywords and names that were not always clear. Before publishing the library, we re-define some variables and keywords to make it more explicitly. When testing, as we used our former hyperparameter trials files, none of these issues appear. So thanks a lot for the feedback.
Dear Lago, Nord Pool data has some errors at daylight change times because of the data format. For example 45,77 was recorded like 45770.
Can you provide an example? Do you mean the data has an error in the database or the error appears when reading the database with the epftoolbox library.
Sorry database look ok. I think it was about my conversion.
trials_filename must start the same like 'DNN_hyperparametersnl' in _dnn_hyperopt.py and _dnn.py.
'batch_normalization' key is not 'BN' self.model = DNNModel(neurons=neurons, n_features=Xtrain.shape[-1], dropout=self.best_hyperparameters['dropout'], batch_normalization=self.best_hyperparameters['BN'], batch_normalization=self.best_hyperparameters['batch_normalization'], lr=self.best_hyperparameters['lr'], verbose=False, optimizer='adam', activation=self.best_hyperparameters['activation'], epochs_early_stopping=20, scaler=self.scaler, loss='mae',