Quickstart: Discrete Dynamic with the command line interface

NeurEcoRNN is the executable used for building, evaluating and exporting Discrete Dynamic models. The executable can be called directly from a terminal / powershell only after a full installation (the portable version does not offer this option).

To build a NeurEco Discrete Dynamic model, run the following command in the terminal:

neurecoRNN build path/to/build/configuration/file/build.conf

The skeleton of a configuration file required to build NeurEco Discrete Dynamic model, here build.conf, looks as follows (for the test case Temperature forecasting). Its fields should be filled according to the problem at hand.

{"neurecoRNN_build":
        {
            "exc_filenames": ["./x_first_year.npy"],
            "output_filenames": ["./y_first_year.npy"],
            "validation_exc_filenames": [],
            "validation_output_filenames": [],
            "test_exc_filenames": [],
            "test_output_filenames": [],
            "write_model_to": "./TemperatureForecasting.ernn",
            "write_model_output_to_directory": "",
            "checkpoint_address": "./TemperatureForecasting.checkpoint",
            "resume": false,
            "settings": {
                "valid_percentage": 30,
                "min_hidden_state": 1,
                "max_hidden_state": 0,
                "steady_state_exc": [],
                "steady_state_out": [],
                "input_normalization": {
                    "shift_type": "mean",
                    "scale_type": "l2",
                    "normalize_per_feature": true},
                "output_normalization": {
                    "shift_type": "mean",
                    "scale_type": "l2",
                    "normalize_per_feature": true}
                    }
        },
}

Note

For detailed documentation on build, see Build NeurEco Discrete Dynamic model with the command line interface. For data preparation, see Data preparation for NeurEco Discrete Dynamic with the command line interface.

To perform an evaluation, run the following command in the terminal:

neurecoDNN evaluate path/to/evaluation/configuration/file/eval.conf

The skeleton of an evaluation configuration file, here eval.conf, looks as follows (for the test case Temperature forecasting). Its fields should be filled according to the problem at hand.

{
         "neurecoRNN_evaluate": {
     "exc_filenames": ["./x_second_year.npy"],
     "init_output_filenames": [],
     "init_exc_filenames": [],
     "ernn_filename": "./TemperatureForecasting.ernn",
     "write_model_output_to_directory": "./EvaluationReults"
 }
     }

Note

For detailed documentation on evaluate, see Evaluate NeurEco Discrete Dynamic model with the command line interface.

To export the model to FMU format, run:

neurecoRNN exportFMU ./TemperatureForecasting.ernn ./TemperatureForecasting.fmu

Export to FMU format requires embed license.

Note

For detailed documentation on Discrete Dynamic with the command line interface, see Discrete Dynamic with the command line interface.