* The supported formats are:

  * CSV with ";" or "," separator;
  
  * NumPy .npy
  
  * MATLAB MAT-files .mat

* Files contain the numerical data, allowed types: int, float, double

* Any **input (excitation) file** contains a table:

  * First column corresponds to a time variable, it is a finite arithmetic sequence with spacing equal to time-step
  
  * Number of columns minus one (for time) is the number of input features (excitations)
  
  * Each line contains: a point of time and the values of input features (excitations) at this point of time
  
  * CSV files could have one additional line for a header
  
* Any **output file** contains a table:

  * First column corresponds to a time variable:
    
    * It must be the same as in the corresponding **input (excitation) file** when provided for the construction of the model or the metrics calculation

    * It can be shorter and contain only the beginning of the time sequence in **input (excitation) file** when provided for the evaluation initialization.
	
  * Number of columns minus one (for time) is the number of output features
  
  * Each line contains: a point of time and the values of output features at this point of time
  
  * CSV files could have one additional line for a header
  
* The **time-step** must be the **same** for all tables

* When data represent multiple experiences, they are passed as multiple **input (excitation)** and **output files**. In this case pay attention to preserving the correspondence between **input (excitation)** and **output files**.

* The time variable columns in different pairs on input/output files are not required to be the same, they can have different length and/or initial time-point, but the time-step must stay the same for all experiences.

 