Time Series Model Package
RNNSPEC Object
The RNNSPEC object generates time series recurrent neural network (RNN) model specifications for use with a TSM object.
Table 11 summarizes the methods that are associated with the TSM.RNNSPEC method.
Table 11: Methods of the RNNSPEC Object
The basic execution pattern for using an RNNSPEC object follows this sequence of operations:
Declare: The object declaration statement creates a new RNNSPEC object.
Open: The RNNSPEC.Open method prepares the default RNNSPEC object for a new configuration.
Configure: The various RNNSPEC.Set methods configure the RNNSPEC object.
Close: The RNNSPEC.Close method finalizes the RNNSPEC object.
Apply: The TSM.Initialize method adds the RNNSPEC to a TSM object.
You can also store the XML representation of the RNN model in an output table. For more information, see the section TSMSPEC Object. Figure 7 illustrates the data flow through the RNNSPEC object.
Figure 7: RNNSPEC Object Data Flow
