Nonlinear Classification Model block
Description
This block implements a nonlinear model, which is a type of model able to learn by a process of trial and error. When constructing a blueprint, the nonlinear model must first be trained and tested before it can be implemented into the blueprint.
As the name suggests, the Nonlinear Classification Model is used for classification of targets, compared to the Nonlinear Model block which is used for prediction of targets.
The Nonlinear Classification Model differs from the Nonlinear Model block only in the output values:
-
the Nonlinear Classification Model output is a string data type, used to classify the target into discrete classes, whereas
-
the Nonlinear Model block output is a double data type, thus an output of numerical value.
Go to instructions on training the model
Nonlinear Classification model block
Block Type
Rules and Models block
Input port
The block contains one input port, that may contain any number of discrete variables as an input fields. These discrete variables will be classified into classes and passed through the model.
In order for this block to run, the model must first be trained and the input port must contain exactly the same number of fields and field names that were used when it was trained.
Output port
The output port of the block contains the output field(s) of the Nonlinear Classification Model block, which is string type data, providing a tool for classification of the model target. The output field name(s) can be modified in the block configuration.
The Nonlinear Classification Model differs from the Nonlinear Model block only in the output values:
-
the Nonlinear Classification Model output is a string data type, used to classify the target into discrete classes, whereas
-
the Nonlinear Model block output is a double data type, thus an output of numerical value.
Functions performed on tags
-
On the Values: The input values are sent through the nonlinear model and the calculated output value(s) of the model are placed in the output fields.
-
On the Timestamp - The timestamp of the output fields will be set to the newest time stamp of the input fields.
-
On the Quality: If any one of the input values is of bad quality, the output value(s) will also be of bad quality. If the Enable Input Range Validation box is checked, then the output will be set to bad quality if any of the input values are not within the range of the input minimum and maximum of the data on which it was trained.
Related topics: