Superset
(AI Studio Core)
Synopsis
This operator takes two ExampleSets as input and adds new features of the first ExampleSet to the second ExampleSet and vice versa to generate two supersets. The resultant supersets have the same set of attributes but the examples may be different.Description
The Superset operator generates supersets of the given ExampleSets by adding new features of one ExampleSet to the other ExampleSet. The values of the new features are set to missing values in the supersets. This operator delivers two supersets as output: The first has all attributes and examples of the first ExampleSet + all attributes of the second ExampleSet (with missing values) The second has all attributes and examples of the second ExampleSet + all attributes of the first ExampleSet (with missing values) Thus both supersets have the same set of regular attributes but the examples may be different. It is important to note that the supersets can have only one special attribute of a kind. By default this operator adds only new 'regular' attributes to the other ExampleSet for generating supersets. For example, if both input ExampleSets have a label attribute then the first superset will have all attributes of the first ExampleSet (including label) + all regular attributes of the second ExampleSet. The second superset will behave correspondingly. The include special attributes parameter can be used for changing this behavior. But it should be used carefully because even if this parameter is set to true, the resultant supersets can have only one special attribute of a kind. Please study the attached Example Process for better understanding.
Input
example set 1 (Data table)This input port expects an ExampleSet. It is the output of the Retrieve operator in the attached Example Process. The output of other operators can also be used as input. It is essential that meta data should be attached with the data for the input because attributes are specified in their meta data.
- example set 2 (Data table)
This input port expects an ExampleSet. It is the output of the Retrieve operator in the attached Example Process. The output of other operators can also be used as input. It is essential that meta data should be attached with the data for the input because attributes are specified in their meta data.
Output
- superset 1 (Data table)
The first superset of the input ExampleSets is delivered through this port.
- superset 2 (Data table)
The second superset of the input ExampleSets is delivered through this port.
Parameters
- include_special_attributesThis parameter indicates if the special attributes should be included for generation of the supersets. This operator should be used carefully especially if both ExampleSets have the same special attributes because the resultant supersets can have only one special attribute of a kind. Range: boolean
Tutorial Processes
Generating supersets of the Golf and Iris data sets
In this process the 'Golf' and 'Iris' data sets are loaded using the Retrieve operators. Breakpoints are inserted after the Retrieve operators so that you can have a look at the input ExampleSets. When you run the process, first you see the 'Golf' data set. It has four regular and one special attribute with 14 examples each. When you continue the process, you will see the 'Iris' data set. It has four regular and two special attributes with 150 examples each. Note that the meta data of both ExampleSets is very different. The Superset operator is applied for generating supersets of these two ExampleSets. The resultant supersets can be seen in the Results Workspace. You can see that one superset has all attributes and examples of the 'Iris' data set + 4 regular attributes of the 'Golf' data set (with missing values). The other superset has all attributes and examples of the 'Golf' data set + 4 regular attributes of the 'Iris' data set (with missing values).
