Managing Attributes in the Data Manager
The attributes in the dataset are displayed in the Attribute List on the left-hand side of the Data Manager. These attributes can be selected, searched and ordered directly in this list (see possible operations below).
It is possible to modify the attributes by:
In the Attributes List, you can:
Add attributes to the current dataset;
Modify the existing attributes.
You must have created a flow;
You must have linked the Data Manager task to the one containing the dataset you want to work on.
In the Attributes List, click on the three-dotted button next to the attribute you want to modify or right-click onto the attribute.
In case you want to add a new attribute, click on the three-dotted button next to the dataset name.
Select the required option among the ones listed below.
Available operations within the Attributes List
To visualize the attribute on the dataset: the attribute is not deleted, it is only a visualization tool. You can choose among:
To remove the attribute from the dataset.
To change the attribute’s features, managing the missing values, and to set the normalization and distance parameters.
More information can be found in the Datasets and Attributes page.
To change the position of the attribute in the table
To change the name the attribute. The attribute name must not contain the symbol $.
To ignore the attribute in the analysis. The attribute won’t be deleted from the dataset.
To set the attribute’s missing value(s).
Set missing value
To fill empty cells with an average value suggested by Rulex. Alternatively you can enter a specific value manually. In both cases, you must click Impute Missing to apply the new values to empty cells.
To change the attribute type from a list of possible values:
To split the attribute’s values into different columns. You can split the attribute by: