Click the Choose button in the Preprocess panel to open a hierarchical menu
(shown in Figure 11.9(a)) from which you select a filter by following the path
corresponding to its full name. Use the path given in the full name above to
select the Remove filter. The text “Remove” will appear in the field next to the
Choose button.
Click on the field containing this text. The Generic Object Editor window, which
is used throughout Weka to set parameter values for all of the tools, opens. In this
case it contains a short explanation of the Remove filter (shown in Figure 11.9(b))—
click More to get a fuller description (Figure 11.9(c)). Enter 3 into the attributeIndices
field and click the OK button. The window with the filter options closes.
Now click the Apply button on the right, which runs the data through the filter. The
filter removes the attribute with index 3 from the dataset, and you can see that this
has happened. This change does not affect the dataset in the file; it only applies to
the data held in memory. The changed dataset can be saved to a new ARFF file by
pressing the Save button and entering a file name. The action of the filter can be
undone by pressing the Undo button. Again, this applies to the version of the data
held in memory.
What we have described illustrates how filters are applied to data. However, in
the particular case of Remove, there is a simpler way of achieving the same effect.
Instead of invoking a filter, attributes can be selected using the small boxes in the
Attributes subpanel and removed using the Remove button that appears at the bottom,
below the list of attributes.