RemoveFrequentValues
Package
weka.filters.unsupervised.instance
Synopsis
Determines which values (frequent or infrequent ones) of an (nominal) attribute are retained and filters the instances accordingly. In case of values with the same frequency, they are kept in the way they appear in the original instances object. E.g. if you have the values "1,2,3,4" with the frequencies "10,5,5,3" and you chose to keep the 2 most common values, the values "1,2" would be returned, since the value "2" comes before "3", even though they have the same frequency.
Options
The table below describes the options available for RemoveFrequentValues.
Option |
Description |
---|---|
attributeIndex |
Choose attribute to be used for selection (default last). |
invertSelection |
Invert matching sense. |
modifyHeader |
When selecting on nominal attributes, removes header references to excluded values. |
numValues |
The number of values to retain. |
useLeastValues |
Retains values with least instance instead of most. |
Capabilities
The table below describes the capabilites of RemoveFrequentValues.
Capability |
Supported |
---|---|
Class |
No class, Missing class values, String class, Numeric class, Empty nominal class, Binary class, Date class, Unary class, Nominal class, Relational class |
Attributes |
Numeric attributes, Relational attributes, Missing values, Empty nominal attributes, Date attributes, Binary attributes, String attributes, Unary attributes, Nominal attributes |
Min # of instances |
0 |