KNIME WEKA nodes (3.7) version 3.6.0.v201805031010 by KNIME AG, Zurich, Switzerland
Classifier that weights a set of class association rules
That are association rules where exclusively one class attribute-value-pair is allowed in the consequence.No pruning is perfomed (except that the number of mined rules can be limited and from that set the user can choose to consider only the top ranked rules with the -L option).
For classification there are three options:a) all rules are equally weighted with 1 (default)
b) all rules are linearly weighted in a decreasing manner according to the sort order of the mining algorithmc) all rules are weighted with the inverse function 1/rank in sort order.
(based on WEKA 3.7)
For further options, click the 'More' - button in the dialog.
All weka dialogs have a panel where you can specify classifier-specific parameters.
A: Full class name of class association rule miner to include, followed by scheme options. eg: "weka.associations.classification.CarApriori -N 100"
W: The type of the weighting function: inverse | linear | equal (default) eg: -T linear
L: The number of rules used for classification (default: all left after pruning)
The Preliminary Attribute Check tests the underlying classifier against the DataTable specification at the inport of the node. Columns that are compatible with the classifier are marked with a green 'ok'. Columns which are potentially not compatible are assigned a red error message.
Important: If a column is marked as 'incompatible', it does not necessarily mean that the classifier cannot be executed! Sometimes, the error message 'Cannot handle String class' simply means that no nominal values are available (yet). This may change during execution of the predecessor nodes.
Capabilities: [Nominal attributes, Binary attributes, Unary attributes, Empty nominal attributes, Missing values, Nominal class, Binary class, Missing class values] Dependencies: [Nominal attributes, Binary attributes, Unary attributes, Empty nominal attributes, Numeric attributes, Date attributes, String attributes, Relational attributes, Missing values, No class, Nominal class, Binary class, Unary class, Empty nominal class, Numeric class, Date class, String class, Relational class, Missing class values, Only multi-Instance data] min # Instance: 1
It shows the command line options according to the current classifier configuration and mainly serves to support the node's configuration via flow variables.
To use this node in KNIME, install KNIME WEKA nodes (3.7) from the following update site: