Skip to main content

Detect Outlier (Densities)

Synopsis​

This operator identifies outliers in the given ExampleSet based on the data density. All objects that have at least

p proportion of all objects farther away than distance D are considered outliers.

Description​

The Detect Outlier (Densities) operator is an outlier detection algorithm that calculates the DB(p,D)-outliers for the given ExampleSet. A DB(p,D)-outlier is an object which is at least D distance away from at least p proportion of all objects. The two real-valued parameters p and D can be specified through the proportion and distance parameters respectively. The DB(p,D)-outliers are distance-based outliers according to Knorr and Ng. This operator implements a global homogenous outlier search.

This operator adds a new boolean attribute named 'outlier' to the given ExampleSet. If the value of this attribute is true, that example is an outlier and vice versa. Different distance functions are supported by this operator. The desired distance function can be selected by the distance function parameter.

An outlier is an example that is numerically distant from the rest of the examples of the ExampleSet. An outlying example is one that appears to deviate markedly from other examples of the ExampleSet. Outliers are often (not always) indicative of measurement error. In this case such examples should be discarded.

Input​

example set input​

This input port expects an ExampleSet. It is the output of the Generate Data operator in the attached Example Process. The output of other operators can also be used as input.

Output​

example set output​

A new boolean attribute 'outlier' is added to the given ExampleSet and the ExampleSet is delivered through this output port.

original​

The ExampleSet that was given as input is passed without changing to the output through this port. This is usually used to reuse the same ExampleSet in further operators or to view the ExampleSet in the Results Workspace.

Parameters​

Distance​

This parameter specifies the distance D parameter for calculation of the DB(p,D)-outliers.

Proportion​

This parameter specifies the proportion p parameter for calculation of the DB(p,D)-outliers.

Distance function​

This parameter specifies the distance function that will be used for calculating the distance between two examples.