Package weka.classifiers.meta.generators

Interface Summary

InstanceHandler	Whether the generator can handle instances directly for setting the parameters.
Mean	A interface indicating that a class expects the mean and standard deviation to be set.
NominalAttributeGenerator	Used to indicate this generator can be used to generate artificial instances for nominal attributes.
NumericAttributeGenerator	Used to indicate this generator can be used to generate artificial instances for numeric attributes.
Ranged	An interface indicating that this generator expect to be given a range of values to operate within.

Class Summary

DiscreteGenerator	An artificial data generator that uses discrete buckets for values. In this discrete generator, values are ranked according to how often they appear.
DiscreteUniformGenerator	An artificial data generator that uses discrete buckets for values. In this discrete uniform generator, all buckets are given the same probability, regardless of how many values fall into each bucket.
EMGenerator	A generator that uses EM as an underlying model.
GaussianGenerator	An artificial data generator that uses a single Gaussian distribution. If a mixture of Gaussians is required, use the EM Generator.
Generator	An artificial data generator.
MixedGaussianGenerator	A mixed Gaussian artificial data generator. This generator only has two Gaussians, each sitting 3 standard deviations (by default) away from the mean of the main distribution.
NominalGenerator	A generator for nominal attributes. Generates artificial data for nominal attributes.
RandomizableDistributionGenerator	An abstract superclass for randomizable generators that make use of mean and standard deviation.
RandomizableGenerator	An abstract superclass for generators that use a seeded internal random number generator.
RandomizableRangedGenerator	Abstract superclass for generators that take ranges and use a seeded random number generator internally
UniformDataGenerator	A uniform artificial data generator. This generator uses a uniform data model - all values have the same probability, and generated values must fall within the range given to the generator.