Package de.lmu.ifi.dbs.elki.datasource.filter

Data filtering, in particular for normalization and projection.

See:
Description

Interface Summary

Normalization<O>	Normalization performs a normalization on a set of feature vectors and is capable to transform a set of feature vectors to the original attribute ranges.
ObjectFilter	Object filters as part of the input step.

Class Summary

AbstractConversionFilter<I,O>	Abstract base class for simple conversion filters such as normalizations and projections.
AbstractFeatureSelectionFilter<V extends FeatureVector<?,?>>	A ProjectionParser projects the objects of its base parser onto a subspace specified by a BitSet.
AbstractFeatureSelectionFilter.Parameterizer<V extends NumberVector<V,?>>	Parameterization class.
AbstractNormalization<O>	Abstract super class for all normalizations.
AbstractRandomFeatureSelectionFilter<V extends FeatureVector<?,?>>	A RandomProjectionParser selects a subset of attributes randomly for projection of a ParsingResult.
AbstractRandomFeatureSelectionFilter.Parameterizer<V extends NumberVector<V,?>>	Parameterization class.
AttributeWiseErfNormalization<O extends NumberVector<O,?>>	Attribute-wise Normalization using the error function.
AttributeWiseMinMaxNormalization<V extends NumberVector<V,?>>	Class to perform and undo a normalization on real vectors with respect to given minimum and maximum in each dimension.
AttributeWiseMinMaxNormalization.Parameterizer<V extends NumberVector<V,?>>	Parameterization class.
AttributeWiseVarianceNormalization<V extends NumberVector<V,?>>	Class to perform and undo a normalization on real vectors with respect to given mean and standard deviation in each dimension.
AttributeWiseVarianceNormalization.Parameterizer<V extends NumberVector<V,?>>	Parameterization class.
ClassLabelFilter	Class that turns a label column into a class label column.
ClassLabelFilter.Parameterizer	Parameterization class.
DoubleVectorProjectionFilter	Parser to project the ParsingResult obtained by a suitable base parser onto a selected subset of attributes.
DoubleVectorProjectionFilter.Parameterizer	Parameterization class.
DoubleVectorRandomProjectionFilter	Parser to project the ParsingResult obtained by a suitable base parser onto a randomly selected subset of attributes.
DoubleVectorRandomProjectionFilter.Parameterizer	Parameterization class.
ExternalIDFilter	Class that turns a label column into an external ID column.
ExternalIDFilter.Parameterizer	Parameterization class.
FilterByLabelFilter	A filter to sort the data set by some label.
FilterByLabelFilter.Parameterizer	Parameterization class.
FilterNoMissingValuesFilter	A filter to remove entries that have missing values.
FilterNoMissingValuesFilter.Parameterizer	Parameterization class.
FixedDBIDsFilter	This filter assigns static DBIDs, based on the sequence the objects appear in the bundle by adding a column of DBID type to the bundle.
FixedDBIDsFilter.Parameterizer	Parameterization class.
InverseDocumentFrequencyNormalization	Normalization for text frequency vectors, using the inverse document frequency.
NoOpFilter	Dummy filter that doesn't do any filtering.
ShuffleObjectsFilter	A filter to shuffle the dataset.
ShuffleObjectsFilter.Parameterizer	Parameterization class.
SortByLabelFilter	A filter to sort the data set by some label.
SparseFloatVectorProjectionFilter	Parser to project the ParsingResult obtained by a suitable base parser onto a selected subset of attributes.
SparseFloatVectorProjectionFilter.Parameterizer	Parameterization class.
SparseFloatVectorRandomProjectionFilter	Parser to project the ParsingResult obtained by a suitable base parser onto a randomly selected subset of attributes.
SparseFloatVectorRandomProjectionFilter.Parameterizer	Parameterization class.
SplitNumberVectorFilter<V extends NumberVector<V,?>>	Split an existing column into two types.
SplitNumberVectorFilter.Parameterizer<V extends NumberVector<V,?>>	Parameterization class.
TFIDFNormalization	Perform full TF-IDF Normalization as commonly used in text mining.

Exception Summary

NonNumericFeaturesException

An exception to signal the encounter of non numeric features where numeric features have been expected.

Package de.lmu.ifi.dbs.elki.datasource.filter Description

Data filtering, in particular for normalization and projection.