6.5. Unsupervised dimensionality reduction

Pipelining

The unsupervised data reduction and the supervised estimator can bechained in one step. See Pipeline: chaining estimators.

looks for a combination of features thatcapture well the variance of the original features. See Decomposing signals in components (matrix factorization problems).

The module: provides several tools for datareduction by random projections. See the relevant section of thedocumentation: .

Examples

• The Johnson-Lindenstrauss bound for embedding with random projections

appliesHierarchical clustering to group together features that behavesimilarly.

Feature scaling