Principle Component Analysis
Contact: Stefan Kramer
Categories: Feature selection
Exposed methods:
Feature selection |
|
---|---|
Input: | |
Output: | |
Input format: | Weka's ARFF format |
Output format: | Weka's ARFF format |
User-specified parameters: | Variance covered Maximum number of attributes to include in transformation |
Reporting information: | The optimal subset of variables |
Description:
The Principle Component Analysis (PCA) is mathematically defined as an orthogonal linear transformation that
transforms the data to a new coordinate system such that the greatest variance by any projection of the data
comes to lie on the first coordinate, the second greatest variance on the second coordinate and so forth. The
coordinates are here called principal components.
Background (publication date, popularity/level of familiarity, rationale of approach, further comments)
PCA is closely related to factor analysis; synonyms: Karhunen-Loève transform (KLT),
Hotelling transform or proper orthogonal decomposition (POD);
Class-blind/class-sensitive feature selection
Class-blind
Type (optimal, greedy, randomized)
Optimal (PCA is theoretically the optimum transform for a given data in least square terms)
Filter/wrapper/hybrid approach
Filter
Type of Descriptor:
Interfaces:
Priority: Medium
Development status:
Homepage:
Dependencies:
External components: WEKA
Technical details
Data: No
Software: Yes
Programming language(s): Java
Operating system(s): Linux, Win, Mac OS
Input format: Weka's ARFF format
Output format: Weka's ARFF format
License: GPL
References
References:
[PEA01] Pearson, K., On Lines and Planes of Closest Fit to Systems of Points in Space, Philosophical Magazine, 2 (6): 559-572.