Module Principle Components Analysis
Principle Components Analysis (PCA) for tables. Implementation based on F. Murtagh's code as provided by the StatLib web site.
References:
Bahrenberg, G., Giese, E., Nipper, J. (1992): Statistische Methoden in der Geographie 2 - Multivariate Statistik. pp.198-277.
- Author: O.Conrad (c) 2010
- Specification: grid
- Menu: Table|Calculus
Parameters
| Name | Type | Identifier | Description | Constraints |
Input | Table | Table (input) | TABLE | - | - |
Output | Principle Components (*) | Table (optional output) | PCA | - | - |
Options | Attributes | Parameters | FIELDS | - | 0 Parameters:
|
Method | Choice | METHOD | - | Available Choices: [0] correlation matrix [1] variance-covariance matrix [2] sums-of-squares-and-cross-products matrix Default: 1 |
Number of Components | Integer | NFIRST | maximum number of calculated first components; set to zero to get all | Minimum: 0 Default: 3 |
(*) optional |
Command-line
Usage: saga_cmd table_calculus 7 -TABLE <str> [-PCA <str>] [-METHOD <str>] [-NFIRST <num>]
-TABLE:<str> Table
Table (input)
-PCA:<str> Principle Components
Table (optional output)
-METHOD:<str> Method
Choice
Available Choices:
[0] correlation matrix
[1] variance-covariance matrix
[2] sums-of-squares-and-cross-products matrix
Default: 1
-NFIRST:<num> Number of Components
Integer
Minimum: 0
Default: 3