Corrmap: Difference between revisions
Jump to navigation
Jump to search
imported>Jeremy (Importing text file) |
imported>Jeremy (Importing text file) |
||
| Line 1: | Line 1: | ||
===Purpose=== | ===Purpose=== | ||
Correlation map with variable regrouping. | Correlation map with variable regrouping. | ||
===Synopsis=== | ===Synopsis=== | ||
:order = corrmap(data,labels,''reord'') | :order = corrmap(data,labels,''reord'') | ||
:order = corrmap(data,reord) | :order = corrmap(data,reord) | ||
===Description=== | ===Description=== | ||
CORRMAP produces a pseudocolor map that shows the correlation between variables (columns) in a data set. The function will reorder the variables by KNN clustering if desired. | CORRMAP produces a pseudocolor map that shows the correlation between variables (columns) in a data set. The function will reorder the variables by KNN clustering if desired. | ||
The input is the data data class "double" or "dataset". | The input is the data data class "double" or "dataset". | ||
Optional input ''labels'' contains the variable labels when the data is class "double". | Optional input ''labels'' contains the variable labels when the data is class "double". | ||
Optional input ''reord'' will cause CORRMAP to keep the original ordering of the variables if set to 0. | Optional input ''reord'' will cause CORRMAP to keep the original ordering of the variables if set to 0. | ||
The output order is a vector of indices with the variable ordering. | The output order is a vector of indices with the variable ordering. | ||
corrmap(data,labels) produces a psuedocolor correlation map with variable reordering. | corrmap(data,labels) produces a psuedocolor correlation map with variable reordering. | ||
corrmap(data,labels,0) produces a psuedocolor correlation map without variable reordering. | corrmap(data,labels,0) produces a psuedocolor correlation map without variable reordering. | ||
===See Also=== | ===See Also=== | ||
[[autocor]], [[crosscor]] | [[autocor]], [[crosscor]] | ||
Revision as of 15:24, 3 September 2008
Purpose
Correlation map with variable regrouping.
Synopsis
- order = corrmap(data,labels,reord)
- order = corrmap(data,reord)
Description
CORRMAP produces a pseudocolor map that shows the correlation between variables (columns) in a data set. The function will reorder the variables by KNN clustering if desired.
The input is the data data class "double" or "dataset".
Optional input labels contains the variable labels when the data is class "double".
Optional input reord will cause CORRMAP to keep the original ordering of the variables if set to 0.
The output order is a vector of indices with the variable ordering.
corrmap(data,labels) produces a psuedocolor correlation map with variable reordering.
corrmap(data,labels,0) produces a psuedocolor correlation map without variable reordering.