FLVarCluster: Variable Clustering.

In Fuzzy-Logix/AdapteR: Converts R syntax to SQL to provide fast analytics using in-database C++ library DB Lytix.

Description

FLVarCluster performs variable clustering on FLTable objects using Principal Component Analysis

Usage

FLVarCluster(x, ...)

Arguments

x	an object of class FLTable, wide or deep
contrib	Level of contribution expected in the output clusters. Value between 0 and 1
matrixType	whether a correlation matrix or a covariance matrix should be used for Eigenvalue decomposition. Allowed values c("COVAR","CORREL")
groupBy	Comma separated column names identifying each data set. Currently not used and NULL always.
excludeCols	the comma separated character string of columns to be excluded
classSpec	list describing the categorical dummy variables
whereconditions	takes the where_clause as a string

Details

The DB Lytix function called is FLVarCluster. Uses a principal component analysis for dimensionality reduction in order to cluster a given set of input variables into a smaller representative set. The number of output clusters depend on the contribution level specified.

Value

FLVarCluster returns a R vector if data can be fetched or a FLVector of cluster to which each variable or column is assigned.

Constraints

If classSpec is not specified, the categorical variables are excluded from analysis by default.

See Also

ClustOfVar package for R reference implementation.

Examples

deeptable  <- FLTable(getTestTableName("tblLogRegr"), "ObsID","VarID",
                      "Num_Val", whereconditions= "ObsID<101")
clustervector <- FLVarCluster(deeptable,0.75,"COVAR",whereconditions=" VarID>0 ")
print(clustervector)

Fuzzy-Logix/AdapteR documentation built on May 6, 2019, 5:07 p.m.