biganalytics (version 1.1.12)

biglm.big.matrix, bigglm.big.matrix: Use Thomas Lumley's ``biglm'' package with a ``big.matrix''

Description

This is a wrapper to Thomas Lumley's biglm package, allowing it to be used with massive data stored in big.matrix objects.

Usage

biglm.big.matrix( formula, data, chunksize=NULL, ..., fc=NULL,
  getNextChunkFunc=NULL)
bigglm.big.matrix( formula, data, chunksize=NULL, ..., fc=NULL,
  getNextChunkFunc=NULL)

Arguments

formula

a model formula.

data

a big.matrix.

chunksize

an integer maximum size of chunks of data to process iteratively.

fc

either column indices or names of variables that are factors.

...

options associated with the biglm

getNextChunkFunc

a function which retrieves chunk data

Value

• an object of class biglm.

Details

See biglm package for more information; chunksize defaults to max(floor(nrow(data)/ncol(data)^2), 10000).

References

Algorithm AS274 Applied Statistics (1992) Vol. 41, No.2

Thomas Lumley (2005). biglm: bounded memory linear and generalized linear models. R package version 0.4.

See Also

biglm, big.matrix

Examples

# This example is quite silly, using the iris
# data.  But it shows that our wrapper to Lumley's biglm() function
# produces the same answer as the plain old lm() function.

require(bigmemory)
x <- matrix(unlist(iris), ncol=5)
colnames(x) <- names(iris)
x <- as.big.matrix(x)
head(x)

silly.biglm <- biglm.big.matrix(Sepal.Length ~ Sepal.Width + Species,
                                data=x, fc="Species")
summary(silly.biglm)

y <- data.frame(x[,])
y$Species <- as.factor(y$Species)
head(y)

silly.lm <- lm(Sepal.Length ~ Sepal.Width + Species, data=y)
summary(silly.lm)