diff cluster.tools/impute.knn.R @ 0:0decf3fd54bc draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cluster.tools/impute.knn.R	Thu Feb 28 01:45:39 2013 -0500
@@ -0,0 +1,44 @@
+#!/usr/bin/env Rscript
+argspec <- c("impute.knn.R replaces missing values, using the impute.knn function from the impute package
+
+        Usage: 
+                impute.knn.R -d <data.file> 
+        Optional:
+                             -o <output_file>
+                \n\n")
+args <- commandArgs(TRUE)
+if ( length( args ) == 1 && args =="--help") { 
+  write(argspec, stderr())
+  q();
+}
+
+lib.load.quiet <- function( package ) {
+   package <- as.character(substitute(package))
+   suppressPackageStartupMessages( do.call( "library", list( package=package ) ) )
+}
+lib.load.quiet(getopt)
+lib.load.quiet( impute )
+
+spec <- matrix( c( "data.fname",      "d", 1, "character",
+                   "output.fname",    "o", 2, "character"
+                   ),
+                nc=4,
+                byrow=TRUE
+               )
+
+opt <- getopt( spec=spec )
+
+data <- as.matrix( read.delim( opt$data.fname, row.names=1, check.names=FALSE ) )
+if ( is.null( opt$replacement.val ) ) { opt$replacement.val <- NA }
+if ( is.null( opt$output.fname ) ) { opt$output.fname <- paste( "impute.knn", basename( opt$data.fname ), sep="." ) }
+
+  ## Set any NA, NAN or Inf entries to 0
+if ( is.nan(data) ) {
+  data[ is.nan( data ) ] <- NA
+}
+if ( is.infinite(data) ) {
+  data[ is.infinite( data ) ] <- NA
+}
+
+data <- impute.knn( data )$data
+write.table( data, opt$output.fname, sep="\t", quote=FALSE, col.names=NA )