[adegenet-commits] r247 - in pkg: R man

[noreply at r-forge.r-project.org]

Author: jombart
Date: 2009-01-26 14:02:33 +0100 (Mon, 26 Jan 2009)
New Revision: 247

Modified:
   pkg/R/sequences.R
   pkg/man/sequences.Rd
Log:
Regexp used to replace NAs, much faster.


Modified: pkg/R/sequences.R
===================================================================
--- pkg/R/sequences.R	2009-01-26 12:24:05 UTC (rev 246)
+++ pkg/R/sequences.R	2009-01-26 13:02:33 UTC (rev 247)
@@ -10,7 +10,7 @@
 ################
 # DNAbin2genind
 ################
-DNAbin2genind <- function(x, pop=NULL, na.char=c("n","-","?"), polyThres=1/100){
+DNAbin2genind <- function(x, pop=NULL, exp.char=c("a","t","g","c"), na.char=NULL, polyThres=1/100){
 
     ## misc checks
     if(!inherits(x,"DNAbin")) stop("x is not a DNAbin object")
@@ -34,7 +34,22 @@
     }
 
     ## replace NAs
-    x[x %in% na.char] <- NA
+    if(is.null(na.char)){
+        if(is.null(exp.char)) stop("both exp.char and na.char are NULL")
+        temp <- paste(exp.char, collapse="", sep="")
+        if(any(exp.char=="-")) {
+            temp <- paste("-",temp, sep="") # string '-' must start the regexp
+        }
+        temp <- paste("[^", temp, "]", sep="") # anything but the expected is NA
+        x <- gsub(temp,NA,x)
+    } else {
+        temp <- paste(na.char, collapse="", sep="")
+        if(any(na.char=="-")) {
+            temp <- paste("-",temp, sep="") # string '-' must start the regexp
+        }
+        temp <- paste("[", temp, "]", sep="")
+        x <- gsub(temp,NA,x)
+    }
 
     ## keep only columns with polymorphism (i.e., SNPs)
     isPoly <- function(vec){

Modified: pkg/man/sequences.Rd
===================================================================
--- pkg/man/sequences.Rd	2009-01-26 12:24:05 UTC (rev 246)
+++ pkg/man/sequences.Rd	2009-01-26 13:02:33 UTC (rev 247)
@@ -12,13 +12,15 @@
   - alignement (seqinr package): to come...
 }
 \usage{
-DNAbin2genind(x, pop=NULL, na.char=c("n","-","?"), polyThres=1/100)
+DNAbin2genind(x, pop=NULL, exp.char=c("a","t","g","c"), na.char=NULL, polyThres=1/100)
 }
 \arguments{
  \item{x}{an object containing aligned sequences.}
  \item{pop}{an optional factor giving the population to which each sequence belongs.}
- \item{na.char}{a character vector providing values that should be
-   considered as NA.}
+ \item{exp.char}{a vector of single character providing expected values;
+  all other characters will be turned to NA.}
+ \item{na.char}{a vector of single characters providing values that should be
+   considered as NA. If not NULL, this is used instead of \code{exp.char}.}
  \item{polyThres}{the minimum frequency of a minor allele for a locus to
   be considered as polymorphic (defaults to 0.01).}
 }