cont with qc reporting

dge_workflow/fastqc_summary.R

 #' # Read Summary Report
-#+ echo=FALSE, message=FALSE
+##+ echo=FALSE, message=FALSE
 
 ## Note This script is supposed to be knitr::spin'ed
 
 devtools::source_url("https://dl.dropboxusercontent.com/u/113630701/datautils/R/core_commons.R")
 devtools::source_url("https://dl.dropboxusercontent.com/u/113630701/datautils/R/ggplot_commons.R")
 
+
 argv = commandArgs(TRUE)
+
+if(str_detect(argv[1], "fastqc_summary")) argv <- argv[-1]
+
 if(length(argv) != 1){
     stop("Usage: fastqc_summmary.R <directory with fastqc results>")
+    echo
 }
 
+
 #baseDir="fastqc"
 #baseDir="/Volumes/projects/bioinfo/holger/projects/helin/mouse/fastqc"
 baseDir=argv[1]
 
+echo("working dir is  data in", getwd())
+echo("processing data in", baseDir)
+
+
 fastqDataFiles <- list.files(path=baseDir, pattern="^fastqc_data.txt", full.names=TRUE, recursive=T)
 
+#echo("files are", fastqDataFiles)
+
 
 #' ## Number of reads per run
 
@@ -27,7 +39,7 @@ readCount <- function(statsFile){
     )
 }
 
-readCounts <- fastqDataFiles %>% ldply(readCount)
+readCounts <- fastqDataFiles %>% ldply(readCount) %>% print_head()
 
 require.auto(scales)
 ggplot(readCounts, aes(run, num_reads)) + geom_bar(stat="identity") + coord_flip() + scale_y_continuous(labels=comma)