# HG changeset patch
# User davidvanzessen
# Date 1494939168 14400
# Node ID 8fa8836bd6054aea8a4f2a163952c67074d5c795
# Parent 75ee66a691a0803bb50d221dea6f2aafda4d83b4
Uploaded
diff -r 75ee66a691a0 -r 8fa8836bd605 merge_and_filter.r
--- a/merge_and_filter.r Mon May 15 03:13:16 2017 -0400
+++ b/merge_and_filter.r Tue May 16 08:52:48 2017 -0400
@@ -224,16 +224,13 @@
if(filter.unique == "remove"){
result = result[duplicated(result$unique.def) | duplicated(result$unique.def, fromLast=T),]
+ unique.defs = data.frame(table(result$unique.def))
+ unique.defs = unique.defs[unique.defs$Freq >= filter.unique.count,]
+ result = result[result$unique.def %in% unique.defs$Var1,]
}
-
+
result$unique.def = paste(result$unique.def, gsub(",.*", "", result$best_match)) #keep the unique sequences that are in multiple classes, gsub so the unmatched don't have a class after it
-
- if(filter.unique == "remove"){
- unique.defs = data.frame(table(result$unique.def))
- unique.defs = unique.defs[unique.defs$Freq >= filter.unique.count,]
- result = result[result$unique.def %in% unique.defs$Var1,]
- }
-
+
result = result[!duplicated(result$unique.def),]
}
diff -r 75ee66a691a0 -r 8fa8836bd605 shm_csr.xml
--- a/shm_csr.xml Mon May 15 03:13:16 2017 -0400
+++ b/shm_csr.xml Tue May 16 08:52:48 2017 -0400
@@ -20,7 +20,7 @@
-
+