Allow duplicates for multiallellic sites

joshua-slaughter · joshua-slaughter · commit 06675fce6b61 · 2025-04-04T16:05:31.000+01:00
diff --git a/.gitignore b/.gitignore
@@ -31,6 +31,9 @@ dev/
 # My personal trash file
 sandbox.jl
 
+# MY (Joshua) personal trash file
+test/data/scratch/string_encodings.jl
+
 # Jupyter
 *checkpoints
 src/generate_results.jl
diff --git a/src/inputs_from_config.jl b/src/inputs_from_config.jl
@@ -219,7 +219,7 @@ function convert_string(snpdata)
         mapped_col = map(value -> map_allele(value, allele1, allele2), allele_col)
         push!(genotypes_data, mapped_col)
     end
-    return DataFrame(genotypes_data, snpdata.snp_info."snpid")
+    return DataFrame(genotypes_data, snpdata.snp_info."snpid", makeunique=true)
 end
 
 function get_genotypes_from_beds(bedprefix)
