From f244741e83f0c6f4b1524432b7569fb053555746 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Mon, 15 Aug 2022 21:29:16 +0100
Subject: [PATCH] added Lin_count.R

---
 scripts/plotting/plotting_thesis/Lin_count.R | 48 ++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 scripts/plotting/plotting_thesis/Lin_count.R

diff --git a/scripts/plotting/plotting_thesis/Lin_count.R b/scripts/plotting/plotting_thesis/Lin_count.R
new file mode 100644
index 0000000..1129d5f
--- /dev/null
+++ b/scripts/plotting/plotting_thesis/Lin_count.R
@@ -0,0 +1,48 @@
+#=============
+# Data: Input
+#==============
+#source("~/git/LSHTM_analysis/config/alr.R")
+#source("~/git/LSHTM_analysis/config/embb.R")
+#source("~/git/LSHTM_analysis/config/gid.R")
+#source("~/git/LSHTM_analysis/config/katg.R")
+#source("~/git/LSHTM_analysis/config/pnca.R")
+source("~/git/LSHTM_analysis/config/rpob.R")
+
+source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
+source("~/git/LSHTM_analysis/scripts/plotting/plotting_colnames.R")
+
+###########################################################
+class(merged_df2)
+foo = as.data.frame(colnames(merged_df2))
+
+cols_to_subset = c('mutationinformation'
+                   , 'snp_frequency'
+                   , 'pos_count'
+                   , 'position'
+                   , 'lineage'
+                   , "sensitivity"
+                   #, 'lineage_multimode'
+                   , 'dst'
+                   , 'dst2'
+                   #, 'dst_multimode'
+                   #, 'dst_multimode_all'
+                   , 'dst_mode')
+
+my_df = merged_df2[ ,cols_to_subset]
+
+cat("\nTotal samples for ALL lineages", tolower(gene),":", nrow(my_df))
+cat("\nTotal muts in ALL lineages", tolower(gene),":"
+    , length(unique(my_df$mutationinformation)))
+
+sel_lineages1 = c("LBOV", "")
+my_df2 = my_df[!my_df$lineage%in%sel_lineages1,]
+table(my_df2$lineage)
+sel_lineages2 = c("L1", "L2", "L3", "L4")
+my_df2 = my_df2[my_df2$lineage%in%sel_lineages2,]
+cat("\nTotal samples for L1-L4", tolower(gene),":", nrow(my_df2))
+cat("\nTotal muts for L1-L4", tolower(gene),":"
+    , length(unique(my_df2$mutationinformation)))
+
+table(my_df2$lineage)
+table(my_df2$lineage,my_df2$sensitivity)
+      
\ No newline at end of file