generated embb lineage plots

scripts/plotting/plotting_thesis/preformatting.R

@@ -21,6 +21,47 @@ geneL_normal  = c("pnca")
 geneL_na      = c("gid", "rpob")
 geneL_ppi2    = c("alr", "embb", "katg", "rpob")
 
+# LigDist_colname # from globals used
+# ppi2Dist_colname #from globals used 
+# naDist_colname #from globals used
+
+common_cols  = c("mutationinformation"
+                 , "X5uhc_position"
+                 , "X5uhc_offset"
+                 , "position"
+                 , "dst_mode"
+                 , "mutation_info_labels"
+                 , "sensitivity", dist_columns )
+
+
+########################################
+categ_cols_to_factor = grep( "_outcome|_info", colnames(merged_df3) )
+fact_cols = colnames(merged_df3)[categ_cols_to_factor]
+
+if (any(lapply(merged_df3[, fact_cols], class) == "character")){
+  cat("\nChanging", length(categ_cols_to_factor), "cols to factor")
+  merged_df3[, fact_cols] <- lapply(merged_df3[, fact_cols], as.factor)
+  if (all(lapply(merged_df3[, fact_cols], class) == "factor")){
+    cat("\nSuccessful: cols changed to factor")
+  }
+}else{
+  cat("\nRequested cols aready factors")
+}
+
+cat("\ncols changed to factor are:\n", colnames(merged_df3)[categ_cols_to_factor] )
+
+####################################
+# merged_df3: NECESSARY pre-processing
+###################################
+#df3 = merged_df3
+plot_cols = c("mutationinformation", "mutation_info_labels", "position", "dst_mode"
+                   , all_cols)
+
+all_cols = c(common_cols
+             , all_stability_cols
+             , all_affinity_cols
+             , all_conserv_cols)
+
 
 # counting
 foo = merged_df3[, c("mutationinformation"