saving work from panino

scripts/count_vars_ML.R

@@ -228,9 +228,11 @@ length(unique((df3$mutationinformation)))
 # 
 # #dm _om
 table(df3$mutation_info)
-table(df3$mutation_info_labels)
 table(df3$mutation_info_orig)
 table(df3$mutation_info_labels_orig)
+
+table(df3$mutation_info_labels) # different, and matches dst_mode
+table(df3$dst_mode)
  
 # test_set
 na_count <-sapply(df3, function(y) sum(length(which(is.na(y)))))
@@ -246,8 +248,10 @@ table(df3[drug])
 
 df3_complete = df3
 table(df3_complete$dst_mode)
-
+comp_lin_all = df3_complete[df3_complete$lineage_labels%in%c("L1", "L2", "L3", "L4"),]
+table(comp_lin_all$lineage); sum(table(comp_lin_all$lineage))
 
 df3_actual =  df3[!is.na(df3$dst), ]
 table(df3_actual$dst_mode)
-
+comp_lin_actual = df3_actual[df3_actual$lineage_labels%in%c("L1", "L2", "L3", "L4"),]
+table(comp_lin_actual$lineage); sum(table(comp_lin_actual$lineage))

scripts/ml/ml_iterator.py

@@ -41,9 +41,9 @@ gene_model_paramD = {'data_combined_model'       : False
 ###############################################################################
 #ml_genes = ["pncA", "embB", "katG", "rpoB", "gid"]
 
-ml_gene_drugD = {'pncA'   : 'pyrazinamide'
-                 , 'embB' : 'ethambutol'
-                 , 'katG' : 'isoniazid'
+ml_gene_drugD = {#'pncA'   : 'pyrazinamide'
+                 # 'embB' : 'ethambutol'
+                 'katG' : 'isoniazid'
                  , 'rpoB' : 'rifampicin'
                  , 'gid'  : 'streptomycin'
                  }