diff --git a/meta_data_analysis/pnca_data_extraction.py b/meta_data_analysis/pnca_data_extraction.py
index e05c39d..2a030f9 100755
--- a/meta_data_analysis/pnca_data_extraction.py
+++ b/meta_data_analysis/pnca_data_extraction.py
@@ -88,10 +88,10 @@ meta_data = meta_data[['id'
        , 'pyrazinamide'
        , 'dr_mutations_pyrazinamide'
        , 'other_mutations_pyrazinamide'
-        ]] #19265, 67
+        ]] 
 
 # checks
-total_samples = meta_data['id'].nunique() # 19265
+total_samples = meta_data['id'].nunique() 
 
 # counts NA per column
 meta_data.isna().sum()
@@ -101,9 +101,7 @@ meta_data.head()
 
 # equivalent of table in R
 # pyrazinamide counts
-meta_data.pyrazinamide.value_counts() #12511
-#0.0    10565
-#1.0     1946 {RESULT: No. of Resistant and Susceptible samples}
+meta_data.pyrazinamide.value_counts() 
 
 clear variables
 #del(basedir, datadir, inpath, infile)
@@ -160,7 +158,7 @@ del(meta_pnca_other)
 
 # Now extract "all" mutations
 meta_pnca_all = meta_data_pnca.loc[meta_data_pnca.dr_mutations_pyrazinamide.str.contains('pncA_p.*') | meta_data_pnca.other_mutations_pyrazinamide.str.contains('pncA_p.*') ]
-#2665, 8
+
 
 meta_pnca_all['id'].nunique() {#RESULT: pnca mutations in ALL samples}
 pnca_samples = len(meta_pnca_all)