diff --git a/data_extraction_formatting_clinical.R b/data_extraction_formatting_clinical.R
index 8ee3f08..95ad909 100644
--- a/data_extraction_formatting_clinical.R
+++ b/data_extraction_formatting_clinical.R
@@ -257,7 +257,7 @@ table(clinical_df$ia_cxr)
 #5 48 13 47 17  3 
 
 # change these first else recoding 0 will be a problem as 0 already exists, mind you -2 categ doesn't exist
-clinical_df$ia_cxr[clinical_df$ia_cxr == -3 | clinical_df$ia_cxr == -1 | clinical_df$ia_cxr == 0 | clinical_df$ia_cxr == 3 ] <- ""
+clinical_df$ia_cxr[clinical_df$ia_cxr == -3 | clinical_df$ia_cxr == -1 | clinical_df$ia_cxr == 0 | clinical_df$ia_cxr == 3 ] <- NA
 table(clinical_df$ia_cxr)
 #    1  2 
 #69 47 17
@@ -304,7 +304,7 @@ table(clinical_df$smoking)
 # reassign the smoking codes
 clinical_df$smoking[clinical_df$smoking == 4 | clinical_df$smoking == 2 ] <- 0
 clinical_df$smoking[clinical_df$smoking == 1 | clinical_df$smoking == 3 ] <- 1
-clinical_df$smoking[clinical_df$smoking == -1 | clinical_df$smoking == -2 | clinical_df$smoking == -3 ] <- ""
+clinical_df$smoking[clinical_df$smoking == -1 | clinical_df$smoking == -2 | clinical_df$smoking == -3 ] <- NA
 
 table(clinical_df$smoking)
 #    0  1 
diff --git a/flu_stats_unpaired_clinical.R b/flu_stats_unpaired_clinical.R
index b17dd2f..67ef423 100755
--- a/flu_stats_unpaired_clinical.R
+++ b/flu_stats_unpaired_clinical.R
@@ -49,6 +49,12 @@ gathercols <- c("age", "los", "onset2final", "onsfindeath", "onset_2_initial", "
 
 clinical_lf = gather_(clinical_df_numerical, keycol, valuecol, gathercols)
 
+if( nrow(clinical_lf) == expected_rows_clinical_lf){
+  cat("PASS: long format data created successfully"
+      , "\nnrow:", nrow(clinical_lf)
+      , "\nncol:", ncol(clinical_lf))
+}
+
 #====================
 # unpaired: clinical
 #====================