Error in derived_variables_generator.py

derived_variables_generator.py

@@ -8,6 +8,7 @@ Created on Wed Nov 10 12:41:12 2021
 import datetime
 import pandas as pd
 import sys
+import math
 
 datafile_path = sys.argv[1]
 csv_separator = ","
@@ -44,12 +45,18 @@ if "DATDS" in datafile.columns:
     
     derived_outcome_month = []
     for x in datafile["DATDS"]:
-        month_num = x.split("/")[1]
-        
-        datetime_object = datetime.datetime.strptime(month_num, "%m")
-        full_month_name = datetime_object.strftime("%B")
-
-        derived_outcome_month.append(full_month_name)
+        if str(x) == 'nan': #math.isnan(x):
+            derived_outcome_month.append(None)
+        else:
+            month_num = x.split("/")
+            if len(month_num) == 3:
+                month_num = month_num[1]
+                datetime_object = datetime.datetime.strptime(month_num, "%m")
+                full_month_name = datetime_object.strftime("%B")
+
+                derived_outcome_month.append(full_month_name)
+            else:
+                derived_outcome_month.append(None)
     
     datafile["DISCHARGE_DATE"] = derived_outcome_month
 
@@ -59,12 +66,18 @@ if "DATAD" in datafile.columns:
     
     derived_outcome_month = []
     for x in datafile["DATAD"]:
-        month_num = x.split("/")[1]
-        
-        datetime_object = datetime.datetime.strptime(month_num, "%m")
-        full_month_name = datetime_object.strftime("%B")
-
-        derived_outcome_month.append(full_month_name)
+        if str(x) == 'nan':  # math.isnan(x):
+            derived_outcome_month.append(None)
+        else:
+            month_num = x.split("/")
+            if len(month_num) == 3:
+                month_num = month_num[1]
+                datetime_object = datetime.datetime.strptime(month_num, "%m")
+                full_month_name = datetime_object.strftime("%B")
+
+                derived_outcome_month.append(full_month_name)
+            else:
+                derived_outcome_month.append(None)
     
     datafile["ADMISSION_DATE"] = derived_outcome_month