increment in aggregate_data.py: implement calculating the age_distrbution using the smsv ids

data_processing/aggregate_data.py

@@ -1,5 +1,7 @@
 import csv
 from age_distribution_by_id import get_age_distribution
+from get_smallAreaInfo import get_smallAreas
+
 
 # Small area id: id of the small area
 # Density: current density of the small area
@@ -21,5 +23,8 @@ def open_file(filename):
     except Exception as e:
         print(f"An error occurred: {e}")
         return []
-    
+
+# get list of smsv, each represented as {"id": smsv_id, "geometry": [(long, lat), ...]}
+smsv_id_geom = get_smallAreas()
+# get_age_distribution([2024] , [smsv["id"] for smsv in smsv_id_geom], "")
 

data_processing/get_smallAreaInfo.py

@@ -10,9 +10,8 @@ with open(file_path, 'r', encoding='utf-8') as file:
 
 def get_smallAreas():
     '''
-    Returns a list of tuples where each tuple (id, geometry) contains
-    the smsv ID and the corresponding geometry (coordinates) for 
-    features in Höfuðborgarsvæði.
+    Returns a list of dict of format {"id": smsv_id, "geometry": [(long, lat), ...]} 
+    for all smsv in in Höfuðborgarsvæði.
     '''
     # Extract smsv IDs and geometries for Höfuðborgarsvæði
     hofudborgarsvaedi_areas = []
@@ -31,5 +30,9 @@ def get_smallAreas():
 
                 hofudborgarsvaedi_areas.append({"id": smsv, "geometry": processed_geometry})
     
+    ids = [area["id"] for area in hofudborgarsvaedi_areas]
+    if len(ids) != len(set(ids)):
+        duplicates = [smsv for smsv in ids if ids.count(smsv) > 1]
+        raise ValueError(f"Duplicate IDs found: {set(duplicates)}")
 
     return hofudborgarsvaedi_areas