Change string representation as number

summarize.py

@@ -26,15 +26,45 @@ straftat_zuordnung = {
     "999999": "Straftaten insgesamt nur Bezirke"
 }
 
+def cleanup_text(text):
+    result = text.replace('.', '')
+    result = result.replace(' ', '')
+    result = result.replace('-', '')
+    return result
+
+def cleanup_int(text):
+    result = cleanup_text(text)
+    if result == "":
+        result = "0"
+    return int(result)
+
+def cleanup_float(text):
+    result = cleanup_text(text)
+    result = result.replace('%', '')
+    result = result.replace(',', '.')
+    if result == "":
+        result = "0.0"
+    return float(result)
+
+
 complete_data = defaultdict(lambda: defaultdict(lambda: defaultdict(dict)))
 for file in glob.glob("*.csv"):
     with open(file, encoding='utf-8') as csvfile:
         csvreader = csv.reader(csvfile, delimiter=';')
         next(csvreader, None)
         delikt_code = file.rpartition('.')[0]
+        print(file)
         for row in csvreader:
-            complete_data[row[0]][row[1]][straftat_zuordnung[delikt_code]]["2023"] = {"erffä": row[2], "aufgefä": row[3], "aufgerel": row[4]}
-            complete_data[row[0]][row[1]][straftat_zuordnung[delikt_code]]["2024"] = {"erffä": row[5], "aufgefä": row[6], "aufgerel": row[7]}
+            complete_data[row[0]][row[1]][straftat_zuordnung[delikt_code]]["2023"] = {
+                "Erfasste Fälle": cleanup_int(row[2]),
+                "Aufgeklärte Fälle": cleanup_int(row[3]),
+                "Aufklärung relativ": cleanup_float(row[4]),
+            }
+            complete_data[row[0]][row[1]][straftat_zuordnung[delikt_code]]["2024"] = {
+                "Erfasste Fälle": cleanup_int(row[5]),
+                "Aufgeklärte Fälle": cleanup_int(row[6]),
+                "Aufklärung relativ": cleanup_float(row[7]),
+            }
 
 with open('data.json', 'w',  encoding="utf-8") as fp:
     json.dump(complete_data, fp, ensure_ascii=False, indent=4)