add class,transform yob, taf encoding and seperator

cleanup.py

@@ -148,4 +148,8 @@ def performance_to_float(performance):
 
         outputDf = outputDf.drop(columns=['Performance'])
 
+        if 'yearOfBirth' in outputDf.columns:
+            outputDf['yearOfBirth'] = outputDf['yearOfBirth'].fillna(-1).astype(float).astype(int)
+            outputDf['yearOfBirth'] = outputDf['yearOfBirth'].replace(-1, "")
+
         outputDf.to_csv(file, index=False)

filter.py

@@ -24,4 +24,8 @@
     filtered_input = filtered_input.fillna("")
     filtered_input = filtered_input.replace("nan", "")
 
-    filtered_input.to_csv(args.output, index=False)
+    # yearOfBirth as int
+    if 'yearOfBirth' in filtered_input.columns:
+        filtered_input['yearOfBirth'] = filtered_input['yearOfBirth'].astype(float).astype(int)
+
+    filtered_input.to_csv(args.output, index=False, sep=';', encoding='ansi')

taf.py

@@ -85,11 +85,12 @@
 
         outputDf = pd.concat([outputDf, df])
 
-
-    desired_order = ['code', 'type', 'discipline', 'result', 'wind', 'venue', 'venueCountry', 'venueCity', 'environment', 'date', 'name', 'firstname', 'lastname', 'nation', 'yearOfBirth', 'sex']
+    outputDf['class'] = outputDf['sex'].apply(lambda x: 'M' if x == 'Male' else ('W' if x == 'Female' else 'X'))
+
+    desired_order = ['code', 'type', 'discipline', 'class', 'result', 'wind', 'venue', 'venueCountry', 'environment', 'date', 'name', 'firstname', 'lastname', 'nation', 'yearOfBirth', 'sex']
     columns_to_drop = set(df.columns) - set(desired_order)
     outputDf = outputDf.drop(columns=columns_to_drop, errors="ignore")
 
     outputDf = outputDf.reindex(columns=desired_order)
 
-    outputDf.to_csv(args.output, index=False)
+    outputDf.to_csv(args.output, index=False, sep=';', encoding='ansi')