Compare la répartition des genres minifigs vs personnages

lib/rebrickable/minifig_characters.py

@@ -195,6 +195,28 @@ def aggregate_by_gender(rows: Iterable[dict]) -> List[dict]:
     return aggregates
 
 
+def aggregate_characters_by_gender(rows: Iterable[dict]) -> List[dict]:
+    """Compte les personnages distincts par genre (hors genres inconnus)."""
+    gender_by_character: Dict[str, str] = {}
+    counts: Dict[str, int] = defaultdict(int)
+    for row in rows:
+        character = row["known_character"].strip()
+        gender = row.get("gender", "").strip().lower()
+        if character == "":
+            continue
+        if gender not in ("male", "female"):
+            continue
+        if character in gender_by_character:
+            continue
+        gender_by_character[character] = gender
+        counts[gender] += 1
+    aggregates: List[dict] = []
+    for gender in ("female", "male"):
+        if gender in counts:
+            aggregates.append({"gender": gender, "character_count": str(counts[gender])})
+    return aggregates
+
+
 def write_character_counts(path: Path, rows: Sequence[dict]) -> None:
     """Écrit le CSV des comptes par personnage."""
     ensure_parent_dir(path)
@@ -206,6 +228,17 @@ def write_character_counts(path: Path, rows: Sequence[dict]) -> None:
             writer.writerow(row)
 
 
+def write_character_gender_counts(path: Path, rows: Sequence[dict]) -> None:
+    """Écrit le CSV des comptes de personnages par genre."""
+    ensure_parent_dir(path)
+    fieldnames = ["gender", "character_count"]
+    with path.open("w", newline="") as csv_file:
+        writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
+        writer.writeheader()
+        for row in rows:
+            writer.writerow(row)
+
+
 def write_new_characters_by_year(path: Path, rows: Sequence[dict]) -> None:
     """Écrit le CSV des personnages introduits chaque année."""
     ensure_parent_dir(path)