Ajoute l’étape 25 de répartition des minifigs par genre

README.md

@@ -254,3 +254,10 @@ Le script lit `data/intermediate/minifigs_by_set.csv` et `data/intermediate/sets
 2. `python -m scripts.plot_minifig_character_spans`
 
 Le script lit `data/intermediate/minifigs_by_set.csv` et `data/intermediate/sets_enriched.csv`, calcule la première et la dernière année d'apparition pour chaque personnage (hors figurants), sérialise `data/intermediate/minifig_character_spans.csv`, puis trace `figures/step24/minifig_character_spans.png` (barres horizontales des spans). Les barres sont colorées selon le genre issu de `config/known_character_genders.csv`.
+
+### Étape 25 : répartition des genres des personnages
+
+1. `source .venv/bin/activate`
+2. `python -m scripts.plot_minifig_gender_share`
+
+Le script lit `data/intermediate/minifigs_by_set.csv`, agrège le nombre de minifigs distinctes par genre (basé sur `config/known_character_genders.csv`), écrit `data/intermediate/minifig_gender_counts.csv`, puis trace `figures/step25/minifig_gender_share.png` (donut indiquant la part des personnages féminins, masculins ou inconnus).

lib/plots/gender_palette.py

@@ -0,0 +1,14 @@
+"""Palette de couleurs et libellés pour les genres des personnages."""
+
+GENDER_COLORS = {
+    "male": "#4c72b0",
+    "female": "#c44e52",
+    "unknown": "#7f7f7f",
+}
+
+GENDER_LABELS = {
+    "male": "Homme",
+    "female": "Femme",
+    "unknown": "Inconnu",
+    "": "Inconnu",
+}

lib/plots/minifig_character_spans.py

@@ -8,22 +8,10 @@ from matplotlib.patches import Patch
 
 from lib.filesystem import ensure_parent_dir
 from lib.milestones import load_milestones
+from lib.plots.gender_palette import GENDER_COLORS, GENDER_LABELS
 from lib.rebrickable.stats import read_rows
 
 
-GENDER_COLORS = {
-    "male": "#4c72b0",
-    "female": "#c44e52",
-    "unknown": "#7f7f7f",
-}
-GENDER_LABELS = {
-    "male": "Homme",
-    "female": "Femme",
-    "unknown": "Inconnu",
-    "": "Inconnu",
-}
-
-
 def load_spans(path: Path) -> List[dict]:
     """Charge le CSV des bornes min/max par personnage."""
     return read_rows(path)

lib/plots/minifig_characters.py

@@ -7,22 +7,10 @@ import matplotlib.pyplot as plt
 from matplotlib.patches import Patch
 
 from lib.filesystem import ensure_parent_dir
+from lib.plots.gender_palette import GENDER_COLORS, GENDER_LABELS
 from lib.rebrickable.stats import read_rows
 
 
-GENDER_COLORS = {
-    "male": "#4c72b0",
-    "female": "#c44e52",
-    "unknown": "#7f7f7f",
-}
-GENDER_LABELS = {
-    "male": "Homme",
-    "female": "Femme",
-    "unknown": "Inconnu",
-    "": "Inconnu",
-}
-
-
 def load_counts(path: Path) -> List[dict]:
     """Charge le CSV des comptes par personnage."""
     return read_rows(path)

lib/plots/minifig_gender_share.py

@@ -0,0 +1,48 @@
+"""Diagramme de répartition des minifigs par genre."""
+
+from pathlib import Path
+from typing import List
+
+import matplotlib.pyplot as plt
+
+from lib.filesystem import ensure_parent_dir
+from lib.plots.gender_palette import GENDER_COLORS, GENDER_LABELS
+from lib.rebrickable.stats import read_rows
+
+
+def load_gender_counts(path: Path) -> List[dict]:
+    """Charge le CSV des comptes par genre."""
+    return read_rows(path)
+
+
+def plot_minifig_gender_share(counts_path: Path, destination_path: Path) -> None:
+    """Trace un diagramme circulaire de la répartition des minifigs par genre."""
+    rows = load_gender_counts(counts_path)
+    if not rows:
+        return
+    genders = [row["gender"] for row in rows]
+    counts = [int(row["minifig_count"]) for row in rows]
+    colors = [GENDER_COLORS.get(gender.strip().lower(), GENDER_COLORS["unknown"]) for gender in genders]
+    total = sum(counts)
+    labels = []
+    for gender, count in zip(genders, counts):
+        percent = (count / total) * 100 if total else 0
+        label = f"{GENDER_LABELS.get(gender.strip().lower(), 'Inconnu')} ({percent:.1f} %)"
+        labels.append(label)
+
+    fig, ax = plt.subplots(figsize=(6, 6))
+    ax.pie(
+        counts,
+        labels=labels,
+        colors=colors,
+        startangle=90,
+        wedgeprops={"linewidth": 0.6, "edgecolor": "#0d0d0d"},
+    )
+    centre_circle = plt.Circle((0, 0), 0.5, fc="white")
+    ax.add_artist(centre_circle)
+    ax.set_title("Répartition des minifigs par genre (thèmes filtrés)")
+
+    ensure_parent_dir(destination_path)
+    fig.tight_layout()
+    fig.savefig(destination_path, dpi=160)
+    plt.close(fig)

lib/rebrickable/minifig_characters.py

@@ -34,6 +34,28 @@ def aggregate_by_character(rows: Iterable[dict]) -> List[dict]:
     return aggregates
 
 
+def aggregate_by_gender(rows: Iterable[dict]) -> List[dict]:
+    """Compte les minifigs distinctes par genre (fig_num unique)."""
+    genders_by_fig: Dict[str, str] = {}
+    counts: Dict[str, int] = defaultdict(int)
+    for row in rows:
+        fig_num = row["fig_num"].strip()
+        gender = row.get("gender", "").strip().lower()
+        normalized = gender if gender in ("male", "female") else "unknown"
+        if fig_num == "":
+            continue
+        if fig_num in genders_by_fig:
+            continue
+        genders_by_fig[fig_num] = normalized
+        counts[normalized] += 1
+    aggregates: List[dict] = []
+    ordered = ["female", "male", "unknown"]
+    for gender in ordered:
+        if gender in counts:
+            aggregates.append({"gender": gender, "minifig_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)
@@ -45,6 +67,17 @@ def write_character_counts(path: Path, rows: Sequence[dict]) -> None:
             writer.writerow(row)
 
 
+def write_gender_counts(path: Path, rows: Sequence[dict]) -> None:
+    """Écrit le CSV des comptes par genre."""
+    ensure_parent_dir(path)
+    fieldnames = ["gender", "minifig_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 load_sets_enriched(path: Path) -> Dict[str, str]:
     """Indexe les années par set_num."""
     lookup: Dict[str, str] = {}

scripts/plot_minifig_gender_share.py

@@ -0,0 +1,27 @@
+"""Trace la répartition des minifigs par genre."""
+
+from pathlib import Path
+
+from lib.plots.minifig_gender_share import plot_minifig_gender_share
+from lib.rebrickable.minifig_characters import (
+    aggregate_by_gender,
+    load_minifigs_by_set,
+    write_gender_counts,
+)
+
+
+MINIFIGS_BY_SET_PATH = Path("data/intermediate/minifigs_by_set.csv")
+GENDER_COUNTS_PATH = Path("data/intermediate/minifig_gender_counts.csv")
+DESTINATION_PATH = Path("figures/step25/minifig_gender_share.png")
+
+
+def main() -> None:
+    """Construit le CSV de répartition par genre et trace le graphique."""
+    rows = load_minifigs_by_set(MINIFIGS_BY_SET_PATH)
+    aggregates = aggregate_by_gender(rows)
+    write_gender_counts(GENDER_COUNTS_PATH, aggregates)
+    plot_minifig_gender_share(GENDER_COUNTS_PATH, DESTINATION_PATH)
+
+
+if __name__ == "__main__":
+    main()

tests/test_minifig_characters.py

@@ -4,10 +4,12 @@ from pathlib import Path
 
 from lib.rebrickable.minifig_characters import (
     aggregate_by_character,
+    aggregate_by_gender,
     aggregate_character_spans,
     aggregate_presence_by_year,
     load_sets_enriched,
     write_character_counts,
+    write_gender_counts,
 )
 
 
@@ -66,6 +68,24 @@ def test_aggregate_by_character_counts_unique_figs() -> None:
     ]
 
 
+def test_aggregate_by_gender_counts_unique_figs() -> None:
+    """Compter les minifigs distinctes par genre."""
+    aggregates = aggregate_by_gender(
+        [
+            {"fig_num": "fig-a", "gender": "male"},
+            {"fig_num": "fig-a", "gender": "male"},
+            {"fig_num": "fig-b", "gender": "female"},
+            {"fig_num": "fig-c", "gender": ""},
+        ]
+    )
+
+    assert aggregates == [
+        {"gender": "female", "minifig_count": "1"},
+        {"gender": "male", "minifig_count": "1"},
+        {"gender": "unknown", "minifig_count": "1"},
+    ]
+
+
 def test_write_character_counts_outputs_csv(tmp_path: Path) -> None:
     """Écrit le CSV des comptes par personnage."""
     destination = tmp_path / "counts.csv"
@@ -79,6 +99,19 @@ def test_write_character_counts_outputs_csv(tmp_path: Path) -> None:
     assert destination.read_text() == "known_character,gender,minifig_count\nA,male,2\nB,female,1\n"
 
 
+def test_write_gender_counts_outputs_csv(tmp_path: Path) -> None:
+    """Écrit le CSV des comptes par genre."""
+    destination = tmp_path / "gender_counts.csv"
+    rows = [
+        {"gender": "male", "minifig_count": "2"},
+        {"gender": "female", "minifig_count": "1"},
+    ]
+
+    write_gender_counts(destination, rows)
+
+    assert destination.read_text() == "gender,minifig_count\nmale,2\nfemale,1\n"
+
+
 def test_aggregate_presence_by_year_excludes_figurants(tmp_path: Path) -> None:
     """Calcule le total annuel en excluant les figurants."""
     sets_path = tmp_path / "sets_enriched.csv"

tests/test_minifig_gender_share_plot.py

@@ -0,0 +1,26 @@
+"""Tests du diagramme de répartition des genres."""
+
+import matplotlib
+from pathlib import Path
+
+from lib.plots.minifig_gender_share import plot_minifig_gender_share
+
+
+matplotlib.use("Agg")
+
+
+def test_plot_minifig_gender_share(tmp_path: Path) -> None:
+    """Génère le graphique de répartition par genre."""
+    counts_path = tmp_path / "gender_counts.csv"
+    destination = tmp_path / "figures" / "step25" / "minifig_gender_share.png"
+    counts_path.write_text(
+        "gender,minifig_count\n"
+        "male,2\n"
+        "female,1\n"
+        "unknown,1\n"
+    )
+
+    plot_minifig_gender_share(counts_path, destination)
+
+    assert destination.exists()
+    assert destination.stat().st_size > 0