Ajoute le genre des personnages et colore les graphiques

README.md

@@ -222,7 +222,7 @@ Cette étape se lance après le téléchargement des données d'inventaire (éta
 1. `source .venv/bin/activate`
 2. `python -m scripts.compute_minifigs_by_set`
 
-Le script lit l'inventaire agrégé `data/intermediate/parts_filtered.csv`, les inventaires `data/raw/inventories.csv`, `data/raw/inventory_parts.csv`, `data/raw/inventory_minifigs.csv`, le catalogue des pièces (`data/raw/parts.csv`) et celui des minifigs (`data/raw/minifigs.csv`). Il sélectionne les têtes de minifigs (catégorie 59), ignore les rechanges et dédoublonne par set et référence. Si une tête est associée à une minifig précise dans l'inventaire du set, `known_character` est renseigné avec le nom de la minifig et `fig_num` est indiqué ; sinon, `known_character` reste vide après tentative de correspondance automatique. Le CSV `data/intermediate/minifigs_by_set.csv` contient : `set_num`, `part_num`, `known_character`, `fig_num`.
+Le script lit l'inventaire agrégé `data/intermediate/parts_filtered.csv`, les inventaires `data/raw/inventories.csv`, `data/raw/inventory_parts.csv`, `data/raw/inventory_minifigs.csv`, le catalogue des pièces (`data/raw/parts.csv`) et celui des minifigs (`data/raw/minifigs.csv`). Il sélectionne les têtes de minifigs (catégorie 59), ignore les rechanges et dédoublonne par set et référence. Si une tête est associée à une minifig précise dans l'inventaire du set, `known_character` est renseigné avec le nom de la minifig et `fig_num` est indiqué ; sinon, `known_character` reste vide après tentative de correspondance automatique. Les correspondances d'alias sont décrites dans `config/known_character_aliases.csv` et les genres des personnages nommés dans `config/known_character_genders.csv`. Le CSV `data/intermediate/minifigs_by_set.csv` contient : `set_num`, `part_num`, `known_character`, `fig_num`, `gender`.
 
 ### Étape 21 : visualiser le nombre de minifigs par set
 
@@ -239,7 +239,7 @@ Le script relit `data/intermediate/sets_enriched.csv`, `data/intermediate/parts_
 1. `source .venv/bin/activate`
 2. `python -m scripts.plot_minifig_characters`
 
-Le script lit `data/intermediate/minifigs_by_set.csv`, compte le nombre de minifigs distinctes par personnage (`known_character` + `fig_num`), écrit `data/intermediate/minifig_characters_counts.csv`, puis trace `figures/step22/minifig_characters.png` (barres horizontales triées).
+Le script lit `data/intermediate/minifigs_by_set.csv`, compte le nombre de minifigs distinctes par personnage (`known_character` + `fig_num`), écrit `data/intermediate/minifig_characters_counts.csv`, puis trace `figures/step22/minifig_characters.png` (barres horizontales triées). Les barres sont colorées en fonction du genre renseigné dans `config/known_character_genders.csv`.
 
 ### Étape 23 : présence annuelle des personnages
 
@@ -253,4 +253,4 @@ Le script lit `data/intermediate/minifigs_by_set.csv` et `data/intermediate/sets
 1. `source .venv/bin/activate`
 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).
+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`.

config/known_character_genders.csv

@@ -0,0 +1,54 @@
+known_character,gender
+ACU Trooper,unknown
+Allison Miles,female
+Alan Grant,male
+Atwater,male
+Barry,male
+Ben,male
+Brooklynn,female
+Claire Dearing,female
+Danny Nedermeyer,male
+Darius,male
+Dennis Nedry,male
+Donald Gennaro,male
+Dr Wu,male
+Duncan Kincaid,male
+Eli Mills,male
+Ellie Sattler,female
+Figurant,unknown
+Franklin Web,male
+Franklin Webb,male
+Gray,male
+Gray Mitchell,male
+Gunnar Eversol,male
+Henry Loomis,male
+Henry Wu,male
+Hudson Harper,male
+Ian Malcolm,male
+Isabella Delgado,female
+John Hammond,male
+Kayla Watts,female
+Ken Wheatley,male
+Kenji,male
+Lex Murphy,female
+LeClerc,male
+Maisie Lockwood,female
+Martin Krebs,male
+Owen Grady,male
+Rainn DeLaCourt,male
+Ray Arnold,male
+Reuben Delgado,male
+Robert Muldoon,male
+Sammy,female
+Simon Masrani,male
+Sinjin Prescott,male
+Soyona Santos,female
+Teresa Delgado,female
+Tim Murphy,male
+Vic Hoskins,male
+Xavier Dobbs,male
+Yaz,female
+Zach,male
+Zach Mitchell,male
+Zia Rodriguez,female
+Zora Bennett,female

lib/plots/minifig_character_spans.py

@@ -1,20 +1,35 @@
 """Diagramme de longévité des personnages (bornes d'apparition)."""
 
 from pathlib import Path
-from typing import List
+from typing import Dict, List
 
 import matplotlib.pyplot as plt
+from matplotlib.patches import Patch
 
 from lib.filesystem import ensure_parent_dir
+from lib.milestones import load_milestones
 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)
 
 
-def plot_character_spans(spans_path: Path, destination_path: Path) -> None:
+def plot_character_spans(spans_path: Path, destination_path: Path, milestones_path: Path | None = None) -> None:
     """Trace un diagramme en barres représentant la longévité des personnages."""
     rows = load_spans(spans_path)
     if not rows:
@@ -23,18 +38,22 @@ def plot_character_spans(spans_path: Path, destination_path: Path) -> None:
     starts = [int(row["start_year"]) for row in rows]
     ends = [int(row["end_year"]) for row in rows]
     counts = [int(row["total_minifigs"]) for row in rows]
+    genders = [row.get("gender", "") for row in rows]
+    colors = [GENDER_COLORS.get(gender.strip().lower(), GENDER_COLORS["unknown"]) for gender in genders]
     positions = list(range(len(rows)))
     widths = [end - start + 1 for start, end in zip(starts, ends)]
     min_year = min(starts)
     max_year = max(ends)
     height = max(5, len(rows) * 0.3)
 
+    milestones = load_milestones(milestones_path) if milestones_path else []
+
     fig, ax = plt.subplots(figsize=(12, height))
     bars = ax.barh(
         positions,
         widths,
         left=starts,
-        color="#1f77b4",
+        color=colors,
         edgecolor="#0d0d0d",
         linewidth=0.6,
     )
@@ -57,6 +76,55 @@ def plot_character_spans(spans_path: Path, destination_path: Path) -> None:
             color="#0d0d0d",
         )
 
+    legend_entries = []
+    seen = set()
+    for gender in genders:
+        normalized = gender.strip().lower()
+        if normalized in seen:
+            continue
+        seen.add(normalized)
+        legend_entries.append(
+            Patch(
+                facecolor=GENDER_COLORS.get(normalized, GENDER_COLORS["unknown"]),
+                edgecolor="#0d0d0d",
+                linewidth=0.6,
+                label=GENDER_LABELS.get(normalized, "Inconnu"),
+            )
+        )
+    if legend_entries:
+        ax.legend(handles=legend_entries, title="Genre", loc="lower right")
+
+    if milestones:
+        milestones_in_range = sorted(
+            [m for m in milestones if min_year <= m["year"] <= max_year],
+            key=lambda m: (m["year"], m["description"]),
+        )
+        milestone_offsets: Dict[int, int] = {}
+        offset_step = 0.2
+        max_offset = 0
+        y_bottom, y_top = ax.get_ylim()
+        text_y = y_top - (y_top - y_bottom) * 0.01
+        for milestone in milestones_in_range:
+            year = milestone["year"]
+            count_for_year = milestone_offsets.get(year, 0)
+            milestone_offsets[year] = count_for_year + 1
+            horizontal_offset = offset_step * (count_for_year // 2 + 1)
+            max_offset = max(max_offset, count_for_year)
+            if count_for_year % 2 == 1:
+                horizontal_offset *= -1
+            text_x = year + horizontal_offset
+            ax.axvline(year, color="#d62728", linestyle="--", linewidth=1, alpha=0.65)
+            ax.text(
+                text_x,
+                text_y,
+                milestone["description"],
+                rotation=90,
+                verticalalignment="top",
+                horizontalalignment="center",
+                fontsize=8,
+                color="#d62728",
+            )
+
     ensure_parent_dir(destination_path)
     fig.tight_layout()
     fig.savefig(destination_path, dpi=160)

lib/plots/minifig_characters.py

@@ -4,11 +4,25 @@ from pathlib import Path
 from typing import List
 
 import matplotlib.pyplot as plt
+from matplotlib.patches import Patch
 
 from lib.filesystem import ensure_parent_dir
 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)
@@ -24,11 +38,13 @@ def plot_minifigs_per_character(counts_path: Path, destination_path: Path) -> No
     rows = load_counts(counts_path)
     characters = [row["known_character"] for row in rows]
     counts = [int(row["minifig_count"]) for row in rows]
+    genders = [row.get("gender", "") for row in rows]
+    colors = [GENDER_COLORS.get(gender.strip().lower(), GENDER_COLORS["unknown"]) for gender in genders]
     positions = list(range(len(rows)))
     height = max(6, len(rows) * 0.22)
 
     fig, ax = plt.subplots(figsize=(12, height))
-    bars = ax.barh(positions, counts, color="#1f77b4", edgecolor="#0d0d0d", linewidth=0.6)
+    bars = ax.barh(positions, counts, color=colors, edgecolor="#0d0d0d", linewidth=0.6)
     ax.set_yticks(positions)
     ax.set_yticklabels(characters)
     ax.invert_yaxis()
@@ -40,6 +56,23 @@ def plot_minifigs_per_character(counts_path: Path, destination_path: Path) -> No
     for index, bar in enumerate(bars):
         value = counts[index]
         ax.text(value + 0.1, bar.get_y() + bar.get_height() / 2, str(value), va="center", fontsize=8)
+    legend_entries = []
+    seen = set()
+    for gender in genders:
+        normalized = gender.strip().lower()
+        if normalized in seen:
+            continue
+        seen.add(normalized)
+        legend_entries.append(
+            Patch(
+                facecolor=GENDER_COLORS.get(normalized, GENDER_COLORS["unknown"]),
+                edgecolor="#0d0d0d",
+                linewidth=0.6,
+                label=GENDER_LABELS.get(normalized, "Inconnu"),
+            )
+        )
+    if legend_entries:
+        ax.legend(handles=legend_entries, title="Genre", loc="lower right")
 
     ensure_parent_dir(destination_path)
     fig.tight_layout()

lib/rebrickable/minifig_characters.py

@@ -1,12 +1,12 @@
 """Agrégation des minifigs par personnage représenté."""
 
+import csv
 from collections import defaultdict
 from pathlib import Path
 from typing import Dict, Iterable, List, Sequence, Set
 
-from lib.rebrickable.stats import read_rows
 from lib.filesystem import ensure_parent_dir
-import csv
+from lib.rebrickable.stats import read_rows
 
 
 def load_minifigs_by_set(path: Path) -> List[dict]:
@@ -15,17 +15,21 @@ def load_minifigs_by_set(path: Path) -> List[dict]:
 
 
 def aggregate_by_character(rows: Iterable[dict]) -> List[dict]:
-    """Compte les minifigs distinctes par personnage (fig_num unique)."""
+    """Compte les minifigs distinctes par personnage (fig_num unique) avec genre."""
     fig_nums_by_character: Dict[str, set] = defaultdict(set)
+    genders: Dict[str, str] = {}
     for row in rows:
         character = row["known_character"].strip()
         fig_num = row["fig_num"].strip()
+        gender = row.get("gender", "").strip()
         if character == "" or fig_num == "":
             continue
         fig_nums_by_character[character].add(fig_num)
+        if character not in genders:
+            genders[character] = gender
     aggregates: List[dict] = []
     for character, fig_nums in fig_nums_by_character.items():
-        aggregates.append({"known_character": character, "minifig_count": len(fig_nums)})
+        aggregates.append({"known_character": character, "gender": genders.get(character, ""), "minifig_count": len(fig_nums)})
     aggregates.sort(key=lambda r: (-r["minifig_count"], r["known_character"]))
     return aggregates
 
@@ -33,7 +37,7 @@ def aggregate_by_character(rows: Iterable[dict]) -> List[dict]:
 def write_character_counts(path: Path, rows: Sequence[dict]) -> None:
     """Écrit le CSV des comptes par personnage."""
     ensure_parent_dir(path)
-    fieldnames = ["known_character", "minifig_count"]
+    fieldnames = ["known_character", "gender", "minifig_count"]
     with path.open("w", newline="") as csv_file:
         writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
         writer.writeheader()
@@ -110,9 +114,11 @@ def aggregate_character_spans(
     excluded = set(excluded_characters or [])
     spans: Dict[str, Dict[str, int]] = {}
     total_counts: Dict[str, int] = defaultdict(int)
+    genders: Dict[str, str] = {}
     for row in minifigs_rows:
         character = row["known_character"].strip()
         fig_num = row["fig_num"].strip()
+        gender = row.get("gender", "").strip()
         if character == "" or fig_num == "":
             continue
         if character in excluded:
@@ -122,6 +128,8 @@ def aggregate_character_spans(
             continue
         year_int = int(year)
         total_counts[character] += 1
+        if character not in genders:
+            genders[character] = gender
         current = spans.get(character)
         if current is None:
             spans[character] = {"start": year_int, "end": year_int}
@@ -136,6 +144,7 @@ def aggregate_character_spans(
                 "start_year": str(bounds["start"]),
                 "end_year": str(bounds["end"]),
                 "total_minifigs": str(total_counts[character]),
+                "gender": genders.get(character, ""),
             }
         )
     results.sort(key=lambda r: (int(r["start_year"]), int(r["end_year"]), r["known_character"]))
@@ -145,7 +154,7 @@ def aggregate_character_spans(
 def write_character_spans(path: Path, rows: Sequence[dict]) -> None:
     """Écrit le CSV des bornes min/max par personnage."""
     ensure_parent_dir(path)
-    fieldnames = ["known_character", "start_year", "end_year", "total_minifigs"]
+    fieldnames = ["known_character", "start_year", "end_year", "total_minifigs", "gender"]
     with path.open("w", newline="") as csv_file:
         writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
         writer.writeheader()

lib/rebrickable/minifigs_by_set.py

@@ -128,6 +128,16 @@ def load_aliases(path: Path) -> Dict[str, str]:
     return aliases
 
 
+def load_gender_overrides(path: Path) -> Dict[str, str]:
+    """Charge les correspondances personnage -> genre."""
+    overrides: Dict[str, str] = {}
+    with path.open() as gender_file:
+        reader = csv.DictReader(gender_file)
+        for row in reader:
+            overrides[row["known_character"].lower()] = row["gender"]
+    return overrides
+
+
 def normalize_known_character(raw_known: str, extracted_name: str, aliases: Dict[str, str]) -> str:
     """Nettoie et mappe un nom vers une version canonique."""
     base = raw_known or extracted_name
@@ -201,6 +211,7 @@ def aggregate_heads_by_set(
     minifig_heads: Dict[str, Set[str]],
     minifig_catalog: Dict[str, dict],
     aliases: Dict[str, str],
+    gender_overrides: Dict[str, str],
 ) -> List[dict]:
     """Agrège les têtes de minifigs par set en éliminant les rechanges et doublons."""
     seen: Set[Tuple[str, str]] = set()
@@ -228,12 +239,14 @@ def aggregate_heads_by_set(
         normalized = normalize_known_character(known_character, extracted, aliases)
         if matched_fig == "":
             continue
+        gender = gender_overrides.get(normalized.lower(), "")
         heads.append(
             {
                 "set_num": row["set_num"],
                 "part_num": row["part_num"],
                 "known_character": normalized,
                 "fig_num": matched_fig,
+                "gender": gender,
             }
         )
         seen.add(key)
@@ -244,7 +257,7 @@ def aggregate_heads_by_set(
 def write_heads_by_set(destination_path: Path, rows: Sequence[dict]) -> None:
     """Écrit le CSV intermédiaire listant les têtes de minifigs par set."""
     ensure_parent_dir(destination_path)
-    fieldnames = ["set_num", "part_num", "known_character", "fig_num"]
+    fieldnames = ["set_num", "part_num", "known_character", "fig_num", "gender"]
     with destination_path.open("w", newline="") as csv_file:
         writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
         writer.writeheader()
@@ -260,6 +273,7 @@ def build_minifigs_by_set(
     inventory_minifigs_path: Path,
     minifigs_path: Path,
     aliases_path: Path,
+    gender_overrides_path: Path,
     destination_path: Path,
 ) -> None:
     """Construit le CSV listant les têtes de minifigs présentes par set."""
@@ -271,6 +285,7 @@ def build_minifigs_by_set(
     minifig_heads = build_minifig_heads_lookup(minifig_catalog, latest_inventories, inventory_parts_path, head_parts)
     set_minifigs = build_set_minifigs_lookup(latest_inventories, inventory_minifigs_path)
     aliases = load_aliases(aliases_path)
+    gender_overrides = load_gender_overrides(gender_overrides_path)
     heads = aggregate_heads_by_set(
         parts_rows,
         parts_catalog,
@@ -279,5 +294,6 @@ def build_minifigs_by_set(
         minifig_heads,
         minifig_catalog,
         aliases,
+        gender_overrides,
     )
     write_heads_by_set(destination_path, heads)

scripts/compute_minifigs_by_set.py

@@ -12,6 +12,7 @@ INVENTORY_PARTS_PATH = Path("data/raw/inventory_parts.csv")
 INVENTORY_MINIFIGS_PATH = Path("data/raw/inventory_minifigs.csv")
 MINIFIGS_PATH = Path("data/raw/minifigs.csv")
 ALIASES_PATH = Path("config/known_character_aliases.csv")
+GENDERS_PATH = Path("config/known_character_genders.csv")
 DESTINATION_PATH = Path("data/intermediate/minifigs_by_set.csv")
 
 
@@ -25,6 +26,7 @@ def main() -> None:
         INVENTORY_MINIFIGS_PATH,
         MINIFIGS_PATH,
         ALIASES_PATH,
+        GENDERS_PATH,
         DESTINATION_PATH,
     )
 

scripts/plot_minifig_character_spans.py

@@ -15,6 +15,7 @@ MINIFIGS_BY_SET_PATH = Path("data/intermediate/minifigs_by_set.csv")
 SETS_ENRICHED_PATH = Path("data/intermediate/sets_enriched.csv")
 SPANS_PATH = Path("data/intermediate/minifig_character_spans.csv")
 DESTINATION_PATH = Path("figures/step24/minifig_character_spans.png")
+MILESTONES_PATH = Path("config/milestones.csv")
 EXCLUDED_CHARACTERS = ["Figurant"]
 
 
@@ -24,7 +25,7 @@ def main() -> None:
     sets_years = load_sets_enriched(SETS_ENRICHED_PATH)
     spans = aggregate_character_spans(minifigs, sets_years, excluded_characters=EXCLUDED_CHARACTERS)
     write_character_spans(SPANS_PATH, spans)
-    plot_character_spans(SPANS_PATH, DESTINATION_PATH)
+    plot_character_spans(SPANS_PATH, DESTINATION_PATH, milestones_path=MILESTONES_PATH)
 
 
 if __name__ == "__main__":

tests/test_minifig_character_spans_plot.py

@@ -12,11 +12,11 @@ matplotlib.use("Agg")
 def test_plot_character_spans(tmp_path: Path) -> None:
     """Génère le graphique de span des personnages."""
     spans_path = tmp_path / "minifig_character_spans.csv"
-    destination = tmp_path / "figures" / "step23" / "minifig_character_spans.png"
+    destination = tmp_path / "figures" / "step24" / "minifig_character_spans.png"
     spans_path.write_text(
-        "known_character,start_year,end_year,total_minifigs\n"
+        "known_character,start_year,end_year,total_minifigs,gender\n"
-        "Owen Grady,2020,2022,3\n"
+        "Owen Grady,2020,2022,3,male\n"
-        "Figurant,2019,2020,2\n"
+        "Figurant,2019,2020,2,unknown\n"
     )
 
     plot_character_spans(spans_path, destination)

tests/test_minifig_characters.py

@@ -15,18 +15,54 @@ def test_aggregate_by_character_counts_unique_figs() -> None:
     """Compter les minifigs distinctes par personnage en excluant les noms vides."""
     aggregates = aggregate_by_character(
         [
-            {"set_num": "123-1", "part_num": "head-a", "known_character": "Owen Grady", "fig_num": "fig-owen-1"},
+            {
-            {"set_num": "124-1", "part_num": "head-b", "known_character": "Owen Grady", "fig_num": "fig-owen-1"},
+                "set_num": "123-1",
-            {"set_num": "125-1", "part_num": "head-c", "known_character": "Owen Grady", "fig_num": "fig-owen-2"},
+                "part_num": "head-a",
-            {"set_num": "126-1", "part_num": "head-d", "known_character": "Figurant", "fig_num": "fig-guard-1"},
+                "known_character": "Owen Grady",
-            {"set_num": "128-1", "part_num": "head-f", "known_character": "Figurant", "fig_num": "fig-guard-1"},
+                "fig_num": "fig-owen-1",
-            {"set_num": "129-1", "part_num": "head-g", "known_character": "", "fig_num": "fig-guard-2"},
+                "gender": "male",
+            },
+            {
+                "set_num": "124-1",
+                "part_num": "head-b",
+                "known_character": "Owen Grady",
+                "fig_num": "fig-owen-1",
+                "gender": "male",
+            },
+            {
+                "set_num": "125-1",
+                "part_num": "head-c",
+                "known_character": "Owen Grady",
+                "fig_num": "fig-owen-2",
+                "gender": "male",
+            },
+            {
+                "set_num": "126-1",
+                "part_num": "head-d",
+                "known_character": "Figurant",
+                "fig_num": "fig-guard-1",
+                "gender": "unknown",
+            },
+            {
+                "set_num": "128-1",
+                "part_num": "head-f",
+                "known_character": "Figurant",
+                "fig_num": "fig-guard-1",
+                "gender": "unknown",
+            },
+            {
+                "set_num": "129-1",
+                "part_num": "head-g",
+                "known_character": "",
+                "fig_num": "fig-guard-2",
+                "gender": "unknown",
+            },
         ]
     )
 
     assert aggregates == [
-        {"known_character": "Owen Grady", "minifig_count": 2},
+        {"known_character": "Owen Grady", "gender": "male", "minifig_count": 2},
-        {"known_character": "Figurant", "minifig_count": 1},
+        {"known_character": "Figurant", "gender": "unknown", "minifig_count": 1},
     ]
 
 
@@ -34,13 +70,13 @@ def test_write_character_counts_outputs_csv(tmp_path: Path) -> None:
     """Écrit le CSV des comptes par personnage."""
     destination = tmp_path / "counts.csv"
     rows = [
-        {"known_character": "A", "minifig_count": 2},
+        {"known_character": "A", "gender": "male", "minifig_count": 2},
-        {"known_character": "B", "minifig_count": 1},
+        {"known_character": "B", "gender": "female", "minifig_count": 1},
     ]
 
     write_character_counts(destination, rows)
 
-    assert destination.read_text() == "known_character,minifig_count\nA,2\nB,1\n"
+    assert destination.read_text() == "known_character,gender,minifig_count\nA,male,2\nB,female,1\n"
 
 
 def test_aggregate_presence_by_year_excludes_figurants(tmp_path: Path) -> None:
@@ -52,8 +88,20 @@ def test_aggregate_presence_by_year_excludes_figurants(tmp_path: Path) -> None:
         "124-1,2021\n"
     )
     minifigs_rows = [
-        {"set_num": "123-1", "known_character": "Owen Grady", "fig_num": "fig-owen", "part_num": "head-a"},
+        {
-        {"set_num": "124-1", "known_character": "Figurant", "fig_num": "fig-guard", "part_num": "head-b"},
+            "set_num": "123-1",
+            "known_character": "Owen Grady",
+            "fig_num": "fig-owen",
+            "part_num": "head-a",
+            "gender": "male",
+        },
+        {
+            "set_num": "124-1",
+            "known_character": "Figurant",
+            "fig_num": "fig-guard",
+            "part_num": "head-b",
+            "gender": "unknown",
+        },
     ]
     sets_years = load_sets_enriched(sets_path)
 
@@ -76,13 +124,31 @@ def test_aggregate_character_spans_excludes_figurants(tmp_path: Path) -> None:
     )
     sets_years = load_sets_enriched(sets_path)
     minifigs_rows = [
-        {"set_num": "123-1", "known_character": "Owen Grady", "fig_num": "fig-owen", "part_num": "head-a"},
+        {
-        {"set_num": "124-1", "known_character": "Owen Grady", "fig_num": "fig-owen", "part_num": "head-a"},
+            "set_num": "123-1",
-        {"set_num": "125-1", "known_character": "Figurant", "fig_num": "fig-guard", "part_num": "head-b"},
+            "known_character": "Owen Grady",
+            "fig_num": "fig-owen",
+            "part_num": "head-a",
+            "gender": "male",
+        },
+        {
+            "set_num": "124-1",
+            "known_character": "Owen Grady",
+            "fig_num": "fig-owen",
+            "part_num": "head-a",
+            "gender": "male",
+        },
+        {
+            "set_num": "125-1",
+            "known_character": "Figurant",
+            "fig_num": "fig-guard",
+            "part_num": "head-b",
+            "gender": "unknown",
+        },
     ]
 
     spans = aggregate_character_spans(minifigs_rows, sets_years, excluded_characters=["Figurant"])
 
     assert spans == [
-        {"known_character": "Owen Grady", "start_year": "2020", "end_year": "2021", "total_minifigs": "2"},
+        {"known_character": "Owen Grady", "start_year": "2020", "end_year": "2021", "total_minifigs": "2", "gender": "male"},
     ]

tests/test_minifig_characters_plot.py

@@ -14,9 +14,9 @@ def test_plot_minifigs_per_character(tmp_path: Path) -> None:
     counts_path = tmp_path / "counts.csv"
     destination = tmp_path / "figures" / "step22" / "minifig_characters.png"
     counts_path.write_text(
-        "known_character,minifig_count\n"
+        "known_character,gender,minifig_count\n"
-        "Owen Grady,2\n"
+        "Owen Grady,male,2\n"
-        "Figurant,1\n"
+        "Figurant,unknown,1\n"
     )
 
     plot_minifigs_per_character(counts_path, destination)

tests/test_minifigs_by_set.py

@@ -71,6 +71,13 @@ def test_build_minifigs_by_set_filters_spares_and_deduplicates(tmp_path) -> None
         "alias,canonical\n"
         "Guard in Helmet with Trans-Brown Visor,Figurant\n",
     )
+    genders_path = tmp_path / "known_character_genders.csv"
+    write_csv(
+        genders_path,
+        "known_character,gender\n"
+        "Owen Grady,male\n"
+        "Figurant,unknown\n",
+    )
     destination_path = tmp_path / "minifigs_by_set.csv"
 
     build_minifigs_by_set(
@@ -81,12 +88,13 @@ def test_build_minifigs_by_set_filters_spares_and_deduplicates(tmp_path) -> None
         inventory_minifigs_path,
         minifigs_path,
         aliases_path,
+        genders_path,
         destination_path,
     )
 
     assert destination_path.read_text() == (
-        "set_num,part_num,known_character,fig_num\n"
+        "set_num,part_num,known_character,fig_num,gender\n"
-        "123-1,head-a,Owen Grady,fig-owen\n"
+        "123-1,head-a,Owen Grady,fig-owen,male\n"
-        "123-1,head-b,Figurant,fig-guard\n"
+        "123-1,head-b,Figurant,fig-guard,unknown\n"
-        "124-1,head-b,Figurant,fig-guard\n"
+        "124-1,head-b,Figurant,fig-guard,unknown\n"
     )