Exclusion des pièces imprimées dans la recherche de rareté

lib/rebrickable/part_rarity.py

@@ -46,6 +46,7 @@ def aggregate_filtered_parts(
     parts_catalog: Dict[str, dict],
     ignored_categories: Set[str] = IGNORED_PART_CATEGORY_IDS,
     ignored_minifig_categories: Set[str] = MINIFIG_PART_CATEGORY_IDS,
+    exclude_printed: bool = False,
 ) -> Dict[str, dict]:
     """Agrège les quantités par pièce pour les sets filtrés (rechanges incluses)."""
     aggregated: Dict[str, dict] = {}
@@ -57,6 +58,8 @@ def aggregate_filtered_parts(
             continue
         if part["part_cat_id"] in ignored_minifig_categories:
             continue
+        if exclude_printed and "print" in part["name"].lower():
+            continue
         entry = aggregated.get(row["part_num"])
         if entry is None:
             entry = {"quantity": 0, "set_numbers": set()}
@@ -73,6 +76,7 @@ def compute_other_set_usage(
     filtered_set_numbers: Set[str],
     ignored_categories: Set[str] = IGNORED_PART_CATEGORY_IDS,
     ignored_minifig_categories: Set[str] = MINIFIG_PART_CATEGORY_IDS,
+    exclude_printed: bool = False,
 ) -> Dict[str, int]:
     """Compte les occurrences des pièces dans le reste du catalogue (rechanges incluses)."""
     inventories = select_latest_inventories(inventories_path)
@@ -87,6 +91,8 @@ def compute_other_set_usage(
                 continue
             if part["part_cat_id"] in ignored_minifig_categories:
                 continue
+            if exclude_printed and "print" in part["name"].lower():
+                continue
             totals[row["part_num"]] = totals.get(row["part_num"], 0) + int(row["quantity"])
     return totals
 
@@ -98,6 +104,7 @@ def build_part_rarity(
     parts_catalog_path: Path,
     part_categories_path: Path,
     filtered_sets_path: Path,
+    exclude_printed: bool = False,
 ) -> List[dict]:
     """Construit le classement de rareté des pièces filtrées."""
     parts_catalog = load_parts_catalog(parts_catalog_path)
@@ -105,12 +112,13 @@ def build_part_rarity(
     filtered_sets = load_filtered_sets(filtered_sets_path)
     filtered_set_numbers = set(filtered_sets.keys())
     filtered_rows = read_rows(parts_filtered_path)
-    filtered_usage = aggregate_filtered_parts(filtered_rows, parts_catalog)
+    filtered_usage = aggregate_filtered_parts(filtered_rows, parts_catalog, exclude_printed=exclude_printed)
     other_usage = compute_other_set_usage(
         inventories_path,
         inventory_parts_path,
         parts_catalog,
         filtered_set_numbers,
+        exclude_printed=exclude_printed,
     )
     rows: List[dict] = []
     for part_num, entry in filtered_usage.items():

scripts/compute_part_rarity.py

@@ -12,7 +12,9 @@ PARTS_CATALOG_PATH = Path("data/raw/parts.csv")
 PART_CATEGORIES_PATH = Path("data/raw/part_categories.csv")
 FILTERED_SETS_PATH = Path("data/intermediate/sets_enriched.csv")
 DESTINATION_PATH = Path("data/intermediate/part_rarity.csv")
+DESTINATION_PRINTED_EXCLUDED_PATH = Path("data/intermediate/part_rarity_no_print.csv")
 TOP_DESTINATION_PATH = Path("data/intermediate/part_rarity_exclusive.csv")
+TOP_PRINTED_EXCLUDED_PATH = Path("data/intermediate/part_rarity_exclusive_no_print.csv")
 
 
 def main() -> None:
@@ -29,6 +31,19 @@ def main() -> None:
     top_rows = select_until_reused(rows)
     write_part_rarity(TOP_DESTINATION_PATH, top_rows)
 
+    rows_no_print = build_part_rarity(
+        PARTS_FILTERED_PATH,
+        INVENTORIES_PATH,
+        INVENTORY_PARTS_PATH,
+        PARTS_CATALOG_PATH,
+        PART_CATEGORIES_PATH,
+        FILTERED_SETS_PATH,
+        exclude_printed=True,
+    )
+    write_part_rarity(DESTINATION_PRINTED_EXCLUDED_PATH, rows_no_print)
+    top_rows_no_print = select_until_reused(rows_no_print)
+    write_part_rarity(TOP_PRINTED_EXCLUDED_PATH, top_rows_no_print)
+
 
 if __name__ == "__main__":
     main()

scripts/plot_part_rarity.py

@@ -8,11 +8,14 @@ from lib.plots.part_rarity import plot_part_rarity
 PART_RARITY_TOP_PATH = Path("data/intermediate/part_rarity_exclusive.csv")
 DESTINATION_PATH = Path("figures/step34/part_rarity.png")
 RESOURCES_DIR = Path("figures/rebrickable")
+PART_RARITY_NO_PRINT_PATH = Path("data/intermediate/part_rarity_exclusive_no_print.csv")
+DESTINATION_NO_PRINT = Path("figures/step34/part_rarity_no_print.png")
 
 
 def main() -> None:
     """Charge le top des pièces rares et produit le graphique illustré."""
     plot_part_rarity(PART_RARITY_TOP_PATH, DESTINATION_PATH, resources_dir=RESOURCES_DIR)
+    plot_part_rarity(PART_RARITY_NO_PRINT_PATH, DESTINATION_NO_PRINT, resources_dir=RESOURCES_DIR)
 
 
 if __name__ == "__main__":

tests/test_part_rarity.py

@@ -58,6 +58,7 @@ def test_build_part_rarity_counts_spares_and_ignores_categories(tmp_path: Path)
             ["p4", "Figure Limb", "41", "Plastic"],
             ["p5", "Sticker Sheet", "58", "Plastic"],
             ["p6", "Exclusive Tile", "1", "Plastic"],
+            ["p7", "Slope 45 print", "1", "Plastic"],
         ],
     )
     part_categories = tmp_path / "part_categories.csv"
@@ -95,6 +96,7 @@ def test_build_part_rarity_counts_spares_and_ignores_categories(tmp_path: Path)
             ["3", "p4", "1", "4", "True", ""],
             ["4", "p1", "1", "8", "False", ""],
             ["5", "p5", "1", "9", "False", ""],
+            ["5", "p7", "1", "5", "False", ""],
         ],
     )
 
@@ -150,6 +152,17 @@ def test_build_part_rarity_counts_spares_and_ignores_categories(tmp_path: Path)
     ]
     assert select_until_reused(rows) == [rows[0], rows[1]]
 
+    rows_no_print = build_part_rarity(
+        parts_filtered,
+        inventories,
+        inventory_parts,
+        parts_catalog,
+        part_categories,
+        sets_enriched,
+        exclude_printed=True,
+    )
+    assert all(r["part_num"] != "p7" for r in rows_no_print)
+
 
 def test_write_part_rarity_outputs_csv(tmp_path: Path) -> None:
     """Sérialise le classement de rareté."""