richard/etude_lego_jurassic_world
1
Fork 0
Code Issues Activity

Ajoute le genre des personnages et colore les graphiques

Browse Source
This commit is contained in:
Richard Dern
2025-12-02 11:37:13 +01:00
parent 230b9db239
commit f5c1fa6333
12 changed files with 300 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
lib/rebrickable/minifig_characters.py
View File

@@ -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()