Spaces:
Sleeping
Sleeping
File size: 3,648 Bytes
71c08ae 4ccb3e1 71c08ae 4ccb3e1 71c08ae | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | """Fetch real French car models with their official fuel consumption.
Source: ADEME "Car Labelling" open dataset (combined-cycle WLTP consumption in
L/100 km for every model commercialised in France). We map each model's energy
type to the matching pump fuel and dedupe to one entry per commercial model.
"""
from __future__ import annotations
import json
import urllib.parse
import urllib.request
ADEME_URL = "https://data.ademe.fr/data-fair/api/v1/datasets/ademe-car-labelling/lines"
SELECT = "Marque,Description_Commerciale,Energie,Conso_vitesse_mixte_Min,Conso_vitesse_mixte_Max"
# ADEME "Energie" -> our pump-fuel label (None = no liquid fuel, e.g. pure electric).
ENERGIE_FUEL = {
"ESSENCE": "E10",
"GAZOLE": "Gazole",
"GAZ+ELEC HNR": "Gazole", # diesel hybrid
"ESS+ELEC HNR": "E10", # petrol hybrid
"ELEC+ESSENC HR": "E10", # plug-in petrol hybrid
"ELEC+GAZOLE HR": "Gazole", # plug-in diesel hybrid
"SUPERETHANOL": "E85",
"ESS+G.P.L.": "GPLc",
"ELECTRIC": None,
}
# Suffix appended to the model name so hybrids are explicit in the picker.
HYBRID_TAG = {
"ESS+ELEC HNR": " — hybride",
"GAZ+ELEC HNR": " — hybride",
"ELEC+ESSENC HR": " — hybride rechargeable",
"ELEC+GAZOLE HR": " — hybride rechargeable",
}
def _fetch_all_rows(timeout: int, page_size: int = 10000) -> list[dict]:
"""Page through every line of the dataset via data-fair's `after` cursor.
The API caps a single response, so we follow the server-provided `next` link
(which carries the `after=<cursor>`) until the whole dataset is collected.
"""
url = ADEME_URL + f"?size={page_size}&select=" + urllib.parse.quote(SELECT)
rows: list[dict] = []
for _ in range(200): # hard safety cap on the number of pages
req = urllib.request.Request(url, headers={"User-Agent": "petrol-map/1.0"})
with urllib.request.urlopen(req, timeout=timeout) as resp:
data = json.load(resp)
page = data.get("results", [])
rows.extend(page)
total = data.get("total")
nxt = data.get("next")
if not page or not nxt or (isinstance(total, int) and len(rows) >= total):
break
url = nxt
return rows
def fetch_cars(timeout: int = 90) -> list[list]:
"""Return [[label, fuel, consumption_L_per_100km], ...], sorted by label."""
rows = _fetch_all_rows(timeout)
agg: dict[tuple, list[float]] = {} # (label, fuel) -> [sum_cons, n]
for r in rows:
energie = (r.get("Energie") or "").strip()
fuel = ENERGIE_FUEL.get(energie)
if not fuel:
continue
marque = (r.get("Marque") or "").strip()
desc = (r.get("Description_Commerciale") or "").strip()
if not marque or not desc:
continue
vals = [v for v in (r.get("Conso_vitesse_mixte_Min"), r.get("Conso_vitesse_mixte_Max"))
if isinstance(v, (int, float)) and v > 0]
if not vals:
continue
cons = sum(vals) / len(vals)
label = f"{marque} {desc}{HYBRID_TAG.get(energie, '')}"
key = (label, fuel)
if key in agg:
agg[key][0] += cons
agg[key][1] += 1
else:
agg[key] = [cons, 1]
cars = [[label, fuel, round(s / n, 1)] for (label, fuel), (s, n) in agg.items()]
cars.sort(key=lambda c: c[0])
return cars
if __name__ == "__main__":
cars = fetch_cars()
blob = json.dumps(cars, ensure_ascii=False, separators=(",", ":"))
print(f"{len(cars)} models, embedded size ~{len(blob) / 1024:.0f} KB")
for c in cars[:5]:
print(" ", c)
|