Pumping: the weather of the stations with a position written into data/<SERIAL>/weather/ (extraction/weather.py, after pump.py); the mm (corr_x_mm, corr_y_mm by the sensor_id of each row) and targets.csv with the references (pattern_type, distance_mm, mm_per_px); --replace pumps a range again

pump.py --check passes; the mm and targets.csv parts are not yet run against the database (no VPN).
stations.txt: NIEDERHORN and NORDEND without a position (outside Switzerland).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
maximeandClaude Opus 5.5 committed 2026-11-18 07:17:27 +01:00
1 parent 9adc38f9b9
commit ea0228a73a
8 files changed
+205 -22

No files matched your search

+10
View File
@@ -22,6 +22,7 @@ import json
import math
import re
import sys
import unicodedata
import urllib.parse
import urllib.request
from datetime import datetime, timedelta, timezone
@@ -75,9 +76,18 @@ def locate(place):
raise LookupError(f"place not found: {place}")
attrs = results[0]["attrs"]
label = re.sub(r"<[^>]+>", "", attrs["label"]).split("\n")[0].strip()
# the search always returns its best match ("Toronto" -> "Trient (VS)"): the label must start with the first word asked
# ponytail: first word only; "lat,lon" for a place whose name differs from its label
if not plain(label).startswith(plain(place.split()[0])):
raise LookupError(f"place not found: {place} (best match: {label})")
return attrs["lat"], attrs["lon"], label
def plain(text):
"""Lower case, without accents: "Genève" -> "geneve"."""
return "".join(c for c in unicodedata.normalize("NFKD", text.lower()) if not unicodedata.combining(c))
def distance_km(lat1, lon1, lat2, lon2):
p1, p2 = math.radians(lat1), math.radians(lat2)
a = (math.sin((p2 - p1) / 2) ** 2