Add CSV loading per station for energy analysis

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
maximeandClaude Opus 5.5 committed 2026-10-09 19:25:26 +02:00
1 parent 55ec0499bb
commit 422904757f
2 files changed
+116

No files matched your search

+48
View File
@@ -0,0 +1,48 @@
"""Analyse énergétique MA7D_DROP : tendance de BusVoltage en moyenne glissante.
Spec : docs/superpowers/specs/2026-10-09-energy-ma7d-design.md
Bibliothèque standard uniquement (cible : système embarqué de la station).
"""
import csv
import glob
import os
import re
import sys
from datetime import datetime
NAME_RE = re.compile(r"^(?P<station>[^_]+)_(?P<metric>.+?)_\d{4}_\d{2}_\d{2}_\d{2}_\d{2} to .+\.csv$")
def parse_name(path):
"""'<STATION>_<Metric>_<début> to <fin>.csv' -> (station, metric), ou None."""
m = NAME_RE.match(os.path.basename(path))
return (m["station"], m["metric"]) if m else None
def load_csv(path):
"""CSV ',time_utc,metric' -> {datetime UTC: float ou None (pas de mesure)}."""
with open(path, newline="") as f:
rows = csv.reader(f)
next(rows)
return {datetime.fromisoformat(r[1]): float(r[2]) if r[2] else None for r in rows}
def load_stations(paths):
"""Fichiers et/ou dossiers -> {station: {metric: série}}."""
files = []
for p in paths:
files += sorted(glob.glob(os.path.join(p, "*.csv"))) if os.path.isdir(p) else [p]
stations, seen = {}, {}
for path in files:
real = os.path.realpath(path)
if real in seen.values():
continue
key = parse_name(path)
if key is None:
print(f"ignoré (nom non reconnu) : {path}", file=sys.stderr)
continue
if key in seen:
raise ValueError(f"doublon {key[0]}/{key[1]} : {seen[key]} et {path}")
seen[key] = real
stations.setdefault(key[0], {})[key[1]] = load_csv(path)
return stations
+68
View File
@@ -0,0 +1,68 @@
"""Tests de régression de l'analyse MA7D_DROP, sur données réelles uniquement (spec §9)."""
import functools
import io
import shutil
import sys
import tempfile
import unittest
from contextlib import redirect_stderr
from datetime import datetime, timezone
from pathlib import Path
ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT / "src"))
import energy_check as ec # noqa: E402
DATA, VERMONT = ROOT / "data", ROOT / "vermont"
VERMONT_V = VERMONT / "VERMONT_BusVoltage_2026_04_09_15_00 to 2026_10_09_15_00.csv"
VERMONT_THERMAL = VERMONT / "VERMONT_sensor_thermal_deg_c_2026_02_22_15_00 to 2026_10_09_15_00.csv"
JUNGFRAU_V = DATA / "JUNGFRAU_BusVoltage_2026_09_11_14_00 to 2026_10_09_14_00.csv"
def at(*args):
return datetime(*args, tzinfo=timezone.utc)
@functools.cache
def stations():
return ec.load_stations([str(DATA), str(VERMONT)])
class Loading(unittest.TestCase):
def test_parse_name_metric_with_underscores(self):
self.assertEqual(ec.parse_name(str(VERMONT_THERMAL)), ("VERMONT", "sensor_thermal_deg_c"))
def test_parse_name_rejects_unknown_pattern(self):
self.assertIsNone(ec.parse_name("data/metadata.csv"))
def test_load_csv_empty_value_is_none(self):
s = ec.load_csv(VERMONT_V)
self.assertIsNone(s[at(2026, 4, 9, 15)])
self.assertAlmostEqual(s[at(2026, 4, 9, 16)], 14.011)
def test_load_stations_groups_by_station(self):
self.assertEqual(sorted(stations()), ["FLORIDA", "JUNGFRAU", "MISSISSIPPI", "VERMONT", "WILDSTRUBEL"])
self.assertEqual(len(stations()["VERMONT"]), 7)
def test_same_file_given_twice_is_not_a_duplicate(self):
self.assertIn("BusVoltage", ec.load_stations([str(DATA), str(JUNGFRAU_V)])["JUNGFRAU"])
def test_two_files_same_station_metric_raise(self):
with tempfile.TemporaryDirectory() as d:
shutil.copy(JUNGFRAU_V, Path(d) / "JUNGFRAU_BusVoltage_2026_09_12_14_00 to 2026_10_09_14_00.csv")
with self.assertRaises(ValueError):
ec.load_stations([str(DATA), d])
def test_unknown_csv_name_is_skipped_with_message(self):
with tempfile.TemporaryDirectory() as d:
shutil.copy(JUNGFRAU_V, Path(d) / "export.csv")
shutil.copy(JUNGFRAU_V, d)
err = io.StringIO()
with redirect_stderr(err):
st = ec.load_stations([d])
self.assertEqual(list(st), ["JUNGFRAU"])
self.assertIn("export.csv", err.getvalue())
if __name__ == "__main__":
unittest.main()