Merge remote-tracking branch 'origin/dev' into feat/password-policy-forgot-password
# Conflicts: # apps/backend/app/api/deps.py # apps/backend/pyproject.toml
This commit is contained in:
Johan LEROY
@@ -34,6 +34,7 @@ from app.repositories.site import SiteRepository
|
||||
from app.repositories.user import UserRepository
|
||||
from app.services.alert import AlertService
|
||||
from app.services.auth import AuthService, LoginPolicy, PasswordResetPolicy
|
||||
from app.services.reading import ReadingService
|
||||
from app.services.recommendation import RecommendationService
|
||||
from app.services.sensor import SensorService
|
||||
from app.services.site import SiteService
|
||||
@@ -197,6 +198,13 @@ def get_stats_service(session: SessionDep) -> StatsService:
|
||||
StatsServiceDep = Annotated[StatsService, Depends(get_stats_service)]
|
||||
|
||||
|
||||
def get_reading_service(session: SessionDep) -> ReadingService:
|
||||
return ReadingService(readings=ReadingRepository(session))
|
||||
|
||||
|
||||
ReadingServiceDep = Annotated[ReadingService, Depends(get_reading_service)]
|
||||
|
||||
|
||||
def get_sensor_service(session: SessionDep) -> SensorService:
|
||||
return SensorService(sites=SiteRepository(session), readings=ReadingRepository(session))
|
||||
|
||||
|
||||
@@ -71,6 +71,14 @@ TAGS: Final[list[dict[str, Any]]] = [
|
||||
"description": "Statistiques agrégées de consommation. Accessible à partir du rôle "
|
||||
"`lecteur`.",
|
||||
},
|
||||
{
|
||||
"name": "readings",
|
||||
"description": (
|
||||
"Historique des lectures de consommation. Fenêtre temporelle plafonnée à 90 jours, "
|
||||
"24 dernières heures par défaut si `start`/`end` sont omis. Accessible à partir du "
|
||||
"rôle `lecteur`."
|
||||
),
|
||||
},
|
||||
{
|
||||
"name": "sensors",
|
||||
"description": "État de santé des capteurs par site. Réservé au rôle `admin`.",
|
||||
|
||||
@@ -0,0 +1,54 @@
|
||||
from datetime import datetime
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Query, status
|
||||
|
||||
from app.api.deps import LecteurDep, ReadingServiceDep
|
||||
from app.api.openapi import REPONSE_VALIDATION, Reponses
|
||||
from app.schemas.errors import ErrorResponse
|
||||
from app.schemas.reading import ReadingResponse
|
||||
from app.services.reading import FenetreInverseeError, FenetreTropLargeError
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
REPONSES_FENETRE: Reponses = {
|
||||
**REPONSE_VALIDATION,
|
||||
400: {
|
||||
"model": ErrorResponse,
|
||||
"description": (
|
||||
"Fenêtre temporelle invalide : `start` postérieur ou égal à `end`, ou écart entre "
|
||||
"les deux supérieur à 90 jours."
|
||||
),
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
@router.get(
|
||||
"",
|
||||
response_model=list[ReadingResponse],
|
||||
summary="Liste l'historique des lectures",
|
||||
responses=REPONSES_FENETRE,
|
||||
)
|
||||
async def list_readings(
|
||||
_: LecteurDep,
|
||||
service: ReadingServiceDep,
|
||||
site_id: str | None = None,
|
||||
start: datetime | None = None,
|
||||
end: datetime | None = None,
|
||||
limit: int = Query(500, ge=1, le=2000),
|
||||
offset: int = Query(0, ge=0),
|
||||
) -> list[ReadingResponse]:
|
||||
try:
|
||||
lectures = await service.list_history(
|
||||
site_id=site_id, start=start, end=end, limit=limit, offset=offset
|
||||
)
|
||||
except FenetreInverseeError as erreur:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail="`start` doit être strictement antérieur à `end`",
|
||||
) from erreur
|
||||
except FenetreTropLargeError as erreur:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail="L'écart entre `start` et `end` ne peut pas dépasser 90 jours",
|
||||
) from erreur
|
||||
return [ReadingResponse.model_validate(lecture) for lecture in lectures]
|
||||
@@ -1,7 +1,17 @@
|
||||
from fastapi import APIRouter
|
||||
|
||||
from app.api.openapi import REPONSE_SERVEUR, REPONSES_ADMIN, REPONSES_LECTEUR
|
||||
from app.api.v1.endpoints import alerts, auth, health, recommendations, sensors, sites, stats, users
|
||||
from app.api.v1.endpoints import (
|
||||
alerts,
|
||||
auth,
|
||||
health,
|
||||
readings,
|
||||
recommendations,
|
||||
sensors,
|
||||
sites,
|
||||
stats,
|
||||
users,
|
||||
)
|
||||
|
||||
api_router = APIRouter(responses=REPONSE_SERVEUR)
|
||||
api_router.include_router(health.router, prefix="/health", tags=["health"])
|
||||
@@ -18,6 +28,9 @@ api_router.include_router(
|
||||
responses=REPONSES_LECTEUR,
|
||||
)
|
||||
api_router.include_router(stats.router, prefix="/stats", tags=["stats"], responses=REPONSES_LECTEUR)
|
||||
api_router.include_router(
|
||||
readings.router, prefix="/readings", tags=["readings"], responses=REPONSES_LECTEUR
|
||||
)
|
||||
api_router.include_router(
|
||||
sensors.router, prefix="/sensors", tags=["sensors"], responses=REPONSES_ADMIN
|
||||
)
|
||||
|
||||
@@ -0,0 +1,621 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import asyncio
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any, cast
|
||||
|
||||
import pandas as pd
|
||||
from sqlalchemy import text
|
||||
from sqlalchemy.ext.asyncio import AsyncConnection, create_async_engine
|
||||
|
||||
from app.core.config import get_settings
|
||||
|
||||
REQUIRED_COLUMNS = {
|
||||
"timestamp",
|
||||
"site_id",
|
||||
"site_type",
|
||||
"site_name",
|
||||
"consumption_kwh",
|
||||
"consumption_euros",
|
||||
"temperature_celsius",
|
||||
"humidity_percent",
|
||||
"solar_irradiance_wm2",
|
||||
"hour",
|
||||
"day_of_week",
|
||||
"day_name",
|
||||
"month",
|
||||
"is_weekend",
|
||||
"is_working_hours",
|
||||
}
|
||||
|
||||
MEASURE_COLUMNS = [
|
||||
"consumption_kwh",
|
||||
"consumption_euros",
|
||||
"temperature_celsius",
|
||||
"humidity_percent",
|
||||
"solar_irradiance_wm2",
|
||||
]
|
||||
|
||||
SOURCE_NAME = "csv"
|
||||
|
||||
|
||||
def compute_sha256(path: Path) -> str:
|
||||
"""Calcule l'empreinte SHA-256 du fichier source."""
|
||||
sha256 = hashlib.sha256()
|
||||
|
||||
with path.open("rb") as source:
|
||||
for block in iter(lambda: source.read(1024 * 1024), b""):
|
||||
sha256.update(block)
|
||||
|
||||
return sha256.hexdigest()
|
||||
|
||||
|
||||
def load_metadata(path: Path) -> dict[str, Any]:
|
||||
"""Charge les métadonnées fournies avec le dataset."""
|
||||
with path.open("r", encoding="utf-8") as source:
|
||||
metadata = json.load(source)
|
||||
|
||||
if not isinstance(metadata, dict):
|
||||
raise ValueError("Le fichier de métadonnées doit contenir un objet JSON.")
|
||||
|
||||
return cast(dict[str, Any], metadata)
|
||||
|
||||
|
||||
def classify_quality(
|
||||
row: dict[str, Any],
|
||||
) -> tuple[str, list[str]]:
|
||||
"""
|
||||
Déduit une qualité technique à partir des champs manquants.
|
||||
|
||||
Les valeurs NULL sont conservées. On ne cherche pas ici à
|
||||
déterminer la cause physique exacte de leur absence.
|
||||
"""
|
||||
missing = [column for column in MEASURE_COLUMNS if pd.isna(row.get(column))]
|
||||
|
||||
if not missing:
|
||||
quality = "good"
|
||||
elif len(missing) == len(MEASURE_COLUMNS):
|
||||
quality = "critical"
|
||||
elif "consumption_kwh" in missing:
|
||||
quality = "degraded"
|
||||
else:
|
||||
quality = "partial"
|
||||
|
||||
reasons = [f"missing:{column}" for column in missing]
|
||||
|
||||
return quality, reasons
|
||||
|
||||
|
||||
def validate_source(
|
||||
frame: pd.DataFrame,
|
||||
metadata: dict[str, Any],
|
||||
) -> None:
|
||||
"""Valide le dataset avant tout chargement en base."""
|
||||
missing_columns = REQUIRED_COLUMNS.difference(frame.columns)
|
||||
|
||||
if missing_columns:
|
||||
raise ValueError(f"Colonnes obligatoires absentes : {sorted(missing_columns)}")
|
||||
|
||||
expected_records = int(metadata["total_records"])
|
||||
|
||||
if len(frame) != expected_records:
|
||||
raise ValueError(f"Nombre de lignes inattendu : {len(frame)} au lieu de {expected_records}")
|
||||
|
||||
expected_sites = set(metadata["sites"].keys())
|
||||
actual_sites = set(frame["site_id"].unique())
|
||||
|
||||
if actual_sites != expected_sites:
|
||||
raise ValueError(
|
||||
f"Sites incohérents. Attendus={sorted(expected_sites)}, trouvés={sorted(actual_sites)}"
|
||||
)
|
||||
|
||||
duplicated = frame.duplicated(subset=["site_id", "timestamp"]).sum()
|
||||
|
||||
if duplicated:
|
||||
raise ValueError(f"{duplicated} doublons (site_id, timestamp) détectés")
|
||||
|
||||
static_variants = frame.groupby("site_id")[["site_type", "site_name"]].nunique()
|
||||
|
||||
if (static_variants > 1).any().any():
|
||||
raise ValueError("Un site possède plusieurs valeurs de site_type ou site_name.")
|
||||
|
||||
# Vérifie également que tous les timestamps
|
||||
# peuvent être interprétés correctement.
|
||||
pd.to_datetime(
|
||||
frame["timestamp"],
|
||||
errors="raise",
|
||||
)
|
||||
|
||||
|
||||
def normalize_timestamps(
|
||||
frame: pd.DataFrame,
|
||||
source_timezone: str,
|
||||
) -> pd.DataFrame:
|
||||
"""
|
||||
Normalise les timestamps et leur associe une timezone.
|
||||
|
||||
Les timestamps originaux sont conservés dans une colonne
|
||||
temporaire afin de pouvoir les stocker dans raw_data.
|
||||
"""
|
||||
normalized = frame.copy()
|
||||
|
||||
normalized["_source_timestamp"] = normalized["timestamp"]
|
||||
|
||||
timestamps = pd.to_datetime(
|
||||
normalized["timestamp"],
|
||||
errors="raise",
|
||||
)
|
||||
|
||||
if timestamps.dt.tz is None:
|
||||
timestamps = timestamps.dt.tz_localize(source_timezone)
|
||||
else:
|
||||
timestamps = timestamps.dt.tz_convert(source_timezone)
|
||||
|
||||
normalized["timestamp"] = timestamps
|
||||
|
||||
return normalized
|
||||
|
||||
|
||||
def to_json_value(value: Any) -> Any:
|
||||
"""
|
||||
Convertit une valeur Pandas/Numpy en valeur
|
||||
compatible JSON.
|
||||
"""
|
||||
if value is None:
|
||||
return None
|
||||
|
||||
try:
|
||||
if pd.isna(value):
|
||||
return None
|
||||
except TypeError, ValueError:
|
||||
pass
|
||||
|
||||
if isinstance(value, pd.Timestamp):
|
||||
return value.isoformat()
|
||||
|
||||
if hasattr(value, "item"):
|
||||
return value.item()
|
||||
|
||||
return value
|
||||
|
||||
|
||||
async def ensure_dataset(
|
||||
connection: AsyncConnection,
|
||||
metadata: dict[str, Any],
|
||||
sha256: str,
|
||||
source_timezone: str,
|
||||
storage_uri: str,
|
||||
) -> int:
|
||||
"""
|
||||
Crée l'entrée dataset si elle n'existe pas.
|
||||
|
||||
Le SHA-256 permet de reconnaître un fichier déjà importé
|
||||
et participe à l'idempotence et à la traçabilité.
|
||||
"""
|
||||
result = await connection.execute(
|
||||
text(
|
||||
"""
|
||||
SELECT dataset_id
|
||||
FROM dataset
|
||||
WHERE archive_sha256 = :sha256
|
||||
LIMIT 1
|
||||
"""
|
||||
),
|
||||
{
|
||||
"sha256": sha256,
|
||||
},
|
||||
)
|
||||
|
||||
existing = result.scalar_one_or_none()
|
||||
|
||||
if existing is not None:
|
||||
return int(existing)
|
||||
|
||||
metadata_summary = {
|
||||
"generator_version": metadata.get("generator_version"),
|
||||
"total_sites": metadata.get("total_sites"),
|
||||
"total_records": metadata.get("total_records"),
|
||||
"date_range": metadata.get("date_range"),
|
||||
"frequency": metadata.get("frequency"),
|
||||
"null_injection_enabled": metadata.get("null_injection_enabled"),
|
||||
"null_strategies": metadata.get("null_strategies"),
|
||||
"importer": "historical_import_v1",
|
||||
}
|
||||
|
||||
result = await connection.execute(
|
||||
text(
|
||||
"""
|
||||
INSERT INTO dataset (
|
||||
dataset_name,
|
||||
archive_sha256,
|
||||
storage_uri,
|
||||
source_timezone,
|
||||
"metadata"
|
||||
)
|
||||
VALUES (
|
||||
:dataset_name,
|
||||
:archive_sha256,
|
||||
:storage_uri,
|
||||
:source_timezone,
|
||||
CAST(:metadata AS jsonb)
|
||||
)
|
||||
RETURNING dataset_id
|
||||
"""
|
||||
),
|
||||
{
|
||||
"dataset_name": ("EnerVision historical dataset 2023-2024"),
|
||||
"archive_sha256": sha256,
|
||||
"storage_uri": storage_uri,
|
||||
"source_timezone": source_timezone,
|
||||
"metadata": json.dumps(
|
||||
metadata_summary,
|
||||
ensure_ascii=False,
|
||||
),
|
||||
},
|
||||
)
|
||||
|
||||
return int(result.scalar_one())
|
||||
|
||||
|
||||
async def upsert_sites(
|
||||
connection: AsyncConnection,
|
||||
frame: pd.DataFrame,
|
||||
) -> None:
|
||||
"""Insère ou met à jour les sites du dataset."""
|
||||
sites = cast(
|
||||
list[dict[str, Any]],
|
||||
frame[
|
||||
[
|
||||
"site_id",
|
||||
"site_type",
|
||||
"site_name",
|
||||
]
|
||||
]
|
||||
.drop_duplicates(subset=["site_id"])
|
||||
.to_dict(orient="records"),
|
||||
)
|
||||
|
||||
await connection.execute(
|
||||
text(
|
||||
"""
|
||||
INSERT INTO site (
|
||||
site_id,
|
||||
site_type,
|
||||
site_name
|
||||
)
|
||||
VALUES (
|
||||
:site_id,
|
||||
:site_type,
|
||||
:site_name
|
||||
)
|
||||
ON CONFLICT (site_id)
|
||||
DO UPDATE SET
|
||||
site_type = EXCLUDED.site_type,
|
||||
site_name = EXCLUDED.site_name
|
||||
"""
|
||||
),
|
||||
sites,
|
||||
)
|
||||
|
||||
|
||||
def build_reading_batch(
|
||||
chunk: pd.DataFrame,
|
||||
dataset_id: int,
|
||||
) -> list[dict[str, Any]]:
|
||||
"""
|
||||
Transforme un chunk Pandas en lignes prêtes
|
||||
à être chargées dans la table reading.
|
||||
"""
|
||||
rows: list[dict[str, Any]] = []
|
||||
|
||||
records = cast(
|
||||
list[dict[str, Any]],
|
||||
chunk.to_dict(orient="records"),
|
||||
)
|
||||
|
||||
for record in records:
|
||||
quality, reasons = classify_quality(record)
|
||||
|
||||
raw_data = {
|
||||
column: to_json_value(value)
|
||||
for column, value in record.items()
|
||||
if column != "_source_timestamp"
|
||||
}
|
||||
|
||||
# Dans raw_data, on conserve le timestamp
|
||||
# exactement tel qu'il était dans le CSV.
|
||||
raw_data["timestamp"] = to_json_value(record["_source_timestamp"])
|
||||
|
||||
rows.append(
|
||||
{
|
||||
"site_id": record["site_id"],
|
||||
"timestamp": record["timestamp"],
|
||||
"source": SOURCE_NAME,
|
||||
"dataset_id": dataset_id,
|
||||
# Non fourni par le dataset historique.
|
||||
"consumption_kw": None,
|
||||
"consumption_kwh": to_json_value(record["consumption_kwh"]),
|
||||
"consumption_euros": to_json_value(record["consumption_euros"]),
|
||||
# Non fournis par le CSV historique.
|
||||
"voltage_v": None,
|
||||
"current_a": None,
|
||||
"power_factor": None,
|
||||
"temperature_celsius": (to_json_value(record["temperature_celsius"])),
|
||||
"humidity_percent": (to_json_value(record["humidity_percent"])),
|
||||
"solar_irradiance_wm2": (to_json_value(record["solar_irradiance_wm2"])),
|
||||
"is_working_hours": bool(record["is_working_hours"]),
|
||||
"data_quality": quality,
|
||||
"null_reasons": reasons,
|
||||
# Aucune imputation pendant l'ingestion RAW.
|
||||
# Les valeurs manquantes sont conservées telles quelles
|
||||
# afin de préserver la donnée source.
|
||||
"imputed_values": None,
|
||||
"imputation_method": None,
|
||||
# Conservation de la donnée source
|
||||
# pour la traçabilité.
|
||||
"raw_data": json.dumps(
|
||||
raw_data,
|
||||
ensure_ascii=False,
|
||||
),
|
||||
}
|
||||
)
|
||||
|
||||
return rows
|
||||
|
||||
|
||||
READING_INSERT = text(
|
||||
"""
|
||||
INSERT INTO reading (
|
||||
site_id,
|
||||
timestamp,
|
||||
source,
|
||||
dataset_id,
|
||||
consumption_kw,
|
||||
consumption_kwh,
|
||||
consumption_euros,
|
||||
voltage_v,
|
||||
current_a,
|
||||
power_factor,
|
||||
temperature_celsius,
|
||||
humidity_percent,
|
||||
solar_irradiance_wm2,
|
||||
is_working_hours,
|
||||
data_quality,
|
||||
null_reasons,
|
||||
imputed_values,
|
||||
imputation_method,
|
||||
raw_data
|
||||
)
|
||||
VALUES (
|
||||
:site_id,
|
||||
:timestamp,
|
||||
:source,
|
||||
:dataset_id,
|
||||
:consumption_kw,
|
||||
:consumption_kwh,
|
||||
:consumption_euros,
|
||||
:voltage_v,
|
||||
:current_a,
|
||||
:power_factor,
|
||||
:temperature_celsius,
|
||||
:humidity_percent,
|
||||
:solar_irradiance_wm2,
|
||||
:is_working_hours,
|
||||
:data_quality,
|
||||
:null_reasons,
|
||||
CAST(:imputed_values AS jsonb),
|
||||
:imputation_method,
|
||||
CAST(:raw_data AS jsonb)
|
||||
)
|
||||
ON CONFLICT DO NOTHING
|
||||
"""
|
||||
)
|
||||
|
||||
|
||||
async def import_historical(
|
||||
csv_path: Path,
|
||||
metadata_path: Path,
|
||||
source_timezone: str,
|
||||
batch_size: int,
|
||||
dry_run: bool,
|
||||
storage_uri: str,
|
||||
) -> None:
|
||||
"""
|
||||
Exécute le pipeline ETL historique EnerVision.
|
||||
|
||||
Étapes :
|
||||
1. Extract
|
||||
2. Validate
|
||||
3. Transform
|
||||
4. Load
|
||||
"""
|
||||
metadata = load_metadata(metadata_path)
|
||||
|
||||
frame = pd.read_csv(csv_path)
|
||||
|
||||
validate_source(
|
||||
frame,
|
||||
metadata,
|
||||
)
|
||||
|
||||
print(f"Lignes : {len(frame)}")
|
||||
print(f"Sites : {frame['site_id'].nunique()}")
|
||||
print(f"Période : {frame['timestamp'].min()} -> {frame['timestamp'].max()}")
|
||||
print(f"Doublons : {frame.duplicated(['site_id', 'timestamp']).sum()}")
|
||||
|
||||
print("\nValeurs NULL :")
|
||||
print(frame[MEASURE_COLUMNS].isna().sum())
|
||||
|
||||
sha256 = compute_sha256(csv_path)
|
||||
|
||||
print(f"\nSHA-256 : {sha256}")
|
||||
|
||||
if dry_run:
|
||||
print("\nDry-run terminé : aucune donnée écrite.")
|
||||
return
|
||||
|
||||
normalized = normalize_timestamps(
|
||||
frame,
|
||||
source_timezone,
|
||||
)
|
||||
|
||||
settings = get_settings()
|
||||
|
||||
engine = create_async_engine(
|
||||
str(settings.database_url),
|
||||
pool_pre_ping=True,
|
||||
)
|
||||
|
||||
try:
|
||||
async with engine.begin() as connection:
|
||||
dataset_id = await ensure_dataset(
|
||||
connection=connection,
|
||||
metadata=metadata,
|
||||
sha256=sha256,
|
||||
source_timezone=source_timezone,
|
||||
storage_uri=storage_uri,
|
||||
)
|
||||
|
||||
await upsert_sites(
|
||||
connection,
|
||||
normalized,
|
||||
)
|
||||
|
||||
result = await connection.execute(
|
||||
text(
|
||||
"""
|
||||
SELECT COUNT(*)
|
||||
FROM reading
|
||||
WHERE dataset_id = :dataset_id
|
||||
AND source = :source
|
||||
"""
|
||||
),
|
||||
{
|
||||
"dataset_id": dataset_id,
|
||||
"source": SOURCE_NAME,
|
||||
},
|
||||
)
|
||||
|
||||
before = int(result.scalar_one())
|
||||
|
||||
for start in range(
|
||||
0,
|
||||
len(normalized),
|
||||
batch_size,
|
||||
):
|
||||
chunk = normalized.iloc[start : start + batch_size]
|
||||
|
||||
rows = build_reading_batch(
|
||||
chunk,
|
||||
dataset_id,
|
||||
)
|
||||
|
||||
await connection.execute(
|
||||
READING_INSERT,
|
||||
rows,
|
||||
)
|
||||
|
||||
loaded = min(
|
||||
start + batch_size,
|
||||
len(normalized),
|
||||
)
|
||||
|
||||
print(f"Chargement : {loaded}/{len(normalized)}")
|
||||
|
||||
result = await connection.execute(
|
||||
text(
|
||||
"""
|
||||
SELECT COUNT(*)
|
||||
FROM reading
|
||||
WHERE dataset_id = :dataset_id
|
||||
AND source = :source
|
||||
"""
|
||||
),
|
||||
{
|
||||
"dataset_id": dataset_id,
|
||||
"source": SOURCE_NAME,
|
||||
},
|
||||
)
|
||||
|
||||
after = int(result.scalar_one())
|
||||
|
||||
print("\nImport terminé.")
|
||||
print(f"dataset_id : {dataset_id}")
|
||||
print(f"lectures avant : {before}")
|
||||
print(f"lectures après : {after}")
|
||||
print(f"nouvelles lectures : {after - before}")
|
||||
|
||||
finally:
|
||||
await engine.dispose()
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
"""Définit les arguments CLI de l'import."""
|
||||
parser = argparse.ArgumentParser(description=("Import historique EnerVision"))
|
||||
|
||||
parser.add_argument(
|
||||
"--csv",
|
||||
type=Path,
|
||||
required=True,
|
||||
help="Chemin vers le CSV historique.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--metadata",
|
||||
type=Path,
|
||||
required=True,
|
||||
help=("Chemin vers le fichier dataset_metadata.json."),
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--source-timezone",
|
||||
default="UTC",
|
||||
help=("Timezone associée aux timestamps du dataset. Défaut : UTC."),
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--batch-size",
|
||||
type=int,
|
||||
default=1000,
|
||||
help=("Nombre de lignes insérées par batch. Défaut : 1000."),
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--dry-run",
|
||||
action="store_true",
|
||||
help=("Valide les données sans écrire en base."),
|
||||
)
|
||||
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main() -> None:
|
||||
"""Point d'entrée CLI du pipeline."""
|
||||
args = parse_args()
|
||||
|
||||
if args.batch_size <= 0:
|
||||
raise ValueError("--batch-size doit être strictement supérieur à 0.")
|
||||
|
||||
# resolve() est volontairement exécuté ici,
|
||||
# dans la partie synchrone du programme.
|
||||
# Cela évite une opération filesystem bloquante
|
||||
# à l'intérieur d'une fonction async.
|
||||
storage_uri = args.csv.resolve().as_uri()
|
||||
|
||||
asyncio.run(
|
||||
import_historical(
|
||||
csv_path=args.csv,
|
||||
metadata_path=args.metadata,
|
||||
source_timezone=(args.source_timezone),
|
||||
batch_size=args.batch_size,
|
||||
dry_run=args.dry_run,
|
||||
storage_uri=storage_uri,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,4 +1,5 @@
|
||||
from collections.abc import Sequence
|
||||
from datetime import datetime
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
@@ -19,3 +20,23 @@ class ReadingRepository:
|
||||
.order_by(Reading.site_id, Reading.timestamp.desc())
|
||||
)
|
||||
return (await self._session.execute(requete)).scalars().all()
|
||||
|
||||
async def list_history(
|
||||
self,
|
||||
*,
|
||||
start: datetime,
|
||||
end: datetime,
|
||||
site_id: str | None = None,
|
||||
limit: int,
|
||||
offset: int,
|
||||
) -> Sequence[Reading]:
|
||||
requete = (
|
||||
select(Reading)
|
||||
.where(Reading.timestamp >= start, Reading.timestamp < end)
|
||||
.order_by(Reading.timestamp.desc(), Reading.reading_id.desc())
|
||||
.limit(limit)
|
||||
.offset(offset)
|
||||
)
|
||||
if site_id is not None:
|
||||
requete = requete.where(Reading.site_id == site_id)
|
||||
return (await self._session.scalars(requete)).all()
|
||||
|
||||
@@ -0,0 +1,45 @@
|
||||
from datetime import datetime
|
||||
from decimal import Decimal
|
||||
from enum import StrEnum
|
||||
from typing import Any
|
||||
|
||||
from pydantic import BaseModel, ConfigDict
|
||||
|
||||
|
||||
class ReadingSource(StrEnum):
|
||||
CSV = "csv"
|
||||
API_CURRENT = "api_current"
|
||||
API_HISTORY = "api_history"
|
||||
|
||||
|
||||
class ReadingDataQuality(StrEnum):
|
||||
GOOD = "good"
|
||||
PARTIAL = "partial"
|
||||
DEGRADED = "degraded"
|
||||
CRITICAL = "critical"
|
||||
|
||||
|
||||
class ReadingResponse(BaseModel):
|
||||
model_config = ConfigDict(from_attributes=True)
|
||||
|
||||
reading_id: int
|
||||
site_id: str
|
||||
timestamp: datetime
|
||||
source: ReadingSource
|
||||
consumption_kw: float | None
|
||||
consumption_kwh: float | None
|
||||
# Piège : `Decimal` (miroir de `Numeric(14, 2)` en base, pour ne pas arrondir un montant)
|
||||
# sérialise en chaîne dans le JSON, pas en nombre — un consommateur qui ferait un `parseFloat`
|
||||
# naïf perdrait la précision que ce choix visait à garder.
|
||||
consumption_euros: Decimal | None
|
||||
voltage_v: float | None
|
||||
current_a: float | None
|
||||
power_factor: float | None
|
||||
temperature_celsius: float | None
|
||||
humidity_percent: float | None
|
||||
solar_irradiance_wm2: float | None
|
||||
is_working_hours: bool | None
|
||||
data_quality: ReadingDataQuality | None
|
||||
null_reasons: list[str] | None
|
||||
imputed_values: dict[str, Any] | None
|
||||
imputation_method: str | None
|
||||
@@ -0,0 +1,59 @@
|
||||
from collections.abc import Sequence
|
||||
from datetime import UTC, datetime, timedelta
|
||||
|
||||
from app.models.energy import Reading
|
||||
from app.repositories.reading import ReadingRepository
|
||||
|
||||
FENETRE_PAR_DEFAUT = timedelta(hours=24)
|
||||
FENETRE_MAXIMALE = timedelta(days=90)
|
||||
|
||||
|
||||
class FenetreInverseeError(Exception):
|
||||
"""`start` est postérieur ou égal à `end`."""
|
||||
|
||||
|
||||
class FenetreTropLargeError(Exception):
|
||||
"""L'écart entre `start` et `end` dépasse `FENETRE_MAXIMALE`."""
|
||||
|
||||
|
||||
class ReadingService:
|
||||
def __init__(self, *, readings: ReadingRepository) -> None:
|
||||
self._readings = readings
|
||||
|
||||
async def list_history(
|
||||
self,
|
||||
*,
|
||||
site_id: str | None = None,
|
||||
start: datetime | None = None,
|
||||
end: datetime | None = None,
|
||||
limit: int,
|
||||
offset: int,
|
||||
) -> Sequence[Reading]:
|
||||
debut, fin = self._resoudre_fenetre(start, end)
|
||||
return await self._readings.list_history(
|
||||
site_id=site_id, start=debut, end=fin, limit=limit, offset=offset
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _resoudre_fenetre(
|
||||
start: datetime | None, end: datetime | None
|
||||
) -> tuple[datetime, datetime]:
|
||||
# Piège : un datetime naïf (sans fuseau dans la chaîne ISO reçue) fait échouer la
|
||||
# comparaison à `reading.timestamp` (`timestamptz`) au niveau du pilote, en 500 plutôt
|
||||
# qu'un refus propre. On le traite comme de l'UTC plutôt que de le rejeter.
|
||||
debut = _vers_utc(start)
|
||||
fin = _vers_utc(end) or datetime.now(UTC)
|
||||
if debut is None:
|
||||
debut = fin - FENETRE_PAR_DEFAUT
|
||||
|
||||
if debut >= fin:
|
||||
raise FenetreInverseeError
|
||||
if fin - debut > FENETRE_MAXIMALE:
|
||||
raise FenetreTropLargeError
|
||||
return debut, fin
|
||||
|
||||
|
||||
def _vers_utc(instant: datetime | None) -> datetime | None:
|
||||
if instant is None:
|
||||
return None
|
||||
return instant if instant.tzinfo is not None else instant.replace(tzinfo=UTC)
|
||||
Reference in New Issue
Block a user