fix(etl): traite les retours de revue du DAG historique

docs(architecture,ml): vue CI/CD, ML-START.md et SAST Bandit

.github/workflows/airflow.yml

@@ -91,11 +91,12 @@ jobs:
           bash -c "cd /opt/ml && env -u VIRTUAL_ENV uv run --no-sync python -m enervision_ml.train --help"
 
       # `--help` sort par argparse avant `get_settings()` : ni base ni secret requis, et
-      # l'import du module prouve que l'environnement /opt/backend est complet. Les deux
-      # commandes du DAG `alertes` sont couvertes, `app.cli` tirant tout FastAPI derrière lui.
-      - name: Vérifie que les deux commandes du DAG alertes s'importent sans réseau
+      # l'import des modules prouve que l'environnement /opt/backend est complet.
+      # Les deux commandes du DAG `alertes` et la commande du DAG historique sont couvertes.
+      - name: Vérifie que les trois commandes backend s'importent sans réseau
         run: >
           docker run --rm --network none enervision-airflow:ci
           bash -c "cd /opt/backend
           && env -u VIRTUAL_ENV uv run --no-sync python -m app.detection.internal_alerts --help
-          && env -u VIRTUAL_ENV uv run --no-sync python -m app.cli generate-recommendations --help"
+          && env -u VIRTUAL_ENV uv run --no-sync python -m app.cli generate-recommendations --help
+          && env -u VIRTUAL_ENV uv run --no-sync python -m app.etl.historical_import --help"

.github/workflows/sonarqube.yml

@@ -5,11 +5,15 @@ on:
     paths:
       - "apps/frontend/**"
       - "apps/backend/**"
+      - "ml/**"
+      - "etl/airflow/**"
       - ".github/workflows/sonarqube.yml"
   pull_request:
     paths:
       - "apps/frontend/**"
       - "apps/backend/**"
+      - "ml/**"
+      - "etl/airflow/**"
       - ".github/workflows/sonarqube.yml"
 
 
@@ -108,8 +112,36 @@ jobs:
           name: backend-coverage
           path: apps/backend/coverage.xml
 
+  test-ml:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+      - name: Installe uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+          cache-dependency-glob: ml/uv.lock
+
+      - name: Installe l'interpréteur déclaré par .python-version
+        run: uv python install
+        working-directory: ml
+
+      - name: Synchronise les dépendances sans dévier du verrou
+        run: uv sync --all-groups --frozen
+        working-directory: ml
+
+      - name: Lancement des tests et génération du rapport de couverture (ML)
+        run: uv run pytest --cov-report=xml
+        working-directory: ml
+
+      - name: Upload coverage
+        uses: actions/upload-artifact@v4
+        with:
+          name: ml-coverage
+          path: ml/coverage.xml
+
   sonarqube:
-    needs: [build-front, build-back, test-front, test-back]
+    needs: [build-front, build-back, test-front, test-back, test-ml]
     name: SonarQube
     runs-on: ubuntu-latest
     steps:
@@ -126,6 +158,11 @@ jobs:
         with:
           name: backend-coverage
           path: apps/backend
+      - name: Téléchargement du rapport de couverture (ML)
+        uses: actions/download-artifact@v4
+        with:
+          name: ml-coverage
+          path: ml
       - name: SonarQube Scan
         uses: SonarSource/sonarqube-scan-action@v8
         env:

README.md

@@ -21,7 +21,7 @@ Ce que la documentation apporte à chacun : [docs/architecture/00-vue-ensemble.m
 | Backend    | FastAPI, Python 3.14                | `apps/backend`      | Initialise    |
 | Frontend   | Angular 22, Node 24 LTS             | `apps/frontend`     | Tableau de bord |
 | Base       | PostgreSQL 17 + TimescaleDB         | `db`                | Initialise    |
-| ETL        | Apache Airflow                      | `etl/airflow`       | Trois DAGs    |
+| ETL        | Apache Airflow                      | `etl/airflow`       | Quatre DAGs   |
 | Infra      | Terraform (k3s single-node)         | `infra/terraform`   | Initialise    |
 | Reverse proxy | Nginx, TLS                       | `infra/proxy`       | En place      |
 | CI/CD      | GitHub Actions                      | `.github/workflows` | Backend en place |
@@ -48,7 +48,7 @@ L'etat detaille de chaque brique et les vues d'architecture sont dans
 │   ├── migrations/     Migrations SQL versionnees
 │   └── seeds/          Jeux de donnees de reference
 ├── etl/airflow/
-│   ├── dags/           DAGs d'orchestration (pipeline ML, alertes)
+│   ├── dags/           DAGs d'orchestration (pipeline ML, alertes, import historique)
 │   ├── plugins/        Operateurs et hooks maison
 │   ├── include/        Requetes SQL et ressources des DAGs
 │   └── tests/          Tests d'integrite des DAGs

apps/backend/Dockerfile

@@ -11,13 +11,14 @@ WORKDIR /app
 RUN --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,source=uv.lock,target=uv.lock \
     --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
-    uv sync --locked --no-install-project --no-dev
+    uv sync --locked --no-install-project --no-dev --no-build
 
+# Le projet lui-meme n'est pas installe (pas de second `uv sync`) : il tourne depuis /app, le
+# repertoire de travail, et rien ne lit ses metadonnees. L'installer imposerait de le construire
+# (backend hatchling), donc de retirer `--no-build` de l'etape ci-dessus, qui garantit que
+# l'installation des dependances n'execute aucun script de build (regle Sonar docker:S8541).
 COPY . /app
 
-RUN --mount=type=cache,target=/root/.cache/uv \
-    uv sync --locked --no-dev
-
 
 FROM python:3.14-slim AS runtime
 

apps/backend/tests/db/test_data_schema.py

@@ -112,8 +112,10 @@ async def test_duplicate_reading_is_rejected_when_key_matches(
     )
     await data_connection.execute(statement)
 
+    savepoint = data_connection.begin_nested()
+
     with pytest.raises(IntegrityError):
-        async with data_connection.begin_nested():
+        async with savepoint:
             await data_connection.execute(statement)
 
 
@@ -147,9 +149,12 @@ async def test_invalid_reading_is_rejected_when_constraints_fail(
     }
     values.update(changes)
 
+    statement = insert(Reading).values(**values)
+    savepoint = data_connection.begin_nested()
+
     with pytest.raises(IntegrityError):
-        async with data_connection.begin_nested():
-            await data_connection.execute(insert(Reading).values(**values))
+        async with savepoint:
+            await data_connection.execute(statement)
 
 
 async def test_prediction_requires_period_when_energy_is_predicted(
@@ -164,8 +169,10 @@ async def test_prediction_requires_period_when_energy_is_predicted(
         model_reference="test-model/1",
     )
 
+    savepoint = data_connection.begin_nested()
+
     with pytest.raises(IntegrityError):
-        async with data_connection.begin_nested():
+        async with savepoint:
             await data_connection.execute(statement)
 
 
@@ -212,21 +219,22 @@ async def test_alert_rejects_prediction_when_site_differs(
         )
     ).scalar_one()
 
+    statement = insert(Alert).values(
+        source_alert_id=str(uuid4()),
+        site_id=other_site,
+        source="enervision",
+        timestamp=MOMENT,
+        type="spike",
+        severity="high",
+        message="Test",
+        prediction_id=prediction_id,
+        raw_data={},
+    )
+    savepoint = data_connection.begin_nested()
+
     with pytest.raises(IntegrityError):
-        async with data_connection.begin_nested():
-            await data_connection.execute(
-                insert(Alert).values(
-                    source_alert_id=str(uuid4()),
-                    site_id=other_site,
-                    source="enervision",
-                    timestamp=MOMENT,
-                    type="spike",
-                    severity="high",
-                    message="Test",
-                    prediction_id=prediction_id,
-                    raw_data={},
-                )
-            )
+        async with savepoint:
+            await data_connection.execute(statement)
 
 
 async def test_recommendation_is_unique_when_alert_and_rule_match(
@@ -256,6 +264,8 @@ async def test_recommendation_is_unique_when_alert_and_rule_match(
     )
     await data_connection.execute(statement)
 
+    savepoint = data_connection.begin_nested()
+
     with pytest.raises(IntegrityError):
-        async with data_connection.begin_nested():
+        async with savepoint:
             await data_connection.execute(statement)

apps/backend/tests/etl/test_historical_import.py

@@ -1,239 +1,245 @@
-import hashlib
-import json
-
-import pandas as pd
-import pytest
-
-from app.etl.historical_import import (
-    SOURCE_NAME,
-    build_reading_batch,
-    classify_quality,
-    compute_sha256,
-    load_metadata,
-    normalize_timestamps,
-    validate_source,
-)
-
-
-def make_metadata() -> dict:
-    return {
-        "total_records": 2,
-        "sites": {
-            "SITE001": {},
-        },
-    }
-
-
-def make_dataframe() -> pd.DataFrame:
-    return pd.DataFrame(
-        [
-            {
-                "timestamp": "2023-01-01 00:00:00",
-                "site_id": "SITE001",
-                "site_type": "office",
-                "site_name": "Site 1",
-                "consumption_kwh": 10.5,
-                "consumption_euros": 2.5,
-                "temperature_celsius": 20.0,
-                "humidity_percent": 50.0,
-                "solar_irradiance_wm2": 0.0,
-                "hour": 0,
-                "day_of_week": 6,
-                "day_name": "Sunday",
-                "month": 1,
-                "is_weekend": True,
-                "is_working_hours": False,
-            },
-            {
-                "timestamp": "2023-01-01 01:00:00",
-                "site_id": "SITE001",
-                "site_type": "office",
-                "site_name": "Site 1",
-                "consumption_kwh": 11.0,
-                "consumption_euros": 2.7,
-                "temperature_celsius": 19.5,
-                "humidity_percent": 52.0,
-                "solar_irradiance_wm2": 0.0,
-                "hour": 1,
-                "day_of_week": 6,
-                "day_name": "Sunday",
-                "month": 1,
-                "is_weekend": True,
-                "is_working_hours": False,
-            },
-        ]
-    )
-
-
-def test_compute_sha256(tmp_path):
-    file_path = tmp_path / "dataset.csv"
-    content = b"hello-enervision"
-
-    file_path.write_bytes(content)
-
-    expected = hashlib.sha256(content).hexdigest()
-
-    assert compute_sha256(file_path) == expected
-
-
-def test_load_metadata(tmp_path):
-    metadata_path = tmp_path / "metadata.json"
-
-    metadata = {
-        "total_records": 2,
-        "sites": {
-            "SITE001": {},
-        },
-    }
-
-    metadata_path.write_text(
-        json.dumps(metadata),
-        encoding="utf-8",
-    )
-
-    assert load_metadata(metadata_path) == metadata
-
-
-def test_validate_source_accepts_valid_dataset():
-    frame = make_dataframe()
-
-    validate_source(
-        frame,
-        make_metadata(),
-    )
-
-
-def test_validate_source_rejects_missing_column():
-    frame = make_dataframe().drop(columns=["consumption_kwh"])
-
-    with pytest.raises(
-        ValueError,
-        match="Colonnes obligatoires absentes",
-    ):
-        validate_source(
-            frame,
-            make_metadata(),
-        )
-
-
-def test_validate_source_rejects_duplicates():
-    frame = make_dataframe()
-
-    frame.loc[1, "timestamp"] = frame.loc[
-        0,
-        "timestamp",
-    ]
-
-    with pytest.raises(
-        ValueError,
-        match="doublons",
-    ):
-        validate_source(
-            frame,
-            make_metadata(),
-        )
-
-
-def test_validate_source_rejects_unknown_site():
-    frame = make_dataframe()
-
-    frame.loc[1, "site_id"] = "SITE999"
-
-    with pytest.raises(
-        ValueError,
-        match="Sites incohérents",
-    ):
-        validate_source(
-            frame,
-            make_metadata(),
-        )
-
-
-def test_normalize_timestamps_adds_timezone():
-    frame = make_dataframe()
-
-    normalized = normalize_timestamps(
-        frame,
-        "UTC",
-    )
-
-    assert normalized["timestamp"].dt.tz is not None
-
-    assert "_source_timestamp" in normalized.columns
-
-
-def test_classify_quality_good():
-    row = make_dataframe().iloc[0].to_dict()
-
-    quality, reasons = classify_quality(row)
-
-    assert quality == "good"
-    assert reasons == []
-
-
-def test_classify_quality_degraded_when_consumption_missing():
-    row = make_dataframe().iloc[0].to_dict()
-    row["consumption_kwh"] = None
-
-    quality, reasons = classify_quality(row)
-
-    assert quality == "degraded"
-
-    assert "missing:consumption_kwh" in reasons
-
-
-def test_build_reading_batch_respects_database_contract():
-    frame = normalize_timestamps(
-        make_dataframe(),
-        "UTC",
-    )
-
-    rows = build_reading_batch(
-        frame.iloc[:1],
-        dataset_id=3,
-    )
-
-    assert len(rows) == 1
-
-    row = rows[0]
-
-    assert row["dataset_id"] == 3
-
-    # Important :
-    # contrainte ck_reading_dataset_source.
-    assert row["source"] == "csv"
-    assert SOURCE_NAME == "csv"
-
-    # Important :
-    # contrainte ck_reading_imputation.
-    assert row["imputed_values"] is None
-    assert row["imputation_method"] is None
-
-    assert row["data_quality"] == "good"
-    assert row["null_reasons"] == []
-
-
-def test_build_reading_batch_keeps_missing_values():
-    frame = make_dataframe()
-
-    frame.loc[0, "temperature_celsius"] = None
-
-    frame = normalize_timestamps(
-        frame,
-        "UTC",
-    )
-
-    rows = build_reading_batch(
-        frame.iloc[:1],
-        dataset_id=3,
-    )
-
-    row = rows[0]
-
-    assert row["temperature_celsius"] is None
-
-    assert "missing:temperature_celsius" in row["null_reasons"]
-
-    # RAW ingestion : aucune imputation.
-    assert row["imputed_values"] is None
-    assert row["imputation_method"] is None
+import hashlib
+import json
+
+import pandas as pd
+import pytest
+
+from app.etl.historical_import import (
+    SOURCE_NAME,
+    build_reading_batch,
+    classify_quality,
+    compute_sha256,
+    load_metadata,
+    normalize_timestamps,
+    validate_source,
+)
+
+
+def make_metadata() -> dict:
+    return {
+        "total_records": 2,
+        "sites": {
+            "SITE001": {},
+        },
+    }
+
+
+def make_dataframe() -> pd.DataFrame:
+    return pd.DataFrame(
+        [
+            {
+                "timestamp": "2023-01-01 00:00:00",
+                "site_id": "SITE001",
+                "site_type": "office",
+                "site_name": "Site 1",
+                "consumption_kwh": 10.5,
+                "consumption_euros": 2.5,
+                "temperature_celsius": 20.0,
+                "humidity_percent": 50.0,
+                "solar_irradiance_wm2": 0.0,
+                "hour": 0,
+                "day_of_week": 6,
+                "day_name": "Sunday",
+                "month": 1,
+                "is_weekend": True,
+                "is_working_hours": False,
+            },
+            {
+                "timestamp": "2023-01-01 01:00:00",
+                "site_id": "SITE001",
+                "site_type": "office",
+                "site_name": "Site 1",
+                "consumption_kwh": 11.0,
+                "consumption_euros": 2.7,
+                "temperature_celsius": 19.5,
+                "humidity_percent": 52.0,
+                "solar_irradiance_wm2": 0.0,
+                "hour": 1,
+                "day_of_week": 6,
+                "day_name": "Sunday",
+                "month": 1,
+                "is_weekend": True,
+                "is_working_hours": False,
+            },
+        ]
+    )
+
+
+def test_compute_sha256(tmp_path):
+    file_path = tmp_path / "dataset.csv"
+    content = b"hello-enervision"
+
+    file_path.write_bytes(content)
+
+    expected = hashlib.sha256(content).hexdigest()
+
+    assert compute_sha256(file_path) == expected
+
+
+def test_load_metadata(tmp_path):
+    metadata_path = tmp_path / "metadata.json"
+
+    metadata = {
+        "total_records": 2,
+        "sites": {
+            "SITE001": {},
+        },
+    }
+
+    metadata_path.write_text(
+        json.dumps(metadata),
+        encoding="utf-8",
+    )
+
+    assert load_metadata(metadata_path) == metadata
+
+
+def test_validate_source_accepts_valid_dataset():
+    frame = make_dataframe()
+
+    validate_source(
+        frame,
+        make_metadata(),
+    )
+
+
+def test_validate_source_rejects_missing_column():
+    frame = make_dataframe().drop(columns=["consumption_kwh"])
+
+    metadata = make_metadata()
+
+    with pytest.raises(
+        ValueError,
+        match="Colonnes obligatoires absentes",
+    ):
+        validate_source(
+            frame,
+            metadata,
+        )
+
+
+def test_validate_source_rejects_duplicates():
+    frame = make_dataframe()
+
+    frame.loc[1, "timestamp"] = frame.loc[
+        0,
+        "timestamp",
+    ]
+
+    metadata = make_metadata()
+
+    with pytest.raises(
+        ValueError,
+        match="doublons",
+    ):
+        validate_source(
+            frame,
+            metadata,
+        )
+
+
+def test_validate_source_rejects_unknown_site():
+    frame = make_dataframe()
+
+    frame.loc[1, "site_id"] = "SITE999"
+
+    metadata = make_metadata()
+
+    with pytest.raises(
+        ValueError,
+        match="Sites incohérents",
+    ):
+        validate_source(
+            frame,
+            metadata,
+        )
+
+
+def test_normalize_timestamps_adds_timezone():
+    frame = make_dataframe()
+
+    normalized = normalize_timestamps(
+        frame,
+        "UTC",
+    )
+
+    assert normalized["timestamp"].dt.tz is not None
+
+    assert "_source_timestamp" in normalized.columns
+
+
+def test_classify_quality_good():
+    row = make_dataframe().iloc[0].to_dict()
+
+    quality, reasons = classify_quality(row)
+
+    assert quality == "good"
+    assert reasons == []
+
+
+def test_classify_quality_degraded_when_consumption_missing():
+    row = make_dataframe().iloc[0].to_dict()
+    row["consumption_kwh"] = None
+
+    quality, reasons = classify_quality(row)
+
+    assert quality == "degraded"
+
+    assert "missing:consumption_kwh" in reasons
+
+
+def test_build_reading_batch_respects_database_contract():
+    frame = normalize_timestamps(
+        make_dataframe(),
+        "UTC",
+    )
+
+    rows = build_reading_batch(
+        frame.iloc[:1],
+        dataset_id=3,
+    )
+
+    assert len(rows) == 1
+
+    row = rows[0]
+
+    assert row["dataset_id"] == 3
+
+    # Important :
+    # contrainte ck_reading_dataset_source.
+    assert row["source"] == "csv"
+    assert SOURCE_NAME == "csv"
+
+    # Important :
+    # contrainte ck_reading_imputation.
+    assert row["imputed_values"] is None
+    assert row["imputation_method"] is None
+
+    assert row["data_quality"] == "good"
+    assert row["null_reasons"] == []
+
+
+def test_build_reading_batch_keeps_missing_values():
+    frame = make_dataframe()
+
+    frame.loc[0, "temperature_celsius"] = None
+
+    frame = normalize_timestamps(
+        frame,
+        "UTC",
+    )
+
+    rows = build_reading_batch(
+        frame.iloc[:1],
+        dataset_id=3,
+    )
+
+    row = rows[0]
+
+    assert row["temperature_celsius"] is None
+
+    assert "missing:temperature_celsius" in row["null_reasons"]
+
+    # RAW ingestion : aucune imputation.
+    assert row["imputed_values"] is None
+    assert row["imputation_method"] is None

apps/backend/tests/repositories/test_audit_log.py

@@ -49,8 +49,10 @@ async def test_the_database_refuses_to_mutate_the_audit_log(
 ) -> None:
     await une_ligne(session)
 
+    requete = text(instruction)
+
     with pytest.raises(DBAPIError, match="ajout seul"):
-        await session.execute(text(instruction))
+        await session.execute(requete)
     await session.rollback()
 
 

apps/backend/tests/repositories/test_password_reset_token.py

@@ -131,11 +131,14 @@ async def test_the_database_refuses_two_tokens_sharing_a_fingerprint(
         user_agent=None,
     )
 
+    empreinte = fingerprint_refresh(secret)
+    expiration = datetime.now(UTC) + DUREE
+
     with pytest.raises(IntegrityError):
         await depot.create(
             user_id=compte,
-            token_hash=fingerprint_refresh(secret),
-            expires_at=datetime.now(UTC) + DUREE,
+            token_hash=empreinte,
+            expires_at=expiration,
             client_ip=None,
             user_agent=None,
         )

apps/backend/tests/repositories/test_refresh_token.py

@@ -178,12 +178,16 @@ async def test_the_database_refuses_two_tokens_sharing_a_fingerprint(
         user_agent=None,
     )
 
+    famille = uuid.uuid4()
+    empreinte = fingerprint_refresh(secret)
+    expiration = datetime.now(UTC) + DUREE
+
     with pytest.raises(IntegrityError):
         await depot.create(
             user_id=compte,
-            family_id=uuid.uuid4(),
-            token_hash=fingerprint_refresh(secret),
-            expires_at=datetime.now(UTC) + DUREE,
+            family_id=famille,
+            token_hash=empreinte,
+            expires_at=expiration,
             client_ip=None,
             user_agent=None,
         )

apps/backend/tests/repositories/test_user.py

@@ -31,14 +31,12 @@ async def test_the_database_refuses_an_email_written_in_upper_case(
 ) -> None:
     saisie = adresse().upper()
 
+    requete = text(
+        "insert into app_user (email, password_hash, role) values (:e, '$argon2id$x', 'lecteur')"
+    )
+
     with pytest.raises(IntegrityError):
-        await session.execute(
-            text(
-                "insert into app_user (email, password_hash, role) "
-                "values (:e, '$argon2id$x', 'lecteur')"
-            ),
-            {"e": saisie},
-        )
+        await session.execute(requete, {"e": saisie})
     await session.rollback()
 
 

apps/backend/tests/services/test_reading.py

@@ -116,13 +116,11 @@ async def test_list_history_normalizes_naive_datetimes_to_utc() -> None:
 async def test_list_history_raises_when_start_is_after_end() -> None:
     service = ReadingService(readings=FakeRepository([]))
 
+    debut = datetime(2026, 9, 2, tzinfo=UTC)
+    fin = datetime(2026, 9, 1, tzinfo=UTC)
+
     with pytest.raises(FenetreInverseeError):
-        await service.list_history(
-            start=datetime(2026, 9, 2, tzinfo=UTC),
-            end=datetime(2026, 9, 1, tzinfo=UTC),
-            limit=500,
-            offset=0,
-        )
+        await service.list_history(start=debut, end=fin, limit=500, offset=0)
 
 
 async def test_list_history_raises_when_start_equals_end() -> None:

apps/backend/tests/services/test_user.py

@@ -235,5 +235,7 @@ async def test_every_operation_refuses_an_unknown_account(action: str) -> None:
     if action == "set_active":
         arguments["is_active"] = False
 
+    methode = getattr(attirail.service, action)
+
     with pytest.raises(UserNotFoundError):
-        await getattr(attirail.service, action)(**arguments)
+        await methode(**arguments)

apps/backend/tests/test_cli.py

@@ -19,13 +19,17 @@ def test_build_parser_reads_the_create_admin_arguments() -> None:
 
 
 def test_build_parser_requires_a_subcommand() -> None:
+    parser = cli.build_parser()
+
     with pytest.raises(SystemExit):
-        cli.build_parser().parse_args([])
+        parser.parse_args([])
 
 
 def test_build_parser_requires_an_email() -> None:
+    parser = cli.build_parser()
+
     with pytest.raises(SystemExit):
-        cli.build_parser().parse_args(["create-admin"])
+        parser.parse_args(["create-admin"])
 
 
 def test_read_password_generates_a_long_secret_when_asked(

docker-compose.yml

@@ -36,6 +36,7 @@ x-airflow-common: &airflow-common
   volumes:
     - ./etl/airflow/dags:/opt/airflow/dags
     - ./etl/airflow/plugins:/opt/airflow/plugins
+    - ./data/raw:/opt/data/raw:ro
     - airflow_logs:/opt/airflow/logs
     - airflow_ml_state:/opt/ml/state
   restart: unless-stopped

docs/architecture/00-vue-ensemble.md

@@ -70,10 +70,11 @@ Le lien `front -.-> api` reste en pointillé : le frontend appelle bien une API,
 intercepteur répond à sa place tant que les endpoints n'existent pas. Voir
 [30-frontend.md](30-frontend.md).
 
-Le lien `airflow --> db` est maintenant en trait plein : trois DAGs tournent, deux pour
+Le lien `airflow --> db` est maintenant en trait plein : quatre DAGs tournent, deux pour
 l'entraînement et le scoring du modèle ML (issue #115), un pour la détection d'alertes et la
-génération des recommandations (issue #116), cf. plus bas et [20-backend.md](20-backend.md). Le
-reste du périmètre Airflow envisagé (ingestion, issues #15/#16) reste en pointillé, non construit.
+génération des recommandations (issue #116), et `historical_import` pour l'ingestion du dataset
+historique (issue #119). L'orchestration de l'import API Mock et la réconciliation globale des
+deux sources restent à compléter dans l'issue #15.
 
 Le lien `prom -.-> api` de même : l'API expose bien `/metrics` au format Prometheus, mais aucun
 collecteur ne vient le lire.
@@ -88,7 +89,7 @@ collecteur ne vient le lire.
 | ML | LightGBM, MLflow | `ml` | `En cours` | Pipeline d'entraînement et de scoring (`enervision_ml.train`/`.score`, features par lags/moyennes glissantes partagées entre les deux, baseline de persistance saisonnière, suivi MLflow local), exposé en lecture via `GET /predictions`, orchestré par Airflow (`ml_train`/`ml_score`). Voir [ADR 0005](../adr/0005-modele-prediction-lightgbm.md) et [ML-START.md](../ML-START.md). Surveillance de dérive (EC06, #44/#45) pas encore construite |
 | Infra | Docker Compose, Nginx, Terraform, k3s single-node | `infra`, `docker-compose.prod.yml` | `En cours` | Reverse proxy et overlay de déploiement écrits et validés, jamais lancés sur le serveur ([ADR 0007](../adr/0007-terminaison-tls-et-reverse-proxy-nginx.md)). Module d'installation k3s jamais appliqué, aucune ressource Kubernetes déclarée |
 | Monitoring | Prometheus, Grafana, Alertmanager | `monitoring` | `Cible` | Rien, hors le `/metrics` exposé par l'API |
-| ETL | Apache Airflow | `etl/airflow` | `En cours` | Webserver + scheduler (LocalExecutor) tournent via docker-compose, base de métadonnées Postgres dédiée. Trois DAGs en sous-processus `uv run` : `ml_train` manuel et `ml_score` `@hourly` pour le pipeline ML (issue #115), `alertes` à `15 * * * *` pour la détection et les recommandations (issue #116, [ADR 0008](../adr/0008-airflow-execute-le-code-du-backend.md)). L'ingestion (issues #15/#16) n'a pas encore de DAG |
+| ETL | Apache Airflow | `etl/airflow` | `En cours` | Webserver + scheduler (LocalExecutor) tournent via docker-compose, base de métadonnées Postgres dédiée. Quatre DAGs en sous-processus `uv run` : `ml_train`, `ml_score`, `alertes` et `historical_import`. Le DAG historique orchestre `app.etl.historical_import` et charge `dataset`, `site` et `reading`. L'orchestration API Mock reste à compléter dans #15 |
 | CI/CD | GitHub Actions | `.github/workflows` | `En cours` | 5 workflows, 16 jobs : lint, typage, tests avec seuil de couverture bloquant, tests d'intégration sur TimescaleDB réel, audit de dépendances, SAST Bandit, quality gate SonarCloud, intégrité des DAGs Airflow. Détail dans [50-cicd.md](50-cicd.md). **Aucun job de déploiement** (#21) |
 
 ## Flux bout en bout

docs/architecture/10-infra.md

@@ -51,7 +51,7 @@ Trois pièges sont documentés en tête du `docker-compose.yml`, ils ne se devin
 - `LocalExecutor` exécute les tâches comme sous-processus du **scheduler**, jamais du webserver :
   c'est le scheduler qui a besoin du volume `airflow_ml_state` (modèle, magasin MLflow).
 
-### Airflow (issues #115 et #116)
+### Airflow (issues #115, #116 et #119)
 
 Trois services, `docker compose profiles` non utilisés (démarrage explicite via `make
 airflow-up`, pas dans `make dev`) :
@@ -75,6 +75,12 @@ l'[ADR 0008](../adr/0008-airflow-execute-le-code-du-backend.md).
 | `ml_train` | manuelle | `enervision_ml.train`, dans `/opt/ml/.venv` |
 | `ml_score` | `0 * * * *` | `enervision_ml.score`, dans `/opt/ml/.venv` |
 | `alertes` | `15 * * * *` | `app.detection.internal_alerts` puis `app.cli generate-recommendations`, dans `/opt/backend/.venv` |
+| `historical_import` | manuelle | `app.etl.historical_import`, dans `/opt/backend/.venv` ; les fichiers de `data/raw` sont montés en lecture seule dans `/opt/data/raw` |
+
+Le DAG `historical_import` réutilise le pipeline historique existant sans dupliquer sa logique.
+Il reste manuel, car le dataset sert à initialiser l'environnement. Le montage
+`./data/raw:/opt/data/raw:ro` permet au scheduler de lire les fichiers CSV/JSON sans pouvoir les
+modifier.
 
 **Pourquoi `alertes` tourne à la quinzième minute.** Sa règle `anomaly` compare une lecture à la
 `prediction` du même instant, que `ml_score` écrit à l'heure pile. Le décalage laisse le scoring

docs/architecture/50-cicd.md

@@ -44,6 +44,7 @@ flowchart TB
   subgraph sq["SonarQube · sonarqube.yml"]
     sb1["build-front / test-front"]
     sb2["build-back / test-back"]
+    sb3["test-ml"]
     sscan["sonarqube<br/>quality gate SonarCloud"]
   end
 
@@ -132,10 +133,18 @@ partie de la suite, et son taux n'aurait aucun sens face au seuil de 85 %.
 
 ## SonarCloud, et l'incident qui a immobilisé trois PR
 
-Le workflow `sonarqube.yml` exécute quatre jobs de préparation (`build-front`, `test-front`,
-`build-back`, `test-back`) qui produisent chacun un rapport de couverture en artefact, puis un
-cinquième job qui les télécharge et lance `SonarSource/sonarqube-scan-action@v8` avec le secret
-`SONAR_TOKEN`. Le périmètre est décrit par `sonar-project.properties` à la racine.
+Le workflow `sonarqube.yml` exécute cinq jobs de préparation (`build-front`, `test-front`,
+`build-back`, `test-back`, `test-ml`) dont les tests produisent chacun un rapport de couverture en
+artefact, puis un dernier job qui les télécharge et lance `SonarSource/sonarqube-scan-action@v8`
+avec le secret `SONAR_TOKEN`. Le périmètre est décrit par `sonar-project.properties` à la racine.
+
+Le périmètre couvre `apps/frontend`, `apps/backend`, `ml/` et `etl/airflow` (les deux derniers
+ajoutés après coup : ils n'étaient pas analysés, une PR qui ne touchait qu'eux ne lançait pas
+Sonar). `ml/` publie `ml/coverage.xml` (`pytest-cov`, même mécanisme que le backend, sans seuil
+propre : la gate porte sur le code neuf). `etl/airflow` est exclu de la **couverture**
+(`sonar.coverage.exclusions`) : ses tests ne font que charger les DAGs, ils ne mesurent rien.
+Piège : tout nouveau dossier de tests doit être déclaré dans `sonar.tests`, faute de quoi il est
+compté comme code de production non couvert (cf. l'incident ci-dessous).
 
 **L'incident, à raconter tel quel.** Les 18 et 19 septembre, trois PR (#103, #105, #107) sont
 restées bloquées sur une quality gate rouge annonçant une couverture du code neuf à 0 %, alors que

etl/README.md

@@ -663,8 +663,16 @@ mock_api_import.py
 
 La logique d'extraction, de transformation et de chargement est donc disponible pour les deux sources de données du MVP.
 
-Airflow tourne désormais réellement (`etl/airflow/`, `make airflow-up`) et orchestre le pipeline ML (`ml_train`/`ml_score`, issue #115) ainsi que la détection d'alertes et la génération des recommandations (`alertes`, issue #116). Il n'orchestre pas encore ces deux imports : `historical_import.py` et `mock_api_import.py` (normalisation et chargement micro-batch, issues #15/#16) restent à faire.
+Airflow tourne désormais réellement (`etl/airflow/`, `make airflow-up`) et orchestre le pipeline
+ML (`ml_train`/`ml_score`, issue #115), la détection d'alertes et la génération des
+recommandations (`alertes`, issue #116), ainsi que l'import historique
+(`historical_import`, issue #119).
 
-Airflow permet de planifier les traitements, gérer leur ordre d'exécution, suivre leur état et remonter les erreurs. Il ne remplace pas la logique ETL Python existante : les scripts actuels restent responsables de l'extraction, de la validation, de la transformation et du chargement. `etl/airflow/dags/ml_train.py`, `ml_score.py` et `alertes.py` montrent le patron retenu (des `BashOperator` qui invoquent le script tel quel, dans l'environnement `uv` que l'image embarque pour lui).
+Le DAG `historical_import` est déclenché manuellement. Il exécute
+`app.etl.historical_import` avec les fichiers montés en lecture seule depuis `data/raw` vers
+`/opt/data/raw`. L'orchestration de l'import API Mock et la réconciliation globale des deux
+sources restent couvertes par l'issue #15.
+
+Airflow permet de planifier les traitements, gérer leur ordre d'exécution, suivre leur état et remonter les erreurs. Il ne remplace pas la logique ETL Python existante : les scripts actuels restent responsables de l'extraction, de la validation, de la transformation et du chargement. `etl/airflow/dags/ml_train.py`, `ml_score.py` et `alertes.py` et `historical_import.py` montrent le patron retenu (des `BashOperator` qui invoquent le script tel quel, dans l'environnement `uv` que l'image embarque pour lui).
 
 Le pipeline Data servira ensuite à préparer les données nécessaires au modèle de Machine Learning.

etl/airflow/dags/historical_import.py

@@ -0,0 +1,45 @@
+"""DAG d'import du dataset historique EnerVision (issue #119).
+
+Orchestre le pipeline existant `app.etl.historical_import` sans dupliquer sa logique ETL.
+Le dataset historique sert à initialiser l'environnement : le DAG reste donc manuel.
+
+Le backend est exécuté dans l'environnement `/opt/backend` embarqué dans l'image Airflow,
+sur le même patron que le DAG `alertes` (ADR 0008).
+"""
+
+from __future__ import annotations
+
+from datetime import datetime, timedelta
+
+from airflow.models.dag import DAG
+from airflow.operators.bash import BashOperator
+
+COMMANDE_BACKEND = "cd /opt/backend && env -u VIRTUAL_ENV uv run --no-sync python -m"
+
+CSV_PATH = "/opt/data/raw/all_sites_combined.csv"
+METADATA_PATH = "/opt/data/raw/dataset_metadata.json"
+SOURCE_TIMEZONE = "UTC"
+BATCH_SIZE = 1000
+
+with DAG(
+    dag_id="historical_import",
+    description="Importe le dataset historique CSV/JSON dans dataset, site et reading.",
+    schedule=None,
+    start_date=datetime(2026, 1, 1),
+    catchup=False,
+    max_active_runs=1,
+    tags=["etl", "historical"],
+) as dag:
+    BashOperator(
+        task_id="import_historical",
+        bash_command=(
+            f"{COMMANDE_BACKEND} app.etl.historical_import "
+            f"--csv {CSV_PATH} "
+            f"--metadata {METADATA_PATH} "
+            "--source-timezone UTC "
+            "--batch-size 1000"
+        ),
+        retries=1,
+        retry_delay=timedelta(minutes=2),
+        execution_timeout=timedelta(minutes=30),
+    )

etl/airflow/tests/test_dags.py

@@ -10,12 +10,13 @@ from airflow.models.dagbag import DagBag
 
 DAGS_FOLDER = Path(__file__).resolve().parent.parent / "dags"
 
-DAG_IDS = ["ml_train", "ml_score", "alertes"]
+DAG_IDS = ["ml_train", "ml_score", "alertes", "historical_import"]
 TACHES = [
     ("ml_train", "train"),
     ("ml_score", "score"),
     ("alertes", "detection"),
     ("alertes", "recommandations"),
+    ("historical_import", "import_historical"),
 ]
 
 
@@ -47,6 +48,10 @@ def test_alertes_runs_after_the_hourly_scoring(dagbag: DagBag) -> None:
     assert dagbag.dags["alertes"].timetable.summary == "15 * * * *"
 
 
+def test_historical_import_has_no_schedule(dagbag: DagBag) -> None:
+    assert dagbag.dags["historical_import"].timetable.summary == "None"
+
+
 def test_ml_train_task_calls_the_training_module(dagbag: DagBag) -> None:
     tache = dagbag.dags["ml_train"].get_task("train")
     assert "enervision_ml.train" in tache.bash_command
@@ -67,12 +72,29 @@ def test_alertes_recommendation_task_calls_the_backend_cli(dagbag: DagBag) -> No
     assert "app.cli generate-recommendations" in tache.bash_command
 
 
+def test_historical_import_calls_the_existing_backend_module(dagbag: DagBag) -> None:
+    tache = dagbag.dags["historical_import"].get_task("import_historical")
+    assert "app.etl.historical_import" in tache.bash_command
+
+
+def test_historical_import_uses_the_expected_source_files(dagbag: DagBag) -> None:
+    commande = dagbag.dags["historical_import"].get_task("import_historical").bash_command
+
+    assert "--csv /opt/data/raw/all_sites_combined.csv" in commande
+    assert "--metadata /opt/data/raw/dataset_metadata.json" in commande
+
+
 @pytest.mark.parametrize("task_id", ["detection", "recommandations"])
 def test_alertes_tasks_run_in_the_backend_environment(dagbag: DagBag, task_id: str) -> None:
     # Le backend a son propre venv dans l'image, distinct de celui de ml/ (ADR 0008).
     assert "/opt/backend" in dagbag.dags["alertes"].get_task(task_id).bash_command
 
 
+def test_historical_import_runs_in_the_backend_environment(dagbag: DagBag) -> None:
+    commande = dagbag.dags["historical_import"].get_task("import_historical").bash_command
+    assert "/opt/backend" in commande
+
+
 def test_alertes_generates_recommendations_after_detecting(dagbag: DagBag) -> None:
     # `recommendation.alert_id` est une cle etrangere `NOT NULL` : la generation n'a rien a lire
     # tant que la detection n'a pas ecrit.
@@ -133,6 +155,10 @@ def test_alertes_retries_after_a_transient_failure(dagbag: DagBag, task_id: str)
     assert dagbag.dags["alertes"].get_task(task_id).retries >= 1
 
 
+def test_historical_import_retries_after_a_transient_failure(dagbag: DagBag) -> None:
+    assert dagbag.dags["historical_import"].get_task("import_historical").retries >= 1
+
+
 @pytest.mark.parametrize(("dag_id", "task_id"), TACHES)
 def test_tasks_never_resync_the_baked_environment(
     dagbag: DagBag, dag_id: str, task_id: str

ml/README.md

@@ -103,7 +103,7 @@ prevision (utile plus tard pour comparer prevision et realise, surveillance de d
 uv run ruff check .                       # lint
 uv run ruff format .                      # format
 uv run mypy enervision_ml tests           # typage strict
-uv run pytest                             # tests
+uv run pytest                             # tests + couverture (ml/coverage.xml avec --cov-report=xml, lu par Sonar)
 ```
 
 Depuis la racine du monorepo, via le `Makefile` : `make install-ml`, `make ml-lint`,

ml/pyproject.toml

@@ -17,6 +17,7 @@ dev = [
     "ruff>=0.16.7",
     "mypy>=2.3.1",
     "pytest>=9.1.1",
+    "pytest-cov>=7.1.0",
     "pandas-stubs>=3.0.5.260914",
 ]
 
@@ -75,5 +76,14 @@ ignore_missing_imports = true
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
-addopts = "-q --strict-markers -m 'not integration'"
+addopts = "-q --strict-markers -m 'not integration' --cov=enervision_ml --cov-report=term-missing"
 markers = ["integration: requiert une base PostgreSQL joignable"]
+
+# Rapport lu par SonarCloud (`ml/coverage.xml`, cf. sonar-project.properties), meme mecanisme que
+# apps/backend. Pas de seuil ici : celui de la quality gate porte sur le code nouveau.
+[tool.coverage.run]
+source = ["enervision_ml"]
+branch = true
+
+[tool.coverage.report]
+show_missing = true

ml/uv.lock

@@ -388,6 +388,45 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/19/37/c9aa45e47819dc15a38fc5c81a2fb987fde55e9d3b991fbde514e3b6b5f5/contourpy-1.4.0-cp314-cp314t-win_arm64.whl", hash = "sha256:fc9feef8f1f001c5b87decadc67c4a5d1eebb62ca39c4763d1237ff62cf2b707", size = 587071, upload-time = "2026-09-11T19:04:09.898Z" },
 ]
 
+[[package]]
+name = "coverage"
+version = "7.16.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/65/2d/c738872f477f5687152acae68635790387425d407ae37dd3d3a8a6692307/coverage-7.16.1.tar.gz", hash = "sha256:f83981779bcf9dfa06fa0a8d4cb43e0faec1706328ce07aa3e7b665b4ac0f210", size = 969651, upload-time = "2026-09-13T19:12:21.422Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8e/b4/2a7c793965bae9f067aabab793a44d7a2f3ee7fb16b01ce1976bbd4a0218/coverage-7.16.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:cc0b37fe6f5ce5f1ccc62ad4fa9b1ad201d8e9b6027fd5e0170877beee4b2d15", size = 223546, upload-time = "2026-09-13T19:10:06.019Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/e2/633469076a2dbbea036cc15a268a3a5d6b2c7dd5d9a9567b2553dfc5ad61/coverage-7.16.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:6618f481053b63fc6121faf8fc676bd9b7163c2a19d9e984a2e850002c28ab57", size = 223881, upload-time = "2026-09-13T19:10:08.246Z" },
+    { url = "https://files.pythonhosted.org/packages/de/c3/f06150c13284569d53273b909f31222874276a595637b7852571dfeb2c18/coverage-7.16.1-cp314-cp314-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:fa02d561eb1d8d2f8ba43ba6e3cef4c6c402a3b632a9460fa329fcadcd5df6a3", size = 254919, upload-time = "2026-09-13T19:10:10.254Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/40/47e25b215ae18a29010c8e29be8782a6e04d18ba6224be2bf6cebfce6427/coverage-7.16.1-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:bc5354a124799f1f87b7637bbe6f18cd4bc66a1f37f6aa2b5db40f9adad531dc", size = 257428, upload-time = "2026-09-13T19:10:12.124Z" },
+    { url = "https://files.pythonhosted.org/packages/27/4b/1e2a4267d14cbd12a8489364a9d40020233e6be836d929b363f0e77209e2/coverage-7.16.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:34bafe9f4094315248573e6223e11af0ec1b25f9cbca43bf0e9a26a189ba2751", size = 258771, upload-time = "2026-09-13T19:10:14.031Z" },
+    { url = "https://files.pythonhosted.org/packages/be/2e/9aa6146cea929fab9185bb2642ffef7f47520a6e5efe407f75f9b12f4cf0/coverage-7.16.1-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:29c4d3e32a3b5efa420a3dc627c7e570deb80ef997def52c7686a474f5edc7ab", size = 261086, upload-time = "2026-09-13T19:10:16.213Z" },
+    { url = "https://files.pythonhosted.org/packages/13/3c/f9ad8bcd4fb3d21c9d20a16d6d6c6f999eee8f4498ed7659a3dbd2f4b74a/coverage-7.16.1-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f2066c447fdd0bca39a9633a082d8ce67bf9a539a203b85059a364a405dc9fe9", size = 254895, upload-time = "2026-09-13T19:10:18.602Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/d1/47eda9fd1eaeea39fa7b5b13a63b2bed92ab901841fb120b3f9f5e1dc30c/coverage-7.16.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:fd8ac10cd2458b3c6343aac082fb9bd0e3fa806cb2c4975f2280153474b88412", size = 256783, upload-time = "2026-09-13T19:10:20.778Z" },
+    { url = "https://files.pythonhosted.org/packages/38/c3/565edf044877cb8cd3373c56885347ffc38f0edfd1f1679a487b208c19a8/coverage-7.16.1-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:9d8c54ec32e5c102b9241f75d88ae26538b53662868ca491736611db448d9c7a", size = 254742, upload-time = "2026-09-13T19:10:22.733Z" },
+    { url = "https://files.pythonhosted.org/packages/fd/88/87d2b2aeaba719192b2089ff1c2cf89a06cf73a6d2e9f1f145626617700c/coverage-7.16.1-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:6dd8dda3402a01a1a8fe8b753a282466f615128574a5590a9108acd07b1f8540", size = 259016, upload-time = "2026-09-13T19:10:24.769Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/1b/70813185b125768abdcf7899fec4d37edc2e5fc9b60c7045c8f4271ec757/coverage-7.16.1-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:79afa9726438912e5cddd1fe541815cea9763c92935f594835e4c432565b68a9", size = 254559, upload-time = "2026-09-13T19:10:26.781Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/fa/e7aa5af279aafda633a1ede8bfd7d6916b0c8b2082be86759e0b52e73a61/coverage-7.16.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:3db3978211c3cead5437a80136ca0556bab8bc7828de15a762884b0598c41361", size = 256215, upload-time = "2026-09-13T19:10:28.714Z" },
+    { url = "https://files.pythonhosted.org/packages/38/87/7a894fa4f8c6662d2b6a87a3436950e15b1fa56e01765c9d6634fb2cbeb8/coverage-7.16.1-cp314-cp314-win32.whl", hash = "sha256:49c39c7068a494f8eb427155f5682f44feee43f9b3107fd54b1e52465379c54b", size = 225719, upload-time = "2026-09-13T19:10:30.743Z" },
+    { url = "https://files.pythonhosted.org/packages/8b/01/fa7193c8005fb85488f02b0e1cc3c05a233cf2640206dd978af447aeecbf/coverage-7.16.1-cp314-cp314-win_amd64.whl", hash = "sha256:c510dad19552d912058e4c3e3cbec3fb155dbe8d0ce0ceb7e7dbf5c5822bae0b", size = 226208, upload-time = "2026-09-13T19:10:32.698Z" },
+    { url = "https://files.pythonhosted.org/packages/da/5c/a08634c714924c3eaef811bb3576c044128aa5e7dfa86c75e52f0761849e/coverage-7.16.1-cp314-cp314-win_arm64.whl", hash = "sha256:b7d4d7e6dcaf33e85f1919f03346403bdcc27437c420a78835f3805bca0ab71f", size = 225633, upload-time = "2026-09-13T19:10:34.79Z" },
+    { url = "https://files.pythonhosted.org/packages/43/df/ddb8a4c664046b1a0ee29c9c2d25b993e5dbc8fbde715df3694a64532781/coverage-7.16.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:3d0a3681c12d3e0bcdea3d9414b04087828d6c1a482802d6f7f42c37ed530152", size = 224281, upload-time = "2026-09-13T19:10:36.853Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/d0/9076e0c762d8afd91182e60a520fa5c92c4a334785eeb9fd6b8ef8fe7e3c/coverage-7.16.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:3f3b4469d3da3ecced775d1a8c9c5d9fc80f259e30b7b89f9fed0700d6035ecb", size = 224547, upload-time = "2026-09-13T19:10:39.359Z" },
+    { url = "https://files.pythonhosted.org/packages/03/e5/9c59e64b6161704f35fe91549bb19b2bb355e95caf596c26a2065564807c/coverage-7.16.1-cp314-cp314t-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:c08ae35c1be2fe1ce4b4c628df5c6fc0dc9a87f8e5fe8e20238d249678984741", size = 265906, upload-time = "2026-09-13T19:10:41.434Z" },
+    { url = "https://files.pythonhosted.org/packages/57/5a/13ccaffb77f766101bf6f38be9dba9e468b02cc92da4552a57877dbf1c1f/coverage-7.16.1-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:8ee71a38c54bb2676bbe762b8b0943a79ccb1c2fd6a52054f66e63eda392f8c1", size = 268023, upload-time = "2026-09-13T19:10:43.533Z" },
+    { url = "https://files.pythonhosted.org/packages/ad/a1/05cfcf01d3c7c922832698ad46e51d3441d820ce87a943014bb5cf5710dd/coverage-7.16.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:76491917771f179f9772efe218c5ccc65950dbdb35f4439298d8a8dfc6ec1f72", size = 270442, upload-time = "2026-09-13T19:10:45.895Z" },
+    { url = "https://files.pythonhosted.org/packages/72/15/a2f1544b8e3835d7b769f7dabcc9ac0283e0b646ef3344703ff8f18d83e6/coverage-7.16.1-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f4aa0b0a6f81fa3deb211e643f6954e78b4376b62b9c218271236cfa757664e8", size = 271565, upload-time = "2026-09-13T19:10:48.123Z" },
+    { url = "https://files.pythonhosted.org/packages/df/5b/963c2993a82bd313f298d663afe03e164b96ace4d9d4c7561740a559e13d/coverage-7.16.1-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:756ba2d96d073c5a2a55d67fa22784763710fadbe22c41adde2d9cfa4dd78a8c", size = 264959, upload-time = "2026-09-13T19:10:50.195Z" },
+    { url = "https://files.pythonhosted.org/packages/12/59/5eba06d1943735d7cd61d46d8c8a20ffe8ddd2da06b3c94366078dadeb9b/coverage-7.16.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:99bf9ea435cefcefd220f8687c3ddbbf78dc2de0bd11b57c3ae9fbbdf8d5561a", size = 267897, upload-time = "2026-09-13T19:10:52.252Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/48/af6c30f6ea431bb9b83f9070d268a9cc4fc97490abd32080164177ea999f/coverage-7.16.1-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:35cbc81f937fc402971df45c897d2df2bfb2014efcd990360032aa0a651635da", size = 265504, upload-time = "2026-09-13T19:10:54.432Z" },
+    { url = "https://files.pythonhosted.org/packages/80/f2/6e13852a8656d05fa83284567dd5a5b1e6d89bef79fe3effca2787159eab/coverage-7.16.1-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:8fae08e85b334ac6ac886002b5041396a31bcf805225bbe19847627203da99e2", size = 269235, upload-time = "2026-09-13T19:10:56.563Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/32/b4fe465daa64ece674f83a750dfa4ba0fa3c5c74d6ef5dbb8dfce892cf0d/coverage-7.16.1-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:83362b64e215ef00b0ba33fcf13655ace6c9fdd144d5ad2ab59ac86c2daf166e", size = 264347, upload-time = "2026-09-13T19:10:58.634Z" },
+    { url = "https://files.pythonhosted.org/packages/54/f3/88b5c0e4ca3994c6d5feb7b1bf4c9a62cee205553159184968426930a7b1/coverage-7.16.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:33300f2e140ccf26af3d8152e62bff71993f9310cfc63ba7a20940b0d246a0ae", size = 266660, upload-time = "2026-09-13T19:11:00.746Z" },
+    { url = "https://files.pythonhosted.org/packages/97/72/6eff5456d7ba7f1c4678af531c33f9d957cae3201bd229b056fd13a204a3/coverage-7.16.1-cp314-cp314t-win32.whl", hash = "sha256:5539304fdbb2cc144df684d35a33b81145334d23e1c2367b5a923d25107f70b2", size = 226026, upload-time = "2026-09-13T19:11:02.846Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/c8/6e5ae3d8d4d0f2c0078985bf4db55fafd90e8107b1bf91ee3547a13f5694/coverage-7.16.1-cp314-cp314t-win_amd64.whl", hash = "sha256:715dcb72c3280c428c3a20134b87e42c29acec9669136e899ab2de69ca86218d", size = 226862, upload-time = "2026-09-13T19:11:04.921Z" },
+    { url = "https://files.pythonhosted.org/packages/be/c7/68f9f0734afc904a92b974b489545b6a15700f3b1c4bd36eae764561e661/coverage-7.16.1-cp314-cp314t-win_arm64.whl", hash = "sha256:dac8b84c03e6029d272b8249c77018db83de59ca009a9adef7c144b4a62ee5e6", size = 226171, upload-time = "2026-09-13T19:11:06.969Z" },
+    { url = "https://files.pythonhosted.org/packages/96/1a/d6d16babd0a5fe4c3fae40702158c570351694e74516d8d81b86c5637448/coverage-7.16.1-py3-none-any.whl", hash = "sha256:3d8bd4e58b6a5c2018d808f297905393c6c61da466a48c3f0596a76a4900ebe4", size = 215264, upload-time = "2026-09-13T19:12:18.895Z" },
+]
+
 [[package]]
 name = "cryptography"
 version = "50.0.1"
@@ -494,6 +533,7 @@ dev = [
     { name = "mypy" },
     { name = "pandas-stubs" },
     { name = "pytest" },
+    { name = "pytest-cov" },
     { name = "ruff" },
 ]
 
@@ -512,6 +552,7 @@ dev = [
     { name = "mypy", specifier = ">=2.3.1" },
     { name = "pandas-stubs", specifier = ">=3.0.5.260914" },
     { name = "pytest", specifier = ">=9.1.1" },
+    { name = "pytest-cov", specifier = ">=7.1.0" },
     { name = "ruff", specifier = ">=0.16.7" },
 ]
 
@@ -1591,6 +1632,20 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/24/25/1de2678b631f5a49215c6c96fff41ba892b0a34df68d6d80292b1b48aa7f/pytest-9.1.1-py3-none-any.whl", hash = "sha256:37a86b45efb9a47a61a36449063e8e18d0cab3161329fc099eb21783169c4f0c", size = 386536, upload-time = "2026-06-19T10:58:31.347Z" },
 ]
 
+[[package]]
+name = "pytest-cov"
+version = "7.1.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "coverage" },
+    { name = "pluggy" },
+    { name = "pytest" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b1/51/a849f96e117386044471c8ec2bd6cfebacda285da9525c9106aeb28da671/pytest_cov-7.1.0.tar.gz", hash = "sha256:30674f2b5f6351aa09702a9c8c364f6a01c27aae0c1366ae8016160d1efc56b2", size = 55592, upload-time = "2026-03-21T20:11:16.284Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9d/7a/d968e294073affff457b041c2be9868a40c1c71f4a35fcc1e45e5493067b/pytest_cov-7.1.0-py3-none-any.whl", hash = "sha256:a0461110b7865f9a271aa1b51e516c9a95de9d696734a2f71e3e78f46e1d4678", size = 22876, upload-time = "2026-03-21T20:11:14.438Z" },
+]
+
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"

sonar-project.properties

@@ -3,15 +3,17 @@ sonar.organization=groupe3-ener-vision
 sonar.sourceEncoding=UTF-8
 
 #  Dossier contenant le code source
-sonar.sources=apps/frontend/src,apps/backend
+sonar.sources=apps/frontend/src,apps/backend,ml,etl/airflow
 #  Dossier contenant les tests
-sonar.tests=apps/frontend/src,apps/backend/tests
+sonar.tests=apps/frontend/src,apps/backend/tests,ml/tests,etl/airflow/tests
 sonar.test.inclusions=**/*.spec.ts,**/*.test.ts,**/*test_*.py,**/*test.py
 
 #  Liste des fichiers et dossiers à exclure de l'analyse
-sonar.exclusions=.pytest_cache,.venv,alembic,tests,**/*/node_modules/**,**/*/dist/**,**/*/build/**,**/*.spec.ts,**/*.test.ts,**/*test_*.py,**/*test.py,**/*.spec.ts
+sonar.exclusions=.pytest_cache,.venv,.airflow_home,alembic,tests,ml/data/**,ml/models/**,ml/mlruns/**,ml/mlartifacts/**,**/*/node_modules/**,**/*/dist/**,**/*/build/**,**/*.spec.ts,**/*.test.ts,**/*test_*.py,**/*test.py,**/*.spec.ts
 
 #  Chemin vers le rapport de couverture de code
 #  Fichier généré par Pytest
-sonar.python.coverage.reportPaths=apps/backend/coverage.xml
+sonar.python.coverage.reportPaths=apps/backend/coverage.xml,ml/coverage.xml
+#  Les DAGs n'ont pas de couverture mesurable : leurs tests ne font que les charger (DagBag)
+sonar.coverage.exclusions=etl/airflow/**
 sonar.javascript.lcov.reportPaths=apps/frontend/coverage/frontend/lcov.info