feat(ml): initialise le pipeline d'entrainement LightGBM (ADR 0005)

2026-09-17 14:12:26 +02:00
parent 016f226fdb
commit 4f69199734
22 changed files with 3086 additions and 3 deletions
@@ -0,0 +1,79 @@
+[project]
+name = "enervision-ml"
+version = "0.1.0"
+description = "Pipeline d'entrainement et de scoring du modele de prediction EnerVision (LightGBM)"
+requires-python = ">=3.14,<3.15"
+dependencies = [
+    "pandas>=3.0.5",
+    "sqlalchemy>=2.0.52",
+    "psycopg[binary]>=3.2",
+    "lightgbm>=4.6",
+    "scikit-learn>=1.7",
+    "mlflow>=3.0",
+]
+
+[dependency-groups]
+dev = [
+    "ruff>=0.16.7",
+    "mypy>=2.3.1",
+    "pytest>=9.1.1",
+    "pandas-stubs>=3.0.5.260914",
+]
+
+[build-system]
+requires = ["hatchling>=1.32.0"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["enervision_ml"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py314"
+src = ["enervision_ml", "tests"]
+
+[tool.ruff.lint]
+select = [
+    "E", "W",
+    "F",
+    "I",
+    "N",
+    "UP",
+    "B",
+    "C4",
+    "SIM",
+    "TID",
+    "RUF",
+    "S",
+    "PT",
+]
+# N806 : `X`/`y` (donnees/cible) est la convention scikit-learn/LightGBM, pas une variable mal
+# nommee.
+ignore = ["B008", "N806"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**/*.py" = ["S101"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["enervision_ml"]
+
+[tool.ruff.format]
+quote-style = "double"
+
+[tool.mypy]
+python_version = "3.14"
+strict = true
+warn_unreachable = true
+
+[[tool.mypy.overrides]]
+module = ["tests.*"]
+disallow_untyped_defs = false
+
+[[tool.mypy.overrides]]
+module = ["lightgbm.*", "mlflow.*", "sklearn.*"]
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q --strict-markers -m 'not integration'"
+markers = ["integration: requiert une base PostgreSQL joignable"]