TP2 Partie 1 : package lab + DVC (split full_history v1)

2026-07-21 14:05:19 +02:00
parent f8549972d5
commit 0c0bd77156
17 changed files with 384 additions and 9 deletions
--- a/lab/constants.py
+++ b/lab/constants.py
@@ -0,0 +1,72 @@
+import datetime
+from enum import StrEnum
+from pathlib import Path
+from typing import Literal
+
+# Racine du depot de travail (/home/user/tp sur la VM) : lab/constants.py -> parents[1]
+REPO_ROOT = Path(__file__).resolve().parents[1]
+
+# Donnees source, deja preparees (hors git, volumineuses) : voir /data sur la VM
+SOURCE_DIR = Path("/data/modelling")
+
+# Sorties de split versionnees par DVC dans le depot
+DATASET_DIR = REPO_ROOT / "data"
+
+FEATURE_FILENAME = "features.parquet"
+TARGET_FILENAME = "target.parquet"
+
+
+class SplitStrategy(StrEnum):
+    FULL_HISTORY = "full_history"
+    RECENT_HISTORY = "recent_history"
+
+
+# Strategie de split active : pilote a la fois le decoupage produit par split/cli.py
+# et le parametre "split_strategy" logge dans MLflow. On la modifie (et on committe)
+# a chaque changement de version de dataset pour synchroniser DVC et Git.
+CHOSEN_SPLIT_STRATEGY = SplitStrategy.FULL_HISTORY
+
+DatasetPart = Literal["train", "test", "validation"]
+
+DATASET_SPLIT_DATES: dict[SplitStrategy, dict[DatasetPart, tuple[datetime.date, datetime.date]]] = {
+    # Partie 1 : tout l'historique disponible pour l'entrainement
+    SplitStrategy.FULL_HISTORY: {
+        "train": (datetime.date(2011, 1, 1), datetime.date(2012, 12, 31)),
+        "validation": (datetime.date(2013, 1, 1), datetime.date(2013, 12, 31)),
+        "test": (datetime.date(2014, 1, 1), datetime.date(2014, 12, 31)),
+    },
+    # Partie 2 : donnees plus recentes uniquement
+    SplitStrategy.RECENT_HISTORY: {
+        "train": (datetime.date(2013, 1, 1), datetime.date(2013, 12, 31)),
+        "validation": (datetime.date(2014, 1, 1), datetime.date(2014, 5, 31)),
+        "test": (datetime.date(2014, 6, 1), datetime.date(2014, 12, 31)),
+    },
+}
+
+
+class ModellingStrategy(StrEnum):
+    SHORT_MEMORY = "short_memory"
+    SEASONALITY = "seasonality"
+    TENDENCY = "tendency"
+    MIXED = "mixed"
+    FULL = "full"
+
+
+Features = Literal["lag_1d", "lag_7d", "lag_30d", "lag_365d", "rolling_mean_7d", "rolling_mean_30d"]
+TARGET = "consumption_kwh"
+
+MODELLING_FEATURES: dict[ModellingStrategy, list] = {
+    # La conso depend surtout de la veille
+    ModellingStrategy.SHORT_MEMORY: ["lag_1d"],
+    # La conso est plus saisonniere que journaliere
+    ModellingStrategy.SEASONALITY: ["lag_7d", "lag_30d"],
+    # La conso suit surtout une tendance
+    ModellingStrategy.TENDENCY: ["rolling_mean_7d", "rolling_mean_30d"],
+    # Melange lags + tendance
+    ModellingStrategy.MIXED: ["lag_1d", "lag_7d", "lag_30d", "rolling_mean_30d"],
+    # Toutes les features disponibles (ajoutee en Partie 2 Etape 3)
+    ModellingStrategy.FULL: ["lag_1d", "lag_7d", "lag_30d", "lag_365d", "rolling_mean_7d", "rolling_mean_30d"],
+}
+
+# Valeurs d'alpha demandees par l'enonce (Partie 3)
+RIDGE_ALPHAS = [1, 1e3, 1e9]