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

lab/modeling_ridge/cli.py

@@ -0,0 +1,85 @@
+import logging
+
+import mlflow
+import pandas as pd
+import typer
+from sklearn import linear_model
+from sklearn import metrics
+
+from .. import constants
+
+app = typer.Typer()
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+
+@app.command()
+def main(
+    strategy: constants.ModellingStrategy = constants.ModellingStrategy.MIXED,
+):
+    training_file_path = constants.DATASET_DIR / "train.parquet"
+    validation_file_path = constants.DATASET_DIR / "validation.parquet"
+
+    features = constants.MODELLING_FEATURES[strategy]
+
+    train_df = pd.read_parquet(training_file_path)
+    validation_df = pd.read_parquet(validation_file_path)
+
+    train_df = train_df.dropna(
+        subset=features + [constants.TARGET]
+    )
+    validation_df = validation_df.dropna(
+        subset=features + [constants.TARGET]
+    )
+
+    X_train = train_df[features]
+    y_train = train_df[constants.TARGET]
+
+    X_validation = validation_df[features]
+    y_validation = validation_df[constants.TARGET]
+
+    logger.info(f"Training Ridge with strategy '{strategy}' and features {features}")
+
+    for alpha in constants.RIDGE_ALPHAS:
+        with mlflow.start_run(run_name=f"modelling_{strategy.value}_ridge_alpha_{alpha:g}"):
+            mlflow.log_param("model_type", "ridge")
+            mlflow.log_param("strategy", strategy.value)
+            mlflow.log_param("split_strategy", constants.CHOSEN_SPLIT_STRATEGY.value)
+
+            mlflow.log_param("features", ",".join(features))
+            mlflow.log_param("alpha", alpha)
+            model = linear_model.Ridge(alpha=alpha)
+            model.fit(X_train, y_train)
+
+            train_predictions = model.predict(X_train)
+            validation_predictions = model.predict(X_validation)
+
+            train_rmse = metrics.root_mean_squared_error(y_train, train_predictions)
+            validation_rmse = metrics.root_mean_squared_error(y_validation, validation_predictions)
+
+            train_mae = metrics.mean_absolute_error(y_train, train_predictions)
+            validation_mae = metrics.mean_absolute_error(y_validation, validation_predictions)
+
+            mlflow.log_metric("train_rmse", train_rmse)
+            mlflow.log_metric("validation_rmse", validation_rmse)
+
+            mlflow.log_metric("train_mae", train_mae)
+            mlflow.log_metric("validation_mae", validation_mae)
+
+            for feature_name, coefficient in zip(
+                features,
+                model.coef_,
+                strict=True,
+            ):
+                mlflow.log_metric(f"coef_{feature_name}", float(coefficient))
+
+            mlflow.sklearn.log_model(
+                sk_model=model,
+                name="electricity_consumption_model",
+                registered_model_name="electricity_consumption_model",
+            )
+
+
+if __name__ == "__main__":
+    app()