Progettare pipeline di forecasting per la produzione
Rami Krispin
Senior Manager, Data Science and Engineering


Ingestione dati
Aggiornamento forecast
Robustezza






Approcci
Requisiti
from lightgbm import LGBMRegressor from mlforecast import MLForecast import mlflow import mlforecast.flavorexperiment_name = "ml_forecast" mlflow_path = "file:///mlruns"meta = mlflow.get_experiment_by_name(experiment_name)
model = LGBMRegressor(n_estimators = 500, learning_rate= 0.05)params = { "freq": "h", "lags": list(range(1, 24)), "date_features": ["month", "day", "dayofweek", "week", "hour"] }
mlf = MLForecast(
models= model,
freq= params["freq"],
lags=params["lags"],
date_features=params["date_features"]
)
mlf.fit(ts)
run_time = datetime.datetime.now().strftime("%Y-%m-%d %H-%M-%S") run_name = f"lightGBM6_{run_time}"print(run_name)
'lightGBM6_2025-05-19 05-12-16'
with mlflow.start_run(experiment_id=meta.experiment_id,
run_name=run_name) as run:
mlforecast.flavor.log_model(model=mlf, artifact_path="prod_model")



Progettare pipeline di forecasting per la produzione