Add LGBM model

tests/test_models.py

@@ -15,6 +15,7 @@
     DartsLocalForecastingModel,
     LinearRegressionModel,
     RandomForestModel,
+    LGBMModel,
 )
 from tot.models.models_naive import NaiveModel, SeasonalNaiveModel
 from tot.models.models_neuralprophet import NeuralProphetModel, TorchProphetModel
@@ -406,6 +407,44 @@ def test_darts_StatsForecastAutoARIMA_model():
     print(results_test)
 
 
+def test_darts_LGBM_model():
+    air_passengers_df = pd.read_csv(AIR_FILE, nrows=NROWS)
+    ercot_df_aux = pd.read_csv(ERCOT_FILE)
+    ercot_df = pd.DataFrame()
+    for region in ERCOT_REGIONS:
+        ercot_df = pd.concat(
+            (
+                ercot_df,
+                ercot_df_aux[ercot_df_aux["ID"] == region].iloc[:NROWS].copy(deep=True),
+            ),
+            ignore_index=True,
+        )
+
+    dataset_list = [
+        Dataset(df=air_passengers_df, name="air_passengers", freq="MS"),
+        Dataset(df=ercot_df, name="ercot_df", freq="H"),
+    ]
+    model_classes_and_params = [
+        (
+            LGBMModel,
+            {"lags": 12, "n_forecasts": 1},
+        ),
+    ]
+    log.debug("{}".format(model_classes_and_params))
+
+    benchmark = SimpleBenchmark(
+        model_classes_and_params=model_classes_and_params,
+        datasets=dataset_list,
+        metrics=list(ERROR_FUNCTIONS.keys()),
+        test_percentage=0.25,
+        save_dir=SAVE_DIR,
+        num_processes=1,
+    )
+    results_train, results_test = benchmark.run()
+    log.info("#### test_darts_local_model")
+    print(results_test)
+
+
 def test_torch_prophet_model():
     air_passengers_df = pd.read_csv(AIR_FILE, nrows=NROWS)
     peyton_manning_df = pd.read_csv(PEYTON_FILE, nrows=NROWS)

tot/models/models_darts.py

@@ -30,7 +30,7 @@
     )
 
 try:
-    from darts.models import RegressionModel
+    from darts.models import LightGBMModel, RegressionModel
 
     _darts_installed = True
 except ImportError:
@@ -395,3 +395,51 @@ class RandomForestModel(DartsRegressionModel):
     """
 
     regression_class: Type = RandomForestRegressor
+
+
+@dataclass
+class LGBMModel(DartsRegressionModel):
+    """
+    A forecasting model using a LightGBMModel to obtain a forecast.
+
+    Examples
+    --------
+    >>> model_classes_and_params = [
+    >>>     (
+    >>>         LGBMModel,
+    >>>         {"lags": 12, "n_forecasts": 4},
+    >>>     ),
+    >>> ]
+    >>>
+    >>> benchmark = SimpleBenchmark(
+    >>>     model_classes_and_params=model_classes_and_params,
+    >>>     datasets=dataset_list,
+    >>>     metrics=list(ERROR_FUNCTIONS.keys()),
+    >>>     test_percentage=25,
+    >>>     save_dir=SAVE_DIR,
+    >>>     num_processes=1,
+    >>> )
+    """
+
+    def __post_init__(self):
+        # check if installed
+        if not (_darts_installed or _sklearn_installed):
+            raise RuntimeError(
+                "Requires darts and sklearn to be installed:"
+                "https://scikit-learn.org/stable/install.html"
+                "https://github.com/unit8co/darts/blob/master/INSTALL.md"
+            )
+        params = deepcopy(self.params)
+        params.pop("_data_params")
+        # n_forecasts is not a parameter of the model
+        params.pop("n_forecasts")
+        params.pop("retrain", None)
+        params.pop("norm_mode", None)
+        params.pop("norm_type", None)
+        params.pop("norm_affine", None)
+        # overwrite output_chunk_length with n_forecasts
+        params.update({"output_chunk_length": self.params["n_forecasts"]})
+        self.model = LightGBMModel(**params)
+        self.n_forecasts = self.params["n_forecasts"]
+        self.n_lags = params["lags"]
+        # input checks are provided by model itself