Merge branch 'mobt_877_implement_qrf' into mobt_877_implement_qrf_extra

Author: Kat-90

improver/calibration/load_and_apply_quantile_regression_random_forest.py

@@ -32,7 +32,7 @@ def __init__(
         feature_config: dict[str, list[str]],
         target_cube_name: str,
         transformation: str = None,
-        pre_transform_addition: float = 0,
+        pre_transform_addition: float = None,
     ):
         """Initialise the plugin.
 
@@ -131,6 +131,10 @@ def _get_inputs(
             )
             raise ValueError(msg)
 
+        if not qrf_model:
+            # The specified model doesn't exist and the forecast will not be calibrated
+            return forecast_cube
+        
         # If target diagnostic not a feature in the training then remove.
         if self.target_cube_name not in self.feature_config.keys():
             cube_inputs.remove(forecast_cube)

improver/calibration/load_and_train_quantile_regression_random_forest.py

@@ -78,6 +78,9 @@ def _split_cubes_and_parquet_files(self, file_paths):
                         truth_table_path = file_path
                     if forecast_table_path and truth_table_path:
                         break
+            except OSError:
+                print("The directory doesn't exist, calibration is skipped for this cycle")
+                return
 
         if len(self.feature_config.keys()) not in [
             len(cube_inputs),
@@ -122,6 +125,7 @@ def _read_parquet_files(
                 ("experiment", "==", self.experiment),
             ]
         ]
+
         for file in Path(forecast_table_path).glob("**/*.parquet"):
             if pq.read_schema(file).get_all_field_indices("percentile"):
                 altered_schema = FORECAST_SCHEMA
@@ -162,6 +166,7 @@ def _read_parquet_files(
         truth_df = pd.read_parquet(
             truth_table_path, filters=filters, schema=TRUTH_SCHEMA, engine="pyarrow"
         )
+        
         truth_df["time"] = pd.to_datetime(truth_df["time"], unit="ns", utc=True)
 
         if truth_df.empty:

improver/calibration/quantile_regression_random_forest.py

@@ -501,6 +501,7 @@ def __init__(
                 f"and cbrt. The transformation supplied was {self.transformation}."
             )
             raise ValueError(msg)
+        print(pre_transform_addition)
         self.pre_transform_addition = pre_transform_addition
 
     def _reverse_transformation(self, forecast_cube: Cube):

improver/cli/apply_quantile_regression_random_forest.py

@@ -14,7 +14,6 @@ def process(
     *file_paths: cli.inputpath,
     feature_config: cli.inputjson,
     target_cube_name: str,
-    n_estimators: int = 100,
     transformation: str = None,
     pre_transform_addition: float = 0,
 ):
@@ -52,8 +51,6 @@ def process(
             A string containing the cube name of the forecast to be
             calibrated. This will be used to separate it from the rest of the
             feature cubes, if present.
-        n_estimators (int):
-            Number of trees in the forest.
         transformation (str):
             Transformation to be applied to the data before fitting.
         pre_transform_addition (float):
@@ -71,7 +68,6 @@ def process(
         file_paths,
         feature_config=feature_config,
         target_cube_name=target_cube_name,
-        n_estimators=n_estimators,
         transformation=transformation,
         pre_transform_addition=pre_transform_addition,
     )