feat[DEI-118]: pass start_date as parameter from input yaml

decoimpact/data/api/i_dataset.py

@@ -24,6 +24,11 @@ class IDatasetData(ABC):
     def path(self) -> Path:
         """File path to the dataset"""
 
+    @property
+    @abstractmethod
+    def start_date(self) -> str:
+        """start date to filter the dataset"""
+
     @property
     @abstractmethod
     def mapping(self) -> dict[str, str]:

decoimpact/data/entities/data_access_layer.py

@@ -13,6 +13,7 @@
 """
 
 import re
+from datetime import datetime
 from pathlib import Path
 from typing import Any
 
@@ -68,8 +69,11 @@ def read_input_dataset(self, dataset_data: IDatasetData) -> _xr.Dataset:
         Returns:
             _xr.Dataset: Dataset based on provided dataset_data
         """
-        start_time = "2014-01-01"
-        end_time = "2015-12-31"
+        # filter_start_date = "2014-01-01"
+        ds_start_date = dataset_data.start_date
+        date_format = "%d-%m-%Y"
+        filter_start_date = datetime.strptime(ds_start_date, date_format)
+        filter_end_date = "2015-12-31"
 
         if not Path.exists(dataset_data.path):
             message = f"""The file {dataset_data.path} is not found. \
@@ -96,7 +100,7 @@ def read_input_dataset(self, dataset_data: IDatasetData) -> _xr.Dataset:
         # apply time filter on input dataset
         try:
             # dataset = dataset.where(dataset["time.year"] > 2014, drop=True)
-            dataset = dataset.sel(time=slice(start_time, end_time))
+            dataset = dataset.sel(time=slice(filter_start_date, filter_end_date))
         except ValueError as exc:
             msg = "ERROR: error applying time filter on dataset"
             raise ValueError(msg) from exc

decoimpact/data/entities/dataset_data.py

@@ -12,9 +12,12 @@
 
 """
 
+import datetime
 from pathlib import Path
 from typing import Any
 
+from tomlkit import date
+
 from decoimpact.data.api.i_dataset import IDatasetData
 from decoimpact.data.dictionary_utils import get_dict_element
 
@@ -30,12 +33,18 @@ def __init__(self, dataset: dict[str, Any]):
         """
         super()
         self._path = Path(get_dict_element("filename", dataset)).resolve()
+        self._start_date = str(get_dict_element("start_date", dataset, False))
         self._get_mapping(dataset)
 
     @property
     def path(self) -> Path:
         """File path to the input dataset"""
         return self._path
+
+    @property
+    def start_date(self) -> str:
+        """optional start and end date to filter the dataset"""
+        return self._start_date
 
     @property
     def mapping(self) -> dict[str, str]:

docs/tutorials/input.md

@@ -25,6 +25,8 @@ The model needs at least one rule under “rules” to execute.
 input-data:
   - dataset:
       filename: <path_to_file_including_file_name_and_type>
+      start_date: "<start_date>"
+      end_date: "<end_date>"
       variable_mapping:
         <variable1_input_file>: "<variable1_name_in_model>"
         <variable2_input_file>: "<variable2_name_in_model>"