feat(Config): added start_date property (#245)

* refactor(Training): remove non-expanding window option

* feat(Config): added `start_date` property

* fix(Inference): added start_date here as well

* fix(Linter): ran

config/hashing.py

@@ -20,6 +20,7 @@ def hash_data_config(data_config: dict) -> str:
                 data_config["target_asset"].path
                 + data_config["target_asset"].file_name,
                 data_config["load_non_target_asset"],
+                data_config["start_date"],
                 hash_feature_extractors(data_config["own_features"]),
                 hash_feature_extractors(data_config["other_features"]),
                 hash_feature_extractors(data_config["exogenous_features"]),

config/presets.py

@@ -14,6 +14,7 @@ def get_default_config() -> RawConfig:
     meta_models = ["LogisticRegression_two_class", "LGBM"]
 
     return RawConfig(
+        start_date=None,
         dimensionality_reduction_ratio=0.5,
         n_features_to_select=50,
         initial_window_size=3800,

config/types.py

@@ -11,6 +11,7 @@ from transformations.base import Transformation
 
 # RawConfig is needed to ensure we can declare config presets here with static typing, we then convert it to Config
 class RawConfig(BaseModel):
+    start_date: Optional[str]
     dimensionality_reduction_ratio: float
     n_features_to_select: int
     initial_window_size: int
@@ -40,9 +41,9 @@ class RawConfig(BaseModel):
 
 @dataclass
 class Config:
+    start_date: Optional[str]
     initial_window_size: int
     retrain_every: int
-
     assets: DataCollection
     target_asset: DataSource
     other_assets: DataCollection