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

data_loader/load.py

@@ -33,6 +33,7 @@ def __load_data(
     own_features: list[tuple[str, FeatureExtractor, list[int]]],
     other_features: list[tuple[str, FeatureExtractor, list[int]]],
     exogenous_features: list[tuple[str, FeatureExtractor, list[int]]],
+    start_date: Optional[str],
 ) -> tuple[XDataFrame, ReturnSeries]:
     """
     Loads asset data from the specified path.
@@ -98,6 +99,9 @@ def __load_data(
     X = pd.concat([df.reindex(X[0].index) for df in X], axis=1).fillna(0.0)
 
     X.index = pd.DatetimeIndex(X.index)
+    if start_date is not None:
+        X = X[start_date:]
+        df_target_asset_only_returns = df_target_asset_only_returns[start_date:]
 
     ## Create target
     returns = df_target_asset_only_returns[target_asset.file_name + "_returns"]

data_loader/process.py

@@ -18,4 +18,4 @@ def check_data(X: XDataFrame, config: Config) -> bool:
 def has_enough_samples_to_train(X: XDataFrame, config: Config) -> bool:
     first_valid_index = get_first_valid_return_index(X.iloc[:, 0])
     samples_to_train = len(X) - first_valid_index
-    return samples_to_train > (config.initial_window_size * 2) + 100
+    return samples_to_train > config.retrain_every * 3 + config.initial_window_size

run_inference.py

@@ -39,6 +39,7 @@ def __inference(config: Config, pipeline_outcome: PipelineOutcome):
         own_features=config.own_features,
         other_features=config.other_features,
         exogenous_features=config.exogenous_features,
+        start_date=config.start_date,
     )
     assert check_data(X, config) == True, "Data is not valid. Cancelling Inference."
 

run_pipeline.py

@@ -59,6 +59,7 @@ def run_training(config: Config) -> PipelineOutcome:
         own_features=config.own_features,
         other_features=config.other_features,
         exogenous_features=config.exogenous_features,
+        start_date=config.start_date,
     )
 
     assert check_data(X, config) == True, "Data is not valid."