refactor(Training): use date indexes instead of integers, need this to prepare for Events (#185)

config/config.py

@@ -27,7 +27,6 @@ class RawConfig(BaseModel):
     other_features: list[str]
     exogenous_features: list[str]
     no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced']
-    index_column: Literal['date', 'int']
 
     primary_models: list[str]
     meta_labeling_models: list[str]
@@ -56,7 +55,6 @@ class Config(BaseModel):
     other_features: list[tuple[str, FeatureExtractor, list[int]]]
     exogenous_features: list[tuple[str, FeatureExtractor, list[int]]]
     no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced']
-    index_column: Literal['date', 'int']
 
     primary_models: list[tuple[str, Model]]
     meta_labeling_models: list[tuple[str, Model]]
@@ -92,7 +90,6 @@ def get_dev_config() -> RawConfig:
         own_features = ['level_2', 'date_days'],
         other_features = ['single_mom'],
         exogenous_features = ['z_score'],
-        index_column= 'int',
         no_of_classes= 'two',
 
         primary_models = classification_models,
@@ -129,7 +126,6 @@ def get_default_ensemble_config() -> RawConfig:
         own_features = ['level_2', 'date_days', 'lags_up_to_5'],
         other_features = ['level_2', 'lags_up_to_5'],
         exogenous_features = ['z_score'],
-        index_column= 'int',
         no_of_classes= 'two',
 
         primary_models = classification_models,
@@ -167,7 +163,6 @@ def get_lightweight_ensemble_config() -> RawConfig:
         own_features = ['level_2' ],
         other_features = ['level_2'],
         exogenous_features = ['z_score'],
-        index_column= 'int',
         no_of_classes= 'two',
 
         primary_models = classification_models,

config/hashing.py

@@ -17,6 +17,5 @@ def hash_data_config(data_config: dict) -> str:
         hash_feature_extractors(data_config['own_features']),
         hash_feature_extractors(data_config['other_features']),
         hash_feature_extractors(data_config['exogenous_features']),
-        data_config['index_column'],
         data_config['no_of_classes'],
     ]))

config/sweep_ensemble.yaml

@@ -40,8 +40,6 @@ parameters:
       value: True
     log_returns: 
       value: True
-    index_column: 
-      value: 'int'
     primary_models: 
       distribution: categorical
       values:

config/sweep_meta_labeling.yaml

@@ -46,8 +46,6 @@ parameters:
       distribution: categorical
     log_returns: 
       value: True
-    index_column: 
-      value: 'int'
     primary_models: 
       value: ["LogisticRegression_two_class", "LDA", "KNN", "CART", "NB", "AB", "RFC", "StaticMom"]
     meta_labeling_models: 

config/sweep_primary_models.yaml

@@ -40,8 +40,6 @@ parameters:
       value: True
     log_returns: 
       value: True
-    index_column: 
-      value: 'int'
     primary_models: 
       values: [['LogisticRegression_two_class'], ['SVC'], ['LDA'], ['KNN'], ['CART'], ['MNB'], ['NB'], ['AB'], ['RFC'], ['XGB_two_class'], ['LGBM']]
       distribution: categorical