refactor(Types): added nested types for Reporting (#162)

training/inference.py

@@ -4,9 +4,9 @@ from data_loader.load_data import load_data
 from typing import Optional, Union
 import warnings
 
-from utils.encapsulation import Asset, Single_Model, Training_Step 
+from reporting.types import Reporting 
 
-def run_inference_pipeline(data_config:dict, training_config:dict, all_models_all_assets:list[Asset]):
+def run_inference_pipeline(data_config:dict, training_config:dict, all_models_all_assets:list[Reporting.Asset]):
     data_params = data_config.copy()
     data_params['target_asset'] = data_params['assets'][0]
     
@@ -20,7 +20,7 @@ def run_inference_pipeline(data_config:dict, training_config:dict, all_models_al
     return result
 
 
-def __inference(data:pd.DataFrame, primary_step:Union[Training_Step,None], secondary_step:Union[Training_Step,None]) -> pd.DataFrame:
+def __inference(data:pd.DataFrame, primary_step:Union[Reporting.Training_Step,None], secondary_step:Union[Reporting.Training_Step,None]) -> pd.DataFrame:
     assert primary_step is not None, "No primary models found. Cancelling Inference."
     
     data = __primary_models(data, primary_step)
@@ -32,7 +32,7 @@ def __inference(data:pd.DataFrame, primary_step:Union[Training_Step,None], secon
     return data
 
 
-def __select_models( data_params:dict, all_models_all_assets:list[Asset])-> tuple[Union[Training_Step,None], Union[Training_Step, None]]:
+def __select_models( data_params:dict, all_models_all_assets:list[Reporting.Asset])-> tuple[Union[Reporting.Training_Step,None], Union[Reporting.Training_Step, None]]:
     target_asset_name = data_params['target_asset'][1]
     primary_step, secondary_step, = None, None
     target_asset_models = next((x for x in all_models_all_assets if x.name == target_asset_name), None)

training/meta_labeling.py

@@ -5,7 +5,7 @@ from feature_selection.feature_selection import select_features
 import pandas as pd
 from models.model_map import default_feature_selector_regression, default_feature_selector_classification
 from models.base import Model
-from utils.encapsulation import Single_Model
+from reporting.types import Reporting
 
 
 def train_meta_labeling_model(
@@ -19,7 +19,7 @@ def train_meta_labeling_model(
                             model_config: dict,
                             training_config: dict,
                             model_suffix: str
-                        ) -> tuple[pd.Series, pd.Series, pd.DataFrame, list[Single_Model]]:
+                        ) -> tuple[pd.Series, pd.Series, pd.DataFrame, list[Reporting.Single_Model]]:
 
     
     discretize = discretize_threeway_threshold(0.33)

training/primary_model.py

@@ -5,8 +5,7 @@ from utils.evaluate import evaluate_predictions
 from models.base import Model
 from utils.scaler import get_scaler
 from utils.types import ScalerTypes
-from utils.encapsulation import Training_Step, Single_Model, Asset
-from transformations.sklearn import SKLearnTransformation
+from reporting.types import Reporting
 
 def train_primary_model(
                     ticker_to_predict: str,
@@ -23,12 +22,12 @@ def train_primary_model(
                     no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced'],
                     level: str,
                     print_results: bool,
-    ) -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame, list[Single_Model]]:
+    ) -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame, list[Reporting.Single_Model]]:
 
     results = pd.DataFrame()
     predictions = pd.DataFrame(index=y.index)
     probabilities = pd.DataFrame(index=y.index)
-    all_models_single_asset:list[Single_Model] = []
+    all_models_single_asset: list[Reporting.Single_Model] = []
     
     
     
@@ -69,7 +68,7 @@ def train_primary_model(
         results[column_name] = result
         
 
-        all_models_single_asset.append(Single_Model(model_name=column_name, model_over_time=model_over_time.tolist()))
+        all_models_single_asset.append(Reporting.Single_Model(model_name=column_name, model_over_time=model_over_time.tolist()))
   
         # column names for model outputs should be different, so we can differentiate between original data and model predictions later, where necessary
         predictions[column_name] = preds

training/training_steps.py

@@ -4,11 +4,20 @@ from operator import itemgetter
 from training.primary_model import train_primary_model
 from training.meta_labeling import train_meta_labeling_model
 
-from utils.encapsulation import Reporting, Asset, Single_Model, Training_Step
+from reporting.types import Reporting
 
 
-def primary_step(X: pd.DataFrame, y:pd.Series, original_X:pd.DataFrame, X_pca:pd.DataFrame, asset:list, target_returns:pd.Series, configs: dict, reporting: Reporting) -> tuple[Training_Step, pd.DataFrame]:
-    training_step = Training_Step(level='primary')
+def primary_step(
+                X: pd.DataFrame,
+                y:pd.Series,
+                original_X:pd.DataFrame,
+                X_pca:pd.DataFrame,
+                asset:list,
+                target_returns:pd.Series,
+                configs: dict,
+                reporting: Reporting
+                ) -> tuple[Reporting.Training_Step, pd.DataFrame]:
+    training_step = Reporting.Training_Step(level='primary')
     model_config, training_config, data_config = itemgetter('model_config', 'training_config', 'data_config')(configs)
 
     # 3. Train Primary models
@@ -60,8 +69,18 @@ def primary_step(X: pd.DataFrame, y:pd.Series, original_X:pd.DataFrame, X_pca:pd
     return training_step, current_predictions
 
 
-def secondary_step(X:pd.DataFrame, y:pd.Series, original_X:pd.DataFrame, X_pca:pd.DataFrame, current_predictions:pd.DataFrame, asset:list, target_returns:pd.Series, configs: dict, reporting: Reporting) -> Training_Step:
-    training_step = Training_Step(level='secondary')
+def secondary_step(
+                X:pd.DataFrame,
+                y:pd.Series,
+                original_X:pd.DataFrame,
+                X_pca:pd.DataFrame,
+                current_predictions:pd.DataFrame,
+                asset:list,
+                target_returns:pd.Series,
+                configs: dict,
+                reporting: Reporting
+                ) -> Reporting.Training_Step:
+    training_step = Reporting.Training_Step(level='secondary')
     model_config, training_config, data_config = itemgetter('model_config', 'training_config', 'data_config')(configs)
     
     # 5. Ensemble primary model predictions (If Ensemble model is present)
@@ -90,7 +109,6 @@ def secondary_step(X:pd.DataFrame, y:pd.Series, original_X:pd.DataFrame, X_pca:p
         reporting.all_predictions = pd.concat([reporting.all_predictions, ensemble_predictions], axis=1)
     
         
-        
         if len(model_config['meta_labeling_models']) > 0: 
 
             # 3. Train a Meta-labeling model on the averaged level-1 model predictions