Refactor(Training): new outcome types, representative pipeline steps, bet-sizing (#187)

* refactor(Training): added InferenceResult & TrainedModel types * refactor(Pipeline): introduced TrainingOutcome, BetSizingWithMetaOutcome, etc. * fix(Pipeline): getting it to compile * refactor(WalkForward): separate preprocessing step * feat(Pipeline): separate out transformations processing step * refactor(Pipeline): use the Directional model terminology, put bet_sizing into pipeline instead of hiding it in a step * refactor(WalkForward): moved functions to separate folder * fix(WalkForward): use sparse array to store models, process transformations in parallel (lot faster) * fix(Tests): and evaluation * fix(Tests): for realz * fix(Inference): preloading everything now, renamed primary models to directional models * fix(BetSizing): was running transformations on the wrong data, oops * fix(BetSizing): concatenated on the wrong axis accidentally * fix(Reporting): able to use the new Stats type * fix(BetSizing): renamed int column names * fix(Portfolio): name the column properly * fix(Reporting): rename the correct Series, lol * fix(Inference): walk_forwad_inference() can deal with models not being aligned with the starting index * fix(WalkForward): accidentally using the wrong index * fix(WalkForward): use the correct indicies to fetch last model/transformations * fix(CI): changed the name of the results
2026-08-15 20:08:08 +00:00 · 2022-01-29 06:41:40 +01:00
parent 42a1bc59cb
commit 3eb3ea94e3
42 changed files with 772 additions and 736 deletions
@@ -0,0 +1,62 @@
+import pandas as pd
+
+from .types import DirectionalTrainingOutcome
+from training.train_model import train_model
+from training.walk_forward import walk_forward_process_transformations
+
+from typing import Optional
+from config.types import Config 
+from models.base import Model
+from models.model_map import default_feature_selector_classification
+
+from transformations.scaler import get_scaler
+from transformations.rfe import RFETransformation
+from transformations.pca import PCATransformation
+
+def train_directional_models(
+                X: pd.DataFrame,
+                y: pd.Series,
+                forward_returns: pd.Series,
+                config: Config,
+                models: list[Model],
+                from_index: Optional[pd.Timestamp],
+                preloaded_training_step: Optional[DirectionalTrainingOutcome] = None,
+            ) -> DirectionalTrainingOutcome:
+
+    if preloaded_training_step is None:
+        print("Preprocess transformations")
+        transformations_over_time = walk_forward_process_transformations(
+            X = X,
+            y = y,
+            forward_returns = forward_returns,
+            expanding_window = config.expanding_window_base,
+            window_size = config.sliding_window_size_base,
+            retrain_every = config.retrain_every,
+            from_index = from_index,
+            transformations= [
+                get_scaler(config.scaler),
+                PCATransformation(ratio_components_to_keep=0.5, sliding_window_size=config.sliding_window_size_base),
+                RFETransformation(n_feature_to_select=40, model=default_feature_selector_classification)
+            ],
+        )
+    else:
+        transformations_over_time = preloaded_training_step.transformations
+
+    training_outcomes = [train_model(
+        ticker_to_predict = config.target_asset[1],
+        X = X,
+        y = y,
+        forward_returns = forward_returns,
+        model = model,
+        expanding_window = config.expanding_window_base,
+        sliding_window_size = config.sliding_window_size_base,
+        retrain_every =  config.retrain_every,
+        from_index = from_index,
+        no_of_classes = config.no_of_classes,
+        level = 'primary',
+        print_results= True,
+        transformations_over_time = transformations_over_time,
+        model_over_time = preloaded_training_step.training[index].model_over_time if preloaded_training_step else None
+    ) for index, model in enumerate(models)]
+    return DirectionalTrainingOutcome(training_outcomes, transformations_over_time)
+