feat(Core): ensemble models, correct forward returns calculation, scaling, only train from when asset returns are available, major bug fixed in walk_forward_train_test (#35)

* fix(Core): correct forward returns calculation, classifiers are now working again, only train from when asset returns are available * feat(Utils): added get_first_valid_return_index() * feat(Ensemble): return models from `run_whole_pipeline` * feat(Ensemble): added ensemble step, fixed walk_forward_train_test predictions index confusion, * chore(Pipeline): remove unnecessary extra ensemble results dataframe * refactor(Core): removed unnecessary ensemble_train_predict, moved run_single_asset_trainig_pipeline to a separate file * feat(Training): added scaling on expanding window (the past) to walk_forward_train_test(), now printing out mean sharpe ratio * feat(CI): added environment.yml file * chore(Environment): update env.yml * feat(CI): added testing workflow * fix(CI): renamed enviroment.yml * fix(Tests): added missing new parameter to walk_forward_train_test()
2026-08-21 14:58:11 +00:00 · 2021-12-17 14:32:17 +01:00
parent 1eaba0c221
commit cc7061b456
12 changed files with 385 additions and 195 deletions
@@ -0,0 +1,60 @@
+import pandas as pd
+from typing import Literal
+from training.walk_forward import walk_forward_train_test
+from sklearn.preprocessing import MinMaxScaler, Normalizer, StandardScaler
+from utils.evaluate import evaluate_predictions
+from utils.typing import SKLearnModel
+
+def __get_scaler(type: Literal['normalize', 'minmax', 'standardize', 'none']):
+    if type == 'normalize':
+        return Normalizer()
+    elif type == 'minmax':
+        return MinMaxScaler(feature_range= (-1, 1))
+    elif type == 'standardize':
+        return StandardScaler()
+    else:
+        return None
+
+def run_single_asset_trainig_pipeline(
+                    ticker_to_predict: str,
+                    X: pd.DataFrame,
+                    y: pd.Series,
+                    target_returns: pd.Series,
+                    models: list[tuple[str, SKLearnModel]],
+                    method: Literal['regression', 'classification'],
+                    sliding_window_size: int,
+                    retrain_every: int,
+                    scaler: Literal['normalize', 'minmax', 'standardize', 'none'],
+                    ) -> tuple[pd.DataFrame, pd.DataFrame]:
+
+
+    scaler = __get_scaler(scaler)
+
+    results = pd.DataFrame()
+    predictions = pd.DataFrame()
+
+    for model_name, model in models:
+
+        model_over_time, preds = walk_forward_train_test(
+            model_name=model_name,
+            model = model,
+            X = X,
+            y = y,
+            target_returns = target_returns,
+            window_size = sliding_window_size,
+            retrain_every = retrain_every,
+            scaler = scaler
+        )
+        assert len(preds) == len(y)
+        result = evaluate_predictions(
+            model_name = model_name,
+            target_returns = target_returns,
+            y_pred = preds,
+            sliding_window_size = sliding_window_size,
+            method = method,
+        )
+        column_name = ticker_to_predict + "_" + model_name
+        results[column_name] = result
+        predictions[column_name] = preds
+
+    return results, predictions