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
2026-08-13 10:58:06 +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 +1,55 @@
+import pandas as pd
+from models.base import Model
+from training.types import ModelOverTime, TransformationsOverTime
+from utils.helpers import get_first_valid_return_index
+from tqdm import tqdm
+from typing import Optional
+from data_loader.types import ForwardReturnSeries, XDataFrame, ySeries
+
+
+def walk_forward_train(
+                    model: Model,
+                    X: XDataFrame,
+                    y: ySeries,
+                    forward_returns: ForwardReturnSeries,
+                    expanding_window: bool,
+                    window_size: int,
+                    retrain_every: int,
+                    from_index: Optional[pd.Timestamp],
+                    transformations_over_time: TransformationsOverTime,
+                ) -> ModelOverTime:
+    models_over_time = pd.Series(index=y.index).rename(model.name)
+
+    first_nonzero_return = max(get_first_valid_return_index(forward_returns), get_first_valid_return_index(X.iloc[:,0]), get_first_valid_return_index(y))
+    train_from = first_nonzero_return + window_size + 1 if from_index is None else X.index.to_list().index(from_index)
+    train_till = len(y)
+
+    if model.only_column is not None:
+        X = X[[column for column in X.columns if model.only_column in column]]
+    
+    if model.data_transformation == 'original':
+        transformations_over_time = []
+    
+    for index in tqdm(range(train_from, train_till, retrain_every)):
+        train_window_start = X.index[first_nonzero_return] if expanding_window else X.index[index - window_size - 1]
+
+        train_window_end = X.index[index - 1]
+        current_transformations = [transformation_over_time[index] for transformation_over_time in transformations_over_time]
+        X_slice = X[train_window_start:train_window_end]
+
+        for transformation in current_transformations:
+            X_slice = transformation.transform(X_slice)
+        
+        X_slice = X_slice.to_numpy()
+        y_slice = y[train_window_start:train_window_end].to_numpy()
+
+        current_model = model.clone()
+
+        current_model.initialize_network(input_dim = len(X_slice[0]), output_dim=1) 
+        current_model.fit(X_slice, y_slice)
+
+        models_over_time[X.index[index]] = current_model
+        for transformation_index, transformation in enumerate(current_transformations):
+            transformations_over_time[transformation_index][X.index[index]] = transformation
+
+    return models_over_time