feat(Models): added debug_future_lookahead, sped up LogisticRegression & DecisionTreeClassifier (#74)

* feat(Models): added `debug_future_lookahead`, sped up LogisticRegression & DecisionTreeClassifier

* feat(Training): added ability to train on expanding_window

* feat(Models): tuned some hyperparameters, added expanding_window to sweep config, fixed tests

* feat(Models): tune parameters of ensemble models

* fix(Config): use window size that works with ensembling

config.py

@@ -5,8 +5,9 @@ from models.model_map import model_names_classification, model_names_regression
 def get_default_config() -> tuple[dict, dict, dict]:
   
     training_config = dict(
-        sliding_window_size = 150,
+        expanding_window = True,
-        retrain_every = 20,
+        sliding_window_size = 200,
+        retrain_every = 100,
         scaler = 'minmax', # 'normalize' 'minmax' 'standardize' 'none'
         include_original_data_in_ensemble = True,
     )

environment.yml

@@ -8,6 +8,7 @@ dependencies:
   - seaborn
   - scikit-learn-intelex=2021.4.0
   - ipython
+  - ipykernel
   - scipy
   - scikit-learn
   - numba

feature_extractors/feature_extractor_presets.py

@@ -1,4 +1,6 @@
-from feature_extractors.feature_extractors import feature_lag, feature_mom, feature_ROC, feature_RSI, feature_STOD, feature_STOK, feature_vol, feature_day_of_month, feature_day_of_week, feature_month
+from feature_extractors.feature_extractors import feature_lag, feature_mom, feature_ROC, feature_RSI, feature_STOD, feature_STOK, feature_vol, feature_day_of_month, feature_day_of_week, feature_month, feature_debug_future_lookahead
+
+debug_future_lookahead = [('debug_future', feature_debug_future_lookahead, [1])]
 
 lags = [('lag', feature_lag, [1,2,3,4,5,6,7,8,9])]
 

feature_extractors/feature_extractors.py

@@ -11,7 +11,11 @@ def __get_close_low_high(df: pd.DataFrame) -> tuple[pd.Series, pd.Series, pd.Ser
 
 ## Feature extractors
 
+def feature_debug_future_lookahead(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+    return df['returns'].shift(-period)
+
 def feature_lag(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+    assert period > 0
     return df['returns'].shift(period)
 
 def feature_day_of_week(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.DataFrame:

models/model_map.py

@@ -15,25 +15,25 @@ from models.naive import StaticNaiveModel
 
 model_map = {
     "regression_models": dict(
-        Lasso = SKLearnModel(Lasso(alpha=0.1, max_iter=1000)),
+        LR = SKLearnModel(LinearRegression(n_jobs=-1)),
+        Lasso = SKLearnModel(Lasso(alpha=100, random_state=1)),
         Ridge = SKLearnModel(Ridge(alpha=0.1)),
         BayesianRidge = SKLearnModel(BayesianRidge()),
         KNN = SKLearnModel(KNeighborsRegressor(n_neighbors=25)),
         AB = SKLearnModel(AdaBoostRegressor(random_state=1)),
-        LR = SKLearnModel(LinearRegression(n_jobs=-1)),
         MLP = SKLearnModel(MLPRegressor(hidden_layer_sizes=(100,20), max_iter=1000)),
         RF = SKLearnModel(RandomForestRegressor(n_jobs=-1)),
         SVR = SKLearnModel(SVR(kernel='rbf', C=1e3, gamma=0.1)),
         StaticNaive = StaticNaiveModel(),
     ),
     "classification_models": dict(
-        LR= SKLearnModel(LogisticRegression(n_jobs=-1)),
+        LR= SKLearnModel(LogisticRegression(solver='liblinear', C=10, max_iter=1000)),
         LDA= SKLearnModel(LinearDiscriminantAnalysis()),
         KNN= SKLearnModel(KNeighborsClassifier()),
-        CART= SKLearnModel(DecisionTreeClassifier()),
+        CART= SKLearnModel(DecisionTreeClassifier(max_depth=15, random_state=1)),
         NB= SKLearnModel(GaussianNB()),
-        AB= SKLearnModel(AdaBoostClassifier()),
+        AB= SKLearnModel(AdaBoostClassifier(n_estimators=15)),
-        RF= SKLearnModel(RandomForestClassifier(n_jobs=-1)),
+        RF= SKLearnModel(RandomForestClassifier(n_jobs=-1, max_depth=20)),
         StaticMom= StaticMomentumModel(allow_short=True),
     ),     
     "classification_ensemble_models": dict(

run_pipeline.py

@@ -40,6 +40,7 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
             target_returns = target_returns,
             models = model_config['level_1_models'],
             method = data_config['method'],
+            expanding_window = training_config['expanding_window'],
             sliding_window_size = training_config['sliding_window_size'],
             retrain_every =  training_config['retrain_every'],
             scaler =  training_config['scaler'],
@@ -64,6 +65,7 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
                 target_returns = target_returns,
                 models = model_config['level_2_models'],
                 method = data_config['method'],
+                expanding_window = training_config['expanding_window'],
                 sliding_window_size = training_config['sliding_window_size'],
                 retrain_every = training_config['retrain_every'],
                 scaler = training_config['scaler'],

sweep.yaml

@@ -11,6 +11,9 @@ metric:
 parameters:
     path : 
       value: 'data/'
+    expanding_window:
+      values: [True, False]
+      distribution: categorical
     sliding_window_size: 
       values: [90, 130, 160, 180, 280, 380]
       distribution: categorical

tests/test_evaluation.py

@@ -68,6 +68,7 @@ def test_evaluation():
         X=X,
         y=y,
         target_returns=y,
+        expanding_window=False,
         window_size=window_length,
         retrain_every=10,
         scaler=scaler

tests/test_walk_forward.py

@@ -65,6 +65,7 @@ def test_walk_forward_train_test():
         X=X,
         y=y,
         target_returns=y,
+        expanding_window=False,
         window_size=window_length,
         retrain_every=10,
         scaler=scaler)

training/training.py

@@ -22,6 +22,7 @@ def run_single_asset_trainig(
                     target_returns: pd.Series,
                     models: list[tuple[str, Model]],
                     method: Literal['regression', 'classification'],
+                    expanding_window: bool,
                     sliding_window_size: int,
                     retrain_every: int,
                     scaler: Literal['normalize', 'minmax', 'standardize', 'none'],
@@ -45,6 +46,7 @@ def run_single_asset_trainig(
             X = X,
             y = y,
             target_returns = target_returns,
+            expanding_window = expanding_window,
             window_size = sliding_window_size,
             retrain_every = retrain_every,
             scaler = scaler

training/walk_forward.py

@@ -11,6 +11,7 @@ def walk_forward_train_test(
                             X: pd.DataFrame,
                             y: pd.Series,
                             target_returns: pd.Series,
+                            expanding_window: bool,
                             window_size: int,
                             retrain_every: int,
                             scaler,
@@ -35,7 +36,11 @@ def walk_forward_train_test(
     for index in range(train_from, train_till):
 
         if iterations_before_retrain <= 0 or pd.isna(models[index-1]):
-            train_window_start = index - window_size - 1
+            if expanding_window:
+                train_window_start = first_nonzero_return
+            else:
+                train_window_start = index - window_size - 1
+
             train_window_end = index - 1
             
             if is_scaling_on: