fix(Config): set remove_overlapping_events=True (#246)

* fix(Config): set remove_overlapping_events=True

* fix(Config): only use level_1 features

* feat(Config): added get_minimal_config

config/presets.py

@@ -24,14 +24,53 @@ def get_default_config() -> RawConfig:
         other_assets=[],
         exogenous_data=[],
         load_non_target_asset=True,
-        own_features=["level_2"],
+        own_features=["level_1"],
         other_features=["z_score"],
         exogenous_features=[],
         directional_models=classification_models,
         meta_models=meta_models,
         event_filter="cusum_vol",
         event_filter_multiplier=3.5,
-        remove_overlapping_events=False,
+        remove_overlapping_events=True,
+        labeling="two_class",
+        forecasting_horizon=10,
+        transaction_costs=0.002,
+        save_models=True,
+        ensembling_method="voting_soft",
+    )
+
+
+def get_minimal_config() -> RawConfig:
+
+    classification_models = [
+        "LogisticRegression_two_class",
+        # "LDA",
+        # "NB",
+        # "RFC",
+        # "LGBM",
+        # "StaticMom",
+    ]
+    meta_models = ["LogisticRegression_two_class", "LGBM"]
+
+    return RawConfig(
+        dimensionality_reduction_ratio=0,
+        n_features_to_select=0,
+        initial_window_size=3800,
+        retrain_every=2000,
+        scaler="minmax",  # 'normalize' 'minmax' 'standardize' 'robust'
+        assets=["fivemin_crypto"],
+        target_asset="BTCUSDT",
+        other_assets=[],
+        exogenous_data=[],
+        load_non_target_asset=False,
+        own_features=[],
+        other_features=[],
+        exogenous_features=[],
+        directional_models=classification_models,
+        meta_models=meta_models,
+        event_filter="none",
+        event_filter_multiplier=3.5,
+        remove_overlapping_events=True,
         labeling="two_class",
         forecasting_horizon=10,
         transaction_costs=0.002,

tests/test_evaluation.py

@@ -1,6 +1,6 @@
 import numpy as np
 import pandas as pd
-from training.walk_forward import walk_forward_train, walk_forward_inference
+from training.walk_forward import walk_forward_train, walk_forward_inference_batched
 from models.base import Model
 from utils.evaluate import evaluate_predictions
 from sklearn.base import BaseEstimator, ClassifierMixin
@@ -74,7 +74,7 @@ def test_evaluation():
         from_index=None,
         transformations_over_time=[],
     )
-    predictions, _ = walk_forward_inference(
+    predictions, _ = walk_forward_inference_batched(
         model_name="test",
         model_over_time=model_over_time,
         transformations_over_time=[],

tests/test_walk_forward.py

@@ -1,6 +1,6 @@
 import numpy as np
 import pandas as pd
-from training.walk_forward import walk_forward_train, walk_forward_inference
+from training.walk_forward import walk_forward_train, walk_forward_inference_batched
 from models.base import Model
 from sklearn.base import BaseEstimator, ClassifierMixin
 
@@ -70,7 +70,7 @@ def test_walk_forward_train_test():
         from_index=None,
         transformations_over_time=[],
     )
-    predictions, _ = walk_forward_inference(
+    predictions, _ = walk_forward_inference_batched(
         model_name="test",
         model_over_time=model_over_time,
         transformations_over_time=[],