feat(Project): use SKLearn models directly, removed custom ensembling, use 5 minute data, batch inference, numba cusum filter (#192)

* feat(Project): use 5 minute data, running training in parallel, sped up cusum filter by 10x with numba

* fix(WalkForward): inference mini-batch parallelization

* fix(WalkForward): don't use the parallel version of any of the functions

* feat(CI): download the data required

* fix(Project): 5min_crypto folder added

* fix(Evaluate): make sure we have numerical stability in returns

* feat(Models): use SKLearn models directly to enable composability

* feat(Inference): batched inference now working, added forecasting_horizon

* fix(Inference): works again

* fix(Inference)

* chore(Models): remove unused Ensemble model

* fix(Labeller): don't just forward shift returns, also take the sum of the data happened until then

* Update test.yml

labeling/event_filters/cusum.py

@@ -1,8 +1,11 @@
 
 
+from numpy import float32
 from ..types import EventFilter
 from data_loader.types import ReturnSeries
 import pandas as pd
+from numba import njit
+from numba.typed import List
 
 class CUSUMVolatilityEventFilter(EventFilter):
 
@@ -11,7 +14,7 @@ class CUSUMVolatilityEventFilter(EventFilter):
 
     def get_event_start_times(self, returns: ReturnSeries) -> pd.DatetimeIndex:
 
-        rolling_vol = returns.rolling(self.vol_period).std() * 0.15
+        rolling_vol = returns.rolling(self.vol_period).std().mean()
 
         filtered_indices = []
         pos_threshold = 0
@@ -39,22 +42,28 @@ class CUSUMFixedEventFilter(EventFilter):
         self.threshold = threshold
 
     def get_event_start_times(self, returns: ReturnSeries) -> pd.DatetimeIndex:
-        filtered_indices = []
-        pos_threshold = 0
-        neg_threshold = 0
-        diff = returns.diff()
-        for index in diff.index[1:]:
-            pos_threshold, neg_threshold = (
-                max(0, pos_threshold + diff.loc[index]),
-                min(0, neg_threshold + diff.loc[index]),
-            )
+        diffed_returns = returns.diff()
+        int_indicies = _process(List(diffed_returns.to_list()), abs(returns.mean()) * self.threshold)
 
-            if neg_threshold < -self.threshold:
-                neg_threshold = 0
-                filtered_indices.append(index)
+        return pd.DatetimeIndex([returns.index[i] for i in int_indicies])
 
-            elif pos_threshold > self.threshold:
-                pos_threshold = 0
-                filtered_indices.append(index)
+@njit
+def _process(diffed_returns: List, threshold: float32) -> List:
+    pos_threshold: float32 = 0.0 # type: ignore
+    neg_threshold: float32 = 0.0 # type: ignore
+    filtered_indicies = List()
+    for index in range(1, len(diffed_returns[1:])):
+        pos_threshold, neg_threshold = ( # type: ignore
+            max(0, pos_threshold + diffed_returns[index]), # type: ignore
+            min(0, neg_threshold + diffed_returns[index]), # type: ignore
+        )
 
-        return pd.DatetimeIndex(filtered_indices)
+        if neg_threshold < -threshold:
+            neg_threshold = 0.0 # type: ignore
+            filtered_indicies.append(index)
+
+        elif pos_threshold > threshold:
+            pos_threshold = 0.0 # type: ignore
+            filtered_indicies.append(index)
+
+    return filtered_indicies