feat(HPO): added run_hpo script (#237)

* feat(HPO): added `run_hpo` script

* fix(Linter): ran

* feat(HPO): removed any reference to sweep (superseeded by optuna)

* fix(HPO): optimize for sharpe

* fix(Config): removed glassnode data, save trials from hpo

* feat(Labelling): added three-balanced method works again

* fix(BetSizing): set the correct class labels

* fix(HPO): powerset should return what's expected, added two new normalization methods

* fix(Linter): ran

* fix(DataLoader): sort the dataframe when fetching data

* fix(Config): only take z-score of other assets

labeling/event_filters/cusum.py

@@ -7,7 +7,7 @@ from numba.typed import List
 
 
 class CUSUMVolatilityEventFilter(EventFilter):
-    def __init__(self, vol_period: int, multiplier: float):
+    def __init__(self, multiplier: float, vol_period=100):
         self.vol_period = vol_period
         self.multiplier = multiplier
 
@@ -23,13 +23,14 @@ class CUSUMVolatilityEventFilter(EventFilter):
 
 
 class CUSUMFixedEventFilter(EventFilter):
-    def __init__(self, threshold: float):
-        self.threshold = threshold
+    def __init__(self, threshold_multiplier: float):
+        self.threshold_multiplier = threshold_multiplier
 
     def get_event_start_times(self, returns: ReturnSeries) -> pd.DatetimeIndex:
         diffed_returns = returns.diff()
-        int_indicies = _process_fixed(
-            List(diffed_returns.to_list()), abs(returns.mean()) * self.threshold
+        int_indicies = _process(
+            List(diffed_returns.to_list()),
+            abs(returns.mean()) * self.threshold_multiplier,
         )
 
         return pd.DatetimeIndex([returns.index[i] for i in int_indicies])

labeling/event_filters/nofilter.py

@@ -4,5 +4,8 @@ import pandas as pd
 
 
 class NoEventFilter(EventFilter):
+    def __init__(self, ignored_threshold_multiplier: float):
+        pass
+
     def get_event_start_times(self, returns: ReturnSeries) -> pd.DatetimeIndex:
         return returns.index