refactor(Evaluate): print out accuracy, f1, etc. for the final & meta predictions, separated out evaluation step (#228)

* refactor(Evaluate): print out accuracy, f1, etc. for the final & meta predictions, separated out evaluation step

* fix(Linter): ran

* fix(Tests): syntax change

* fix(Inference): runs now again

* fix(Linter): ran

labeling/labellers/fixed_time_three_class_imbalanced.py

@@ -1,6 +1,7 @@
 from ..types import EventLabeller, EventsDataFrame, ReturnSeries
 import pandas as pd
 from .utils import create_forward_returns
+from typing import Callable
 
 
 class FixedTimeHorionThreeClassImbalancedEventLabeller(EventLabeller):
@@ -51,3 +52,9 @@ class FixedTimeHorionThreeClassImbalancedEventLabeller(EventLabeller):
             }
         )
         return events
+
+    def get_labels(self) -> list[int]:
+        return [-1, 0, 1]
+
+    def get_discretize_function(self) -> Callable:
+        raise NotImplementedError