feature(MetaLabeling): replaced previous non-functional Ensembling method with Meta-labeling method available for both lvl1 and lvl2 models (#110)

* feature(MetaLabeling): added hacky prototype

* fix(MetaLabeling): drop index until first valid X & y

* fix(MetaLabeling): transform both X & y before feature selection

* fix(MetaLabeling): got feature selection to work

* fix(MetaLabeling): correct values for meta_y

* feat(MetaLabeling): created predictions multiplied by bet sizes

* feat(Pipeline): print out averaged result

* fix(Evaluation): correctly deal with non-discretized data

* fix(Pipeline): use the right column names

* refactor(Pipeline): move out meta-labeling

* refactor(Pipeline): complete refactoring

* feat(CI): post results to PR

* fix(Pipeline): use the correct filename

* chore(Config): removed now redundant feature_selection flag

* feat(Models): added SVC

* fix(Pipeline): accidentally switched two return values

* feat(Sweep): prepared sweep_meta.yaml, moved report_results() into a separate file

* fix(Pipeline): wrong function name

* fix(Sweep): yaml + run_sweep

* fix(Sweep): typo in name

* fix(Reporting): only save averaged results

* feat(MetaLabeling): use optional meta-labeling step for every lvl1 models, before averaging

* feat(Reporting): print out sharpe improvement in meta-labeling step

* fix(Sweep): adjusted config, defaulted to good defaults

* fix(Sweep): adjusted sweep

utils/helpers.py

@@ -1,12 +1,15 @@
 import pandas as pd
 import numpy as np
 import os
+import string
+import random
+from typing import Union
 
 def get_files_from_dir(path: str) -> list[str]:
     return [f for f in os.listdir(path) if os.path.isfile(os.path.join(path,f)) and not f.startswith('.')]
 
 def get_first_valid_return_index(series: pd.Series) -> int:
-    double_nested_results = np.where(np.logical_and(series != 0, np.logical_not(np.isnan(series))))
+    double_nested_results = np.where(np.logical_and(series != 0, np.logical_not(pd.isna(series))))
     if len(double_nested_results) == 0:
         return 0
     nested_result = double_nested_results[0]
@@ -17,7 +20,7 @@ def get_first_valid_return_index(series: pd.Series) -> int:
 def flatten(list_of_lists: list) -> list:
     return [item for sublist in list_of_lists for item in sublist]
 
-def weighted_average(df: pd.DataFrame, weights_source: str) -> pd.DataFrame:
+def weighted_average(df: pd.DataFrame, weights_source: str) -> pd.Series:
     if df.shape[0] == 0:
         return df
     mean_df = df.iloc[:,0]
@@ -35,4 +38,19 @@ def drop_columns_if_exist(df: pd.DataFrame, columns: list) -> pd.DataFrame:
     for column in columns:
         if column in df.columns:
             df = df.drop(column, axis=1)
-    return df
+    return df
+
+def random_string(n: int) -> str:
+    return ''.join(random.choices(string.ascii_uppercase + string.digits, k=n))
+
+def equal_except_nan(row: pd.Series):
+    if np.isnan(row.iloc[0]) or np.isnan(row.iloc[1]):
+        return np.nan
+    if row.iloc[0] == row.iloc[1]:
+        return 1.
+    else:
+        return 0.
+
+def drop_until_first_valid_index(df: pd.DataFrame, series: pd.Series) -> tuple[pd.DataFrame, pd.Series]:
+    first_valid_index = max(get_first_valid_return_index(df.iloc[:,0]), get_first_valid_return_index(series))
+    return df.iloc[first_valid_index:], series.iloc[first_valid_index:]