fix(Reporting): use weighted average (with no_of_samples as weights) and only report level-1 OR level-2 model performance (#91)

* fix(Reporting): use weighted average (with no_of_samples as weights) and only report level-1 OR level-2 model performance

* chore(Config): updated sweep config

* fix(Reporting): missing import

* fix(Evaluation): get_first_valid_return_index can deal with zero valid indexes

* fix(Training): increase threshold for skipping assets

* fix(DataLoader): target asset should be always the first column

utils/helpers.py

@@ -3,7 +3,24 @@ import pandas as pd
 import numpy as np
 
 def get_first_valid_return_index(series: pd.Series) -> int:
-    return np.where(np.logical_and(series != 0, np.logical_not(np.isnan(series))))[0][0]
+    double_nested_results = np.where(np.logical_and(series != 0, np.logical_not(np.isnan(series))))
+    if len(double_nested_results) == 0:
+        return 0
+    nested_result = double_nested_results[0]
+    if len(nested_result) == 0:
+        return 0
+    return nested_result[0]
 
 def flatten(list_of_lists: list) -> list:
-    return [item for sublist in list_of_lists for item in sublist]
+    return [item for sublist in list_of_lists for item in sublist]
+
+def weighted_average(df: pd.DataFrame, weights_source: str) -> pd.DataFrame:
+    mean_df = df.iloc[:,0]
+    weights = df.loc[weights_source]
+
+    for i, row in df.iterrows():
+        if i == weights_source: continue
+        mean_df.loc[i] = (row * weights).sum() / df.loc[weights_source].sum()
+
+    return mean_df
+

utils/load_data.py

@@ -35,9 +35,10 @@ def load_data(path: str,
         - Series `forward_returns` with the target asset returns shifted by 1 day
     """
 
-    
     files = [f for f in os.listdir(path) if os.path.isfile(os.path.join(path,f)) and not f.startswith('.')]
-    files = [f for f in files if load_other_assets == True or (load_other_assets == False and f.startswith(target_asset))]
+    target_file = [f for f in files if f.startswith(target_asset)]
+    other_files = [f for f in files if load_other_assets == True and f.startswith(target_asset) == False]
+    files = target_file + other_files
     def is_target_asset(target_asset: str, file: str): return file.split('.')[0].startswith(target_asset)
     dfs = [__load_df(
         path=os.path.join(path,f),