From 22b3167cb9847fce50db529b114d85f20e860178 Mon Sep 17 00:00:00 2001
From: Mark Aron Szulyovszky <mark.szulyovszky@gmail.com>
Date: Sun, 9 Jan 2022 14:18:20 +0100
Subject: [PATCH] feat(Evaluate): increase transactions costs, to get a more
 realistic view on performance (#137)

---
 data_loader/load_data.py | 13 ++++++++++++-
 utils/evaluate.py        |  2 +-
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/data_loader/load_data.py b/data_loader/load_data.py
index e56f2b4..03595de 100644
--- a/data_loader/load_data.py
+++ b/data_loader/load_data.py
@@ -55,6 +55,15 @@ def __load_data(assets: DataCollection,
         narrow_format=narrow_format,
     ) for data_source in target_file]
     target_asset_df = ray.get(target_asset_future)
+    
+    target_asset_only_returns_future = __load_df.remote(
+        data_source=target_file[0],
+        prefix=target_file[0][1],
+        returns='returns',
+        feature_extractors=[],
+        narrow_format=narrow_format,
+    )
+    df_target_asset_only_returns = ray.get(target_asset_only_returns_future)
 
     asset_futures = [__load_df.remote(
         data_source=data_source,
@@ -86,14 +95,16 @@ def __load_data(assets: DataCollection,
 
     if index_column == 'int':
         dfs.reset_index(drop=True, inplace=True)
+        df_target_asset_only_returns.reset_index(drop=True, inplace=True)
 
     if narrow_format:
         dfs = dfs.drop(index=dfs.index[0], axis=0)
+        df_target_asset_only_returns = df_target_asset_only_returns.drop(index=dfs.index[0], axis=0)
 
     ## Create target 
     target_col = 'target'
     returns_col = target_asset[1] + '_returns'
-    forward_returns = __create_target_cum_forward_returns(dfs, returns_col, forecasting_horizon)
+    forward_returns = __create_target_cum_forward_returns(df_target_asset_only_returns, returns_col, forecasting_horizon)
     if method == 'regression':
         dfs[target_col] = forward_returns
     elif method == 'classification':
diff --git a/utils/evaluate.py b/utils/evaluate.py
index e4666d3..a0d6a04 100644
--- a/utils/evaluate.py
+++ b/utils/evaluate.py
@@ -6,7 +6,7 @@ from utils.helpers import get_first_valid_return_index
 import pandas as pd
 import numpy as np
 
-def backtest(returns: pd.Series, signal: pd.Series, transaction_cost = 0.002) -> pd.Series:
+def backtest(returns: pd.Series, signal: pd.Series, transaction_cost = 0.008) -> pd.Series:
     delta_pos = signal.diff(1).abs().fillna(0.)
     costs = transaction_cost * delta_pos
     return (signal * returns) - costs