From 8d8c782bd039780f8563e8edf7f735501c9013ab Mon Sep 17 00:00:00 2001
From: Rokas Kupstys <rokups@zoho.com>
Date: Sat, 8 May 2021 16:06:19 +0300
Subject: [PATCH] Slice dataframe in backtesting, preventing access to rows
 past current time.

---
 freqtrade/data/dataprovider.py    | 21 ++++++++++++++++++---
 freqtrade/optimize/backtesting.py |  8 ++++++--
 2 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/freqtrade/data/dataprovider.py b/freqtrade/data/dataprovider.py
index 727768ebb..a5d059e4a 100644
--- a/freqtrade/data/dataprovider.py
+++ b/freqtrade/data/dataprovider.py
@@ -20,6 +20,7 @@ from freqtrade.state import RunMode
 logger = logging.getLogger(__name__)
 
 NO_EXCHANGE_EXCEPTION = 'Exchange is not available to DataProvider.'
+MAX_DATAFRAME_CANDLES = 1000
 
 
 class DataProvider:
@@ -29,6 +30,14 @@ class DataProvider:
         self._exchange = exchange
         self._pairlists = pairlists
         self.__cached_pairs: Dict[PairWithTimeframe, Tuple[DataFrame, datetime]] = {}
+        self.__slice_index = None
+
+    def _set_dataframe_max_index(self, limit_index: int):
+        """
+        Limit analyzed dataframe to max specified index.
+        :param limit_index: dataframe index.
+        """
+        self.__slice_index = limit_index
 
     def _set_cached_df(self, pair: str, timeframe: str, dataframe: DataFrame) -> None:
         """
@@ -85,10 +94,16 @@ class DataProvider:
             combination.
             Returns empty dataframe and Epoch 0 (1970-01-01) if no dataframe was cached.
         """
-        if (pair, timeframe) in self.__cached_pairs:
-            return self.__cached_pairs[(pair, timeframe)]
+        pair_key = (pair, timeframe)
+        if pair_key in self.__cached_pairs:
+            if self.runmode in (RunMode.DRY_RUN, RunMode.LIVE):
+                df, date = self.__cached_pairs[pair_key]
+            else:
+                max_index = self.__slice_index
+                df, date = self.__cached_pairs[pair_key]
+                df = df.iloc[max(0, max_index - MAX_DATAFRAME_CANDLES):max_index]
+            return df, date
         else:
-
             return (DataFrame(), datetime.fromtimestamp(0, tz=timezone.utc))
 
     @property
diff --git a/freqtrade/optimize/backtesting.py b/freqtrade/optimize/backtesting.py
index 80eb34c30..f7c984047 100644
--- a/freqtrade/optimize/backtesting.py
+++ b/freqtrade/optimize/backtesting.py
@@ -373,8 +373,9 @@ class Backtesting:
             open_trade_count_start = open_trade_count
 
             for i, pair in enumerate(data):
+                row_index = indexes[pair]
                 try:
-                    row = data[pair][indexes[pair]]
+                    row = data[pair][row_index]
                 except IndexError:
                     # missing Data for one pair at the end.
                     # Warnings for this are shown during data loading
@@ -383,7 +384,10 @@ class Backtesting:
                 # Waits until the time-counter reaches the start of the data for this pair.
                 if row[DATE_IDX] > tmp:
                     continue
-                indexes[pair] += 1
+
+                row_index += 1
+                self.dataprovider._set_dataframe_max_index(row_index)   # noqa
+                indexes[pair] = row_index
 
                 # without positionstacking, we can only have one open trade per pair.
                 # max_open_trades must be respected