merge develop into feat/shuffle_after_split

freqtrade/freqai/RL/Base3ActionRLEnv.py

@@ -0,0 +1,125 @@
+import logging
+from enum import Enum
+
+from gym import spaces
+
+from freqtrade.freqai.RL.BaseEnvironment import BaseEnvironment, Positions
+
+
+logger = logging.getLogger(__name__)
+
+
+class Actions(Enum):
+    Neutral = 0
+    Buy = 1
+    Sell = 2
+
+
+class Base3ActionRLEnv(BaseEnvironment):
+    """
+    Base class for a 3 action environment
+    """
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.actions = Actions
+
+    def set_action_space(self):
+        self.action_space = spaces.Discrete(len(Actions))
+
+    def step(self, action: int):
+        """
+        Logic for a single step (incrementing one candle in time)
+        by the agent
+        :param: action: int = the action type that the agent plans
+            to take for the current step.
+        :returns:
+            observation = current state of environment
+            step_reward = the reward from `calculate_reward()`
+            _done = if the agent "died" or if the candles finished
+            info = dict passed back to openai gym lib
+        """
+        self._done = False
+        self._current_tick += 1
+
+        if self._current_tick == self._end_tick:
+            self._done = True
+
+        self._update_unrealized_total_profit()
+        step_reward = self.calculate_reward(action)
+        self.total_reward += step_reward
+        self.tensorboard_log(self.actions._member_names_[action])
+
+        trade_type = None
+        if self.is_tradesignal(action):
+            if action == Actions.Buy.value:
+                if self._position == Positions.Short:
+                    self._update_total_profit()
+                self._position = Positions.Long
+                trade_type = "long"
+                self._last_trade_tick = self._current_tick
+            elif action == Actions.Sell.value and self.can_short:
+                if self._position == Positions.Long:
+                    self._update_total_profit()
+                self._position = Positions.Short
+                trade_type = "short"
+                self._last_trade_tick = self._current_tick
+            elif action == Actions.Sell.value and not self.can_short:
+                self._update_total_profit()
+                self._position = Positions.Neutral
+                trade_type = "neutral"
+                self._last_trade_tick = None
+            else:
+                print("case not defined")
+
+            if trade_type is not None:
+                self.trade_history.append(
+                    {'price': self.current_price(), 'index': self._current_tick,
+                     'type': trade_type})
+
+        if (self._total_profit < self.max_drawdown or
+                self._total_unrealized_profit < self.max_drawdown):
+            self._done = True
+
+        self._position_history.append(self._position)
+
+        info = dict(
+            tick=self._current_tick,
+            action=action,
+            total_reward=self.total_reward,
+            total_profit=self._total_profit,
+            position=self._position.value,
+            trade_duration=self.get_trade_duration(),
+            current_profit_pct=self.get_unrealized_profit()
+        )
+
+        observation = self._get_observation()
+
+        self._update_history(info)
+
+        return observation, step_reward, self._done, info
+
+    def is_tradesignal(self, action: int) -> bool:
+        """
+        Determine if the signal is a trade signal
+        e.g.: agent wants a Actions.Buy while it is in a Positions.short
+        """
+        return (
+            (action == Actions.Buy.value and self._position == Positions.Neutral)
+            or (action == Actions.Sell.value and self._position == Positions.Long)
+            or (action == Actions.Sell.value and self._position == Positions.Neutral
+                and self.can_short)
+            or (action == Actions.Buy.value and self._position == Positions.Short
+                and self.can_short)
+        )
+
+    def _is_valid(self, action: int) -> bool:
+        """
+        Determine if the signal is valid.
+        e.g.: agent wants a Actions.Sell while it is in a Positions.Long
+        """
+        if self.can_short:
+            return action in [Actions.Buy.value, Actions.Sell.value, Actions.Neutral.value]
+        else:
+            if action == Actions.Sell.value and self._position != Positions.Long:
+                return False
+            return True

freqtrade/freqai/RL/Base4ActionRLEnv.py

@@ -88,7 +88,8 @@ class Base4ActionRLEnv(BaseEnvironment):
                     {'price': self.current_price(), 'index': self._current_tick,
                      'type': trade_type})
 
-        if self._total_profit < 1 - self.rl_config.get('max_training_drawdown_pct', 0.8):
+        if (self._total_profit < self.max_drawdown or
+                self._total_unrealized_profit < self.max_drawdown):
             self._done = True
 
         self._position_history.append(self._position)

freqtrade/freqai/RL/BaseEnvironment.py

@@ -45,7 +45,8 @@ class BaseEnvironment(gym.Env):
     def __init__(self, df: DataFrame = DataFrame(), prices: DataFrame = DataFrame(),
                  reward_kwargs: dict = {}, window_size=10, starting_point=True,
                  id: str = 'baseenv-1', seed: int = 1, config: dict = {}, live: bool = False,
-                 fee: float = 0.0015):
+                 fee: float = 0.0015, can_short: bool = False, pair: str = "",
+                 df_raw: DataFrame = DataFrame()):
         """
         Initializes the training/eval environment.
         :param df: dataframe of features
@@ -58,13 +59,16 @@ class BaseEnvironment(gym.Env):
         :param config: Typical user configuration file
         :param live: Whether or not this environment is active in dry/live/backtesting
         :param fee: The fee to use for environmental interactions.
+        :param can_short: Whether or not the environment can short
         """
-        self.config = config
-        self.rl_config = config['freqai']['rl_config']
-        self.add_state_info = self.rl_config.get('add_state_info', False)
-        self.id = id
-        self.max_drawdown = 1 - self.rl_config.get('max_training_drawdown_pct', 0.8)
-        self.compound_trades = config['stake_amount'] == 'unlimited'
+        self.config: dict = config
+        self.rl_config: dict = config['freqai']['rl_config']
+        self.add_state_info: bool = self.rl_config.get('add_state_info', False)
+        self.id: str = id
+        self.max_drawdown: float = 1 - self.rl_config.get('max_training_drawdown_pct', 0.8)
+        self.compound_trades: bool = config['stake_amount'] == 'unlimited'
+        self.pair: str = pair
+        self.raw_features: DataFrame = df_raw
         if self.config.get('fee', None) is not None:
             self.fee = self.config['fee']
         else:
@@ -73,7 +77,8 @@ class BaseEnvironment(gym.Env):
         # set here to default 5Ac, but all children envs can override this
         self.actions: Type[Enum] = BaseActions
         self.tensorboard_metrics: dict = {}
-        self.live = live
+        self.can_short: bool = can_short
+        self.live: bool = live
         if not self.live and self.add_state_info:
             self.add_state_info = False
             logger.warning("add_state_info is not available in backtesting. Deactivating.")
@@ -91,13 +96,12 @@ class BaseEnvironment(gym.Env):
         :param reward_kwargs: extra config settings assigned by user in `rl_config`
         :param starting_point: start at edge of window or not
         """
-        self.df = df
-        self.signal_features = self.df
-        self.prices = prices
-        self.window_size = window_size
-        self.starting_point = starting_point
-        self.rr = reward_kwargs["rr"]
-        self.profit_aim = reward_kwargs["profit_aim"]
+        self.signal_features: DataFrame = df
+        self.prices: DataFrame = prices
+        self.window_size: int = window_size
+        self.starting_point: bool = starting_point
+        self.rr: float = reward_kwargs["rr"]
+        self.profit_aim: float = reward_kwargs["profit_aim"]
 
         # # spaces
         if self.add_state_info:

freqtrade/freqai/RL/BaseReinforcementLearningModel.py

@@ -1,3 +1,4 @@
+import copy
 import importlib
 import logging
 from abc import abstractmethod
@@ -50,6 +51,7 @@ class BaseReinforcementLearningModel(IFreqaiModel):
         self.eval_callback: Optional[EvalCallback] = None
         self.model_type = self.freqai_info['rl_config']['model_type']
         self.rl_config = self.freqai_info['rl_config']
+        self.df_raw: DataFrame = DataFrame()
         self.continual_learning = self.freqai_info.get('continual_learning', False)
         if self.model_type in SB3_MODELS:
             import_str = 'stable_baselines3'
@@ -107,6 +109,7 @@ class BaseReinforcementLearningModel(IFreqaiModel):
 
         data_dictionary: Dict[str, Any] = dk.make_train_test_datasets(
             features_filtered, labels_filtered)
+        self.df_raw = copy.deepcopy(data_dictionary["train_features"])
         dk.fit_labels()  # FIXME useless for now, but just satiating append methods
 
         # normalize all data based on train_dataset only
@@ -143,7 +146,7 @@ class BaseReinforcementLearningModel(IFreqaiModel):
         train_df = data_dictionary["train_features"]
         test_df = data_dictionary["test_features"]
 
-        env_info = self.pack_env_dict()
+        env_info = self.pack_env_dict(dk.pair)
 
         self.train_env = self.MyRLEnv(df=train_df,
                                       prices=prices_train,
@@ -158,14 +161,17 @@ class BaseReinforcementLearningModel(IFreqaiModel):
         actions = self.train_env.get_actions()
         self.tensorboard_callback = TensorboardCallback(verbose=1, actions=actions)
 
-    def pack_env_dict(self) -> Dict[str, Any]:
+    def pack_env_dict(self, pair: str) -> Dict[str, Any]:
         """
         Create dictionary of environment arguments
         """
         env_info = {"window_size": self.CONV_WIDTH,
                     "reward_kwargs": self.reward_params,
                     "config": self.config,
-                    "live": self.live}
+                    "live": self.live,
+                    "can_short": self.can_short,
+                    "pair": pair,
+                    "df_raw": self.df_raw}
         if self.data_provider:
             env_info["fee"] = self.data_provider._exchange \
                 .get_fee(symbol=self.data_provider.current_whitelist()[0])  # type: ignore
@@ -279,26 +285,36 @@ class BaseReinforcementLearningModel(IFreqaiModel):
         train_df = data_dictionary["train_features"]
         test_df = data_dictionary["test_features"]
 
+        # %-raw_volume_gen_shift-2_ETH/USDT_1h
         # price data for model training and evaluation
         tf = self.config['timeframe']
-        ohlc_list = [f'%-{pair}raw_open_{tf}', f'%-{pair}raw_low_{tf}',
-                     f'%-{pair}raw_high_{tf}', f'%-{pair}raw_close_{tf}']
-        rename_dict = {f'%-{pair}raw_open_{tf}': 'open', f'%-{pair}raw_low_{tf}': 'low',
-                       f'%-{pair}raw_high_{tf}': ' high', f'%-{pair}raw_close_{tf}': 'close'}
+        rename_dict = {'%-raw_open': 'open', '%-raw_low': 'low',
+                       '%-raw_high': ' high', '%-raw_close': 'close'}
+        rename_dict_old = {f'%-{pair}raw_open_{tf}': 'open', f'%-{pair}raw_low_{tf}': 'low',
+                           f'%-{pair}raw_high_{tf}': ' high', f'%-{pair}raw_close_{tf}': 'close'}
+
+        prices_train = train_df.filter(rename_dict.keys(), axis=1)
+        prices_train_old = train_df.filter(rename_dict_old.keys(), axis=1)
+        if prices_train.empty or not prices_train_old.empty:
+            if not prices_train_old.empty:
+                prices_train = prices_train_old
+                rename_dict = rename_dict_old
+            logger.warning('Reinforcement learning module didnt find the correct raw prices '
+                           'assigned in feature_engineering_standard(). '
+                           'Please assign them with:\n'
+                           'dataframe["%-raw_close"] = dataframe["close"]\n'
+                           'dataframe["%-raw_open"] = dataframe["open"]\n'
+                           'dataframe["%-raw_high"] = dataframe["high"]\n'
+                           'dataframe["%-raw_low"] = dataframe["low"]\n'
+                           'inside `feature_engineering_standard()')
+        elif prices_train.empty:
+            raise OperationalException("No prices found, please follow log warning "
+                                       "instructions to correct the strategy.")
 
-        prices_train = train_df.filter(ohlc_list, axis=1)
-        if prices_train.empty:
-            raise OperationalException('Reinforcement learning module didnt find the raw prices '
-                                       'assigned in populate_any_indicators. Please assign them '
-                                       'with:\n'
-                                       'informative[f"%-{pair}raw_close"] = informative["close"]\n'
-                                       'informative[f"%-{pair}raw_open"] = informative["open"]\n'
-                                       'informative[f"%-{pair}raw_high"] = informative["high"]\n'
-                                       'informative[f"%-{pair}raw_low"] = informative["low"]\n')
         prices_train.rename(columns=rename_dict, inplace=True)
         prices_train.reset_index(drop=True)
 
-        prices_test = test_df.filter(ohlc_list, axis=1)
+        prices_test = test_df.filter(rename_dict.keys(), axis=1)
         prices_test.rename(columns=rename_dict, inplace=True)
         prices_test.reset_index(drop=True)
 
@@ -336,7 +352,7 @@ class BaseReinforcementLearningModel(IFreqaiModel):
         sets a custom reward based on profit and trade duration.
         """
 
-        def calculate_reward(self, action: int) -> float:
+        def calculate_reward(self, action: int) -> float:  # noqa: C901
             """
             An example reward function. This is the one function that users will likely
             wish to inject their own creativity into.
@@ -352,10 +368,19 @@ class BaseReinforcementLearningModel(IFreqaiModel):
             pnl = self.get_unrealized_profit()
             factor = 100.
 
+            # you can use feature values from dataframe
+            rsi_now = self.raw_features[f"%-rsi-period-10_shift-1_{self.pair}_"
+                                        f"{self.config['timeframe']}"].iloc[self._current_tick]
+
             # reward agent for entering trades
             if (action in (Actions.Long_enter.value, Actions.Short_enter.value)
                     and self._position == Positions.Neutral):
-                return 25
+                if rsi_now < 40:
+                    factor = 40 / rsi_now
+                else:
+                    factor = 1
+                return 25 * factor
+
             # discourage agent from not entering trades
             if action == Actions.Neutral.value and self._position == Positions.Neutral:
                 return -1

freqtrade/freqai/data_drawer.py

@@ -59,7 +59,7 @@ class FreqaiDataDrawer:
     Juha Nykänen @suikula, Wagner Costa @wagnercosta, Johan Vlugt @Jooopieeert
     """
 
-    def __init__(self, full_path: Path, config: Config, follow_mode: bool = False):
+    def __init__(self, full_path: Path, config: Config):
 
         self.config = config
         self.freqai_info = config.get("freqai", {})
@@ -84,9 +84,6 @@ class FreqaiDataDrawer:
         self.pair_dictionary_path = Path(self.full_path / "pair_dictionary.json")
         self.global_metadata_path = Path(self.full_path / "global_metadata.json")
         self.metric_tracker_path = Path(self.full_path / "metric_tracker.json")
-        self.follow_mode = follow_mode
-        if follow_mode:
-            self.create_follower_dict()
         self.load_drawer_from_disk()
         self.load_historic_predictions_from_disk()
         self.metric_tracker: Dict[str, Dict[str, Dict[str, list]]] = {}
@@ -149,13 +146,8 @@ class FreqaiDataDrawer:
         if exists:
             with open(self.pair_dictionary_path, "r") as fp:
                 self.pair_dict = rapidjson.load(fp, number_mode=rapidjson.NM_NATIVE)
-        elif not self.follow_mode:
-            logger.info("Could not find existing datadrawer, starting from scratch")
         else:
-            logger.warning(
-                f"Follower could not find pair_dictionary at {self.full_path} "
-                "sending null values back to strategy"
-            )
+            logger.info("Could not find existing datadrawer, starting from scratch")
 
     def load_metric_tracker_from_disk(self):
         """
@@ -193,13 +185,8 @@ class FreqaiDataDrawer:
                     self.historic_predictions = cloudpickle.load(fp)
                 logger.warning('FreqAI successfully loaded the backup historical predictions file.')
 
-        elif not self.follow_mode:
-            logger.info("Could not find existing historic_predictions, starting from scratch")
         else:
-            logger.warning(
-                f"Follower could not find historic predictions at {self.full_path} "
-                "sending null values back to strategy"
-            )
+            logger.info("Could not find existing historic_predictions, starting from scratch")
 
         return exists
 
@@ -248,23 +235,6 @@ class FreqaiDataDrawer:
                 rapidjson.dump(metadata, fp, default=self.np_encoder,
                                number_mode=rapidjson.NM_NATIVE)
 
-    def create_follower_dict(self):
-        """
-        Create or dictionary for each follower to maintain unique persistent prediction targets
-        """
-
-        whitelist_pairs = self.config.get("exchange", {}).get("pair_whitelist")
-
-        exists = self.follower_dict_path.is_file()
-
-        if exists:
-            logger.info("Found an existing follower dictionary")
-
-        for pair in whitelist_pairs:
-            self.follower_dict[pair] = {}
-
-        self.save_follower_dict_to_disk()
-
     def np_encoder(self, object):
         if isinstance(object, np.generic):
             return object.item()
@@ -282,27 +252,17 @@ class FreqaiDataDrawer:
         """
 
         pair_dict = self.pair_dict.get(pair)
-        data_path_set = self.pair_dict.get(pair, self.empty_pair_dict).get("data_path", "")
+        # data_path_set = self.pair_dict.get(pair, self.empty_pair_dict).get("data_path", "")
         return_null_array = False
 
         if pair_dict:
             model_filename = pair_dict["model_filename"]
             trained_timestamp = pair_dict["trained_timestamp"]
-        elif not self.follow_mode:
+        else:
             self.pair_dict[pair] = self.empty_pair_dict.copy()
             model_filename = ""
             trained_timestamp = 0
 
-        if not data_path_set and self.follow_mode:
-            logger.warning(
-                f"Follower could not find current pair {pair} in "
-                f"pair_dictionary at path {self.full_path}, sending null values "
-                "back to strategy."
-            )
-            trained_timestamp = 0
-            model_filename = ''
-            return_null_array = True
-
         return model_filename, trained_timestamp, return_null_array
 
     def set_pair_dict_info(self, metadata: dict) -> None:
@@ -311,7 +271,6 @@ class FreqaiDataDrawer:
             return
         else:
             self.pair_dict[metadata["pair"]] = self.empty_pair_dict.copy()
-
             return
 
     def set_initial_return_values(self, pair: str, pred_df: DataFrame) -> None:

freqtrade/freqai/data_kitchen.py

@@ -1,11 +1,12 @@
 import copy
+import inspect
 import logging
 import random
 import shutil
 from datetime import datetime, timezone
 from math import cos, sin
 from pathlib import Path
-from typing import Any, Dict, List, Tuple
+from typing import Any, Dict, List, Optional, Tuple
 
 import numpy as np
 import numpy.typing as npt
@@ -24,6 +25,7 @@ from freqtrade.constants import Config
 from freqtrade.data.converter import reduce_dataframe_footprint
 from freqtrade.exceptions import OperationalException
 from freqtrade.exchange import timeframe_to_seconds
+from freqtrade.strategy import merge_informative_pair
 from freqtrade.strategy.interface import IStrategy
 
 
@@ -111,7 +113,7 @@ class FreqaiDataKitchen:
     def set_paths(
         self,
         pair: str,
-        trained_timestamp: int = None,
+        trained_timestamp: Optional[int] = None,
     ) -> None:
         """
         Set the paths to the data for the present coin/botloop
@@ -1159,9 +1161,9 @@ class FreqaiDataKitchen:
 
         for pair in pairs:
             pair = pair.replace(':', '')  # lightgbm doesnt like colons
-            valid_strs = [f"%-{pair}", f"%{pair}", f"%_{pair}"]
-            pair_cols = [col for col in dataframe.columns if
-                         any(substr in col for substr in valid_strs)]
+            pair_cols = [col for col in dataframe.columns if col.startswith("%")
+                         and f"{pair}_" in col]
+
             if pair_cols:
                 pair_cols.insert(0, 'date')
                 corr_dataframes[pair] = dataframe.filter(pair_cols, axis=1)
@@ -1190,6 +1192,105 @@ class FreqaiDataKitchen:
 
         return dataframe
 
+    def get_pair_data_for_features(self,
+                                   pair: str,
+                                   tf: str,
+                                   strategy: IStrategy,
+                                   corr_dataframes: dict = {},
+                                   base_dataframes: dict = {},
+                                   is_corr_pairs: bool = False) -> DataFrame:
+        """
+        Get the data for the pair. If it's not in the dictionary, get it from the data provider
+        :param pair: str = pair to get data for
+        :param tf: str = timeframe to get data for
+        :param strategy: IStrategy = user defined strategy object
+        :param corr_dataframes: dict = dict containing the df pair dataframes
+                                (for user defined timeframes)
+        :param base_dataframes: dict = dict containing the current pair dataframes
+                                (for user defined timeframes)
+        :param is_corr_pairs: bool = whether the pair is a corr pair or not
+        :return: dataframe = dataframe containing the pair data
+        """
+        if is_corr_pairs:
+            dataframe = corr_dataframes[pair][tf]
+            if not dataframe.empty:
+                return dataframe
+            else:
+                dataframe = strategy.dp.get_pair_dataframe(pair=pair, timeframe=tf)
+                return dataframe
+        else:
+            dataframe = base_dataframes[tf]
+            if not dataframe.empty:
+                return dataframe
+            else:
+                dataframe = strategy.dp.get_pair_dataframe(pair=pair, timeframe=tf)
+                return dataframe
+
+    def merge_features(self, df_main: DataFrame, df_to_merge: DataFrame,
+                       tf: str, timeframe_inf: str, suffix: str) -> DataFrame:
+        """
+        Merge the features of the dataframe and remove HLCV and date added columns
+        :param df_main: DataFrame = main dataframe
+        :param df_to_merge: DataFrame = dataframe to merge
+        :param tf: str = timeframe of the main dataframe
+        :param timeframe_inf: str = timeframe of the dataframe to merge
+        :param suffix: str = suffix to add to the columns of the dataframe to merge
+        :return: dataframe = merged dataframe
+        """
+        dataframe = merge_informative_pair(df_main, df_to_merge, tf, timeframe_inf=timeframe_inf,
+                                           append_timeframe=False, suffix=suffix, ffill=True)
+        skip_columns = [
+            (f"{s}_{suffix}") for s in ["date", "open", "high", "low", "close", "volume"]
+        ]
+        dataframe = dataframe.drop(columns=skip_columns)
+        return dataframe
+
+    def populate_features(self, dataframe: DataFrame, pair: str, strategy: IStrategy,
+                          corr_dataframes: dict, base_dataframes: dict,
+                          is_corr_pairs: bool = False) -> DataFrame:
+        """
+        Use the user defined strategy functions for populating features
+        :param dataframe: DataFrame = dataframe to populate
+        :param pair: str = pair to populate
+        :param strategy: IStrategy = user defined strategy object
+        :param corr_dataframes: dict = dict containing the df pair dataframes
+        :param base_dataframes: dict = dict containing the current pair dataframes
+        :param is_corr_pairs: bool = whether the pair is a corr pair or not
+        :return: dataframe = populated dataframe
+        """
+        tfs: List[str] = self.freqai_config["feature_parameters"].get("include_timeframes")
+
+        for tf in tfs:
+            metadata = {"pair": pair, "tf": tf}
+            informative_df = self.get_pair_data_for_features(
+                pair, tf, strategy, corr_dataframes, base_dataframes, is_corr_pairs)
+            informative_copy = informative_df.copy()
+
+            for t in self.freqai_config["feature_parameters"]["indicator_periods_candles"]:
+                df_features = strategy.feature_engineering_expand_all(
+                    informative_copy.copy(), t, metadata=metadata)
+                suffix = f"{t}"
+                informative_df = self.merge_features(informative_df, df_features, tf, tf, suffix)
+
+            generic_df = strategy.feature_engineering_expand_basic(
+                informative_copy.copy(), metadata=metadata)
+            suffix = "gen"
+
+            informative_df = self.merge_features(informative_df, generic_df, tf, tf, suffix)
+
+            indicators = [col for col in informative_df if col.startswith("%")]
+            for n in range(self.freqai_config["feature_parameters"]["include_shifted_candles"] + 1):
+                if n == 0:
+                    continue
+                df_shift = informative_df[indicators].shift(n)
+                df_shift = df_shift.add_suffix("_shift-" + str(n))
+                informative_df = pd.concat((informative_df, df_shift), axis=1)
+
+            dataframe = self.merge_features(dataframe.copy(), informative_df,
+                                            self.config["timeframe"], tf, f'{pair}_{tf}')
+
+        return dataframe
+
     def use_strategy_to_populate_indicators(
         self,
         strategy: IStrategy,
@@ -1202,7 +1303,87 @@ class FreqaiDataKitchen:
         """
         Use the user defined strategy for populating indicators during retrain
         :param strategy: IStrategy = user defined strategy object
-        :param corr_dataframes: dict = dict containing the informative pair dataframes
+        :param corr_dataframes: dict = dict containing the df pair dataframes
+                                (for user defined timeframes)
+        :param base_dataframes: dict = dict containing the current pair dataframes
+                                (for user defined timeframes)
+        :param pair: str = pair to populate
+        :param prediction_dataframe: DataFrame = dataframe containing the pair data
+        used for prediction
+        :param do_corr_pairs: bool = whether to populate corr pairs or not
+        :return:
+        dataframe: DataFrame = dataframe containing populated indicators
+        """
+
+        # this is a hack to check if the user is using the populate_any_indicators function
+        new_version = inspect.getsource(strategy.populate_any_indicators) == (
+            inspect.getsource(IStrategy.populate_any_indicators))
+
+        if new_version:
+            tfs: List[str] = self.freqai_config["feature_parameters"].get("include_timeframes")
+            pairs: List[str] = self.freqai_config["feature_parameters"].get(
+                "include_corr_pairlist", [])
+
+            for tf in tfs:
+                if tf not in base_dataframes:
+                    base_dataframes[tf] = pd.DataFrame()
+                for p in pairs:
+                    if p not in corr_dataframes:
+                        corr_dataframes[p] = {}
+                    if tf not in corr_dataframes[p]:
+                        corr_dataframes[p][tf] = pd.DataFrame()
+
+            if not prediction_dataframe.empty:
+                dataframe = prediction_dataframe.copy()
+            else:
+                dataframe = base_dataframes[self.config["timeframe"]].copy()
+
+            corr_pairs: List[str] = self.freqai_config["feature_parameters"].get(
+                "include_corr_pairlist", [])
+            dataframe = self.populate_features(dataframe.copy(), pair, strategy,
+                                               corr_dataframes, base_dataframes)
+            metadata = {"pair": pair}
+            dataframe = strategy.feature_engineering_standard(dataframe.copy(), metadata=metadata)
+            # ensure corr pairs are always last
+            for corr_pair in corr_pairs:
+                if pair == corr_pair:
+                    continue  # dont repeat anything from whitelist
+                if corr_pairs and do_corr_pairs:
+                    dataframe = self.populate_features(dataframe.copy(), corr_pair, strategy,
+                                                       corr_dataframes, base_dataframes, True)
+
+            dataframe = strategy.set_freqai_targets(dataframe.copy(), metadata=metadata)
+
+            self.get_unique_classes_from_labels(dataframe)
+
+            dataframe = self.remove_special_chars_from_feature_names(dataframe)
+
+            if self.config.get('reduce_df_footprint', False):
+                dataframe = reduce_dataframe_footprint(dataframe)
+
+            return dataframe
+
+        else:
+            # the user is using the populate_any_indicators functions which is deprecated
+
+            df = self.use_strategy_to_populate_indicators_old_version(
+                strategy, corr_dataframes, base_dataframes, pair,
+                prediction_dataframe, do_corr_pairs)
+            return df
+
+    def use_strategy_to_populate_indicators_old_version(
+        self,
+        strategy: IStrategy,
+        corr_dataframes: dict = {},
+        base_dataframes: dict = {},
+        pair: str = "",
+        prediction_dataframe: DataFrame = pd.DataFrame(),
+        do_corr_pairs: bool = True,
+    ) -> DataFrame:
+        """
+        Use the user defined strategy for populating indicators during retrain
+        :param strategy: IStrategy = user defined strategy object
+        :param corr_dataframes: dict = dict containing the df pair dataframes
                                 (for user defined timeframes)
         :param base_dataframes: dict = dict containing the current pair dataframes
                                 (for user defined timeframes)

freqtrade/freqai/freqai_interface.py

@@ -1,3 +1,4 @@
+import inspect
 import logging
 import threading
 import time
@@ -65,12 +66,11 @@ class IFreqaiModel(ABC):
         self.retrain = False
         self.first = True
         self.set_full_path()
-        self.follow_mode: bool = self.freqai_info.get("follow_mode", False)
         self.save_backtest_models: bool = self.freqai_info.get("save_backtest_models", True)
         if self.save_backtest_models:
             logger.info('Backtesting module configured to save all models.')
 
-        self.dd = FreqaiDataDrawer(Path(self.full_path), self.config, self.follow_mode)
+        self.dd = FreqaiDataDrawer(Path(self.full_path), self.config)
         # set current candle to arbitrary historical date
         self.current_candle: datetime = datetime.fromtimestamp(637887600, tz=timezone.utc)
         self.dd.current_candle = self.current_candle
@@ -104,6 +104,9 @@ class IFreqaiModel(ABC):
         self.metadata: Dict[str, Any] = self.dd.load_global_metadata_from_disk()
         self.data_provider: Optional[DataProvider] = None
         self.max_system_threads = max(int(psutil.cpu_count() * 2 - 2), 1)
+        self.can_short = True  # overridden in start() with strategy.can_short
+
+        self.warned_deprecated_populate_any_indicators = False
 
         record_params(config, self.full_path)
 
@@ -133,6 +136,10 @@ class IFreqaiModel(ABC):
         self.live = strategy.dp.runmode in (RunMode.DRY_RUN, RunMode.LIVE)
         self.dd.set_pair_dict_info(metadata)
         self.data_provider = strategy.dp
+        self.can_short = strategy.can_short
+
+        # check if the strategy has deprecated populate_any_indicators function
+        self.check_deprecated_populate_any_indicators(strategy)
 
         if self.live:
             self.inference_timer('start')
@@ -145,14 +152,11 @@ class IFreqaiModel(ABC):
         # (backtest window, i.e. window immediately following the training window).
         # FreqAI slides the window and sequentially builds the backtesting results before returning
         # the concatenated results for the full backtesting period back to the strategy.
-        elif not self.follow_mode:
+        else:
             self.dk = FreqaiDataKitchen(self.config, self.live, metadata["pair"])
-            dataframe = self.dk.use_strategy_to_populate_indicators(
-                strategy, prediction_dataframe=dataframe, pair=metadata["pair"]
-            )
             if not self.config.get("freqai_backtest_live_models", False):
                 logger.info(f"Training {len(self.dk.training_timeranges)} timeranges")
-                dk = self.start_backtesting(dataframe, metadata, self.dk)
+                dk = self.start_backtesting(dataframe, metadata, self.dk, strategy)
                 dataframe = dk.remove_features_from_df(dk.return_dataframe)
             else:
                 logger.info(
@@ -253,7 +257,7 @@ class IFreqaiModel(ABC):
                     self.dd.save_metric_tracker_to_disk()
 
     def start_backtesting(
-        self, dataframe: DataFrame, metadata: dict, dk: FreqaiDataKitchen
+        self, dataframe: DataFrame, metadata: dict, dk: FreqaiDataKitchen, strategy: IStrategy
     ) -> FreqaiDataKitchen:
         """
         The main broad execution for backtesting. For backtesting, each pair enters and then gets
@@ -265,19 +269,22 @@ class IFreqaiModel(ABC):
         :param dataframe: DataFrame = strategy passed dataframe
         :param metadata: Dict = pair metadata
         :param dk: FreqaiDataKitchen = Data management/analysis tool associated to present pair only
+        :param strategy: Strategy to train on
         :return:
             FreqaiDataKitchen = Data management/analysis tool associated to present pair only
         """
 
         self.pair_it += 1
         train_it = 0
+        pair = metadata["pair"]
+        populate_indicators = True
+        check_features = True
         # Loop enforcing the sliding window training/backtesting paradigm
         # tr_train is the training time range e.g. 1 historical month
         # tr_backtest is the backtesting time range e.g. the week directly
         # following tr_train. Both of these windows slide through the
         # entire backtest
         for tr_train, tr_backtest in zip(dk.training_timeranges, dk.backtesting_timeranges):
-            pair = metadata["pair"]
             (_, _, _) = self.dd.get_pair_dict_info(pair)
             train_it += 1
             total_trains = len(dk.backtesting_timeranges)
@@ -299,18 +306,44 @@ class IFreqaiModel(ABC):
             dk.set_new_model_names(pair, timestamp_model_id)
 
             if dk.check_if_backtest_prediction_is_valid(len_backtest_df):
-                self.dd.load_metadata(dk)
-                dk.find_features(dataframe)
-                self.check_if_feature_list_matches_strategy(dk)
+                if check_features:
+                    self.dd.load_metadata(dk)
+                    dataframe_dummy_features = self.dk.use_strategy_to_populate_indicators(
+                        strategy, prediction_dataframe=dataframe.tail(1), pair=metadata["pair"]
+                    )
+                    dk.find_features(dataframe_dummy_features)
+                    self.check_if_feature_list_matches_strategy(dk)
+                    check_features = False
                 append_df = dk.get_backtesting_prediction()
                 dk.append_predictions(append_df)
             else:
-                dataframe_train = dk.slice_dataframe(tr_train, dataframe)
-                dataframe_backtest = dk.slice_dataframe(tr_backtest, dataframe)
+                if populate_indicators:
+                    dataframe = self.dk.use_strategy_to_populate_indicators(
+                        strategy, prediction_dataframe=dataframe, pair=metadata["pair"]
+                    )
+                    populate_indicators = False
+
+                dataframe_base_train = dataframe.loc[dataframe["date"] < tr_train.stopdt, :]
+                dataframe_base_train = strategy.set_freqai_targets(
+                    dataframe_base_train, metadata=metadata)
+                dataframe_base_backtest = dataframe.loc[dataframe["date"] < tr_backtest.stopdt, :]
+                dataframe_base_backtest = strategy.set_freqai_targets(
+                    dataframe_base_backtest, metadata=metadata)
+
+                dataframe_train = dk.slice_dataframe(tr_train, dataframe_base_train)
+                dataframe_backtest = dk.slice_dataframe(tr_backtest, dataframe_base_backtest)
+
                 if not self.model_exists(dk):
                     dk.find_features(dataframe_train)
                     dk.find_labels(dataframe_train)
-                    self.model = self.train(dataframe_train, pair, dk)
+
+                    try:
+                        self.model = self.train(dataframe_train, pair, dk)
+                    except Exception as msg:
+                        logger.warning(
+                            f"Training {pair} raised exception {msg.__class__.__name__}. "
+                            f"Message: {msg}, skipping.")
+
                     self.dd.pair_dict[pair]["trained_timestamp"] = int(
                         tr_train.stopts)
                     if self.plot_features:
@@ -348,46 +381,27 @@ class IFreqaiModel(ABC):
         dk: FreqaiDataKitchen = Data management/analysis tool associated to present pair only
         """
 
-        # update follower
-        if self.follow_mode:
-            self.dd.update_follower_metadata()
-
         # get the model metadata associated with the current pair
         (_, trained_timestamp, return_null_array) = self.dd.get_pair_dict_info(metadata["pair"])
 
-        # if the metadata doesn't exist, the follower returns null arrays to strategy
-        if self.follow_mode and return_null_array:
-            logger.info("Returning null array from follower to strategy")
-            self.dd.return_null_values_to_strategy(dataframe, dk)
-            return dk
-
         # append the historic data once per round
         if self.dd.historic_data:
             self.dd.update_historic_data(strategy, dk)
             logger.debug(f'Updating historic data on pair {metadata["pair"]}')
             self.track_current_candle()
 
-        if not self.follow_mode:
+        (_, new_trained_timerange, data_load_timerange) = dk.check_if_new_training_required(
+            trained_timestamp
+        )
+        dk.set_paths(metadata["pair"], new_trained_timerange.stopts)
 
-            (_, new_trained_timerange, data_load_timerange) = dk.check_if_new_training_required(
-                trained_timestamp
-            )
-            dk.set_paths(metadata["pair"], new_trained_timerange.stopts)
+        # load candle history into memory if it is not yet.
+        if not self.dd.historic_data:
+            self.dd.load_all_pair_histories(data_load_timerange, dk)
 
-            # load candle history into memory if it is not yet.
-            if not self.dd.historic_data:
-                self.dd.load_all_pair_histories(data_load_timerange, dk)
-
-            if not self.scanning:
-                self.scanning = True
-                self.start_scanning(strategy)
-
-        elif self.follow_mode:
-            dk.set_paths(metadata["pair"], trained_timestamp)
-            logger.info(
-                "FreqAI instance set to follow_mode, finding existing pair "
-                f"using { self.identifier }"
-            )
+        if not self.scanning:
+            self.scanning = True
+            self.start_scanning(strategy)
 
         # load the model and associated data into the data kitchen
         self.model = self.dd.load_data(metadata["pair"], dk)
@@ -911,9 +925,28 @@ class IFreqaiModel(ABC):
         dk.return_dataframe = dk.return_dataframe.drop(columns=list(columns_to_drop))
         dk.return_dataframe = pd.merge(
             dk.return_dataframe, saved_dataframe, how='left', left_on='date', right_on="date_pred")
-        # dk.return_dataframe = dk.return_dataframe[saved_dataframe.columns].fillna(0)
         return dk
 
+    def check_deprecated_populate_any_indicators(self, strategy: IStrategy):
+        """
+        Check and warn if the deprecated populate_any_indicators function is used.
+        :param strategy: strategy object
+        """
+
+        if not self.warned_deprecated_populate_any_indicators:
+            self.warned_deprecated_populate_any_indicators = True
+            old_version = inspect.getsource(strategy.populate_any_indicators) != (
+                inspect.getsource(IStrategy.populate_any_indicators))
+
+            if old_version:
+                logger.warning("DEPRECATION WARNING: "
+                               "You are using the deprecated populate_any_indicators function. "
+                               "This function will raise an error on March 1 2023. "
+                               "Please update your strategy by using "
+                               "the new feature_engineering functions. See \n"
+                               "https://www.freqtrade.io/en/latest/freqai-feature-engineering/"
+                               "for details.")
+
     # Following methods which are overridden by user made prediction models.
     # See freqai/prediction_models/CatboostPredictionModel.py for an example.
 

freqtrade/freqai/prediction_models/ReinforcementLearner_multiproc.py

@@ -34,7 +34,7 @@ class ReinforcementLearner_multiproc(ReinforcementLearner):
         train_df = data_dictionary["train_features"]
         test_df = data_dictionary["test_features"]
 
-        env_info = self.pack_env_dict()
+        env_info = self.pack_env_dict(dk.pair)
 
         env_id = "train_env"
         self.train_env = SubprocVecEnv([make_env(self.MyRLEnv, env_id, i, 1,