Merge pull request #7950 from freqtrade/freqai_feature_engineering_functions

FreqAI Strategy - Improve user experience

freqtrade/freqai/RL/BaseReinforcementLearningModel.py

@@ -280,26 +280,36 @@ 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)
 

freqtrade/freqai/data_kitchen.py

@@ -1,4 +1,5 @@
 import copy
+import inspect
 import logging
 import shutil
 from datetime import datetime, timezone
@@ -23,6 +24,7 @@ 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
 
 
@@ -1145,9 +1147,9 @@ 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)
@@ -1176,6 +1178,103 @@ 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:
+            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)
+                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())
+            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,
@@ -1188,7 +1287,87 @@ 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)
+
+            dataframe = strategy.feature_engineering_standard(dataframe.copy())
+            # 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())
+
+            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
@@ -106,6 +107,8 @@ class IFreqaiModel(ABC):
         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)
 
     def __getstate__(self):
@@ -136,6 +139,9 @@ class IFreqaiModel(ABC):
         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')
             self.dk = FreqaiDataKitchen(self.config, self.live, metadata["pair"])
@@ -149,12 +155,9 @@ class IFreqaiModel(ABC):
         # the concatenated results for the full backtesting period back to the strategy.
         elif not self.follow_mode:
             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(
@@ -255,7 +258,7 @@ 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
@@ -267,19 +270,22 @@ 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)
@@ -301,18 +307,42 @@ 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)
+                dataframe_base_backtest = dataframe.loc[dataframe["date"] < tr_backtest.stopdt, :]
+                dataframe_base_backtest = strategy.set_freqai_targets(dataframe_base_backtest)
+
+                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:
@@ -349,7 +379,6 @@ class IFreqaiModel(ABC):
         :returns:
         dk: FreqaiDataKitchen = Data management/analysis tool associated to present pair only
         """
-
         # update follower
         if self.follow_mode:
             self.dd.update_follower_metadata()
@@ -913,9 +942,28 @@ 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/strategy/interface.py

@@ -598,6 +598,7 @@ class IStrategy(ABC, HyperStrategyMixin):
                                 informative: DataFrame = None,
                                 set_generalized_indicators: bool = False) -> DataFrame:
         """
+        DEPRECATED - USE FEATURE ENGINEERING FUNCTIONS INSTEAD
         Function designed to automatically generate, name and merge features
         from user indicated timeframes in the configuration file. User can add
         additional features here, but must follow the naming convention.
@@ -610,6 +611,98 @@ class IStrategy(ABC, HyperStrategyMixin):
         """
         return df
 
+    def feature_engineering_expand_all(self, dataframe: DataFrame,
+                                       period: int, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        This function will automatically expand the defined features on the config defined
+        `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and
+        `include_corr_pairs`. In other words, a single feature defined in this function
+        will automatically expand to a total of
+        `indicator_periods_candles` * `include_timeframes` * `include_shifted_candles` *
+        `include_corr_pairs` numbers of features added to the model.
+
+        All features must be prepended with `%` to be recognized by FreqAI internals.
+
+        More details on how these config defined parameters accelerate feature engineering
+        in the documentation at:
+
+        https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
+
+        :param df: strategy dataframe which will receive the features
+        :param period: period of the indicator - usage example:
+        dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period)
+        """
+        return dataframe
+
+    def feature_engineering_expand_basic(self, dataframe: DataFrame, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        This function will automatically expand the defined features on the config defined
+        `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`.
+        In other words, a single feature defined in this function
+        will automatically expand to a total of
+        `include_timeframes` * `include_shifted_candles` * `include_corr_pairs`
+        numbers of features added to the model.
+
+        Features defined here will *not* be automatically duplicated on user defined
+        `indicator_periods_candles`
+
+        All features must be prepended with `%` to be recognized by FreqAI internals.
+
+        More details on how these config defined parameters accelerate feature engineering
+        in the documentation at:
+
+        https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
+
+        :param df: strategy dataframe which will receive the features
+        dataframe["%-pct-change"] = dataframe["close"].pct_change()
+        dataframe["%-ema-200"] = ta.EMA(dataframe, timeperiod=200)
+        """
+        return dataframe
+
+    def feature_engineering_standard(self, dataframe: DataFrame, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        This optional function will be called once with the dataframe of the base timeframe.
+        This is the final function to be called, which means that the dataframe entering this
+        function will contain all the features and columns created by all other
+        freqai_feature_engineering_* functions.
+
+        This function is a good place to do custom exotic feature extractions (e.g. tsfresh).
+        This function is a good place for any feature that should not be auto-expanded upon
+        (e.g. day of the week).
+
+        All features must be prepended with `%` to be recognized by FreqAI internals.
+
+        More details about feature engineering available:
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering
+
+        :param df: strategy dataframe which will receive the features
+        usage example: dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7
+        """
+        return dataframe
+
+    def set_freqai_targets(self, dataframe, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        Required function to set the targets for the model.
+        All targets must be prepended with `&` to be recognized by the FreqAI internals.
+
+        More details about feature engineering available:
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering
+
+        :param df: strategy dataframe which will receive the targets
+        usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"]
+        """
+        return dataframe
+
 ###
 # END - Intended to be overridden by strategy
 ###

freqtrade/templates/FreqaiExampleHybridStrategy.py

@@ -95,65 +95,132 @@ class FreqaiExampleHybridStrategy(IStrategy):
     short_rsi = IntParameter(low=51, high=100, default=70, space='sell', optimize=True, load=True)
     exit_short_rsi = IntParameter(low=1, high=50, default=30, space='buy', optimize=True, load=True)
 
-    # FreqAI required function, user can add or remove indicators, but general structure
-    # must stay the same.
-    def populate_any_indicators(
-        self, pair, df, tf, informative=None, set_generalized_indicators=False
-    ):
+    def feature_engineering_expand_all(self, dataframe, period, **kwargs):
         """
-        User feeds these indicators to FreqAI to train a classifier to decide
-        if the market will go up or down.
+        *Only functional with FreqAI enabled strategies*
+        This function will automatically expand the defined features on the config defined
+        `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and
+        `include_corr_pairs`. In other words, a single feature defined in this function
+        will automatically expand to a total of
+        `indicator_periods_candles` * `include_timeframes` * `include_shifted_candles` *
+        `include_corr_pairs` numbers of features added to the model.
 
-        :param pair: pair to be used as informative
-        :param df: strategy dataframe which will receive merges from informatives
-        :param tf: timeframe of the dataframe which will modify the feature names
-        :param informative: the dataframe associated with the informative pair
+        All features must be prepended with `%` to be recognized by FreqAI internals.
+
+        More details on how these config defined parameters accelerate feature engineering
+        in the documentation at:
+
+        https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
+
+        :param df: strategy dataframe which will receive the features
+        :param period: period of the indicator - usage example:
+        dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period)
         """
 
-        if informative is None:
-            informative = self.dp.get_pair_dataframe(pair, tf)
+        dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
+        dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period)
+        dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period)
+        dataframe["%-sma-period"] = ta.SMA(dataframe, timeperiod=period)
+        dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period)
 
-        # first loop is automatically duplicating indicators for time periods
-        for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
+        bollinger = qtpylib.bollinger_bands(
+            qtpylib.typical_price(dataframe), window=period, stds=2.2
+        )
+        dataframe["bb_lowerband-period"] = bollinger["lower"]
+        dataframe["bb_middleband-period"] = bollinger["mid"]
+        dataframe["bb_upperband-period"] = bollinger["upper"]
 
-            t = int(t)
-            informative[f"%-{pair}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
-            informative[f"%-{pair}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
-            informative[f"%-{pair}adx-period_{t}"] = ta.ADX(informative, timeperiod=t)
-            informative[f"%-{pair}sma-period_{t}"] = ta.SMA(informative, timeperiod=t)
-            informative[f"%-{pair}ema-period_{t}"] = ta.EMA(informative, timeperiod=t)
-            informative[f"%-{pair}roc-period_{t}"] = ta.ROC(informative, timeperiod=t)
-            informative[f"%-{pair}relative_volume-period_{t}"] = (
-                informative["volume"] / informative["volume"].rolling(t).mean()
-            )
+        dataframe["%-bb_width-period"] = (
+            dataframe["bb_upperband-period"]
+            - dataframe["bb_lowerband-period"]
+        ) / dataframe["bb_middleband-period"]
+        dataframe["%-close-bb_lower-period"] = (
+            dataframe["close"] / dataframe["bb_lowerband-period"]
+        )
 
-        # FreqAI needs the following lines in order to detect features and automatically
-        # expand upon them.
-        indicators = [col for col in informative if col.startswith("%")]
-        # This loop duplicates and shifts all indicators to add a sense of recency to data
-        for n in range(self.freqai_info["feature_parameters"]["include_shifted_candles"] + 1):
-            if n == 0:
-                continue
-            informative_shift = informative[indicators].shift(n)
-            informative_shift = informative_shift.add_suffix("_shift-" + str(n))
-            informative = pd.concat((informative, informative_shift), axis=1)
+        dataframe["%-roc-period"] = ta.ROC(dataframe, timeperiod=period)
 
-        df = merge_informative_pair(df, informative, self.config["timeframe"], tf, ffill=True)
-        skip_columns = [
-            (s + "_" + tf) for s in ["date", "open", "high", "low", "close", "volume"]
-        ]
-        df = df.drop(columns=skip_columns)
+        dataframe["%-relative_volume-period"] = (
+            dataframe["volume"] / dataframe["volume"].rolling(period).mean()
+        )
 
-        # User can set the "target" here (in present case it is the
-        # "up" or "down")
-        if set_generalized_indicators:
-            # User "looks into the future" here to figure out if the future
-            # will be "up" or "down". This same column name is available to
-            # the user
-            df['&s-up_or_down'] = np.where(df["close"].shift(-50) >
-                                           df["close"], 'up', 'down')
+        return dataframe
 
-        return df
+    def feature_engineering_expand_basic(self, dataframe, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        This function will automatically expand the defined features on the config defined
+        `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`.
+        In other words, a single feature defined in this function
+        will automatically expand to a total of
+        `include_timeframes` * `include_shifted_candles` * `include_corr_pairs`
+        numbers of features added to the model.
+
+        Features defined here will *not* be automatically duplicated on user defined
+        `indicator_periods_candles`
+
+        All features must be prepended with `%` to be recognized by FreqAI internals.
+
+        More details on how these config defined parameters accelerate feature engineering
+        in the documentation at:
+
+        https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
+
+        :param df: strategy dataframe which will receive the features
+        dataframe["%-pct-change"] = dataframe["close"].pct_change()
+        dataframe["%-ema-200"] = ta.EMA(dataframe, timeperiod=200)
+        """
+        dataframe["%-pct-change"] = dataframe["close"].pct_change()
+        dataframe["%-raw_volume"] = dataframe["volume"]
+        dataframe["%-raw_price"] = dataframe["close"]
+        return dataframe
+
+    def feature_engineering_standard(self, dataframe, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        This optional function will be called once with the dataframe of the base timeframe.
+        This is the final function to be called, which means that the dataframe entering this
+        function will contain all the features and columns created by all other
+        freqai_feature_engineering_* functions.
+
+        This function is a good place to do custom exotic feature extractions (e.g. tsfresh).
+        This function is a good place for any feature that should not be auto-expanded upon
+        (e.g. day of the week).
+
+        All features must be prepended with `%` to be recognized by FreqAI internals.
+
+        More details about feature engineering available:
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering
+
+        :param df: strategy dataframe which will receive the features
+        usage example: dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7
+        """
+        dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
+        dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
+        return dataframe
+
+    def set_freqai_targets(self, dataframe, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        Required function to set the targets for the model.
+        All targets must be prepended with `&` to be recognized by the FreqAI internals.
+
+        More details about feature engineering available:
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering
+
+        :param df: strategy dataframe which will receive the targets
+        usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"]
+        """
+        dataframe['&s-up_or_down'] = np.where(dataframe["close"].shift(-50) >
+                                        dataframe["close"], 'up', 'down')
+
+        return dataframe
 
     # flake8: noqa: C901
     def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:

freqtrade/templates/FreqaiExampleStrategy.py

@@ -1,12 +1,11 @@
 import logging
 from functools import reduce
 
-import pandas as pd
 import talib.abstract as ta
 from pandas import DataFrame
 from technical import qtpylib
 
-from freqtrade.strategy import CategoricalParameter, IStrategy, merge_informative_pair
+from freqtrade.strategy import CategoricalParameter, IStrategy
 
 
 logger = logging.getLogger(__name__)
@@ -18,8 +17,8 @@ class FreqaiExampleStrategy(IStrategy):
     IFreqaiModel to the strategy. Namely, the user uses:
     self.freqai.start(dataframe, metadata)
 
-    to make predictions on their data. populate_any_indicators() automatically
-    generates the variety of features indicated by the user in the
+    to make predictions on their data. feature_engineering_*() automatically
+    generate the variety of features indicated by the user in the
     canonical freqtrade configuration file under config['freqai'].
     """
 
@@ -40,134 +39,179 @@ class FreqaiExampleStrategy(IStrategy):
     use_exit_signal = True
     # this is the maximum period fed to talib (timeframe independent)
     startup_candle_count: int = 40
-    can_short = False
+    can_short = True
 
     std_dev_multiplier_buy = CategoricalParameter(
         [0.75, 1, 1.25, 1.5, 1.75], default=1.25, space="buy", optimize=True)
     std_dev_multiplier_sell = CategoricalParameter(
         [0.75, 1, 1.25, 1.5, 1.75], space="sell", default=1.25, optimize=True)
 
-    def populate_any_indicators(
-        self, pair, df, tf, informative=None, set_generalized_indicators=False
-    ):
+    def feature_engineering_expand_all(self, dataframe, period, **kwargs):
         """
-        Function designed to automatically generate, name and merge features
-        from user indicated timeframes in the configuration file. User controls the indicators
-        passed to the training/prediction by prepending indicators with `f'%-{pair}`
-        (see convention below). I.e. user should not prepend any supporting metrics
-        (e.g. bb_lowerband below) with % unless they explicitly want to pass that metric to the
-        model.
-        :param pair: pair to be used as informative
-        :param df: strategy dataframe which will receive merges from informatives
-        :param tf: timeframe of the dataframe which will modify the feature names
-        :param informative: the dataframe associated with the informative pair
+        *Only functional with FreqAI enabled strategies*
+        This function will automatically expand the defined features on the config defined
+        `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and
+        `include_corr_pairs`. In other words, a single feature defined in this function
+        will automatically expand to a total of
+        `indicator_periods_candles` * `include_timeframes` * `include_shifted_candles` *
+        `include_corr_pairs` numbers of features added to the model.
+
+        All features must be prepended with `%` to be recognized by FreqAI internals.
+
+        More details on how these config defined parameters accelerate feature engineering
+        in the documentation at:
+
+        https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
+
+        :param df: strategy dataframe which will receive the features
+        :param period: period of the indicator - usage example:
+        dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period)
         """
 
-        if informative is None:
-            informative = self.dp.get_pair_dataframe(pair, tf)
+        dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
+        dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period)
+        dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period)
+        dataframe["%-sma-period"] = ta.SMA(dataframe, timeperiod=period)
+        dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period)
 
-        # first loop is automatically duplicating indicators for time periods
-        for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
+        bollinger = qtpylib.bollinger_bands(
+            qtpylib.typical_price(dataframe), window=period, stds=2.2
+        )
+        dataframe["bb_lowerband-period"] = bollinger["lower"]
+        dataframe["bb_middleband-period"] = bollinger["mid"]
+        dataframe["bb_upperband-period"] = bollinger["upper"]
 
-            t = int(t)
-            informative[f"%-{pair}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
-            informative[f"%-{pair}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
-            informative[f"%-{pair}adx-period_{t}"] = ta.ADX(informative, timeperiod=t)
-            informative[f"%-{pair}sma-period_{t}"] = ta.SMA(informative, timeperiod=t)
-            informative[f"%-{pair}ema-period_{t}"] = ta.EMA(informative, timeperiod=t)
+        dataframe["%-bb_width-period"] = (
+            dataframe["bb_upperband-period"]
+            - dataframe["bb_lowerband-period"]
+        ) / dataframe["bb_middleband-period"]
+        dataframe["%-close-bb_lower-period"] = (
+            dataframe["close"] / dataframe["bb_lowerband-period"]
+        )
 
-            bollinger = qtpylib.bollinger_bands(
-                qtpylib.typical_price(informative), window=t, stds=2.2
-            )
-            informative[f"{pair}bb_lowerband-period_{t}"] = bollinger["lower"]
-            informative[f"{pair}bb_middleband-period_{t}"] = bollinger["mid"]
-            informative[f"{pair}bb_upperband-period_{t}"] = bollinger["upper"]
+        dataframe["%-roc-period"] = ta.ROC(dataframe, timeperiod=period)
 
-            informative[f"%-{pair}bb_width-period_{t}"] = (
-                informative[f"{pair}bb_upperband-period_{t}"]
-                - informative[f"{pair}bb_lowerband-period_{t}"]
-            ) / informative[f"{pair}bb_middleband-period_{t}"]
-            informative[f"%-{pair}close-bb_lower-period_{t}"] = (
-                informative["close"] / informative[f"{pair}bb_lowerband-period_{t}"]
+        dataframe["%-relative_volume-period"] = (
+            dataframe["volume"] / dataframe["volume"].rolling(period).mean()
+        )
+
+        return dataframe
+
+    def feature_engineering_expand_basic(self, dataframe, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        This function will automatically expand the defined features on the config defined
+        `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`.
+        In other words, a single feature defined in this function
+        will automatically expand to a total of
+        `include_timeframes` * `include_shifted_candles` * `include_corr_pairs`
+        numbers of features added to the model.
+
+        Features defined here will *not* be automatically duplicated on user defined
+        `indicator_periods_candles`
+
+        All features must be prepended with `%` to be recognized by FreqAI internals.
+
+        More details on how these config defined parameters accelerate feature engineering
+        in the documentation at:
+
+        https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
+
+        :param df: strategy dataframe which will receive the features
+        dataframe["%-pct-change"] = dataframe["close"].pct_change()
+        dataframe["%-ema-200"] = ta.EMA(dataframe, timeperiod=200)
+        """
+        dataframe["%-pct-change"] = dataframe["close"].pct_change()
+        dataframe["%-raw_volume"] = dataframe["volume"]
+        dataframe["%-raw_price"] = dataframe["close"]
+        return dataframe
+
+    def feature_engineering_standard(self, dataframe, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        This optional function will be called once with the dataframe of the base timeframe.
+        This is the final function to be called, which means that the dataframe entering this
+        function will contain all the features and columns created by all other
+        freqai_feature_engineering_* functions.
+
+        This function is a good place to do custom exotic feature extractions (e.g. tsfresh).
+        This function is a good place for any feature that should not be auto-expanded upon
+        (e.g. day of the week).
+
+        All features must be prepended with `%` to be recognized by FreqAI internals.
+
+        More details about feature engineering available:
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering
+
+        :param df: strategy dataframe which will receive the features
+        usage example: dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7
+        """
+        dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
+        dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
+        return dataframe
+
+    def set_freqai_targets(self, dataframe, **kwargs):
+        """
+        *Only functional with FreqAI enabled strategies*
+        Required function to set the targets for the model.
+        All targets must be prepended with `&` to be recognized by the FreqAI internals.
+
+        More details about feature engineering available:
+
+        https://www.freqtrade.io/en/latest/freqai-feature-engineering
+
+        :param df: strategy dataframe which will receive the targets
+        usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"]
+        """
+        dataframe["&-s_close"] = (
+            dataframe["close"]
+            .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
+            .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
+            .mean()
+            / dataframe["close"]
+            - 1
             )
 
-            informative[f"%-{pair}roc-period_{t}"] = ta.ROC(informative, timeperiod=t)
+        # Classifiers are typically set up with strings as targets:
+        # df['&s-up_or_down'] = np.where( df["close"].shift(-100) >
+        #                                 df["close"], 'up', 'down')
 
-            informative[f"%-{pair}relative_volume-period_{t}"] = (
-                informative["volume"] / informative["volume"].rolling(t).mean()
-            )
+        # If user wishes to use multiple targets, they can add more by
+        # appending more columns with '&'. User should keep in mind that multi targets
+        # requires a multioutput prediction model such as
+        # freqai/prediction_models/CatboostRegressorMultiTarget.py,
+        # freqtrade trade --freqaimodel CatboostRegressorMultiTarget
 
-        informative[f"%-{pair}pct-change"] = informative["close"].pct_change()
-        informative[f"%-{pair}raw_volume"] = informative["volume"]
-        informative[f"%-{pair}raw_price"] = informative["close"]
+        # df["&-s_range"] = (
+        #     df["close"]
+        #     .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
+        #     .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
+        #     .max()
+        #     -
+        #     df["close"]
+        #     .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
+        #     .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
+        #     .min()
+        # )
 
-        indicators = [col for col in informative if col.startswith("%")]
-        # This loop duplicates and shifts all indicators to add a sense of recency to data
-        for n in range(self.freqai_info["feature_parameters"]["include_shifted_candles"] + 1):
-            if n == 0:
-                continue
-            informative_shift = informative[indicators].shift(n)
-            informative_shift = informative_shift.add_suffix("_shift-" + str(n))
-            informative = pd.concat((informative, informative_shift), axis=1)
-
-        df = merge_informative_pair(df, informative, self.config["timeframe"], tf, ffill=True)
-        skip_columns = [
-            (s + "_" + tf) for s in ["date", "open", "high", "low", "close", "volume"]
-        ]
-        df = df.drop(columns=skip_columns)
-
-        # Add generalized indicators here (because in live, it will call this
-        # function to populate indicators during training). Notice how we ensure not to
-        # add them multiple times
-        if set_generalized_indicators:
-            df["%-day_of_week"] = (df["date"].dt.dayofweek + 1) / 7
-            df["%-hour_of_day"] = (df["date"].dt.hour + 1) / 25
-
-            # user adds targets here by prepending them with &- (see convention below)
-            df["&-s_close"] = (
-                df["close"]
-                .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
-                .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
-                .mean()
-                / df["close"]
-                - 1
-            )
-
-            # Classifiers are typically set up with strings as targets:
-            # df['&s-up_or_down'] = np.where( df["close"].shift(-100) >
-            #                                 df["close"], 'up', 'down')
-
-            # If user wishes to use multiple targets, they can add more by
-            # appending more columns with '&'. User should keep in mind that multi targets
-            # requires a multioutput prediction model such as
-            # freqai/prediction_models/CatboostRegressorMultiTarget.py,
-            # freqtrade trade --freqaimodel CatboostRegressorMultiTarget
-
-            # df["&-s_range"] = (
-            #     df["close"]
-            #     .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
-            #     .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
-            #     .max()
-            #     -
-            #     df["close"]
-            #     .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
-            #     .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
-            #     .min()
-            # )
-
-        return df
+        return dataframe
 
     def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
 
-        # All indicators must be populated by populate_any_indicators() for live functionality
-        # to work correctly.
+        # All indicators must be populated by feature_engineering_*() functions
 
-        # the model will return all labels created by user in `populate_any_indicators`
+        # the model will return all labels created by user in `feature_engineering_*`
         # (& appended targets), an indication of whether or not the prediction should be accepted,
         # the target mean/std values for each of the labels created by user in
-        # `populate_any_indicators()` for each training period.
+        # `set_freqai_targets()` for each training period.
 
         dataframe = self.freqai.start(dataframe, metadata, self)
+
         for val in self.std_dev_multiplier_buy.range:
             dataframe[f'target_roi_{val}'] = (
                 dataframe["&-s_close_mean"] + dataframe["&-s_close_std"] * val