add self-retraining functionality for live/dry

config_examples/config_freqai.example.json

@@ -13,7 +13,7 @@
         "exit": 30
     },
     "exchange": {
-        "name": "ftx",
+        "name": "binance",
         "key": "",
         "secret": "",
         "ccxt_config": {
@@ -55,7 +55,9 @@
         ],
         "train_period": 30,
         "backtest_period": 7,
-        "identifier": "example",
+        "identifier": "livetest5",
+        "live_trained_timerange": "20220330-20220429",
+        "live_full_backtestrange": "20220302-20220501",
         "base_features": [
             "rsi",
             "close_over_20sma",
@@ -68,6 +70,7 @@
             "macd"
         ],
         "corr_pairlist": [
+            "BTC/USDT",
             "ETH/USDT",
             "LINK/USDT",
             "DOT/USDT"

freqtrade/constants.py

@@ -440,6 +440,8 @@ CONF_SCHEMA = {
                 "train_period": {"type": "integer", "default": 0},
                 "backtest_period": {"type": "integer", "default": 7},
                 "identifier": {"type": "str", "default": "example"},
+                "live_trained_timerange": {"type": "str"},
+                "live_full_backtestrange": {"type": "str"},
                 "base_features": {"type": "list"},
                 "corr_pairlist": {"type": "list"},
                 "feature_parameters": {

freqtrade/freqai/data_kitchen.py

@@ -16,6 +16,10 @@ from sklearn.metrics.pairwise import pairwise_distances
 from sklearn.model_selection import train_test_split
 
 from freqtrade.configuration import TimeRange
+from freqtrade.data.history import load_pair_history
+from freqtrade.data.history.history_utils import refresh_backtest_ohlcv_data
+from freqtrade.resolvers import ExchangeResolver
+from freqtrade.strategy.interface import IStrategy
 
 
 SECONDS_IN_DAY = 86400
@@ -30,7 +34,7 @@ class FreqaiDataKitchen:
     author: Robert Caulk, rob.caulk@gmail.com
     """
 
-    def __init__(self, config: Dict[str, Any], dataframe: DataFrame):
+    def __init__(self, config: Dict[str, Any], dataframe: DataFrame, live: bool = False):
         self.full_dataframe = dataframe
         self.data: Dict[Any, Any] = {}
         self.data_dictionary: Dict[Any, Any] = {}
@@ -45,17 +49,29 @@ class FreqaiDataKitchen:
         self.full_target_mean: npt.ArrayLike = np.array([])
         self.full_target_std: npt.ArrayLike = np.array([])
         self.model_path = Path()
-        self.model_filename = ""
+        self.model_filename: str = ""
 
-        self.full_timerange = self.create_fulltimerange(
-            self.config["timerange"], self.freqai_config["train_period"]
-        )
+        if not live:
+            self.full_timerange = self.create_fulltimerange(self.config["timerange"],
+                                                            self.freqai_config["train_period"]
+                                                            )
 
-        (self.training_timeranges, self.backtesting_timeranges) = self.split_timerange(
-            self.full_timerange,
-            config["freqai"]["train_period"],
-            config["freqai"]["backtest_period"],
-        )
+            (self.training_timeranges, self.backtesting_timeranges) = self.split_timerange(
+                self.full_timerange,
+                config["freqai"]["train_period"],
+                config["freqai"]["backtest_period"],
+            )
+
+    def set_paths(self) -> None:
+        self.full_path = Path(self.config['user_data_dir'] /
+                              "models" /
+                              str(self.freqai_config['live_full_backtestrange'] +
+                                  self.freqai_config['identifier']))
+
+        self.model_path = Path(self.full_path / str("sub-train" + "-" +
+                               str(self.freqai_config['live_trained_timerange'])))
+
+        return
 
     def save_data(self, model: Any) -> None:
         """
@@ -187,10 +203,10 @@ class FreqaiDataKitchen:
             labels = labels[
                 (drop_index == 0) & (drop_index_labels == 0)
             ]  # assuming the labels depend entirely on the dataframe here.
-            logger.info(
-                "dropped %s training points due to NaNs, ensure all historical data downloaded",
-                len(unfiltered_dataframe) - len(filtered_dataframe),
-            )
+            # logger.info(
+            #     "dropped %s training points due to NaNs, ensure all historical data downloaded",
+            #     len(unfiltered_dataframe) - len(filtered_dataframe),
+            # )
             self.data["filter_drop_index_training"] = drop_index
 
         else:
@@ -485,11 +501,11 @@ class FreqaiDataKitchen:
                     shift = ""
                     if n > 0:
                         shift = "_shift-" + str(n)
-                    features.append(ft + shift + "_" + tf)
+                    # features.append(ft + shift + "_" + tf)
                     for p in config["freqai"]["corr_pairlist"]:
                         features.append(p.split("/")[0] + "-" + ft + shift + "_" + tf)
 
-        logger.info("number of features %s", len(features))
+        # logger.info("number of features %s", len(features))
         return features
 
     def check_if_pred_in_training_spaces(self) -> None:
@@ -513,10 +529,10 @@ class FreqaiDataKitchen:
             0,
         )
 
-        logger.info(
-            "Distance checker tossed %s predictions for being too far from training data",
-            len(do_predict) - do_predict.sum(),
-        )
+        # logger.info(
+        #     "Distance checker tossed %s predictions for being too far from training data",
+        #     len(do_predict) - do_predict.sum(),
+        # )
 
         self.do_predict += do_predict
         self.do_predict -= 1
@@ -577,15 +593,105 @@ class FreqaiDataKitchen:
             / str(full_timerange + self.freqai_config["identifier"])
         )
 
+        config_path = Path(self.config["config_files"][0])
+
         if not self.full_path.is_dir():
             self.full_path.mkdir(parents=True, exist_ok=True)
             shutil.copy(
-                Path(self.config["config_files"][0]).name,
-                Path(self.full_path / self.config["config_files"][0]),
+                config_path.name,
+                Path(self.full_path / config_path.parts[-1]),
             )
 
         return full_timerange
 
+    def check_if_new_training_required(self, training_timerange: str,
+                                       metadata: dict) -> Tuple[bool, str]:
+
+        time = datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
+
+        trained_timerange = TimeRange.parse_timerange(training_timerange)
+
+        elapsed_time = (time - trained_timerange.stopts) / SECONDS_IN_DAY
+
+        trained_timerange.startts += self.freqai_config['backtest_period'] * SECONDS_IN_DAY
+        trained_timerange.stopts += self.freqai_config['backtest_period'] * SECONDS_IN_DAY
+        start = datetime.datetime.utcfromtimestamp(trained_timerange.startts)
+        stop = datetime.datetime.utcfromtimestamp(trained_timerange.stopts)
+
+        new_trained_timerange = start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d")
+
+        retrain = elapsed_time > self.freqai_config['backtest_period']
+
+        if retrain:
+            coin, _ = metadata['pair'].split("/")
+            # set the new model_path
+            self.model_path = Path(self.full_path / str("sub-train" + "-" +
+                                   str(new_trained_timerange)))
+
+            self.model_filename = "cb_" + coin.lower() + "_" + new_trained_timerange
+            # this is not persistent at the moment TODO
+            self.freqai_config['live_trained_timerange'] = new_trained_timerange
+            # enables persistence, but not fully implemented into save/load data yer
+            self.data['live_trained_timerange'] = new_trained_timerange
+
+        return retrain, new_trained_timerange
+
+    def download_new_data_for_retraining(self, new_timerange: str, metadata: dict) -> None:
+
+        exchange = ExchangeResolver.load_exchange(self.config['exchange']['name'],
+                                                  self.config, validate=False)
+        pairs = self.freqai_config['corr_pairlist'] + [metadata['pair']]
+        timerange = TimeRange.parse_timerange(new_timerange)
+        # data_handler = get_datahandler(datadir, data_format)
+
+        refresh_backtest_ohlcv_data(
+                        exchange, pairs=pairs, timeframes=self.freqai_config['timeframes'],
+                        datadir=self.config['datadir'], timerange=timerange,
+                        new_pairs_days=self.config['new_pairs_days'],
+                        erase=False, data_format=self.config['dataformat_ohlcv'],
+                        trading_mode=self.config.get('trading_mode', 'spot'),
+                        prepend=self.config.get('prepend_data', False)
+                    )
+
+    def load_pairs_histories(self, new_timerange: str, metadata: dict) -> Tuple[Dict[Any, Any],
+                                                                                DataFrame]:
+        corr_dataframes: Dict[Any, Any] = {}
+        # pair_dataframes: Dict[Any, Any] = {}
+        pairs = self.freqai_config['corr_pairlist']  # + [metadata['pair']]
+        timerange = TimeRange.parse_timerange(new_timerange)
+
+        for p in pairs:
+            corr_dataframes[p] = {}
+            for tf in self.freqai_config['timeframes']:
+                corr_dataframes[p][tf] = load_pair_history(datadir=self.config['datadir'],
+                                                           timeframe=tf,
+                                                           pair=p, timerange=timerange)
+
+        base_dataframe = [dataframe for key, dataframe in corr_dataframes.items()
+                          if metadata['pair'] in key]
+
+        # [0] indexes the lowest tf for the basepair
+        return corr_dataframes, base_dataframe[0][self.config['timeframe']]
+
+    def use_strategy_to_populate_indicators(self, strategy: IStrategy, metadata: dict,
+                                            corr_dataframes: dict,
+                                            dataframe: DataFrame) -> DataFrame:
+
+        # dataframe = pair_dataframes[0]  # this is the base tf pair df
+
+        for tf in self.freqai_config["timeframes"]:
+            # dataframe = strategy.populate_any_indicators(metadata["pair"], dataframe.copy,
+            #                                              tf, pair_dataframes[tf])
+            for i in self.freqai_config["corr_pairlist"]:
+                dataframe = strategy.populate_any_indicators(i,
+                                                             dataframe.copy(),
+                                                             tf,
+                                                             corr_dataframes[i][tf],
+                                                             coin=i.split("/")[0] + "-"
+                                                             )
+
+        return dataframe
+
     def np_encoder(self, object):
         if isinstance(object, np.generic):
             return object.item()

freqtrade/freqai/freqai_interface.py

@@ -8,9 +8,9 @@ import numpy.typing as npt
 import pandas as pd
 from pandas import DataFrame
 
-from freqtrade.data.dataprovider import DataProvider
 from freqtrade.enums import RunMode
 from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+from freqtrade.strategy.interface import IStrategy
 
 
 pd.options.mode.chained_assignment = None
@@ -33,15 +33,14 @@ class IFreqaiModel(ABC):
         self.data_split_parameters = config["freqai"]["data_split_parameters"]
         self.model_training_parameters = config["freqai"]["model_training_parameters"]
         self.feature_parameters = config["freqai"]["feature_parameters"]
-        self.backtest_timerange = config["timerange"]
+        # self.backtest_timerange = config["timerange"]
 
         self.time_last_trained = None
         self.current_time = None
         self.model = None
         self.predictions = None
-        self.live_trained_timerange = None
 
-    def start(self, dataframe: DataFrame, metadata: dict, dp: DataProvider) -> DataFrame:
+    def start(self, dataframe: DataFrame, metadata: dict, strategy: IStrategy) -> DataFrame:
         """
         Entry point to the FreqaiModel, it will train a new model if
         necesssary before making the prediction.
@@ -57,11 +56,18 @@ class IFreqaiModel(ABC):
         the model.
         :metadata: pair metadataa coming from strategy.
         """
+
+        live = strategy.dp.runmode in (RunMode.DRY_RUN, RunMode.LIVE)
+
         self.pair = metadata["pair"]
-        self.dh = FreqaiDataKitchen(self.config, dataframe)
+        self.dh = FreqaiDataKitchen(self.config, dataframe, live)
 
-        if dp.runmode in (RunMode.DRY_RUN, RunMode.LIVE):
-            logger.info('testing live')
+        if live:
+            # logger.info('testing live')
+            self.start_live(dataframe, metadata, strategy)
+
+            return (self.dh.full_predictions, self.dh.full_do_predict,
+                    self.dh.full_target_mean, self.dh.full_target_std)
 
         logger.info("going to train %s timeranges", len(self.dh.training_timeranges))
 
@@ -98,6 +104,42 @@ class IFreqaiModel(ABC):
         return (self.dh.full_predictions, self.dh.full_do_predict,
                 self.dh.full_target_mean, self.dh.full_target_std)
 
+    def start_live(self, dataframe: DataFrame, metadata: dict, strategy: IStrategy) -> None:
+
+        self.dh.set_paths()
+
+        file_exists = self.model_exists(metadata['pair'],
+                                        training_timerange=self.freqai_info[
+                                                           'live_trained_timerange'])
+
+        (retrain,
+         new_trained_timerange) = self.dh.check_if_new_training_required(self.freqai_info[
+                                                                        'live_trained_timerange'],
+                                                                         metadata)
+
+        if retrain or not file_exists:
+            self.dh.download_new_data_for_retraining(new_trained_timerange, metadata)
+            # dataframe = download-data
+            corr_dataframes, pair_dataframes = self.dh.load_pairs_histories(new_trained_timerange,
+                                                                            metadata)
+
+            unfiltered_dataframe = self.dh.use_strategy_to_populate_indicators(strategy,
+                                                                               metadata,
+                                                                               corr_dataframes,
+                                                                               pair_dataframes)
+
+            self.model = self.train(unfiltered_dataframe, metadata)
+            self.dh.save_data(self.model)
+
+            self.freqai_info
+
+        self.model = self.dh.load_data()
+        preds, do_preds = self.predict(dataframe)
+        self.dh.append_predictions(preds, do_preds, len(dataframe))
+        # dataframe should have len 1 here
+
+        return
+
     def make_labels(self, dataframe: DataFrame) -> DataFrame:
         """
         User defines the labels here (target values).

freqtrade/strategy/interface.py

@@ -532,6 +532,22 @@ class IStrategy(ABC, HyperStrategyMixin):
         """
         return None
 
+    def populate_any_indicators(self, pair: str, df: DataFrame, tf: str,
+                                informative: DataFrame = None, coin: str = "") -> DataFrame:
+        """
+        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.
+        Defined in IStrategy because Freqai needs to know it exists.
+        :params:
+        :pair: pair to be used as informative
+        :df: strategy dataframe which will receive merges from informatives
+        :tf: timeframe of the dataframe which will modify the feature names
+        :informative: the dataframe associated with the informative pair
+        :coin: the name of the coin which will modify the feature names.
+        """
+        return df
+
 ###
 # END - Intended to be overridden by strategy
 ###

freqtrade/templates/ExamplePredictionModel.py

@@ -124,7 +124,7 @@ class ExamplePredictionModel(IFreqaiModel):
         data (NaNs) or felt uncertain about data (PCA and DI index)
         """
 
-        logger.info("--------------------Starting prediction--------------------")
+        # logger.info("--------------------Starting prediction--------------------")
 
         original_feature_list = self.dh.build_feature_list(self.config)
         filtered_dataframe, _ = self.dh.filter_features(
@@ -151,8 +151,8 @@ class ExamplePredictionModel(IFreqaiModel):
         predictions = self.model.predict(self.dh.data_dictionary["prediction_features"])
 
         # compute the non-standardized predictions
-        predictions = predictions * self.dh.data["labels_std"] + self.dh.data["labels_mean"]
+        self.dh.predictions = predictions * self.dh.data["labels_std"] + self.dh.data["labels_mean"]
 
-        logger.info("--------------------Finished prediction--------------------")
+        # logger.info("--------------------Finished prediction--------------------")
 
-        return (predictions, self.dh.do_predict)
+        return (self.dh.predictions, self.dh.do_predict)

freqtrade/templates/FreqaiExampleStrategy.py

@@ -44,13 +44,16 @@ class FreqaiExampleStrategy(IStrategy):
 
     stoploss = -0.05
     use_sell_signal = True
-    startup_candle_count: int = 1000
+    startup_candle_count: int = 300
 
     def informative_pairs(self):
-        pairs = self.freqai_info["corr_pairlist"]
+        pairs = self.config["freqai"]["corr_pairlist"]
         informative_pairs = []
-        for tf in self.timeframes:
-            informative_pairs.append([(pair, tf) for pair in pairs])
+        for tf in self.config["freqai"]["timeframes"]:
+            # informative_pairs.append((self.pair, tf))
+            # informative_pairs.append([(pair, tf) for pair in pairs])
+            for pair in pairs:
+                informative_pairs.append((pair, tf))
         return informative_pairs
 
     def populate_any_indicators(self, pair, df, tf, informative=None, coin=""):
@@ -129,6 +132,7 @@ class FreqaiExampleStrategy(IStrategy):
 
         # the configuration file parameters are stored here
         self.freqai_info = self.config["freqai"]
+        self.pair = metadata['pair']
 
         # the model is instantiated here
         self.model = CustomModel(self.config)
@@ -138,12 +142,13 @@ class FreqaiExampleStrategy(IStrategy):
         # the following loops are necessary for building the features
         # indicated by the user in the configuration file.
         for tf in self.freqai_info["timeframes"]:
-            dataframe = self.populate_any_indicators(metadata["pair"], dataframe.copy(), tf)
-            for i in self.freqai_info["corr_pairlist"]:
+            # dataframe = self.populate_any_indicators(metadata["pair"], dataframe.copy(), tf)
+            for pair in self.freqai_info["corr_pairlist"]:
                 dataframe = self.populate_any_indicators(
-                    i, dataframe.copy(), tf, coin=i.split("/")[0] + "-"
+                    pair, dataframe.copy(), tf, coin=pair.split("/")[0] + "-"
                 )
 
+        print('dataframe_built')
         # the model will return 4 values, its prediction, an indication of whether or not the
         # prediction should be accepted, the target mean/std values from the labels used during
         # each training period.
@@ -152,7 +157,7 @@ class FreqaiExampleStrategy(IStrategy):
             dataframe["do_predict"],
             dataframe["target_mean"],
             dataframe["target_std"],
-        ) = self.model.bridge.start(dataframe, metadata)
+        ) = self.model.bridge.start(dataframe, metadata, self)
 
         dataframe["target_roi"] = dataframe["target_mean"] + dataframe["target_std"] * 0.5
         dataframe["sell_roi"] = dataframe["target_mean"] - dataframe["target_std"] * 1.5