chore: make DOCS_LINK in constants.py, ensure datasieve is added to setup.py

freqtrade/constants.py

@@ -8,6 +8,7 @@ from typing import Any, Dict, List, Literal, Tuple
 from freqtrade.enums import CandleType, PriceType, RPCMessageType
 
 
+DOCS_LINK = "https://www.freqtrade.io/en/stable"
 DEFAULT_CONFIG = 'config.json'
 DEFAULT_EXCHANGE = 'bittrex'
 PROCESS_THROTTLE_SECS = 5  # sec

freqtrade/freqai/RL/BaseReinforcementLearningModel.py

@@ -119,7 +119,6 @@ class BaseReinforcementLearningModel(IFreqaiModel):
         prices_train, prices_test = self.build_ohlc_price_dataframes(dk.data_dictionary, pair, dk)
 
         dk.feature_pipeline = self.define_data_pipeline(threads=dk.thread_count)
-        dk.label_pipeline = self.define_label_pipeline(threads=dk.thread_count)
 
         (dd["train_features"],
          dd["train_labels"],

freqtrade/freqai/data_kitchen.py

@@ -12,7 +12,6 @@ import numpy.typing as npt
 import pandas as pd
 import psutil
 from datasieve.pipeline import Pipeline
-from datasieve.transforms import SKLearnWrapper
 from pandas import DataFrame
 from sklearn.model_selection import train_test_split
 
@@ -966,35 +965,7 @@ class FreqaiDataKitchen:
                        "in a future version.\n"
                        "This version does not include any outlier configurations")
 
-        import datasieve.transforms as ds
-        from sklearn.preprocessing import MinMaxScaler
-        dd = data_dictionary
-
-        self.feature_pipeline = Pipeline([
-            ('variance_threshold', ds.VarianceThreshold()),
-            ('scaler', SKLearnWrapper(MinMaxScaler(feature_range=(-1, 1))))
-            ])
-
-        (dd["train_features"],
-         dd["train_labels"],
-         dd["train_weights"]) = self.feature_pipeline.fit_transform(dd["train_features"],
-                                                                    dd["train_labels"],
-                                                                    dd["train_weights"])
-
-        (dd["test_features"],
-         dd["test_labels"],
-         dd["test_weights"]) = self.feature_pipeline.transform(dd["test_features"],
-                                                               dd["test_labels"],
-                                                               dd["test_weights"])
-
-        self.label_pipeline = Pipeline([
-            ('scaler', SKLearnWrapper(MinMaxScaler(feature_range=(-1, 1))))
-            ])
-
-        dd["train_labels"], _, _ = self.label_pipeline.fit_transform(dd["train_labels"])
-        dd["test_labels"], _, _ = self.label_pipeline.transform(dd["test_labels"])
-
-        return dd
+        return data_dictionary
 
     def denormalize_labels_from_metadata(self, df: DataFrame) -> DataFrame:
         """

freqtrade/freqai/freqai_interface.py

@@ -18,7 +18,7 @@ from pandas import DataFrame
 from sklearn.preprocessing import MinMaxScaler
 
 from freqtrade.configuration import TimeRange
-from freqtrade.constants import Config
+from freqtrade.constants import DOCS_LINK, Config
 from freqtrade.data.dataprovider import DataProvider
 from freqtrade.enums import RunMode
 from freqtrade.exceptions import OperationalException
@@ -974,20 +974,20 @@ class IFreqaiModel(ABC):
         """
         throw deprecation warning if this function is called
         """
-        ft = "https://www.freqtrade.io/en/latest"
         logger.warning(f"Your model {self.__class__.__name__} relies on the deprecated"
                        " data pipeline. Please update your model to use the new data pipeline."
                        " This can be achieved by following the migration guide at "
-                       f"{ft}/strategy_migration/#freqai-new-data-pipeline")
+                       f"{DOCS_LINK}/strategy_migration/#freqai-new-data-pipeline")
+        dk.feature_pipeline = self.define_data_pipeline(threads=dk.thread_count)
         return
 
     def data_cleaning_predict(self, dk: FreqaiDataKitchen, pair: str):
         """
         throw deprecation warning if this function is called
         """
-        ft = "https://www.freqtrade.io/en/latest"
         logger.warning(f"Your model {self.__class__.__name__} relies on the deprecated"
                        " data pipeline. Please update your model to use the new data pipeline."
                        " This can be achieved by following the migration guide at "
-                       f"{ft}/strategy_migration/#freqai-new-data-pipeline")
+                       f"{DOCS_LINK}/strategy_migration/#freqai-new-data-pipeline")
+        dk.label_pipeline = self.define_data_pipeline(threads=dk.thread_count)
         return

setup.py

@@ -16,7 +16,8 @@ freqai = [
     'catboost; platform_machine != "aarch64"',
     'lightgbm',
     'xgboost',
-    'tensorboard'
+    'tensorboard',
+    'datasieve>=0.1.4'
 ]
 
 freqai_rl = [