enable continual learning and evaluation sets on multioutput models.

freqtrade/freqai/base_models/BaseClassifierModel.py

@@ -0,0 +1,99 @@
+import logging
+from typing import Any, Tuple
+
+import numpy as np
+import numpy.typing as npt
+import pandas as pd
+from pandas import DataFrame
+
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+from freqtrade.freqai.freqai_interface import IFreqaiModel
+
+
+logger = logging.getLogger(__name__)
+
+
+class BaseClassifierModel(IFreqaiModel):
+    """
+    Base class for regression type models (e.g. Catboost, LightGBM, XGboost etc.).
+    User *must* inherit from this class and set fit() and predict(). See example scripts
+    such as prediction_models/CatboostPredictionModel.py for guidance.
+    """
+
+    def train(
+        self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
+    ) -> Any:
+        """
+        Filter the training data and train a model to it. Train makes heavy use of the datakitchen
+        for storing, saving, loading, and analyzing the data.
+        :param unfiltered_df: Full dataframe for the current training period
+        :param metadata: pair metadata from strategy.
+        :return:
+        :model: Trained model which can be used to inference (self.predict)
+        """
+
+        logger.info("-------------------- Starting training " f"{pair} --------------------")
+
+        # filter the features requested by user in the configuration file and elegantly handle NaNs
+        features_filtered, labels_filtered = dk.filter_features(
+            unfiltered_df,
+            dk.training_features_list,
+            dk.label_list,
+            training_filter=True,
+        )
+
+        start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
+        end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
+        logger.info(f"-------------------- Training on data from {start_date} to "
+                    f"{end_date}--------------------")
+        # split data into train/test data.
+        data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
+        if not self.freqai_info.get('fit_live_predictions', 0) or not self.live:
+            dk.fit_labels()
+        # normalize all data based on train_dataset only
+        data_dictionary = dk.normalize_data(data_dictionary)
+
+        # optional additional data cleaning/analysis
+        self.data_cleaning_train(dk)
+
+        logger.info(
+            f'Training model on {len(dk.data_dictionary["train_features"].columns)}' " features"
+        )
+        logger.info(f'Training model on {len(data_dictionary["train_features"])} data points')
+
+        model = self.fit(data_dictionary, dk)
+
+        logger.info(f"--------------------done training {pair}--------------------")
+
+        return model
+
+    def predict(
+        self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
+    ) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
+        """
+        Filter the prediction features data and predict with it.
+        :param: unfiltered_df: Full dataframe for the current backtest period.
+        :return:
+        :pred_df: dataframe containing the predictions
+        :do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
+        data (NaNs) or felt uncertain about data (PCA and DI index)
+        """
+
+        dk.find_features(unfiltered_df)
+        filtered_df, _ = dk.filter_features(
+            unfiltered_df, dk.training_features_list, training_filter=False
+        )
+        filtered_df = dk.normalize_data_from_metadata(filtered_df)
+        dk.data_dictionary["prediction_features"] = filtered_df
+
+        self.data_cleaning_predict(dk, filtered_df)
+
+        predictions = self.model.predict(dk.data_dictionary["prediction_features"])
+        pred_df = DataFrame(predictions, columns=dk.label_list)
+
+        predictions_prob = self.model.predict_proba(dk.data_dictionary["prediction_features"])
+        pred_df_prob = DataFrame(predictions_prob, columns=self.model.classes_)
+
+        pred_df = pd.concat([pred_df, pred_df_prob], axis=1)
+
+        return (pred_df, dk.do_predict)

freqtrade/freqai/base_models/BaseRegressionModel.py

@@ -0,0 +1,96 @@
+import logging
+from typing import Any, Tuple
+
+import numpy as np
+import numpy.typing as npt
+from pandas import DataFrame
+
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+from freqtrade.freqai.freqai_interface import IFreqaiModel
+
+
+logger = logging.getLogger(__name__)
+
+
+class BaseRegressionModel(IFreqaiModel):
+    """
+    Base class for regression type models (e.g. Catboost, LightGBM, XGboost etc.).
+    User *must* inherit from this class and set fit() and predict(). See example scripts
+    such as prediction_models/CatboostPredictionModel.py for guidance.
+    """
+
+    def train(
+        self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
+    ) -> Any:
+        """
+        Filter the training data and train a model to it. Train makes heavy use of the datakitchen
+        for storing, saving, loading, and analyzing the data.
+        :param unfiltered_df: Full dataframe for the current training period
+        :param metadata: pair metadata from strategy.
+        :return:
+        :model: Trained model which can be used to inference (self.predict)
+        """
+
+        logger.info("-------------------- Starting training " f"{pair} --------------------")
+
+        # filter the features requested by user in the configuration file and elegantly handle NaNs
+        features_filtered, labels_filtered = dk.filter_features(
+            unfiltered_df,
+            dk.training_features_list,
+            dk.label_list,
+            training_filter=True,
+        )
+
+        start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
+        end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
+        logger.info(f"-------------------- Training on data from {start_date} to "
+                    f"{end_date}--------------------")
+        # split data into train/test data.
+        data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
+        if not self.freqai_info.get('fit_live_predictions', 0) or not self.live:
+            dk.fit_labels()
+        # normalize all data based on train_dataset only
+        data_dictionary = dk.normalize_data(data_dictionary)
+
+        # optional additional data cleaning/analysis
+        self.data_cleaning_train(dk)
+
+        logger.info(
+            f'Training model on {len(dk.data_dictionary["train_features"].columns)}' " features"
+        )
+        logger.info(f'Training model on {len(data_dictionary["train_features"])} data points')
+
+        model = self.fit(data_dictionary, dk)
+
+        logger.info(f"--------------------done training {pair}--------------------")
+
+        return model
+
+    def predict(
+        self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
+    ) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
+        """
+        Filter the prediction features data and predict with it.
+        :param: unfiltered_df: Full dataframe for the current backtest period.
+        :return:
+        :pred_df: dataframe containing the predictions
+        :do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
+        data (NaNs) or felt uncertain about data (PCA and DI index)
+        """
+
+        dk.find_features(unfiltered_df)
+        filtered_df, _ = dk.filter_features(
+            unfiltered_df, dk.training_features_list, training_filter=False
+        )
+        filtered_df = dk.normalize_data_from_metadata(filtered_df)
+        dk.data_dictionary["prediction_features"] = filtered_df
+
+        # optional additional data cleaning/analysis
+        self.data_cleaning_predict(dk, filtered_df)
+
+        predictions = self.model.predict(dk.data_dictionary["prediction_features"])
+        pred_df = DataFrame(predictions, columns=dk.label_list)
+
+        pred_df = dk.denormalize_labels_from_metadata(pred_df)
+
+        return (pred_df, dk.do_predict)

freqtrade/freqai/base_models/BaseTensorFlowModel.py

@@ -0,0 +1,64 @@
+import logging
+from typing import Any
+
+from pandas import DataFrame
+
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+from freqtrade.freqai.freqai_interface import IFreqaiModel
+
+
+logger = logging.getLogger(__name__)
+
+
+class BaseTensorFlowModel(IFreqaiModel):
+    """
+    Base class for TensorFlow type models.
+    User *must* inherit from this class and set fit() and predict().
+    """
+
+    def train(
+        self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
+    ) -> Any:
+        """
+        Filter the training data and train a model to it. Train makes heavy use of the datakitchen
+        for storing, saving, loading, and analyzing the data.
+        :param unfiltered_df: Full dataframe for the current training period
+        :param metadata: pair metadata from strategy.
+        :return:
+        :model: Trained model which can be used to inference (self.predict)
+        """
+
+        logger.info("-------------------- Starting training " f"{pair} --------------------")
+
+        # filter the features requested by user in the configuration file and elegantly handle NaNs
+        features_filtered, labels_filtered = dk.filter_features(
+            unfiltered_df,
+            dk.training_features_list,
+            dk.label_list,
+            training_filter=True,
+        )
+
+        start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
+        end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
+        logger.info(f"-------------------- Training on data from {start_date} to "
+                    f"{end_date}--------------------")
+        # split data into train/test data.
+        data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
+        if not self.freqai_info.get('fit_live_predictions', 0) or not self.live:
+            dk.fit_labels()
+        # normalize all data based on train_dataset only
+        data_dictionary = dk.normalize_data(data_dictionary)
+
+        # optional additional data cleaning/analysis
+        self.data_cleaning_train(dk)
+
+        logger.info(
+            f'Training model on {len(dk.data_dictionary["train_features"].columns)}' " features"
+        )
+        logger.info(f'Training model on {len(data_dictionary["train_features"])} data points')
+
+        model = self.fit(data_dictionary, dk)
+
+        logger.info(f"--------------------done training {pair}--------------------")
+
+        return model

freqtrade/freqai/base_models/FreqaiMultiOutputRegressor.py

@@ -0,0 +1,75 @@
+
+from joblib import Parallel
+from sklearn.multioutput import MultiOutputRegressor, _fit_estimator
+from sklearn.utils.fixes import delayed
+from sklearn.utils.validation import has_fit_parameter
+
+
+class FreqaiMultiOutputRegressor(MultiOutputRegressor):
+
+    def fit(self, X, y, sample_weight=None, fit_params=None):
+        """Fit the model to data, separately for each output variable.
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            The input data.
+        y : {array-like, sparse matrix} of shape (n_samples, n_outputs)
+            Multi-output targets. An indicator matrix turns on multilabel
+            estimation.
+        sample_weight : array-like of shape (n_samples,), default=None
+            Sample weights. If `None`, then samples are equally weighted.
+            Only supported if the underlying regressor supports sample
+            weights.
+        fit_params : A list of dicts for the fit_params
+            Parameters passed to the ``estimator.fit`` method of each step.
+            Each dict may contain same or different values (e.g. different
+            eval_sets or init_models)
+            .. versionadded:: 0.23
+        Returns
+        -------
+        self : object
+            Returns a fitted instance.
+        """
+
+        if not hasattr(self.estimator, "fit"):
+            raise ValueError("The base estimator should implement a fit method")
+
+        y = self._validate_data(X="no_validation", y=y, multi_output=True)
+
+        # if is_classifier(self):
+        #     check_classification_targets(y)
+
+        if y.ndim == 1:
+            raise ValueError(
+                "y must have at least two dimensions for "
+                "multi-output regression but has only one."
+            )
+
+        if sample_weight is not None and not has_fit_parameter(
+            self.estimator, "sample_weight"
+        ):
+            raise ValueError("Underlying estimator does not support sample weights.")
+
+        # fit_params_validated = _check_fit_params(X, fit_params)
+
+        if not fit_params:
+            fit_params = [None] * y.shape[1]
+
+        # if not init_models:
+        #     init_models = [None] * y.shape[1]
+
+        self.estimators_ = Parallel(n_jobs=self.n_jobs)(
+            delayed(_fit_estimator)(
+                self.estimator, X, y[:, i], sample_weight, **fit_params[i]
+                # init_model=init_models[i], eval_set=eval_sets[i],
+                # **fit_params_validated
+            )
+            for i in range(y.shape[1])
+        )
+
+        if hasattr(self.estimators_[0], "n_features_in_"):
+            self.n_features_in_ = self.estimators_[0].n_features_in_
+        if hasattr(self.estimators_[0], "feature_names_in_"):
+            self.feature_names_in_ = self.estimators_[0].feature_names_in_
+
+        return