Merge remote-tracking branch 'origin/develop' into add-single-precision-freqai

freqtrade/freqai/base_models/FreqaiMultiOutputClassifier.py

@@ -0,0 +1,93 @@
+import numpy as np
+from joblib import Parallel
+from sklearn.base import is_classifier
+from sklearn.multioutput import MultiOutputClassifier, _fit_estimator
+from sklearn.utils.fixes import delayed
+from sklearn.utils.multiclass import check_classification_targets
+from sklearn.utils.validation import has_fit_parameter
+
+from freqtrade.exceptions import OperationalException
+
+
+class FreqaiMultiOutputClassifier(MultiOutputClassifier):
+
+    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 classifier 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.")
+
+        if not fit_params:
+            fit_params = [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]
+            )
+            for i in range(y.shape[1])
+        )
+
+        self.classes_ = []
+        for estimator in self.estimators_:
+            self.classes_.extend(estimator.classes_)
+        if len(set(self.classes_)) != len(self.classes_):
+            raise OperationalException(f"Class labels must be unique across targets: "
+                                       f"{self.classes_}")
+
+        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 self
+
+    def predict_proba(self, X):
+        """
+        Get predict_proba and stack arrays horizontally
+        """
+        results = np.hstack(super().predict_proba(X))
+        return np.squeeze(results)
+
+    def predict(self, X):
+        """
+        Get predict and squeeze into 2D array
+        """
+        results = super().predict(X)
+        return np.squeeze(results)

freqtrade/freqai/data_drawer.py

@@ -87,6 +87,7 @@ class FreqaiDataDrawer:
             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]]] = {}
         self.load_metric_tracker_from_disk()
         self.training_queue: Dict[str, int] = {}
         self.history_lock = threading.Lock()
@@ -97,7 +98,6 @@ class FreqaiDataDrawer:
         self.empty_pair_dict: pair_info = {
                 "model_filename": "", "trained_timestamp": 0,
                 "data_path": "", "extras": {}}
-        self.metric_tracker: Dict[str, Dict[str, Dict[str, list]]] = {}
 
     def update_metric_tracker(self, metric: str, value: float, pair: str) -> None:
         """
@@ -153,6 +153,7 @@ class FreqaiDataDrawer:
             if exists:
                 with open(self.metric_tracker_path, "r") as fp:
                     self.metric_tracker = rapidjson.load(fp, number_mode=rapidjson.NM_NATIVE)
+                logger.info("Loading existing metric tracker from disk.")
             else:
                 logger.info("Could not find existing metric tracker, starting from scratch")
 

freqtrade/freqai/prediction_models/CatboostClassifierMultiTarget.py

@@ -0,0 +1,74 @@
+import logging
+import sys
+from pathlib import Path
+from typing import Any, Dict
+
+from catboost import CatBoostClassifier, Pool
+
+from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
+from freqtrade.freqai.base_models.FreqaiMultiOutputClassifier import FreqaiMultiOutputClassifier
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+
+
+logger = logging.getLogger(__name__)
+
+
+class CatboostClassifierMultiTarget(BaseClassifierModel):
+    """
+    User created prediction model. The class needs to override three necessary
+    functions, predict(), train(), fit(). The class inherits ModelHandler which
+    has its own DataHandler where data is held, saved, loaded, and managed.
+    """
+
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
+        """
+        User sets up the training and test data to fit their desired model here
+        :param data_dictionary: the dictionary constructed by DataHandler to hold
+                                all the training and test data/labels.
+        """
+
+        cbc = CatBoostClassifier(
+            allow_writing_files=True,
+            loss_function='MultiClass',
+            train_dir=Path(dk.data_path),
+            **self.model_training_parameters,
+        )
+
+        X = data_dictionary["train_features"]
+        y = data_dictionary["train_labels"]
+
+        sample_weight = data_dictionary["train_weights"]
+
+        eval_sets = [None] * y.shape[1]
+
+        if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
+            eval_sets = [None] * data_dictionary['test_labels'].shape[1]
+
+            for i in range(data_dictionary['test_labels'].shape[1]):
+                eval_sets[i] = Pool(
+                    data=data_dictionary["test_features"],
+                    label=data_dictionary["test_labels"].iloc[:, i],
+                    weight=data_dictionary["test_weights"],
+                )
+
+        init_model = self.get_init_model(dk.pair)
+
+        if init_model:
+            init_models = init_model.estimators_
+        else:
+            init_models = [None] * y.shape[1]
+
+        fit_params = []
+        for i in range(len(eval_sets)):
+            fit_params.append({
+                'eval_set': eval_sets[i], 'init_model': init_models[i],
+                'log_cout': sys.stdout, 'log_cerr': sys.stderr,
+            })
+
+        model = FreqaiMultiOutputClassifier(estimator=cbc)
+        thread_training = self.freqai_info.get('multitarget_parallel_training', False)
+        if thread_training:
+            model.n_jobs = y.shape[1]
+        model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
+
+        return model

freqtrade/freqai/prediction_models/LightGBMClassifierMultiTarget.py

@@ -0,0 +1,64 @@
+import logging
+from typing import Any, Dict
+
+from lightgbm import LGBMClassifier
+
+from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
+from freqtrade.freqai.base_models.FreqaiMultiOutputClassifier import FreqaiMultiOutputClassifier
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+
+
+logger = logging.getLogger(__name__)
+
+
+class LightGBMClassifierMultiTarget(BaseClassifierModel):
+    """
+    User created prediction model. The class needs to override three necessary
+    functions, predict(), train(), fit(). The class inherits ModelHandler which
+    has its own DataHandler where data is held, saved, loaded, and managed.
+    """
+
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
+        """
+        User sets up the training and test data to fit their desired model here
+        :param data_dictionary: the dictionary constructed by DataHandler to hold
+                                all the training and test data/labels.
+        """
+
+        lgb = LGBMClassifier(**self.model_training_parameters)
+
+        X = data_dictionary["train_features"]
+        y = data_dictionary["train_labels"]
+        sample_weight = data_dictionary["train_weights"]
+
+        eval_weights = None
+        eval_sets = [None] * y.shape[1]
+
+        if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
+            eval_weights = [data_dictionary["test_weights"]]
+            eval_sets = [(None, None)] * data_dictionary['test_labels'].shape[1]  # type: ignore
+            for i in range(data_dictionary['test_labels'].shape[1]):
+                eval_sets[i] = (  # type: ignore
+                    data_dictionary["test_features"],
+                    data_dictionary["test_labels"].iloc[:, i]
+                )
+
+        init_model = self.get_init_model(dk.pair)
+        if init_model:
+            init_models = init_model.estimators_
+        else:
+            init_models = [None] * y.shape[1]
+
+        fit_params = []
+        for i in range(len(eval_sets)):
+            fit_params.append(
+                {'eval_set': eval_sets[i], 'eval_sample_weight': eval_weights,
+                 'init_model': init_models[i]})
+
+        model = FreqaiMultiOutputClassifier(estimator=lgb)
+        thread_training = self.freqai_info.get('multitarget_parallel_training', False)
+        if thread_training:
+            model.n_jobs = y.shape[1]
+        model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
+
+        return model