add strat and config for testing on PR

freqtrade/freqai/base_models/FreqaiMultiOutputClassifier.py

@@ -1,10 +1,13 @@
+import numpy as np
 from joblib import Parallel
-from sklearn.multioutput import MultiOutputRegressor, _fit_estimator
+from sklearn.base import is_classifier
+from sklearn.multioutput import MultiOutputClassifier, _fit_estimator
 from sklearn.utils.fixes import delayed
-from sklearn.utils.validation import has_fit_parameter
+from sklearn.utils.multiclass import check_classification_targets
+from sklearn.utils.validation import check_is_fitted, has_fit_parameter
 
 
-class FreqaiMultiOutputRegressor(MultiOutputRegressor):
+class FreqaiMultiOutputClassifier(MultiOutputClassifier):
 
     def fit(self, X, y, sample_weight=None, fit_params=None):
         """Fit the model to data, separately for each output variable.
@@ -17,7 +20,7 @@ class FreqaiMultiOutputRegressor(MultiOutputRegressor):
             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
+            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.
@@ -35,6 +38,9 @@ class FreqaiMultiOutputRegressor(MultiOutputRegressor):
 
         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 "
@@ -56,9 +62,66 @@ class FreqaiMultiOutputRegressor(MultiOutputRegressor):
             for i in range(y.shape[1])
         )
 
+        self.classes_ = []
+        for estimator in self.estimators_:
+            self.classes_.extend(estimator.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
+        return self
+
+    def predict_proba(self, X):
+        """Return prediction probabilities for each class of each output.
+
+        This method will raise a ``ValueError`` if any of the
+        estimators do not have ``predict_proba``.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The input data.
+
+        Returns
+        -------
+        p : array of shape (n_samples, n_classes), or a list of n_outputs \
+                such arrays if n_outputs > 1.
+            The class probabilities of the input samples. The order of the
+            classes corresponds to that in the attribute :term:`classes_`.
+
+            .. versionchanged:: 0.19
+                This function now returns a list of arrays where the length of
+                the list is ``n_outputs``, and each array is (``n_samples``,
+                ``n_classes``) for that particular output.
+                """
+        check_is_fitted(self)
+        results = np.hstack([estimator.predict_proba(X) for estimator in self.estimators_])
+        return np.squeeze(results)
+
+    def predict(self, X):
+        """Predict multi-output variable using model for each target variable.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            The input data.
+
+        Returns
+        -------
+        y : {array-like, sparse matrix} of shape (n_samples, n_outputs)
+            Multi-output targets predicted across multiple predictors.
+            Note: Separate models are generated for each predictor.
+        """
+        check_is_fitted(self)
+        if not hasattr(self.estimators_[0], "predict"):
+            raise ValueError("The base estimator should implement a predict method")
+
+        y = Parallel(n_jobs=self.n_jobs)(
+            delayed(e.predict)(X) for e in self.estimators_
+        )
+
+        results = np.asarray(y).T
+
+        return np.squeeze(results)