Add mars.learn.ensemble.{BlockwiseVotingClassifier, BlockwiseVotingRegressor}

docs/source/reference/learn/reference.rst

@@ -76,6 +76,22 @@ Matrix Decomposition
    decomposition.PCA
    decomposition.TruncatedSVD
 
+.. _ensemble_ref:
+
+Ensemble Methods
+================
+
+.. automodule:: mars.learn.metrics
+   :no-members:
+   :no-inherited-members:
+
+.. currentmodule:: mars.learn
+
+.. autosummary::
+   :toctree: generated/
+
+   ensemble.BlockwiseVotingClassifier
+   ensemble.BlockwiseVotingRegressor
 
 .. _metrics_ref:
 
@@ -98,6 +114,15 @@ Classification metrics
    metrics.auc
    metrics.roc_curve
 
+Regression metrics
+------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   metrics.r2_score
+
+
 Pairwise metrics
 ----------------
 

mars/_version.py

@@ -16,7 +16,7 @@
 import os
 from typing import NamedTuple, Optional
 
-version_info = (0, 8, 0, 'a2')
+version_info = (0, 8, 0, 'a3')
 _num_index = max(idx if isinstance(v, int) else 0
                  for idx, v in enumerate(version_info))
 __version__ = '.'.join(map(str, version_info[:_num_index + 1])) + \

mars/dataframe/core.py

@@ -1303,7 +1303,9 @@ def between(self, left, right, inclusive="both"):
         --------
         >>> import mars.dataframe as md
         >>> s = md.Series([2, 0, 4, 8, np.nan])
+
         Boundary values are included by default:
+
         >>> s.between(1, 4).execute()
         0     True
         1    False
@@ -1313,6 +1315,7 @@ def between(self, left, right, inclusive="both"):
         dtype: bool
 
         With `inclusive` set to ``"neither"`` boundary values are excluded:
+
         >>> s.between(1, 4, inclusive="neither").execute()
         0     True
         1    False
@@ -1322,6 +1325,7 @@ def between(self, left, right, inclusive="both"):
         dtype: bool
 
         `left` and `right` can be any scalar value:
+
         >>> s = md.Series(['Alice', 'Bob', 'Carol', 'Eve'])
         >>> s.between('Anna', 'Daniel').execute()
         0    False

mars/learn/base.py

@@ -43,7 +43,7 @@ def score(self, X, y, sample_weight=None, session=None, run_kwargs=None):
 
         Returns
         -------
-        score : float
+        score : Tensor
             Mean accuracy of self.predict(X) wrt. y.
         """
         from .metrics import accuracy_score
@@ -52,6 +52,60 @@ def score(self, X, y, sample_weight=None, session=None, run_kwargs=None):
         return result
 
 
+class RegressorMixin:
+    """Mixin class for all regression estimators in scikit-learn."""
+    _estimator_type = "regressor"
+
+    def score(self, X, y, sample_weight=None):
+        """Return the coefficient of determination :math:`R^2` of the
+        prediction.
+
+        The coefficient :math:`R^2` is defined as :math:`(1 - \\frac{u}{v})`,
+        where :math:`u` is the residual sum of squares ``((y_true - y_pred)
+        ** 2).sum()`` and :math:`v` is the total sum of squares ``((y_true -
+        y_true.mean()) ** 2).sum()``. The best possible score is 1.0 and it
+        can be negative (because the model can be arbitrarily worse). A
+        constant model that always predicts the expected value of `y`,
+        disregarding the input features, would get a :math:`R^2` score of
+        0.0.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples. For some estimators this may be a precomputed
+            kernel matrix or a list of generic objects instead with shape
+            ``(n_samples, n_samples_fitted)``, where ``n_samples_fitted``
+            is the number of samples used in the fitting for the estimator.
+
+        y : array-like of shape (n_samples,) or (n_samples, n_outputs)
+            True values for `X`.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            Sample weights.
+
+        Returns
+        -------
+        score : Tensor
+            :math:`R^2` of ``self.predict(X)`` wrt. `y`.
+
+        Notes
+        -----
+        The :math:`R^2` score used when calling ``score`` on a regressor uses
+        ``multioutput='uniform_average'`` from version 0.23 to keep consistent
+        with default value of :func:`~sklearn.metrics.r2_score`.
+        This influences the ``score`` method of all the multioutput
+        regressors (except for
+        :class:`~sklearn.multioutput.MultiOutputRegressor`).
+        """
+
+        from .metrics import r2_score
+        y_pred = self.predict(X)
+        return r2_score(y, y_pred, sample_weight=sample_weight)
+
+    def _more_tags(self):  # noqa: R0201  # pylint: disable=no-self-use
+        return {'requires_y': True}
+
+
 class BaseEstimator(SklearnBaseEstimator):
     def _validate_data(self, X, y=None, reset=True,
                        validate_separately=False, **check_params):

mars/learn/ensemble/__init__.py

@@ -0,0 +1,16 @@
+# Copyright 1999-2021 Alibaba Group Holding Ltd.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+from ._blockwise import BlockwiseVotingClassifier, BlockwiseVotingRegressor