Fix mixin inheritance order, allow overwriting tags (scikit-learn#14884)

Author: amueller

examples/compose/plot_column_transformer.py

@@ -42,7 +42,7 @@
 from sklearn.svm import LinearSVC
 
 
-class TextStats(BaseEstimator, TransformerMixin):
+class TextStats(TransformerMixin, BaseEstimator):
     """Extract features from each document for DictVectorizer"""
 
     def fit(self, x, y=None):
@@ -54,7 +54,7 @@ def transform(self, posts):
                 for text in posts]
 
 
-class SubjectBodyExtractor(BaseEstimator, TransformerMixin):
+class SubjectBodyExtractor(TransformerMixin, BaseEstimator):
     """Extract the subject & body from a usenet post in a single pass.
 
     Takes a sequence of strings and produces a dict of sequences.  Keys are

sklearn/base.py

@@ -129,17 +129,6 @@ def _pprint(params, offset=0, printer=repr):
     return lines
 
 
-def _update_if_consistent(dict1, dict2):
-    common_keys = set(dict1.keys()).intersection(dict2.keys())
-    for key in common_keys:
-        if dict1[key] != dict2[key]:
-            raise TypeError("Inconsistent values for tag {}: {} != {}".format(
-                key, dict1[key], dict2[key]
-            ))
-    dict1.update(dict2)
-    return dict1
-
-
 class BaseEstimator:
     """Base class for all estimators in scikit-learn
 
@@ -320,20 +309,19 @@ def __setstate__(self, state):
         except AttributeError:
             self.__dict__.update(state)
 
+    def _more_tags(self):
+        return _DEFAULT_TAGS
+
     def _get_tags(self):
         collected_tags = {}
-        for base_class in inspect.getmro(self.__class__):
-            if (hasattr(base_class, '_more_tags')
-                    and base_class != self.__class__):
+        for base_class in reversed(inspect.getmro(self.__class__)):
+            if hasattr(base_class, '_more_tags'):
+                # need the if because mixins might not have _more_tags
+                # but might do redundant work in estimators
+                # (i.e. calling more tags on BaseEstimator multiple times)
                 more_tags = base_class._more_tags(self)
-                collected_tags = _update_if_consistent(collected_tags,
-                                                       more_tags)
-        if hasattr(self, '_more_tags'):
-            more_tags = self._more_tags()
-            collected_tags = _update_if_consistent(collected_tags, more_tags)
-        tags = _DEFAULT_TAGS.copy()
-        tags.update(collected_tags)
-        return tags
+                collected_tags.update(more_tags)
+        return collected_tags
 
 
 class ClassifierMixin:

sklearn/calibration.py

@@ -465,7 +465,7 @@ def grad(AB):
     return AB_[0], AB_[1]
 
 
-class _SigmoidCalibration(BaseEstimator, RegressorMixin):
+class _SigmoidCalibration(RegressorMixin, BaseEstimator):
     """Sigmoid regression model.
 
     Attributes

sklearn/cluster/affinity_propagation_.py

@@ -233,7 +233,7 @@ def affinity_propagation(S, preference=None, convergence_iter=15, max_iter=200,
 
 ###############################################################################
 
-class AffinityPropagation(BaseEstimator, ClusterMixin):
+class AffinityPropagation(ClusterMixin, BaseEstimator):
     """Perform Affinity Propagation Clustering of data.
 
     Read more in the :ref:`User Guide <affinity_propagation>`.

sklearn/cluster/bicluster.py

@@ -84,7 +84,7 @@ def _log_normalize(X):
     return L - row_avg - col_avg + avg
 
 
-class BaseSpectral(BaseEstimator, BiclusterMixin, metaclass=ABCMeta):
+class BaseSpectral(BiclusterMixin, BaseEstimator, metaclass=ABCMeta):
     """Base class for spectral biclustering."""
 
     @abstractmethod

sklearn/cluster/birch.py

@@ -319,7 +319,7 @@ def radius(self):
             self.sq_norm_)
 
 
-class Birch(BaseEstimator, TransformerMixin, ClusterMixin):
+class Birch(ClusterMixin, TransformerMixin, BaseEstimator):
     """Implements the Birch clustering algorithm.
 
     It is a memory-efficient, online-learning algorithm provided as an

sklearn/cluster/dbscan_.py

@@ -190,7 +190,7 @@ def dbscan(X, eps=0.5, min_samples=5, metric='minkowski', metric_params=None,
     return np.where(core_samples)[0], labels
 
 
-class DBSCAN(BaseEstimator, ClusterMixin):
+class DBSCAN(ClusterMixin, BaseEstimator):
     """Perform DBSCAN clustering from vector array or distance matrix.
 
     DBSCAN - Density-Based Spatial Clustering of Applications with Noise.

sklearn/cluster/hierarchical.py

@@ -652,7 +652,7 @@ def _hc_cut(n_clusters, children, n_leaves):
 
 ###############################################################################
 
-class AgglomerativeClustering(BaseEstimator, ClusterMixin):
+class AgglomerativeClustering(ClusterMixin, BaseEstimator):
     """
     Agglomerative Clustering
 

sklearn/cluster/k_means_.py

@@ -761,7 +761,7 @@ def _init_centroids(X, k, init, random_state=None, x_squared_norms=None,
     return centers
 
 
-class KMeans(BaseEstimator, ClusterMixin, TransformerMixin):
+class KMeans(TransformerMixin, ClusterMixin, BaseEstimator):
     """K-Means clustering
 
     Read more in the :ref:`User Guide <k_means>`.

sklearn/cluster/mean_shift_.py

@@ -293,7 +293,7 @@ def get_bin_seeds(X, bin_size, min_bin_freq=1):
     return bin_seeds
 
 
-class MeanShift(BaseEstimator, ClusterMixin):
+class MeanShift(ClusterMixin, BaseEstimator):
     """Mean shift clustering using a flat kernel.
 
     Mean shift clustering aims to discover "blobs" in a smooth density of