scikit-learn · rth · Sep 5, 2019 · Sep 4, 2019 · Sep 4, 2019 · Sep 4, 2019
diff --git a/examples/compose/plot_column_transformer.py b/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

diff --git a/sklearn/base.py b/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:

diff --git a/sklearn/calibration.py b/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

diff --git a/sklearn/cluster/affinity_propagation_.py b/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>`.

diff --git a/sklearn/cluster/bicluster.py b/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

diff --git a/sklearn/cluster/birch.py b/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

diff --git a/sklearn/cluster/dbscan_.py b/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.

diff --git a/sklearn/cluster/hierarchical.py b/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
 

diff --git a/sklearn/cluster/k_means_.py b/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>`.

diff --git a/sklearn/cluster/mean_shift_.py b/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

diff --git a/sklearn/cluster/optics_.py b/sklearn/cluster/optics_.py
@@ -21,7 +21,7 @@
 from ..metrics import pairwise_distances
 
 
-class OPTICS(BaseEstimator, ClusterMixin):
+class OPTICS(ClusterMixin, BaseEstimator):
     """Estimate clustering structure from vector array
 
     OPTICS (Ordering Points To Identify the Clustering Structure), closely

diff --git a/sklearn/cluster/spectral.py b/sklearn/cluster/spectral.py
@@ -272,7 +272,7 @@ def spectral_clustering(affinity, n_clusters=8, n_components=None,
     return labels
 
 
-class SpectralClustering(BaseEstimator, ClusterMixin):
+class SpectralClustering(ClusterMixin, BaseEstimator):
     """Apply clustering to a projection of the normalized Laplacian.
 
     In practice Spectral Clustering is very useful when the structure of

diff --git a/sklearn/cluster/tests/test_bicluster.py b/sklearn/cluster/tests/test_bicluster.py
@@ -24,7 +24,7 @@
 from sklearn.datasets import make_biclusters, make_checkerboard
 
 
-class MockBiclustering(BaseEstimator, BiclusterMixin):
+class MockBiclustering(BiclusterMixin, BaseEstimator):
     # Mock object for testing get_submatrix.
     def __init__(self):
         pass

diff --git a/sklearn/compose/_column_transformer.py b/sklearn/compose/_column_transformer.py
@@ -33,7 +33,7 @@
                      "item instead of a scalar.")
 
 
-class ColumnTransformer(_BaseComposition, TransformerMixin):
+class ColumnTransformer(TransformerMixin, _BaseComposition):
     """Applies transformers to columns of an array or pandas DataFrame.
 
     This estimator allows different columns or column subsets of the input

diff --git a/sklearn/compose/_target.py b/sklearn/compose/_target.py
@@ -14,7 +14,7 @@
 __all__ = ['TransformedTargetRegressor']
 
 
-class TransformedTargetRegressor(BaseEstimator, RegressorMixin):
+class TransformedTargetRegressor(RegressorMixin, BaseEstimator):
     """Meta-estimator to regress on a transformed target.
 
     Useful for applying a non-linear transformation in regression

diff --git a/sklearn/compose/tests/test_target.py b/sklearn/compose/tests/test_target.py
@@ -226,7 +226,7 @@ def func(y):
     assert_allclose(y_pred_1d_func, y_pred_2d_func)
 
 
-class DummyCheckerArrayTransformer(BaseEstimator, TransformerMixin):
+class DummyCheckerArrayTransformer(TransformerMixin, BaseEstimator):
 
     def fit(self, X, y=None):
         assert isinstance(X, np.ndarray)
@@ -268,7 +268,7 @@ def test_transform_target_regressor_ensure_y_array():
         tt.predict(X)
 
 
-class DummyTransformer(BaseEstimator, TransformerMixin):
+class DummyTransformer(TransformerMixin, BaseEstimator):
     """Dummy transformer which count how many time fit was called."""
     def __init__(self, fit_counter=0):
         self.fit_counter = fit_counter

diff --git a/sklearn/covariance/elliptic_envelope.py b/sklearn/covariance/elliptic_envelope.py
@@ -9,7 +9,7 @@
 from ..base import OutlierMixin
 
 
-class EllipticEnvelope(MinCovDet, OutlierMixin):
+class EllipticEnvelope(OutlierMixin, MinCovDet):
     """An object for detecting outliers in a Gaussian distributed dataset.
 
     Read more in the :ref:`User Guide <outlier_detection>`.

diff --git a/sklearn/cross_decomposition/cca_.py b/sklearn/cross_decomposition/cca_.py
@@ -4,7 +4,7 @@
 __all__ = ['CCA']
 
 
-class CCA(_PLS, _UnstableArchMixin):
+class CCA(_UnstableArchMixin, _PLS):
     """CCA Canonical Correlation Analysis.
 
     CCA inherits from PLS with mode="B" and deflation_mode="canonical".

diff --git a/sklearn/cross_decomposition/pls_.py b/sklearn/cross_decomposition/pls_.py
@@ -121,7 +121,7 @@ def _center_scale_xy(X, Y, scale=True):
     return X, Y, x_mean, y_mean, x_std, y_std
 
 
-class _PLS(BaseEstimator, TransformerMixin, RegressorMixin, MultiOutputMixin,
+class _PLS(TransformerMixin, RegressorMixin, MultiOutputMixin, BaseEstimator,
            metaclass=ABCMeta):
     """Partial Least Squares (PLS)
 
@@ -750,7 +750,7 @@ def __init__(self, n_components=2, scale=True, algorithm="nipals",
             max_iter=max_iter, tol=tol, copy=copy)
 
 
-class PLSSVD(BaseEstimator, TransformerMixin):
+class PLSSVD(TransformerMixin, BaseEstimator):
     """Partial Least Square SVD
 
     Simply perform a svd on the crosscovariance matrix: X'Y

diff --git a/sklearn/decomposition/base.py b/sklearn/decomposition/base.py
@@ -17,7 +17,7 @@
 from abc import ABCMeta, abstractmethod
 
 
-class _BasePCA(BaseEstimator, TransformerMixin, metaclass=ABCMeta):
+class _BasePCA(TransformerMixin, BaseEstimator, metaclass=ABCMeta):
     """Base class for PCA methods.
 
     Warning: This class should not be used directly.

diff --git a/sklearn/decomposition/dict_learning.py b/sklearn/decomposition/dict_learning.py
@@ -932,7 +932,7 @@ def transform(self, X):
         return code
 
 
-class SparseCoder(BaseEstimator, SparseCodingMixin):
+class SparseCoder(SparseCodingMixin, BaseEstimator):
     """Sparse coding
 
     Finds a sparse representation of data against a fixed, precomputed
@@ -1045,7 +1045,7 @@ def fit(self, X, y=None):
         return self
 
 
-class DictionaryLearning(BaseEstimator, SparseCodingMixin):
+class DictionaryLearning(SparseCodingMixin, BaseEstimator):
     """Dictionary learning
 
     Finds a dictionary (a set of atoms) that can best be used to represent data
@@ -1241,7 +1241,7 @@ def fit(self, X, y=None):
         return self
 
 
-class MiniBatchDictionaryLearning(BaseEstimator, SparseCodingMixin):
+class MiniBatchDictionaryLearning(SparseCodingMixin, BaseEstimator):
     """Mini-batch dictionary learning
 
     Finds a dictionary (a set of atoms) that can best be used to represent data

diff --git a/sklearn/decomposition/factor_analysis.py b/sklearn/decomposition/factor_analysis.py
@@ -32,7 +32,7 @@
 from ..exceptions import ConvergenceWarning
 
 
-class FactorAnalysis(BaseEstimator, TransformerMixin):
+class FactorAnalysis(TransformerMixin, BaseEstimator):
     """Factor Analysis (FA)
 
     A simple linear generative model with Gaussian latent variables.

diff --git a/sklearn/decomposition/fastica_.py b/sklearn/decomposition/fastica_.py
@@ -380,7 +380,7 @@ def g(x, fun_args):
                 return None, W, S
 
 
-class FastICA(BaseEstimator, TransformerMixin):
+class FastICA(TransformerMixin, BaseEstimator):
     """FastICA: a fast algorithm for Independent Component Analysis.
 
     Read more in the :ref:`User Guide <ICA>`.

diff --git a/sklearn/decomposition/kernel_pca.py b/sklearn/decomposition/kernel_pca.py
@@ -16,7 +16,7 @@
 from ..metrics.pairwise import pairwise_kernels
 
 
-class KernelPCA(BaseEstimator, TransformerMixin):
+class KernelPCA(TransformerMixin, BaseEstimator):
     """Kernel Principal component analysis (KPCA)
 
     Non-linear dimensionality reduction through the use of kernels (see

diff --git a/sklearn/decomposition/nmf.py b/sklearn/decomposition/nmf.py
@@ -1068,7 +1068,7 @@ def non_negative_factorization(X, W=None, H=None, n_components=None,
     return W, H, n_iter
 
 
-class NMF(BaseEstimator, TransformerMixin):
+class NMF(TransformerMixin, BaseEstimator):
     r"""Non-Negative Matrix Factorization (NMF)
 
     Find two non-negative matrices (W, H) whose product approximates the non-

diff --git a/sklearn/decomposition/online_lda.py b/sklearn/decomposition/online_lda.py
@@ -132,7 +132,7 @@ def _update_doc_distribution(X, exp_topic_word_distr, doc_topic_prior,
     return (doc_topic_distr, suff_stats)
 
 
-class LatentDirichletAllocation(BaseEstimator, TransformerMixin):
+class LatentDirichletAllocation(TransformerMixin, BaseEstimator):
     """Latent Dirichlet Allocation with online variational Bayes algorithm
 
     .. versionadded:: 0.17

diff --git a/sklearn/decomposition/sparse_pca.py b/sklearn/decomposition/sparse_pca.py
@@ -29,7 +29,7 @@ def _check_normalize_components(normalize_components, estimator_name):
             )
 
 
-class SparsePCA(BaseEstimator, TransformerMixin):
+class SparsePCA(TransformerMixin, BaseEstimator):
     """Sparse Principal Components Analysis (SparsePCA)
 
     Finds the set of sparse components that can optimally reconstruct

diff --git a/sklearn/decomposition/truncated_svd.py b/sklearn/decomposition/truncated_svd.py
@@ -18,7 +18,7 @@
 __all__ = ["TruncatedSVD"]
 
 
-class TruncatedSVD(BaseEstimator, TransformerMixin):
+class TruncatedSVD(TransformerMixin, BaseEstimator):
     """Dimensionality reduction using truncated SVD (aka LSA).
 
     This transformer performs linear dimensionality reduction by means of

diff --git a/sklearn/discriminant_analysis.py b/sklearn/discriminant_analysis.py
@@ -553,7 +553,7 @@ def predict_log_proba(self, X):
         return np.log(self.predict_proba(X))
 
 
-class QuadraticDiscriminantAnalysis(BaseEstimator, ClassifierMixin):
+class QuadraticDiscriminantAnalysis(ClassifierMixin, BaseEstimator):
     """Quadratic Discriminant Analysis
 
     A classifier with a quadratic decision boundary, generated

diff --git a/sklearn/dummy.py b/sklearn/dummy.py
@@ -19,7 +19,7 @@
 from .utils.multiclass import class_distribution
 
 
-class DummyClassifier(BaseEstimator, ClassifierMixin, MultiOutputMixin):
+class DummyClassifier(MultiOutputMixin, ClassifierMixin, BaseEstimator):
     """
     DummyClassifier is a classifier that makes predictions using simple rules.
 
@@ -353,7 +353,7 @@ def score(self, X, y, sample_weight=None):
         return super().score(X, y, sample_weight)
 
 
-class DummyRegressor(BaseEstimator, RegressorMixin, MultiOutputMixin):
+class DummyRegressor(MultiOutputMixin, RegressorMixin, BaseEstimator):
     """
     DummyRegressor is a regressor that makes predictions using
     simple rules.

diff --git a/sklearn/ensemble/_hist_gradient_boosting/binning.py b/sklearn/ensemble/_hist_gradient_boosting/binning.py
@@ -83,7 +83,7 @@ def _find_binning_thresholds(data, max_bins, subsample, random_state):
     return binning_thresholds
 
 
-class _BinMapper(BaseEstimator, TransformerMixin):
+class _BinMapper(TransformerMixin, BaseEstimator):
     """Transformer that maps a dataset into integer-valued bins.
 
     The bins are created in a feature-wise fashion, using quantiles so that

diff --git a/sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py b/sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py
@@ -639,7 +639,7 @@ def n_iter_(self):
         return len(self._predictors)
 
 
-class HistGradientBoostingRegressor(BaseHistGradientBoosting, RegressorMixin):
+class HistGradientBoostingRegressor(RegressorMixin, BaseHistGradientBoosting):
     """Histogram-based Gradient Boosting Regression Tree.
 
     This estimator is much faster than

diff --git a/sklearn/ensemble/bagging.py b/sklearn/ensemble/bagging.py
@@ -429,7 +429,7 @@ def estimators_samples_(self):
                 for _, sample_indices in self._get_estimators_indices()]
 
 
-class BaggingClassifier(BaseBagging, ClassifierMixin):
+class BaggingClassifier(ClassifierMixin, BaseBagging):
     """A Bagging classifier.
 
     A Bagging classifier is an ensemble meta-estimator that fits base
@@ -816,7 +816,7 @@ def decision_function(self, X):
         return decisions
 
 
-class BaggingRegressor(BaseBagging, RegressorMixin):
+class BaggingRegressor(RegressorMixin, BaseBagging):
     """A Bagging regressor.
 
     A Bagging regressor is an ensemble meta-estimator that fits base