Python sklearn.base 模块，ClusterMixin() 实例源码

def _global_clustering(self, X=None):
        """
        Global clustering for the subclusters obtained after fitting
        """
        clusterer = self.n_clusters
        centroids = self.subcluster_centers_
        compute_labels = (X is not None) and self.compute_labels

        # Preprocessing for the global clustering.
        not_enough_centroids = False
        if isinstance(clusterer, int):
            clusterer = AgglomerativeClustering(
                n_clusters=self.n_clusters)
            # There is no need to perform the global clustering step.
            if len(centroids) < self.n_clusters:
                not_enough_centroids = True
        elif (clusterer is not None and not
              hasattr(clusterer, 'fit_predict')):
            raise ValueError("n_clusters should be an instance of "
                             "ClusterMixin or an int")

        # To use in predict to avoid recalculation.
        self._subcluster_norms = row_norms(
            self.subcluster_centers_, squared=True)

        if clusterer is None or not_enough_centroids:
            self.subcluster_labels_ = np.arange(len(centroids))
            if not_enough_centroids:
                warnings.warn(
                    "Number of subclusters found (%d) by Birch is less "
                    "than (%d). Decrease the threshold."
                    % (len(centroids), self.n_clusters))
        else:
            # The global clustering step that clusters the subclusters of
            # the leaves. It assumes the centroids of the subclusters as
            # samples and finds the final centroids.
            self.subcluster_labels_ = clusterer.fit_predict(
                self.subcluster_centers_)

        if compute_labels:
            self.labels_ = self.predict(X)

def _generate_bases_test(est, pd_est):
    def test(self):
        self.assertTrue(isinstance(pd_est, FrameMixin), pd_est)
        self.assertFalse(isinstance(est, FrameMixin))
        self.assertTrue(isinstance(pd_est, base.BaseEstimator))
        try:
            mixins = [
                base.ClassifierMixin,
                base.ClusterMixin,
                base.BiclusterMixin,
                base.TransformerMixin,
                base.DensityMixin,
                base.MetaEstimatorMixin,
                base.ClassifierMixin,
                base.RegressorMixin]
        except:
            if _sklearn_ver > 17:
                raise
            mixins = [
                base.ClassifierMixin,
                base.ClusterMixin,
                base.BiclusterMixin,
                base.TransformerMixin,
                base.MetaEstimatorMixin,
                base.ClassifierMixin,
                base.RegressorMixin]
        for mixin in mixins:
            self.assertEqual(
                isinstance(pd_est, mixin),
                isinstance(est, mixin),
                mixin)

    return test

def get_params_for_est(estimator, name):
    '''Choose initialization parameters for an estimator for auto-testing'''
    is_classifier = ClassifierMixin in estimator.__mro__
    is_cluster = ClusterMixin in estimator.__mro__
    is_ensemble = BaseEnsemble in estimator.__mro__
    uses_counts = any(c in name for c in USES_COUNTS)
    as_1d = name in REQUIRES_1D
    args, params, _ = get_args_kwargs_defaults(estimator.__init__)
    est_keys = set(('estimator', 'base_estimator', 'estimators'))
    est_keys = (set(params) | set(args)) & est_keys
    if is_classifier:
        score_func = feat.f_classif
    else:
        score_func = feat.f_regression
    for key in est_keys:
        if name == 'SelectFromModel':
            params[key] = sklearn.linear_model.LassoCV()
        elif is_classifier:
            params[key] = sklearn.tree.DecisionTreeClassifier()
        else:
            params[key] = sklearn.tree.DecisionTreeRegressor()
        if key == 'estimators':
            params[key] = [(str(_), clone(params[key])) for _ in range(10)]
    kw = dict(is_classifier=is_classifier, is_cluster=is_cluster,
              is_ensemble=is_ensemble, uses_counts=uses_counts)
    if 'score_func' in params:
        params['score_func'] = score_func
    X, y = make_X_y(**kw)
    return X, y, params, kw