scikit-learn
diff --git a/‎doc/whats_new/v0.21.rst
Copy file name to clipboard
+3Lines changed: 3 additions & 0 deletions b/‎doc/whats_new/v0.21.rst
Copy file name to clipboard
+3Lines changed: 3 additions & 0 deletions
diff --git a/‎sklearn/cluster/hierarchical.py
Copy file name to clipboard
+6-3Lines changed: 6 additions & 3 deletions b/‎sklearn/cluster/hierarchical.py
Copy file name to clipboard
+6-3Lines changed: 6 additions & 3 deletions
diff --git a/‎sklearn/cluster/k_means_.py
Copy file name to clipboard
+6-5Lines changed: 6 additions & 5 deletions b/‎sklearn/cluster/k_means_.py
Copy file name to clipboard
+6-5Lines changed: 6 additions & 5 deletions
diff --git a/‎sklearn/cluster/tests/test_hierarchical.py
Copy file name to clipboard
+3-3Lines changed: 3 additions & 3 deletions b/‎sklearn/cluster/tests/test_hierarchical.py
Copy file name to clipboard
+3-3Lines changed: 3 additions & 3 deletions
diff --git a/‎sklearn/datasets/base.py
Copy file name to clipboard
+1-1Lines changed: 1 addition & 1 deletion b/‎sklearn/datasets/base.py
Copy file name to clipboard
+1-1Lines changed: 1 addition & 1 deletion
diff --git a/‎sklearn/datasets/covtype.py
Copy file name to clipboard
+1-1Lines changed: 1 addition & 1 deletion b/‎sklearn/datasets/covtype.py
Copy file name to clipboard
+1-1Lines changed: 1 addition & 1 deletion
diff --git a/‎sklearn/datasets/kddcup99.py
Copy file name to clipboard
+3-3Lines changed: 3 additions & 3 deletions b/‎sklearn/datasets/kddcup99.py
Copy file name to clipboard
+3-3Lines changed: 3 additions & 3 deletions
diff --git a/‎sklearn/datasets/openml.py
Copy file name to clipboard
+1-1Lines changed: 1 addition & 1 deletion b/‎sklearn/datasets/openml.py
Copy file name to clipboard
+1-1Lines changed: 1 addition & 1 deletion
diff --git a/‎sklearn/datasets/rcv1.py
Copy file name to clipboard
+1-1Lines changed: 1 addition & 1 deletion b/‎sklearn/datasets/rcv1.py
Copy file name to clipboard
+1-1Lines changed: 1 addition & 1 deletion
diff --git a/‎sklearn/datasets/samples_generator.py
Copy file name to clipboard
+2-2Lines changed: 2 additions & 2 deletions b/‎sklearn/datasets/samples_generator.py
Copy file name to clipboard
+2-2Lines changed: 2 additions & 2 deletions
@@ -422,6 +422,9 @@ Multiple modules
   but this can be altered with the ``print_changed_only`` option in
   :func:`sklearn.set_config`. :issue:`11705` by :user:`Nicolas Hug
   <NicolasHug>`.
+- |Efficiency| Memory copies are avoided when casting arrays to a different
+  dtype in multiple estimators. :issue:`11973` by :user:`Roman Yurchak`_.
+
 
 Changes to estimator checks
 ---------------------------
 
@@ -22,6 +22,7 @@
 from . import _hierarchical
 from ._feature_agglomeration import AgglomerationTransform
 from ..utils.fast_dict import IntFloatDict
+from ..utils.fixes import _astype_copy_false
 
 ###############################################################################
 # For non fully-connected graphs
@@ -87,7 +88,8 @@ def _single_linkage_tree(connectivity, n_samples, n_nodes, n_clusters,
     from scipy.sparse.csgraph import minimum_spanning_tree
 
     # explicitly cast connectivity to ensure safety
-    connectivity = connectivity.astype('float64')
+    connectivity = connectivity.astype('float64',
+                                       **_astype_copy_false(connectivity))
 
     # Ensure zero distances aren't ignored by setting them to "epsilon"
     epsilon_value = np.finfo(dtype=connectivity.data.dtype).eps
@@ -458,7 +460,7 @@ def linkage_tree(X, connectivity=None, n_clusters=None, linkage='complete',
             i, j = np.triu_indices(X.shape[0], k=1)
             X = X[i, j]
         out = hierarchy.linkage(X, method=linkage, metric=affinity)
-        children_ = out[:, :2].astype(np.int)
+        children_ = out[:, :2].astype(np.int, copy=False)
 
         if return_distance:
             distances = out[:, 2]
@@ -477,7 +479,8 @@ def linkage_tree(X, connectivity=None, n_clusters=None, linkage='complete',
     del diag_mask
 
     if affinity == 'precomputed':
-        distances = X[connectivity.row, connectivity.col].astype('float64')
+        distances = X[connectivity.row, connectivity.col].astype(
+            'float64', **_astype_copy_false(X))
     else:
         # FIXME We compute all the distances, while we could have only computed
         # the "interesting" distances
 
@@ -178,7 +178,7 @@ def _check_sample_weight(X, sample_weight):
                              % (n_samples, len(sample_weight)))
         # normalize the weights to sum up to n_samples
         scale = n_samples / sample_weight.sum()
-        return (sample_weight * scale).astype(X.dtype)
+        return (sample_weight * scale).astype(X.dtype, copy=False)
 
 
 def k_means(X, n_clusters, sample_weight=None, init='k-means++',
@@ -618,7 +618,7 @@ def _labels_inertia_precompute_dense(X, sample_weight, x_squared_norms,
     labels, mindist = pairwise_distances_argmin_min(
         X=X, Y=centers, metric='euclidean', metric_kwargs={'squared': True})
     # cython k-means code assumes int32 inputs
-    labels = labels.astype(np.int32)
+    labels = labels.astype(np.int32, copy=False)
     if n_samples == distances.shape[0]:
         # distances will be changed in-place
         distances[:] = mindist
@@ -1194,9 +1194,10 @@ def _mini_batch_step(X, sample_weight, x_squared_norms, centers, weight_sums,
                       % n_reassigns)
 
             if sp.issparse(X) and not sp.issparse(centers):
-                assign_rows_csr(X, new_centers.astype(np.intp),
-                                np.where(to_reassign)[0].astype(np.intp),
-                                centers)
+                assign_rows_csr(
+                        X, new_centers.astype(np.intp, copy=False),
+                        np.where(to_reassign)[0].astype(np.intp, copy=False),
+                        centers)
             else:
                 centers[to_reassign] = X[new_centers]
         # reset counts of reassigned centers, but don't reset them too small
 
@@ -283,7 +283,7 @@ def test_scikit_vs_scipy():
 
             out = hierarchy.linkage(X, method=linkage)
 
-            children_ = out[:, :2].astype(np.int)
+            children_ = out[:, :2].astype(np.int, copy=False)
             children, _, n_leaves, _ = _TREE_BUILDERS[linkage](X, connectivity)
 
             # Sort the order of child nodes per row for consistency
@@ -482,14 +482,14 @@ def test_connectivity_fixing_non_lil():
 
 def test_int_float_dict():
     rng = np.random.RandomState(0)
-    keys = np.unique(rng.randint(100, size=10).astype(np.intp))
+    keys = np.unique(rng.randint(100, size=10).astype(np.intp, copy=False))
     values = rng.rand(len(keys))
 
     d = IntFloatDict(keys, values)
     for key, value in zip(keys, values):
         assert d[key] == value
 
-    other_keys = np.arange(50).astype(np.intp)[::2]
+    other_keys = np.arange(50, dtype=np.intp)[::2]
     other_values = np.full(50, 0.5)[::2]
     other = IntFloatDict(other_keys, other_values)
     # Complete smoke test
 
@@ -545,7 +545,7 @@ def load_digits(n_class=10, return_X_y=False):
                       delimiter=',')
     with open(join(module_path, 'descr', 'digits.rst')) as f:
         descr = f.read()
-    target = data[:, -1].astype(np.int)
+    target = data[:, -1].astype(np.int, copy=False)
     flat_data = data[:, :-1]
     images = flat_data.view()
     images.shape = (-1, 8, 8)
 
@@ -115,7 +115,7 @@ def fetch_covtype(data_home=None, download_if_missing=True,
         remove(archive_path)
 
         X = Xy[:, :-1]
-        y = Xy[:, -1].astype(np.int32)
+        y = Xy[:, -1].astype(np.int32, copy=False)
 
         _joblib.dump(X, samples_path, compress=9)
         _joblib.dump(y, targets_path, compress=9)
 
@@ -139,9 +139,9 @@ def fetch_kddcup99(subset=None, data_home=None, shuffle=False,
         data = np.c_[data[s, :11], data[s, 12:]]
         target = target[s]
 
-        data[:, 0] = np.log((data[:, 0] + 0.1).astype(float))
-        data[:, 4] = np.log((data[:, 4] + 0.1).astype(float))
-        data[:, 5] = np.log((data[:, 5] + 0.1).astype(float))
+        data[:, 0] = np.log((data[:, 0] + 0.1).astype(float, copy=False))
+        data[:, 4] = np.log((data[:, 4] + 0.1).astype(float, copy=False))
+        data[:, 5] = np.log((data[:, 5] + 0.1).astype(float, copy=False))
 
         if subset == 'http':
             s = data[:, 2] == b'http'
 
@@ -652,7 +652,7 @@ def fetch_openml(name=None, version='active', data_id=None, data_home=None,
     elif all(is_classification):
         y = np.hstack([np.take(np.asarray(nominal_attributes.pop(col_name),
                                           dtype='O'),
-                               y[:, i:i+1].astype(int))
+                               y[:, i:i+1].astype(int, copy=False))
                        for i, col_name in enumerate(target_column)])
     elif any(is_classification):
         raise ValueError('Mix of nominal and non-nominal targets is not '
 
@@ -179,7 +179,7 @@ def fetch_rcv1(data_home=None, subset='all', download_if_missing=True,
         # Training data is before testing data
         X = sp.vstack([Xy[8], Xy[0], Xy[2], Xy[4], Xy[6]]).tocsr()
         sample_id = np.hstack((Xy[9], Xy[1], Xy[3], Xy[5], Xy[7]))
-        sample_id = sample_id.astype(np.uint32)
+        sample_id = sample_id.astype(np.uint32, copy=False)
 
         _joblib.dump(X, samples_path, compress=9)
         _joblib.dump(sample_id, sample_id_path, compress=9)
 
@@ -190,7 +190,7 @@ def make_classification(n_samples=100, n_features=20, n_informative=2,
 
     # Build the polytope whose vertices become cluster centroids
     centroids = _generate_hypercube(n_clusters, n_informative,
-                                    generator).astype(float)
+                                    generator).astype(float, copy=False)
     centroids *= 2 * class_sep
     centroids -= class_sep
     if not hypercube:
@@ -446,7 +446,7 @@ def make_hastie_10_2(n_samples=12000, random_state=None):
 
     shape = (n_samples, 10)
     X = rs.normal(size=shape).reshape(shape)
-    y = ((X ** 2.0).sum(axis=1) > 9.34).astype(np.float64)
+    y = ((X ** 2.0).sum(axis=1) > 9.34).astype(np.float64, copy=False)
     y[y == 0.0] = -1.0
 
     return X, y