MNT replace authors and license with standard text (scikit-learn#30511)

benchmarks/bench_plot_randomized_svd.py

@@ -63,7 +63,8 @@
     A. Szlam et al. 2014
 """
 
-# Author: Giorgio Patrini
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 import gc
 import os.path

examples/decomposition/plot_faces_decomposition.py

@@ -7,10 +7,6 @@
 matrix decomposition (dimension reduction) methods from the module
 :mod:`sklearn.decomposition` (see the documentation chapter
 :ref:`decompositions`).
-
-
-- Authors: Vlad Niculae, Alexandre Gramfort
-- License: BSD 3 clause
 """
 
 # Authors: The scikit-learn developers

examples/ensemble/plot_gradient_boosting_early_stopping.py

@@ -27,9 +27,6 @@
 applied, can be accessed using the `n_estimators_` attribute. Overall, early
 stopping is a valuable tool to strike a balance between model performance and
 efficiency in gradient boosting.
-
-License: BSD 3 clause
-
 """
 
 # Authors: The scikit-learn developers

examples/feature_selection/plot_select_from_model_diabetes.py

@@ -11,12 +11,6 @@
 
 We use the Diabetes dataset, which consists of 10 features collected from 442
 diabetes patients.
-
-Authors: `Manoj Kumar <[email protected]>`_,
-`Maria Telenczuk <https://github.com/maikia>`_, Nicolas Hug.
-
-License: BSD 3 clause
-
 """
 
 # Authors: The scikit-learn developers

examples/neighbors/plot_caching_nearest_neighbors.py

@@ -3,15 +3,15 @@
 Caching nearest neighbors
 =========================
 
-This examples demonstrates how to precompute the k nearest neighbors before
+This example demonstrates how to precompute the k nearest neighbors before
 using them in KNeighborsClassifier. KNeighborsClassifier can compute the
 nearest neighbors internally, but precomputing them can have several benefits,
 such as finer parameter control, caching for multiple use, or custom
 implementations.
 
 Here we use the caching property of pipelines to cache the nearest neighbors
 graph between multiple fits of KNeighborsClassifier. The first call is slow
-since it computes the neighbors graph, while subsequent call are faster as they
+since it computes the neighbors graph, while subsequent calls are faster as they
 do not need to recompute the graph. Here the durations are small since the
 dataset is small, but the gain can be more substantial when the dataset grows
 larger, or when the grid of parameter to search is large.

sklearn/_isotonic.pyx

@@ -1,4 +1,5 @@
-# Author: Nelle Varoquaux, Andrew Tulloch, Antony Lee
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 # Uses the pool adjacent violators algorithm (PAVA), with the
 # enhancement of searching for the longest decreasing subsequence to

sklearn/base.py

@@ -444,7 +444,7 @@ def _repr_html_(self):
         """HTML representation of estimator.
 
         This is redundant with the logic of `_repr_mimebundle_`. The latter
-        should be favorted in the long term, `_repr_html_` is only
+        should be favored in the long term, `_repr_html_` is only
         implemented for consumers who do not interpret `_repr_mimbundle_`.
         """
         if get_config()["display"] != "diagram":

sklearn/cluster/_agglomerative.py

@@ -2,10 +2,6 @@
 
 These routines perform some hierarchical agglomerative clustering of some
 input data.
-
-Authors : Vincent Michel, Bertrand Thirion, Alexandre Gramfort,
-          Gael Varoquaux
-License: BSD 3 clause
 """
 
 # Authors: The scikit-learn developers

sklearn/cluster/_dbscan_inner.pyx

@@ -1,6 +1,7 @@
 # Fast inner loop for DBSCAN.
-# Author: Lars Buitinck
-# License: 3-clause BSD
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 from libcpp.vector cimport vector
 

sklearn/cluster/_hdbscan/_linkage.pyx

@@ -1,9 +1,7 @@
 # Minimum spanning tree single linkage implementation for hdbscan
-# Authors: Leland McInnes <[email protected]>
-#          Steve Astels <[email protected]>
-#          Meekail Zain <[email protected]>
-# Copyright (c) 2015, Leland McInnes
-# All rights reserved.
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are met:

sklearn/cluster/_hdbscan/_reachability.pyx

@@ -1,9 +1,7 @@
 # mutual reachability distance computations
-# Authors: Leland McInnes <[email protected]>
-#          Meekail Zain <[email protected]>
-#          Guillaume Lemaitre <[email protected]>
-# Copyright (c) 2015, Leland McInnes
-# All rights reserved.
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are met:

sklearn/cluster/_hdbscan/_tree.pyx

@@ -1,7 +1,7 @@
 # Tree handling (condensing, finding stable clusters) for hdbscan
-# Authors: Leland McInnes
-# Copyright (c) 2015, Leland McInnes
-# All rights reserved.
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are met:

sklearn/cluster/_hdbscan/hdbscan.py

@@ -6,13 +6,6 @@
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause
 
-# Authors: Leland McInnes <[email protected]>
-#          Steve Astels <[email protected]>
-#          John Healy <[email protected]>
-#          Meekail Zain <[email protected]>
-# Copyright (c) 2015, Leland McInnes
-# All rights reserved.
-
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are met:
 

sklearn/cluster/_hierarchical_fast.pyx

@@ -1,4 +1,5 @@
-# Author: Gael Varoquaux <[email protected]>
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 import numpy as np
 cimport cython

sklearn/cluster/_k_means_elkan.pyx

@@ -1,6 +1,5 @@
-# Author: Andreas Mueller
-#
-# Licence: BSD 3 clause
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 from cython cimport floating
 from cython.parallel import prange, parallel

sklearn/cluster/_optics.py

@@ -2,12 +2,6 @@
 
 These routines execute the OPTICS algorithm, and implement various
 cluster extraction methods of the ordered list.
-
-Authors: Shane Grigsby <[email protected]>
-         Adrin Jalali <[email protected]>
-         Erich Schubert <[email protected]>
-         Hanmin Qin <[email protected]>
-License: BSD 3 clause
 """
 
 # Authors: The scikit-learn developers

sklearn/ensemble/_hist_gradient_boosting/_binning.pyx

@@ -1,4 +1,5 @@
-# Author: Nicolas Hug
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 from cython.parallel import prange
 from libc.math cimport isnan

sklearn/ensemble/_hist_gradient_boosting/_gradient_boosting.pyx

@@ -1,4 +1,5 @@
-# Author: Nicolas Hug
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 from cython.parallel import prange
 import numpy as np

sklearn/ensemble/_hist_gradient_boosting/_predictor.pyx

@@ -1,4 +1,5 @@
-# Author: Nicolas Hug
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 from cython.parallel import prange
 from libc.math cimport isnan

sklearn/ensemble/_hist_gradient_boosting/histogram.pyx

@@ -1,6 +1,7 @@
 """This module contains routines for building histograms."""
 
-# Author: Nicolas Hug
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 cimport cython
 from cython.parallel import prange

sklearn/ensemble/_hist_gradient_boosting/splitting.pyx

@@ -5,7 +5,9 @@
 - Apply a split to a node, i.e. split the indices of the samples at the node
   into the newly created left and right children.
 """
-# Author: Nicolas Hug
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 cimport cython
 from cython.parallel import prange

sklearn/linear_model/_sag_fast.pyx.tp

@@ -9,16 +9,11 @@ Generated file: sag_fast.pyx
 
 Each class is duplicated for all dtypes (float and double). The keywords
 between double braces are substituted during the build.
-
-Authors: Danny Sullivan <[email protected]>
-         Tom Dupre la Tour <[email protected]>
-         Arthur Mensch <[email protected]
-         Arthur Imbert <[email protected]>
-         Joan Massich <[email protected]>
-
-License: BSD 3 clause
 """
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 # name_suffix, c_type, np_type
 dtypes = [('64', 'double', 'np.float64'),
           ('32', 'float', 'np.float32')]

sklearn/linear_model/_sgd_fast.pyx.tp

@@ -8,15 +8,11 @@ Generated file: _sgd_fast.pyx
 
 Each relevant function is duplicated for the dtypes float and double.
 The keywords between double braces are substituted during the build.
-
-Authors: Peter Prettenhofer <[email protected]>
-         Mathieu Blondel (partial_fit support)
-         Rob Zinkov (passive-aggressive)
-         Lars Buitinck
-
-License: BSD 3 clause
 """
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 # The dtypes are defined as follows (name_suffix, c_type, np_type)
 dtypes = [
     ("64", "double", "np.float64"),

sklearn/manifold/_barnes_hut_tsne.pyx

@@ -1,6 +1,6 @@
-# Author: Christopher Moody <[email protected]>
-# Author: Nick Travers <[email protected]>
-# Implementation by Chris Moody & Nick Travers
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 # See http://homepage.tudelft.nl/19j49/t-SNE.html for reference
 # implementations and papers describing the technique
 

sklearn/metrics/_pairwise_distances_reduction/__init__.py

@@ -5,9 +5,6 @@
 # Pairwise Distances Reductions
 # =============================
 #
-#   Authors: The scikit-learn developers.
-#   License: BSD 3 clause
-#
 # Overview
 # --------
 #

sklearn/neighbors/_binary_tree.pxi.tp

@@ -14,14 +14,11 @@ implementation_specific_values = [
 # KD Tree and Ball Tree
 # =====================
 #
-#    Author: Jake Vanderplas <[email protected]>, 2012-2013
-#            Omar Salman <[email protected]>
-#
-#    License: BSD
-#
 # _binary_tree.pxi is generated and is then literally Cython included in
 # ball_tree.pyx and kd_tree.pyx. See ball_tree.pyx.tp and kd_tree.pyx.tp.
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 }}
 
 

sklearn/neighbors/_quad_tree.pxd

@@ -1,5 +1,5 @@
-# Author: Thomas Moreau <[email protected]>
-# Author: Olivier Grisel <[email protected]>
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 # See quad_tree.pyx for details.
 

sklearn/neighbors/_quad_tree.pyx

@@ -1,5 +1,5 @@
-# Author: Thomas Moreau <[email protected]>
-# Author: Olivier Grisel <[email protected]>
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 
 from cpython cimport Py_INCREF, PyObject, PyTypeObject

sklearn/svm/src/libsvm/libsvm_helper.c

@@ -17,9 +17,9 @@
  * but libsvm does not expose this structure, so we define it here
  * along some utilities to convert from numpy arrays.
  *
- * License: BSD 3 clause
+ * Authors: The scikit-learn developers
+ * SPDX-License-Identifier: BSD-3-Clause
  *
- * Author: 2010 Fabian Pedregosa <[email protected]>
  */
 
 

sklearn/utils/_isfinite.pyx

@@ -1,4 +1,5 @@
-# Author: John Kirkham, Meekail Zain, Thomas Fan
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 from libc.math cimport isnan, isinf
 from cython cimport floating

sklearn/utils/_seq_dataset.pyx.tp

@@ -9,14 +9,11 @@ Generated file: _seq_dataset.pyx
 
 Each class is duplicated for all dtypes (float and double). The keywords
 between double braces are substituted during the build.
-
-Author: Peter Prettenhofer <[email protected]>
-        Arthur Imbert <[email protected]>
-        Joan Massich <[email protected]>
-
-License: BSD 3 clause
 """
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 # name_suffix, c_type, np_type
 dtypes = [('64', 'float64_t', 'np.float64'),
           ('32', 'float32_t', 'np.float32')]