scikit-learn
diff --git a/‎examples/applications/plot_cyclical_feature_engineering.py
+1 b/‎examples/applications/plot_cyclical_feature_engineering.py
+1
diff --git a/‎examples/applications/plot_digits_denoising.py
+1-2 b/‎examples/applications/plot_digits_denoising.py
+1-2
diff --git a/‎examples/applications/plot_face_recognition.py
+1-2 b/‎examples/applications/plot_face_recognition.py
+1-2
diff --git a/‎examples/applications/plot_model_complexity_influence.py
-2 b/‎examples/applications/plot_model_complexity_influence.py
-2
diff --git a/‎examples/applications/plot_out_of_core_classification.py
+1 b/‎examples/applications/plot_out_of_core_classification.py
+1
diff --git a/‎examples/applications/plot_outlier_detection_wine.py
-1 b/‎examples/applications/plot_outlier_detection_wine.py
-1
diff --git a/‎examples/applications/plot_species_distribution_modeling.py
+1-2 b/‎examples/applications/plot_species_distribution_modeling.py
+1-2
diff --git a/‎examples/applications/plot_stock_market.py
+1-2 b/‎examples/applications/plot_stock_market.py
+1-2
diff --git a/‎examples/applications/plot_tomography_l1_reconstruction.py
+1-2 b/‎examples/applications/plot_tomography_l1_reconstruction.py
+1-2
diff --git a/‎examples/applications/svm_gui.py
-2 b/‎examples/applications/svm_gui.py
-2
diff --git a/‎examples/applications/wikipedia_principal_eigenvector.py
+1-2 b/‎examples/applications/wikipedia_principal_eigenvector.py
+1-2
diff --git a/‎examples/bicluster/plot_bicluster_newsgroups.py
+1-2 b/‎examples/bicluster/plot_bicluster_newsgroups.py
+1-2
diff --git a/‎examples/bicluster/plot_spectral_biclustering.py
-1 b/‎examples/bicluster/plot_spectral_biclustering.py
-1
diff --git a/‎examples/bicluster/plot_spectral_coclustering.py
-1 b/‎examples/bicluster/plot_spectral_coclustering.py
-1
diff --git a/‎examples/calibration/plot_calibration.py
+1-1 b/‎examples/calibration/plot_calibration.py
+1-1
diff --git a/‎examples/calibration/plot_calibration_curve.py
+2-2 b/‎examples/calibration/plot_calibration_curve.py
+2-2
diff --git a/‎examples/calibration/plot_calibration_multiclass.py
+1 b/‎examples/calibration/plot_calibration_multiclass.py
+1
diff --git a/‎examples/calibration/plot_compare_calibration.py
+1 b/‎examples/calibration/plot_compare_calibration.py
+1
diff --git a/‎examples/classification/plot_classification_probability.py
+1-1 b/‎examples/classification/plot_classification_probability.py
+1-1
diff --git a/‎examples/classification/plot_classifier_comparison.py
+1-2 b/‎examples/classification/plot_classifier_comparison.py
+1-2
diff --git a/‎examples/classification/plot_digits_classification.py
+1-2 b/‎examples/classification/plot_digits_classification.py
+1-2
diff --git a/‎examples/classification/plot_lda.py
+2 b/‎examples/classification/plot_lda.py
+2
diff --git a/‎examples/classification/plot_lda_qda.py
+1-1 b/‎examples/classification/plot_lda_qda.py
+1-1
diff --git a/‎examples/cluster/plot_adjusted_for_chance_measures.py
-1 b/‎examples/cluster/plot_adjusted_for_chance_measures.py
-1
diff --git a/‎examples/cluster/plot_affinity_propagation.py
-1 b/‎examples/cluster/plot_affinity_propagation.py
-1
diff --git a/‎examples/cluster/plot_agglomerative_clustering.py
+4-1 b/‎examples/cluster/plot_agglomerative_clustering.py
+4-1
diff --git a/‎examples/cluster/plot_agglomerative_clustering_metrics.py
+2 b/‎examples/cluster/plot_agglomerative_clustering_metrics.py
+2
diff --git a/‎examples/cluster/plot_agglomerative_dendrogram.py
+1 b/‎examples/cluster/plot_agglomerative_dendrogram.py
+1
diff --git a/‎examples/cluster/plot_birch_vs_minibatchkmeans.py
+1-2 b/‎examples/cluster/plot_birch_vs_minibatchkmeans.py
+1-2
diff --git a/‎examples/cluster/plot_cluster_comparison.py
+1-1 b/‎examples/cluster/plot_cluster_comparison.py
+1-1
diff --git a/‎examples/cluster/plot_cluster_iris.py
-2 b/‎examples/cluster/plot_cluster_iris.py
-2
diff --git a/‎examples/cluster/plot_coin_segmentation.py
+1-1 b/‎examples/cluster/plot_coin_segmentation.py
+1-1
diff --git a/‎examples/cluster/plot_coin_ward_segmentation.py
+1-2 b/‎examples/cluster/plot_coin_ward_segmentation.py
+1-2
diff --git a/‎examples/cluster/plot_color_quantization.py
+2-1 b/‎examples/cluster/plot_color_quantization.py
+2-1
diff --git a/‎examples/cluster/plot_dbscan.py
-1 b/‎examples/cluster/plot_dbscan.py
-1
diff --git a/‎examples/cluster/plot_dict_face_patches.py
+1-1 b/‎examples/cluster/plot_dict_face_patches.py
+1-1
@@ -12,6 +12,7 @@
 `extrapolation="periodic"` option.
 
 """
+
 # %%
 # Data exploration on the Bike Sharing Demand dataset
 # ---------------------------------------------------
 
@@ -18,9 +18,8 @@
       "Learning to find pre-images."
       Advances in neural information processing systems 16 (2004): 449-456.
       <https://papers.nips.cc/paper/2003/file/ac1ad983e08ad3304a97e147f522747e-Paper.pdf>`_
-"""
 
-print(__doc__)
+"""
 
 # Authors: Guillaume Lemaitre <guillaume.lemaitre@inria.fr>
 # Licence: BSD 3 clause
 
@@ -27,6 +27,7 @@
 ================== ============ ======= ========== =======
 
 """
+
 from time import time
 import logging
 import matplotlib.pyplot as plt
@@ -40,8 +41,6 @@
 from sklearn.svm import SVC
 
 
-print(__doc__)
-
 # Display progress logs on stdout
 logging.basicConfig(level=logging.INFO, format="%(asctime)s %(message)s")
 
 
@@ -32,8 +32,6 @@
 
 """
 
-print(__doc__)
-
 # Authors: Eustache Diemert <eustache@diemert.fr>
 #          Maria Telenczuk <https://github.com/maikia>
 #          Guillaume Lemaitre <g.lemaitre58@gmail.com>
 
@@ -11,6 +11,7 @@
 HashingVectorizer that will project each example into the same feature space.
 This is especially useful in the case of text classification where new
 features (words) may appear in each batch.
+
 """
 
 # Authors: Eustache Diemert <eustache@diemert.fr>
 
@@ -33,7 +33,6 @@
 example, none of these could be applied that easily.
 
 """
-print(__doc__)
 
 # Author: Virgile Fritsch <virgile.fritsch@inria.fr>
 # License: BSD 3 clause
 
@@ -33,6 +33,7 @@
    <http://rob.schapire.net/papers/ecolmod.pdf>`_
    S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling,
    190:231-259, 2006.
+
 """
 
 # Authors: Peter Prettenhofer <peter.prettenhofer@gmail.com>
@@ -58,8 +59,6 @@
 except ImportError:
     basemap = False
 
-print(__doc__)
-
 
 def construct_grids(batch):
     """Construct the map grid from the batch object
 
@@ -58,6 +58,7 @@
 is to position the labels minimizing overlap. For this we use an
 heuristic based on the direction of the nearest neighbor along each
 axis.
+
 """
 
 # Author: Gael Varoquaux gael.varoquaux@normalesup.org
@@ -73,8 +74,6 @@
 
 from sklearn import cluster, covariance, manifold
 
-print(__doc__)
-
 
 # #############################################################################
 # Retrieve the data from Internet
 
@@ -33,9 +33,8 @@ class :class:`~sklearn.linear_model.Lasso`, that uses the coordinate descent
 reconstructed image, contrary to the L1 penalization. Note in particular
 the circular artifact separating the pixels in the corners, that have
 contributed to fewer projections than the central disk.
-"""
 
-print(__doc__)
+"""
 
 # Author: Emmanuelle Gouillart <emmanuelle.gouillart@nsup.org>
 # License: BSD 3 clause
 
@@ -14,8 +14,6 @@
 
 """
 
-print(__doc__)
-
 # Author: Peter Prettenhoer <peter.prettenhofer@gmail.com>
 #
 # License: BSD 3 clause
 
@@ -27,6 +27,7 @@
 
 The graph data is fetched from the DBpedia dumps. DBpedia is an extraction
 of the latent structured data of the Wikipedia content.
+
 """
 
 # Author: Olivier Grisel <olivier.grisel@ensta.org>
@@ -46,8 +47,6 @@
 from urllib.request import urlopen
 
 
-print(__doc__)
-
 # #############################################################################
 # Where to download the data, if not already on disk
 redirects_url = "http://downloads.dbpedia.org/3.5.1/en/redirects_en.nt.bz2"
 
@@ -22,6 +22,7 @@
 achieve a better V-measure than clusters found by MiniBatchKMeans.
 
 """
+
 from collections import defaultdict
 import operator
 from time import time
@@ -34,8 +35,6 @@
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.cluster import v_measure_score
 
-print(__doc__)
-
 
 def number_normalizer(tokens):
     """Map all numeric tokens to a placeholder.
 
@@ -15,7 +15,6 @@
 representation of the checkerboard structure.
 
 """
-print(__doc__)
 
 # Author: Kemal Eren <kemal@kemaleren.com>
 # License: BSD 3 clause
 
@@ -14,7 +14,6 @@
 the biclusters.
 
 """
-print(__doc__)
 
 # Author: Kemal Eren <kemal@kemaleren.com>
 # License: BSD 3 clause
 
@@ -20,8 +20,8 @@
 to the expected 0.5 for most of the samples belonging to the middle
 cluster with heterogeneous labels. This results in a significantly improved
 Brier score.
+
 """
-print(__doc__)
 
 # Author: Mathieu Blondel <mathieu@mblondel.org>
 #         Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
 
@@ -9,10 +9,10 @@
 visualize how well calibrated the predicted probabilities are using calibration
 curves, also known as reliability diagrams. Calibration of an uncalibrated
 classifier will also be demonstrated.
+
 """
-print(__doc__)
-# %%
 
+# %%
 # Author: Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
 #         Jan Hendrik Metzen <jhm@informatik.uni-bremen.de>
 # License: BSD 3 clause.
 
@@ -10,6 +10,7 @@
 classifier to the probability vectors predicted by the same classifier after
 sigmoid calibration on a hold-out validation set. Colors indicate the true
 class of an instance (red: class 1, green: class 2, blue: class 3).
+
 """
 
 # %%
 
@@ -13,6 +13,7 @@
 models: :ref:`Logistic_regression`, :ref:`gaussian_naive_bayes`,
 :ref:`Random Forest Classifier <forest>` and :ref:`Linear SVM
 <svm_classification>`.
+
 """
 
 # %%
 
@@ -14,8 +14,8 @@
 The logistic regression with One-Vs-Rest is not a multiclass classifier out of
 the box. As a result it has more trouble in separating class 2 and 3 than the
 other estimators.
+
 """
-print(__doc__)
 
 # Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>
 # License: BSD 3 clause
 
@@ -17,9 +17,8 @@
 The plots show training points in solid colors and testing points
 semi-transparent. The lower right shows the classification accuracy on the test
 set.
-"""
-print(__doc__)
 
+"""
 
 # Code source: Gaël Varoquaux
 #              Andreas Müller
 
@@ -5,9 +5,8 @@
 
 This example shows how scikit-learn can be used to recognize images of
 hand-written digits, from 0-9.
-"""
 
-print(__doc__)
+"""
 
 # Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
 # License: BSD 3 clause
 
@@ -5,7 +5,9 @@
 
 This example illustrates how the Ledoit-Wolf and Oracle Shrinkage
 Approximating (OAS) estimators of covariance can improve classification.
+
 """
+
 import numpy as np
 import matplotlib.pyplot as plt
 
 
@@ -8,8 +8,8 @@
 the double standard deviation for each class. With LDA, the
 standard deviation is the same for all the classes, while each
 class has its own standard deviation with QDA.
+
 """
-print(__doc__)
 
 from scipy import linalg
 import numpy as np
 
@@ -20,7 +20,6 @@
 value of k on various overlapping sub-samples of the dataset.
 
 """
-print(__doc__)
 
 # Author: Olivier Grisel <olivier.grisel@ensta.org>
 # License: BSD 3 clause
 
@@ -8,7 +8,6 @@
 Between Data Points", Science Feb. 2007
 
 """
-print(__doc__)
 
 from sklearn.cluster import AffinityPropagation
 from sklearn import metrics
 
@@ -20,7 +20,10 @@
 (try decreasing the number of neighbors in kneighbors_graph) and with
 complete linkage. In particular, having a very small number of neighbors in
 the graph, imposes a geometry that is close to that of single linkage,
-which is well known to have this percolation instability. """
+which is well known to have this percolation instability.
+
+"""
+
 # Authors: Gael Varoquaux, Nelle Varoquaux
 # License: BSD 3 clause
 
 
@@ -31,7 +31,9 @@
 distance, the separation is good and the waveform classes are recovered.
 Finally, the cosine distance does not separate at all waveform 1 and 2,
 thus the clustering puts them in the same cluster.
+
 """
+
 # Author: Gael Varoquaux
 # License: BSD 3-Clause or CC-0
 
 
@@ -6,6 +6,7 @@
 =========================================
 This example plots the corresponding dendrogram of a hierarchical clustering
 using AgglomerativeClustering and the dendrogram method available in scipy.
+
 """
 
 import numpy as np
 
@@ -11,14 +11,13 @@
 samples to a set of 158 clusters. This can be viewed as a preprocessing
 step before the final (global) clustering step that further reduces these
 158 clusters to 100 clusters.
+
 """
 
 # Authors: Manoj Kumar <manojkumarsivaraj334@gmail.com
 #          Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
 # License: BSD 3 clause
 
-print(__doc__)
-
 from itertools import cycle
 from time import time
 import numpy as np
 
@@ -21,8 +21,8 @@
 While these examples give some intuition about the
 algorithms, this intuition might not apply to very high
 dimensional data.
+
 """
-print(__doc__)
 
 import time
 import warnings
 
@@ -14,8 +14,6 @@
 and finally the ground truth.
 
 """
-print(__doc__)
-
 
 # Code source: Gaël Varoquaux
 # Modified for documentation by Jaques Grobler
 
@@ -16,8 +16,8 @@
   using a kmeans algorithm
 * whereas 'discrete' will iteratively search for the closest partition
   space to the embedding space.
+
 """
-print(__doc__)
 
 # Author: Gael Varoquaux <gael.varoquaux@normalesup.org>, Brian Cheung
 # License: BSD 3 clause
 
@@ -6,14 +6,13 @@
 Compute the segmentation of a 2D image with Ward hierarchical
 clustering. The clustering is spatially constrained in order
 for each segmented region to be in one piece.
+
 """
 
 # Author : Vincent Michel, 2010
 #          Alexandre Gramfort, 2011
 # License: BSD 3 clause
 
-print(__doc__)
-
 import time as time
 
 import numpy as np
 
@@ -17,14 +17,15 @@
 
 For comparison, a quantized image using a random codebook (colors picked up
 randomly) is also shown.
+
 """
+
 # Authors: Robert Layton <robertlayton@gmail.com>
 #          Olivier Grisel <olivier.grisel@ensta.org>
 #          Mathieu Blondel <mathieu@mblondel.org>
 #
 # License: BSD 3 clause
 
-print(__doc__)
 import numpy as np
 import matplotlib.pyplot as plt
 from sklearn.cluster import KMeans
 
@@ -7,7 +7,6 @@
 Finds core samples of high density and expands clusters from them.
 
 """
-print(__doc__)
 
 import numpy as np
 
 
@@ -18,8 +18,8 @@
 partial-fit. This is because the number of patches that they represent
 has become too low, and it is better to choose a random new
 cluster.
+
 """
-print(__doc__)
 
 import time
Original file line number	Diff line number	Diff line change
`@@ -14,8 +14,6 @@`
`14`	`14`
`15`	`15`	`"""`
`16`	`16`
`17`		`-print(__doc__)`
`18`		`-`
`19`	`17`	`# Author: Peter Prettenhoer <peter.prettenhofer@gmail.com>`
`20`	`18`	`#`
`21`	`19`	`# License: BSD 3 clause`