scikit-learn · jnothman · Dec 18, 2018 · Nov 22, 2018 · Nov 22, 2018 · Nov 22, 2018
diff --git a/build_tools/generate_authors_table.py b/build_tools/generate_authors_table.py
@@ -97,7 +97,7 @@ def key(profile):
 contributors = get_contributors()
 
 print(".. raw :: html\n")
-print("    <!-- Generated by gen_authors.py -->")
+print("    <!-- Generated by generate_authors_table.py -->")
 print("    <table>")
 print("    <col style='width:%d%%' span='%d'>"
       % (int(100 / ROW_SIZE), ROW_SIZE))

diff --git a/doc/authors.rst b/doc/authors.rst
@@ -1,6 +1,6 @@
 .. raw :: html
 
-    <!-- Generated by gen_authors.py -->
+    <!-- Generated by generate_authors_table.py -->
     <table>
     <col style='width:14%' span='7'>
     <style>
@@ -70,7 +70,7 @@
     <tr>
     <td>
     <a href='https://github.com/chrisfilo'><img src='https://avatars2.githubusercontent.com/u/238759?v=4' class='avatar' /></a> <br />
-    <p>Chris Filo Gorgolewski</p>
+    <p>Chris Gorgolewski</p>
     </td>
     <td>
     <a href='https://github.com/agramfort'><img src='https://avatars2.githubusercontent.com/u/161052?v=4' class='avatar' /></a> <br />
@@ -93,12 +93,16 @@
     <p>Brian Holt</p>
     </td>
     <td>
-    <a href='https://github.com/arjoly'><img src='https://avatars0.githubusercontent.com/u/1274722?v=4' class='avatar' /></a> <br />
-    <p>Arnaud Joly</p>
+    <a href='https://github.com/adrinjalali'><img src='https://avatars3.githubusercontent.com/u/1663864?v=4' class='avatar' /></a> <br />
+    <p>Adrin Jalali</p>
     </td>
     </tr>
     <tr>
     <td>
+    <a href='https://github.com/arjoly'><img src='https://avatars0.githubusercontent.com/u/1274722?v=4' class='avatar' /></a> <br />
+    <p>Arnaud Joly</p>
+    </td>
+    <td>
     <a href='https://github.com/thouis'><img src='https://avatars1.githubusercontent.com/u/473043?v=4' class='avatar' /></a> <br />
     <p>Thouis (Ray) Jones</p>
     </td>
@@ -122,12 +126,12 @@
     <a href='https://github.com/weilinear'><img src='https://avatars0.githubusercontent.com/u/2232328?v=4' class='avatar' /></a> <br />
     <p>Wei Li</p>
     </td>
+    </tr>
+    <tr>
     <td>
     <a href='https://github.com/paolo-losi'><img src='https://avatars1.githubusercontent.com/u/264906?v=4' class='avatar' /></a> <br />
     <p>Paolo Losi</p>
     </td>
-    </tr>
-    <tr>
     <td>
     <a href='https://github.com/glouppe'><img src='https://avatars3.githubusercontent.com/u/477771?v=4' class='avatar' /></a> <br />
     <p>Gilles Louppe</p>
@@ -152,12 +156,12 @@
     <a href='https://github.com/vene'><img src='https://avatars0.githubusercontent.com/u/241745?v=4' class='avatar' /></a> <br />
     <p>Vlad Niculae</p>
     </td>
+    </tr>
+    <tr>
     <td>
     <a href='https://github.com/jnothman'><img src='https://avatars2.githubusercontent.com/u/78827?v=4' class='avatar' /></a> <br />
     <p>Joel Nothman</p>
     </td>
-    </tr>
-    <tr>
     <td>
     <a href='https://github.com/alextp'><img src='https://avatars0.githubusercontent.com/u/5061?v=4' class='avatar' /></a> <br />
     <p>Alexandre Passos</p>
@@ -182,12 +186,12 @@
     <a href='https://github.com/jmschrei'><img src='https://avatars2.githubusercontent.com/u/3916816?v=4' class='avatar' /></a> <br />
     <p>Jacob Schreiber</p>
     </td>
+    </tr>
+    <tr>
     <td>
     <a href='https://github.com/bthirion'><img src='https://avatars1.githubusercontent.com/u/234454?v=4' class='avatar' /></a> <br />
     <p>Bertrand Thirion</p>
     </td>
-    </tr>
-    <tr>
     <td>
     <a href='https://github.com/TomDLT'><img src='https://avatars2.githubusercontent.com/u/11065596?v=4' class='avatar' /></a> <br />
     <p>Tom Dupré la Tour</p>
@@ -212,6 +216,8 @@
     <a href='https://github.com/ronw'><img src='https://avatars2.githubusercontent.com/u/113819?v=4' class='avatar' /></a> <br />
     <p>Ron Weiss</p>
     </td>
+    </tr>
+    <tr>
     <td>
     <a href='https://github.com/rth'><img src='https://avatars0.githubusercontent.com/u/630936?v=4' class='avatar' /></a> <br />
     <p>Roman Yurchak</p>

diff --git a/doc/developers/contributing.rst b/doc/developers/contributing.rst
@@ -432,7 +432,7 @@ Building the documentation
 
 Building the documentation requires installing some additional packages::
 
-    pip install sphinx sphinx-gallery numpydoc matplotlib Pillow pandas scikit-image
+    pip install sphinx sphinx-gallery numpydoc matplotlib Pillow pandas scikit-image joblib
 
 To build the documentation, you need to be in the ``doc`` folder::
 

diff --git a/doc/developers/maintainer.rst b/doc/developers/maintainer.rst
@@ -33,21 +33,21 @@ For more information see https://github.com/scikit-learn/scikit-learn/wiki/How-t
 
     $ git push origin --tags
 
-4. create tarballs:
+4. create the source tarball:
 
    - Wipe clean your repo::
 
        $ git clean -xfd
 
-   - Register and upload on PyPI::
+   - Generate the tarball::
 
-       $ python setup.py sdist register upload
+       $ python setup.py sdist
 
+   The result should be in the `dist/` folder. We will upload it later
+   with the wheels. Check that you can install it in a new virtualenv and
+   that the tests pass.
 
-5. Push the documentation to the website. Circle CI should do this
-   automatically for master and <N>.<N>.X branches.
-
-6. Build binaries using dedicated CI servers by updating the git submodule
+5. Build binaries using dedicated CI servers by updating the git submodule
    reference to the new scikit-learn tag of the release at:
 
    https://github.com/MacPython/scikit-learn-wheels
@@ -56,9 +56,21 @@ For more information see https://github.com/scikit-learn/scikit-learn/wiki/How-t
    packages and upload them to PyPI by running the following commands in the
    scikit-learn source folder (checked out at the release tag)::
 
-       $ pip install -U wheelhouse_uploader
-       $ python setup.py sdist fetch_artifacts upload_all
+       $ pip install -U wheelhouse_uploader twine
+       $ python setup.py fetch_artifacts
+
+   Check the content of the `dist/` folder: it should contain all the wheels
+   along with the source tarball ("scikit-learn-XXX.tar.gz").
+
+   Make sure that you do not have developer versions or older versions of
+   the scikit-learn package in that folder.
 
+   Upload everything at once to https://pypi.org::
+
+       $ twine upload dist/
+
+6. Push the documentation to the website. Circle CI should do this
+   automatically for master and <N>.<N>.X branches.
 
 7. FOR FINAL RELEASE: Update the release date in What's New
 

diff --git a/doc/developers/performance.rst b/doc/developers/performance.rst
@@ -383,7 +383,7 @@ TODO: give a simple teaser example here.
 
 Checkout the official joblib documentation:
 
-- https://pythonhosted.org/joblib
+- https://joblib.readthedocs.io
 
 
 .. _warm-restarts:

diff --git a/doc/documentation.rst b/doc/documentation.rst
@@ -16,7 +16,7 @@ Documentation of scikit-learn |version|
                     <h2><a href="tutorial/basic/tutorial.html">Quick Start</a></h2>
                     <blockquote>A very short introduction into machine learning
                     problems and how to solve them using scikit-learn.
-                    Introduced basic concepts and conventions.
+                    Presents basic concepts and conventions.
                     </blockquote>
                 </div>
                 <div class="span4 box">
@@ -101,5 +101,10 @@ Documentation of scikit-learn |version|
                     scope or not well established enough for scikit-learn.
                     </blockquote>
                 </div>
+                <div class="span4 box">
+                    <h2><a href="roadmap.html">Roadmap</a></h2>
+                    <blockquote>Roadmap of the project.
+                    </blockquote>
+                </div>
 
             </div>
diff --git a/doc/index.rst b/doc/index.rst
@@ -209,6 +209,8 @@
                     </li>
                     <li><strong>Scikit-learn 0.21 will drop support for Python 2.7 and Python 3.4.</strong>
                     </li>
+                    <li><em>December 2018.</em> scikit-learn 0.20.2 is available for download (<a href="whats_new.html#version-0-20-2">Changelog</a>).
+                    </li>
                     <li><em>November 2018.</em> scikit-learn 0.20.1 is available for download (<a href="whats_new.html#version-0-20-1">Changelog</a>).
                     </li>
                     <li><em>September 2018.</em> scikit-learn 0.20.0 is available for download (<a href="whats_new.html#version-0-20-0">Changelog</a>).

diff --git a/doc/modules/clustering.rst b/doc/modules/clustering.rst
@@ -1680,12 +1680,12 @@ Drawbacks
    "A Cluster Separation Measure"
    IEEE Transactions on Pattern Analysis and Machine Intelligence.
    PAMI-1 (2): 224-227.
-   `doi:10.1109/TPAMI.1979.4766909 <http://dx.doi.org/10.1109/TPAMI.1979.4766909>`_.
+   `doi:10.1109/TPAMI.1979.4766909 <https://doi.org/10.1109/TPAMI.1979.4766909>`_.
 
  * Halkidi, Maria; Batistakis, Yannis; Vazirgiannis, Michalis (2001).
    "On Clustering Validation Techniques"
    Journal of Intelligent Information Systems, 17(2-3), 107-145.
-   `doi:10.1023/A:1012801612483 <http://dx.doi.org/10.1023/A:1012801612483>`_.
+   `doi:10.1023/A:1012801612483 <https://doi.org/10.1023/A:1012801612483>`_.
 
  * `Wikipedia entry for Davies-Bouldin index
    <https://en.wikipedia.org/wiki/Davies–Bouldin_index>`_.

diff --git a/doc/modules/linear_model.rst b/doc/modules/linear_model.rst
@@ -775,7 +775,12 @@ The "saga" solver [7]_ is a variant of "sag" that also supports the
 non-smooth `penalty="l1"` option. This is therefore the solver of choice
 for sparse multinomial logistic regression.
 
-In a nutshell, the following table summarizes the penalties supported by each solver:
+The "lbfgs" is an optimization algorithm that approximates the 
+Broyden–Fletcher–Goldfarb–Shanno algorithm [8]_, which belongs to
+quasi-Newton methods. The "lbfgs" solver is recommended for use for
+small data-sets but for larger datasets its performance suffers. [9]_
+
+The following table summarizes the penalties supported by each solver:
 
 +------------------------------+-----------------+-------------+-----------------+-----------+------------+
 |                              |                       **Solvers**                                        |
@@ -799,11 +804,10 @@ In a nutshell, the following table summarizes the penalties supported by each so
 | Robust to unscaled datasets  |       yes       |     yes     |       yes       |    no     |    no      |
 +------------------------------+-----------------+-------------+-----------------+-----------+------------+
 
-The "saga" solver is often the best choice but requires scaling. The "liblinear" solver is
-used by default for historical reasons.
-
+The "lbfgs" solver is used by default for its robustness. For large datasets
+the "saga" solver is usually faster.
 For large dataset, you may also consider using :class:`SGDClassifier`
-with 'log' loss.
+with 'log' loss, which might be even faster but require more tuning.
 
 .. topic:: Examples:
 
@@ -855,6 +859,12 @@ loss.
 
     .. [7] Aaron Defazio, Francis Bach, Simon Lacoste-Julien: `SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives. <https://arxiv.org/abs/1407.0202>`_
 
+    .. [8] https://en.wikipedia.org/wiki/Broyden%E2%80%93Fletcher%E2%80%93Goldfarb%E2%80%93Shanno_algorithm
+
+    .. [9] `"Performance Evaluation of Lbfgs vs other solvers"
+            <http://www.fuzihao.org/blog/2016/01/16/Comparison-of-Gradient-Descent-Stochastic-Gradient-Descent-and-L-BFGS/>`_
+
+
 Stochastic Gradient Descent - SGD
 =================================
 

diff --git a/doc/modules/model_evaluation.rst b/doc/modules/model_evaluation.rst
@@ -440,10 +440,10 @@ the total number of predictions).
 
 In contrast, if the conventional accuracy is above chance only because the
 classifier takes advantage of an imbalanced test set, then the balanced
-accuracy, as appropriate, will drop to :math:`\frac{1}{\text{n\_classes}}`.
+accuracy, as appropriate, will drop to :math:`\frac{1}{n\_classes}`.
 
 The score ranges from 0 to 1, or when ``adjusted=True`` is used, it rescaled to
-the range :math:`\frac{1}{1 - \text{n\_classes}}` to 1, inclusive, with
+the range :math:`\frac{1}{1 - n\_classes}` to 1, inclusive, with
 performance at random scoring 0.
 
 If :math:`y_i` is the true value of the :math:`i`-th sample, and :math:`w_i`
@@ -463,7 +463,7 @@ defined as:
 
 With ``adjusted=True``, balanced accuracy reports the relative increase from
 :math:`\texttt{balanced-accuracy}(y, \mathbf{0}, w) =
-\frac{1}{\text{n\_classes}}`.  In the binary case, this is also known as
+\frac{1}{n\_classes}`.  In the binary case, this is also known as
 `*Youden's J statistic* <https://en.wikipedia.org/wiki/Youden%27s_J_statistic>`_,
 or *informedness*.
 
@@ -1433,7 +1433,7 @@ score associated with each label
 the ranking loss is defined as
 
 .. math::
-  \text{ranking\_loss}(y, \hat{f}) =  \frac{1}{n_{\text{samples}}}
+  ranking\_loss(y, \hat{f}) =  \frac{1}{n_{\text{samples}}}
     \sum_{i=0}^{n_{\text{samples}} - 1} \frac{1}{||y_i||_0(n_\text{labels} - ||y_i||_0)}
     \left|\left\{(k, l): \hat{f}_{ik} \leq \hat{f}_{il}, y_{ik} = 1, y_{il} = 0 \right\}\right|
 
@@ -1509,7 +1509,7 @@ then the explained variance is estimated as follow:
 
 .. math::
 
-  \texttt{explained\_{}variance}(y, \hat{y}) = 1 - \frac{Var\{ y - \hat{y}\}}{Var\{y\}}
+  explained\_{}variance(y, \hat{y}) = 1 - \frac{Var\{ y - \hat{y}\}}{Var\{y\}}
 
 The best possible score is 1.0, lower values are worse.