[DOC] Fix broken links

CONTRIBUTING.md

@@ -12,10 +12,10 @@ How to contribute
 -----------------
 
 The preferred way to contribute to scikit-learn is to fork the 
-[main repository](http://github.com/scikit-learn/scikit-learn/) on
+[main repository](https://github.com/scikit-learn/scikit-learn) on
 GitHub:
 
-1. Fork the [project repository](http://github.com/scikit-learn/scikit-learn):
+1. Fork the [project repository](https://github.com/scikit-learn/scikit-learn):
    click on the 'Fork' button near the top of the page. This creates
    a copy of the code under your account on the GitHub server.
 

doc/README

@@ -35,5 +35,5 @@ to update the http://scikit-learn.org/dev tree of the website.
 
 The configuration of this server is managed at:
 
-  http://github.com/scikit-learn/sklearn-docbuilder
+  https://github.com/scikit-learn/sklearn-docbuilder
 

doc/about.rst

@@ -63,7 +63,7 @@ High quality PNG and SVG logos are available in the `doc/logos/ <https://github.
 Funding
 -------
 
-`INRIA <http://www.inria.fr>`_ actively supports this project. It has
+`INRIA <https://www.inria.fr>`_ actively supports this project. It has
 provided funding for Fabian Pedregosa (2010-2012), Jaques Grobler
 (2012-2013) and Olivier Grisel (2013-2015) to work on this project
 full-time. It also hosts coding sprints and other events.
@@ -88,9 +88,9 @@ Environment also funds several students to work on the project part-time.
    :width: 200pt
    :align: center
 
-The following students were sponsored by `Google <http://code.google.com/opensource/>`_
+The following students were sponsored by `Google <https://developers.google.com/open-source/>`_
 to work on scikit-learn through the
-`Google Summer of Code <http://en.wikipedia.org/wiki/Google_Summer_of_Code>`_
+`Google Summer of Code <https://en.wikipedia.org/wiki/Google_Summer_of_Code>`_
 program.
 
 - 2007 - David Cournapeau
@@ -102,14 +102,14 @@ program.
 It also provided funding for sprints and events around scikit-learn. If
 you would like to participate in the next Google Summer of code
 program, please see `this page
-<http://github.com/scikit-learn/scikit-learn/wiki/SummerOfCode>`_
+<https://github.com/scikit-learn/scikit-learn/wiki/SummerOfCode>`_
 
 The `NeuroDebian <http://neuro.debian.net>`_ project providing `Debian
 <http://www.debian.org>`_ packaging and contributions is supported by
 `Dr. James V. Haxby <http://haxbylab.dartmouth.edu/>`_ (`Dartmouth
-College <http://www.dartmouth.edu/~psych/>`_).
+College <http://pbs.dartmouth.edu>`_).
 
-The `PSF <http://www.python.org/psf/>`_ helped find and manage funding for our
+The `PSF <https://www.python.org/psf/>`_ helped find and manage funding for our
 2011 Granada sprint. More information can be found `here
 <https://github.com/scikit-learn/scikit-learn/wiki/Past-sprints#granada-19th-21th-dec-2011>`__
 
@@ -121,12 +121,12 @@ Donating to the project
 ~~~~~~~~~~~~~~~~~~~~~~~
 
 If you are interested in donating to the project or to one of our code-sprints, you can use
-the *Paypal* button below or the `NumFOCUS Donations Page <http://numfocus.org/donatejoin/>`_ (if you use the latter, please indicate that you are donating for the scikit-learn project).
+the *Paypal* button below or the `NumFOCUS Donations Page <http://www.numfocus.org/support-numfocus.html>`_ (if you use the latter, please indicate that you are donating for the scikit-learn project).
 
 All donations will be handled by `NumFOCUS
-<http://numfocus.org/donations>`_, a non-profit-organization which is
+<http://www.numfocus.org>`_, a non-profit-organization which is
 managed by a board of `Scipy community members
-<http://numfocus.org/board>`_. NumFOCUS's mission is to foster
+<http://www.numfocus.org/board>`_. NumFOCUS's mission is to foster
 scientific computing software, in particular in Python. As a fiscal home
 of scikit-learn, it ensures that money is available when needed to keep
 the project funded and available while in compliance with tax regulations.

doc/datasets/twenty_newsgroups.rst

@@ -111,7 +111,7 @@ components by sample in a more than 30000-dimensional space
 ready-to-use tfidf features instead of file names.
 
 .. _`20 newsgroups website`: http://people.csail.mit.edu/jrennie/20Newsgroups/
-.. _`TF-IDF`: http://en.wikipedia.org/wiki/Tf-idf
+.. _`TF-IDF`: https://en.wikipedia.org/wiki/Tf-idf
 
 
 Filtering text for more realistic training

doc/developers/advanced_installation.rst

@@ -140,7 +140,7 @@ from source package
 ~~~~~~~~~~~~~~~~~~~
 
 download the source package from 
-`pypi <http://pypi.python.org/pypi/scikit-learn/>`_,
+`pypi <https://pypi.python.org/pypi/scikit-learn>`_,
 , unpack the sources and cd into the source directory.
 
 this packages uses distutils, which is the default way of installing
@@ -163,12 +163,12 @@ or alternatively (also from within the scikit-learn source folder)::
 windows
 -------
 
-first, you need to install `numpy <http://numpy.scipy.org/>`_ and `scipy
+first, you need to install `numpy <http://www.numpy.org/>`_ and `scipy
 <http://www.scipy.org/>`_ from their own official installers.
 
 wheel packages (.whl files) for scikit-learn from `pypi
 <https://pypi.python.org/pypi/scikit-learn/>`_ can be installed with the `pip
-<http://pip.readthedocs.org/en/latest/installing.html>`_ utility.
+<https://pip.readthedocs.org/en/stable/installing/>`_ utility.
 open a console and type the following to install or upgrade scikit-learn to the
 latest stable release::
 
@@ -280,9 +280,7 @@ path environment variable.
 
 for 32-bit python it is possible use the standalone installers for
 `microsoft visual c++ express 2008 <http://go.microsoft.com/?linkid=7729279>`_
-for python 2 or
-`microsoft visual c++ express 2010 <http://go.microsoft.com/?linkid=9709949>`_
-or python 3.
+for python 2 or microsoft visual c++ express 2010 for python 3.
 
 once installed you should be able to build scikit-learn without any
 particular configuration by running the following command in the scikit-learn

doc/developers/contributing.rst

@@ -7,7 +7,7 @@ Contributing
 This project is a community effort, and everyone is welcome to
 contribute.
 
-The project is hosted on http://github.com/scikit-learn/scikit-learn
+The project is hosted on https://github.com/scikit-learn/scikit-learn
 
 Scikit-learn is somewhat :ref:`selective <selectiveness>` when it comes to
 adding new algorithms, and the best way to contribute and to help the project
@@ -19,7 +19,7 @@ Submitting a bug report
 
 In case you experience issues using this package, do not hesitate to submit a
 ticket to the
-`Bug Tracker <http://github.com/scikit-learn/scikit-learn/issues>`_. You are
+`Bug Tracker <https://github.com/scikit-learn/scikit-learn/issues>`_. You are
 also welcome to post feature requests or pull requests.
 
 
@@ -29,7 +29,7 @@ Retrieving the latest code
 ==========================
 
 We use `Git <http://git-scm.com/>`_ for version control and
-`GitHub <http://github.com/>`_ for hosting our main repository.
+`GitHub <https://github.com/>`_ for hosting our main repository.
 
 You can check out the latest sources with the command::
 
@@ -82,14 +82,14 @@ How to contribute
 -----------------
 
 The preferred way to contribute to scikit-learn is to fork the `main
-repository <http://github.com/scikit-learn/scikit-learn/>`__ on GitHub,
+repository <https://github.com/scikit-learn/scikit-learn/>`__ on GitHub,
 then submit a "pull request" (PR):
 
- 1. `Create an account <https://github.com/signup/free>`_ on
+ 1. `Create an account <https://github.com/join>`_ on
     GitHub if you do not already have one.
 
  2. Fork the `project repository
-    <http://github.com/scikit-learn/scikit-learn>`__: click on the 'Fork'
+    <https://github.com/scikit-learn/scikit-learn>`__: click on the 'Fork'
     button near the top of the page. This creates a copy of the code under your
     account on the GitHub server.
 
@@ -237,8 +237,8 @@ and are viewable in a web browser. See the README file in the doc/ directory
 for more information.
 
 For building the documentation, you will need `sphinx
-<http://sphinx.pocoo.org/>`_,
-`matplotlib <http://matplotlib.sourceforge.net/>`_ and
+<http://sphinx-doc.org/>`_,
+`matplotlib <http://matplotlib.org>`_ and
 `pillow <http://pillow.readthedocs.org/en/latest/>`_.
 
 **When you are writing documentation**, it is important to keep a good
@@ -297,7 +297,7 @@ Finally, follow the formatting rules below to make it consistently good:
 Testing and improving test coverage
 ------------------------------------
 
-High-quality `unit testing <http://en.wikipedia.org/wiki/Unit_testing>`_
+High-quality `unit testing <https://en.wikipedia.org/wiki/Unit_testing>`_
 is a corner-stone of the scikit-learn development process. For this
 purpose, we use the `nose <http://nose.readthedocs.org/en/latest/>`_
 package. The tests are functions appropriately named, located in `tests`
@@ -313,7 +313,7 @@ We expect code coverage of new features to be at least around 90%.
 .. note:: **Workflow to improve test coverage**
 
    To test code coverage, you need to install the `coverage
-   <http://pypi.python.org/pypi/coverage>`_ package in addition to nose.
+   <https://pypi.python.org/pypi/coverage>`_ package in addition to nose.
 
    1. Run 'make test-coverage'. The output lists for each file the line
       numbers that are not tested.
@@ -392,7 +392,7 @@ the review easier so new code can be integrated in less time.
 
 Uniformly formatted code makes it easier to share code ownership. The
 scikit-learn project tries to closely follow the official Python guidelines
-detailed in `PEP8 <http://www.python.org/dev/peps/pep-0008/>`_ that
+detailed in `PEP8 <https://www.python.org/dev/peps/pep-0008>`_ that
 detail how code should be formatted and indented. Please read it and
 follow it.
 
@@ -414,7 +414,7 @@ In addition, we add the following guidelines:
 
     * **Please don't use** ``import *`` **in any case**. It is considered harmful
       by the `official Python recommendations
-      <http://docs.python.org/howto/doanddont.html#from-module-import>`_.
+      <https://docs.python.org/2/howto/doanddont.html#from-module-import>`_.
       It makes the code harder to read as the origin of symbols is no
       longer explicitly referenced, but most important, it prevents
       using a static analysis tool like `pyflakes

doc/developers/performance.rst

@@ -40,7 +40,7 @@ this means trying to **replace any nested for loops by calls to equivalent
 Numpy array methods**. The goal is to avoid the CPU wasting time in the
 Python interpreter rather than crunching numbers to fit your statistical
 model. It's generally a good idea to consider NumPy and SciPy performance tips:
-http://wiki.scipy.org/PerformanceTips
+http://scipy.github.io/old-wiki/pages/PerformanceTips
 
 Sometimes however an algorithm cannot be expressed efficiently in simple
 vectorized Numpy code. In this case, the recommended strategy is the
@@ -304,7 +304,7 @@ Memory usage profiling
 ======================
 
 You can analyze in detail the memory usage of any Python code with the help of
-`memory_profiler <http://pypi.python.org/pypi/memory_profiler>`_. First,
+`memory_profiler <https://pypi.python.org/pypi/memory_profiler>`_. First,
 install the latest version::
 
     $ pip install -U memory_profiler
@@ -401,7 +401,7 @@ project.
 TODO: html report, type declarations, bound checks, division by zero checks,
 memory alignment, direct blas calls...
 
-- http://www.euroscipy.org/file/3696?vid=download
+- https://www.youtube.com/watch?v=gMvkiQ-gOW8
 - http://conference.scipy.org/proceedings/SciPy2009/paper_1/
 - http://conference.scipy.org/proceedings/SciPy2009/paper_2/
 
@@ -421,16 +421,16 @@ Using yep and google-perftools
 
 Easy profiling without special compilation options use yep:
 
-- http://pypi.python.org/pypi/yep
-- http://fseoane.net/blog/2011/a-profiler-for-python-extensions/
+- https://pypi.python.org/pypi/yep
+- http://fa.bianp.net/blog/2011/a-profiler-for-python-extensions
 
 .. note::
 
   google-perftools provides a nice 'line by line' report mode that
   can be triggered with the ``--lines`` option. However this
   does not seem to work correctly at the time of writing. This
   issue can be tracked on the `project issue tracker
-  <https://code.google.com/p/google-perftools/issues/detail?id=326>`_.
+  <https://github.com/gperftools/gperftools>`_.
 
 
 
@@ -460,7 +460,7 @@ TODO: give a simple teaser example here.
 
 Checkout the official joblib documentation:
 
-- http://packages.python.org/joblib/
+- https://pythonhosted.org/joblib
 
 
 .. _warm-restarts:

doc/developers/utilities.rst

@@ -93,7 +93,7 @@ Efficient Linear Algebra & Array Operations
   by directly calling the BLAS
   ``nrm2`` function.  This is more stable than ``scipy.linalg.norm``.  See
   `Fabian's blog post
-  <http://fseoane.net/blog/2011/computing-the-vector-norm/>`_ for a discussion.
+  <http://fa.bianp.net/blog/2011/computing-the-vector-norm>`_ for a discussion.
 
 - :func:`extmath.fast_logdet`: efficiently compute the log of the determinant
   of a matrix.

doc/install.rst

@@ -51,8 +51,8 @@ Canopy and Anaconda for all supported platforms
 -----------------------------------------------
 
 `Canopy
-<http://www.enthought.com/products/canopy>`_ and `Anaconda
-<https://store.continuum.io/cshop/anaconda/>`_ both ship a recent
+<https://www.enthought.com/products/canopy>`_ and `Anaconda
+<https://www.continuum.io/downloads>`_ both ship a recent
 version of scikit-learn, in addition to a large set of scientific python
 library for Windows, Mac OSX and Linux.
 
@@ -83,9 +83,8 @@ Anaconda offers scikit-learn as part of its free distribution.
 Python(x,y) for Windows
 -----------------------
 
-The `Python(x,y) <https://code.google.com/p/pythonxy/>`_ project distributes
-scikit-learn as an additional plugin, which can be found in the `Additional
-plugins <http://code.google.com/p/pythonxy/wiki/AdditionalPlugins>`_ page.
+The `Python(x,y) <https://python-xy.github.io>`_ project distributes
+scikit-learn as an additional plugin.
 
 
 For installation instructions for particular operating systems or for compiling

doc/modules/clustering.rst

@@ -1010,7 +1010,7 @@ random labelings by defining the adjusted Rand index as follows:
 .. topic:: References
 
  * `Comparing Partitions
-   <http://www.springerlink.com/content/x64124718341j1j0/>`_
+   <http://link.springer.com/article/10.1007%2FBF01908075>`_
    L. Hubert and P. Arabie, Journal of Classification 1985
 
  * `Wikipedia entry for the adjusted Rand index
@@ -1170,7 +1170,7 @@ calculated using a similar form to that of the adjusted Rand index:
  * Vinh, Epps, and Bailey, (2009). "Information theoretic measures
    for clusterings comparison". Proceedings of the 26th Annual International
    Conference on Machine Learning - ICML '09.
-   `doi:10.1145/1553374.1553511 <http://dx.doi.org/10.1145/1553374.1553511>`_.
+   `doi:10.1145/1553374.1553511 <https://dl.acm.org/citation.cfm?doid=1553374.1553511>`_.
    ISBN 9781605585161.
 
  * Vinh, Epps, and Bailey, (2010). Information Theoretic Measures for

doc/modules/computational_performance.rst

@@ -241,8 +241,8 @@ Linear algebra libraries
 As scikit-learn relies heavily on Numpy/Scipy and linear algebra in general it
 makes sense to take explicit care of the versions of these libraries.
 Basically, you ought to make sure that Numpy is built using an optimized `BLAS
-<http://en.wikipedia.org/wiki/Basic_Linear_Algebra_Subprograms>`_ /
-`LAPACK <http://en.wikipedia.org/wiki/LAPACK>`_ library.
+<https://en.wikipedia.org/wiki/Basic_Linear_Algebra_Subprograms>`_ /
+`LAPACK <https://en.wikipedia.org/wiki/LAPACK>`_ library.
 
 Not all models benefit from optimized BLAS and Lapack implementations. For
 instance models based on (randomized) decision trees typically do not rely on
@@ -308,7 +308,7 @@ compromise between model compactness and prediction power. One can also
 further tune the ``l1_ratio`` parameter (in combination with the
 regularization strength ``alpha``) to control this tradeoff.
 
-A typical `benchmark <https://github.com/scikit-learn/scikit-learn/tree/master/benchmarks/bench_sparsify.py>`_
+A typical `benchmark <https://github.com/scikit-learn/scikit-learn/blob/master/benchmarks/bench_sparsify.py>`_
 on synthetic data yields a >30% decrease in latency when both the model and
 input are sparse (with 0.000024 and 0.027400 non-zero coefficients ratio
 respectively). Your mileage may vary depending on the sparsity and size of

doc/modules/cross_validation.rst

@@ -66,7 +66,7 @@ and the results can depend on a particular random choice for the pair of
 (train, validation) sets.
 
 A solution to this problem is a procedure called
-`cross-validation <http://en.wikipedia.org/wiki/Cross-validation_(statistics)>`_
+`cross-validation <https://en.wikipedia.org/wiki/Cross-validation_(statistics)>`_
 (CV for short).
 A test set should still be held out for final evaluation,
 but the validation set is no longer needed when doing CV.
@@ -337,11 +337,11 @@ fold cross validation should be preferred to LOO.
 
  * `<http://www.faqs.org/faqs/ai-faq/neural-nets/part3/section-12.html>`_;
  * T. Hastie, R. Tibshirani, J. Friedman,  `The Elements of Statistical Learning
-   <http://www-stat.stanford.edu/~tibs/ElemStatLearn>`_, Springer 2009;
+   <http://statweb.stanford.edu/~tibs/ElemStatLearn>`_, Springer 2009
  * L. Breiman, P. Spector `Submodel selection and evaluation in regression: The X-random case
    <http://digitalassets.lib.berkeley.edu/sdtr/ucb/text/197.pdf>`_, International Statistical Review 1992;
  * R. Kohavi, `A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection
-   <http://www.cs.iastate.edu/~jtian/cs573/Papers/Kohavi-IJCAI-95.pdf>`_, Intl. Jnt. Conf. AI;
+   <http://web.cs.iastate.edu/~jtian/cs573/Papers/Kohavi-IJCAI-95.pdf>`_, Intl. Jnt. Conf. AI
  * R. Bharat Rao, G. Fung, R. Rosales, `On the Dangers of Cross-Validation. An Experimental Evaluation
    <http://www.siam.org/proceedings/datamining/2008/dm08_54_Rao.pdf>`_, SIAM 2008;
  * G. James, D. Witten, T. Hastie, R Tibshirani, `An Introduction to

doc/modules/decomposition.rst

@@ -732,7 +732,7 @@ and the regularized objective function is:
 .. topic:: References:
 
     * `"Learning the parts of objects by non-negative matrix factorization"
-      <http://hebb.mit.edu/people/seung/papers/ls-lponm-99.pdf>`_
+      <http://www.columbia.edu/~jwp2128/Teaching/W4721/papers/nmf_nature.pdf>`_
       D. Lee, S. Seung, 1999
 
     * `"Non-negative Matrix Factorization with Sparseness Constraints"

doc/modules/density.rst

@@ -139,7 +139,7 @@ The kernel density estimator can be used with any of the valid distance
 metrics (see :class:`sklearn.neighbors.DistanceMetric` for a list of available metrics), though
 the results are properly normalized only for the Euclidean metric.  One
 particularly useful metric is the
-`Haversine distance <http://en.wikipedia.org/wiki/Haversine_formula>`_
+`Haversine distance <https://en.wikipedia.org/wiki/Haversine_formula>`_
 which measures the angular distance between points on a sphere.  Here
 is an example of using a kernel density estimate for a visualization
 of geospatial data, in this case the distribution of observations of two

doc/modules/ensemble.rst

@@ -414,7 +414,7 @@ decision trees).
 Gradient Tree Boosting
 ======================
 
-`Gradient Tree Boosting <http://en.wikipedia.org/wiki/Gradient_boosting>`_
+`Gradient Tree Boosting <https://en.wikipedia.org/wiki/Gradient_boosting>`_
 or Gradient Boosted Regression Trees (GBRT) is a generalization
 of boosting to arbitrary
 differentiable loss functions. GBRT is an accurate and effective