[scikit-learn] annotated tag 0.15.2 created (now 5c3ec84)

[Andreas Tille]

This is an automated email from the git hooks/post-receive script.

tille pushed a change to annotated tag 0.15.2
in repository scikit-learn.

        at  5c3ec84   (tag)
   tagging  2068ff2fd94abe4f14b0334eb4372a64b268f6b4 (commit)
  replaces  0.15.1
 tagged by  Olivier Grisel
        on  Thu Sep 4 16:29:43 2014 +0200

- Log -----------------------------------------------------------------
Release 0.15.2

Alexandre Gramfort (1):
      fix_gnb_proba

Anders Aagaard (1):
      FIX six issue with module imports

Andreas Mueller (3):
      FIX bug where distances were of illegal shape
      [DOC] minor fixes
      Catch ConvergenceWarning in RandomizedL1

Andrew Walker (1):
      DOC typo in plot_kernel_approximation.py

Arnaud Joly (1):
      DOC update what's new

Benedikt Koehler (1):
      Typo

Calvin Giles (1):
      Changed f=open() to with open() as f to eliminate ResourceWarnings. Fixes #3410.

Daiki Aminaka (1):
      fix typo (on -> one)

Fabian Pedregosa (2):
      DOC: write cost function of logistic regression.
      DOC: expand documentation for logistic regression

Gael Varoquaux (13):
      MAINT: be robust to numpy's DeprecationWarning
      BUG: n_samples instead of n_features in cd_fast
      DOC: fix classes not referenced in docs
      TEST: metrics sample_weight test: almost_equal
      MISC: avoid overridding figure in benchs
      DOC: Fix class link
      DOC:Typo in doc
      MAINT: add license info
      MAINT: update joblib to latest release 0.8.3
      MAINT: better gitignore
      DOC: more explicit title
      ENH: minor speed-up in k-means
      ENH: Remove unused copy in k-means

Ilambharathi Kanniah (1):
      DOC adding return type and improving module doc

Jan Dlabal (2):
      Fix grammar
      Fix labels of inliers vs outliers

Jan Hendrik Metzen (2):
      FIX Using random_state.rand rather than scipy.rand consistently in Gaussian Process
      TST regression test for optimum over several random-starts of GP

Joel Nothman (14):
      FIX only use testing.ignore_warnings in tests
      DOC mention doc-building dependency on Pillow
      FIX Py3k support for out-of-core example
      DOC fix see also reference
      DOC fix markup error
      DOC move Attributes section to after Parameters and style likewise
      DOC fix typos
      DOC specify X shape for precomputed
      DOC correct default value
      DOC correct shape of Tree.value
      FIX out-of-core example had been broken
      DOC avoid the plot_ prefix in example where no plot
      DOC fix line references in tutorial
      FIX update sklearn.__all__ to include all end-user submodules

Lars Buitinck (13):
      DOC double backticks for fixed-width (code) font
      FIX Gaussian KDE should return array, not scalar
      COSMIT use explicit RandomState in KDE tests
      DOC optimize some PNG images, shaves off 24kB
      DOC numpydoc convention for Bunch-returning functions
      FIX expit bug with out != None
      FIX potential overflow in _tree.safe_realloc
      MAINT NumPy 1.10-safe version comparisons in joblib
      DOC GP fixes in what's new
      DOC typo
      DOC vectorizers were referring to a private function in public docs
      TST fix doctest for k-NN
      DOC deprecation of **kwargs in neighbors per 0.18

Laurent Direr (2):
      TST hashing vectorizer behavior with np.nan input
      Added a parameter check on n_estimators in BaseEnsemble to raise error if it is not strictly positive.

Loic Esteve (1):
      MAINT get rid of NumPy DeprecationWarnings

MLG (1):
      FIX RFE + test

Manoj Kumar (4):
      FIX: Incomplete download of 20newsgroup_dataset
      DOC: Explicit instructions for Python3
      DOC: Added np.sqrt since default is 'squared=False'
      FIX: Fix the imputation example

Martin Billinger (1):
      FIX LDA transform to project onto most dicriminative direction

Nikolay Mayorov (1):
      FIX bug with set_params on minkowski 'p'.

Noel Dawe (1):
      utils.testing: add assert_greater_equal and assert_less_equal

Olivier Grisel (11):
      FIX wording in whats new in 0.15.1
      FIX #3566: redefine isfinite alias in sklearn
      FIX bump up the miniconda installation script
      FIX define CC and CXX for travis
      FIX Windows CI: use prebuilt numpy / scipy
      FIX heisenfailure in test_lasso_lars_path_length
      FIX heisenfailure on 32 bit python + speedup
      ENH upload Windows wheels to rackspace
      DOC fixes in 0.15.2
      Release 0.15.2
      FIX appveyor.yml path

Peter Prettenhofer (1):
      fix: i might be undefined

Rahiel Kasim (1):
      Repeated word: 'the the' -> 'the'

Robert Bradshaw (1):
      Lift division out of loop in _isotonic_regression.

Sam Nicholls (1):
      FIX Verbose message in RFE to count from 1, not 0

Steve Tjoa (1):
      fixed typo: diriclet -> dirichlet

Tomas Kazmar (1):
      FIX MinMaxScaler behavior on 1D inputs.

Vincent Dubourg (2):
      FIX: random_start feature in GaussianProcess
      FIX: gp_diabetes_dataset examples (theta_ attribute)

Vlad Niculae (4):
      TYPO remove mutli (did you mean Muttley?)
      Turn useless line of code into descriptive comment
      FIX set vectorizer vocabulary outside of init
      Deprecate vectorizer fixed_vocabulary attribute

cgohlke (1):
      MAINT Include binary_tree.pxi in source distribution

pvnguyen (1):
      Update outlier_detection.rst

tejesh95 (1):
      Update gaussian_process.py

ugurthemaster (1):
      COSMIT Move imports in example

-----------------------------------------------------------------------

No new revisions were added by this update.

-- 
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-science/packages/scikit-learn.git