* Add a warning for GP Regressor if optimized hyperparameter matches one of its bounds
* pep8 fix
* Add a test and use np.isclose
* More verbose warning message
* remove print
* Ad a more precise warning and update tests
* fix warning and update tests
* fix test dims
* fix multiple dimensions test
* fix pep8
* change variable name
* add warning for GP classifier
* tests for gpc
* pep8 fix
* put the warning in a function
* add comment to warning function
* update name in gpr and gpc
* update whats_new
* update whats_new
* update whats_new
* remove merge conflict text
* add WhiteKernel
* put the log in the last version
* Add example for PairwiseKernel
* Remove empty line
* Do not return standard deviation
It is not really needed in this minimal example.
* Implement classifier example
* normalize_components in sparsePCA
* changed default strategy of Dummy to prior and removed outputs_2d ttribute
* removed usage of None to drop estimator in ensemble and behaviour param of IsolationForest
* remove support for drop=None in Voting
* removed some warning decorators
* remove feature_extraction.extract_patches
* removed VectorizerMixin and copy parameter from TFIDFVectorizer
* kernel.set_params now raises attributeerror
* removed fig from plot_partial_dependence
* removed iid parameter of search estimators
* removed brier_scorer
* raise error in split when shuffle is False and random_state is not None
* removed MultiOutputEstimator
* removed base classes of NaiveBayes
* removed drop from pipeline
* removed utils in random_projection
* removed presort and classes_ in trees
* flake8
* fixed some tests
* flake
* fixed docstring
* fixed other one
* some left
* mmmm
* insert versionadded versionchanged directives in docstrings for 0.18
indicate where exception classes were moved from
* moved versionadded in the proper places
* Make sure set_params does not break clone on kernels
For example, in kernels such as RBF, using set_params with a
length_scale of different length, used to break clone because of
the non-trivial modification of length_scale in the constructor.
This PR resolves this by moving this logic to __call__ and
making hyperparameter attributes properties.
* Fix tests by using get_params and implement __eq__ for Hyperparameter
* Explain XXX
* Check that hyperparameters are equal after non-trivial set_params
* Refactor into _check_length-scale
Thomas J. Fan
Hanmin Qin