Merge pull request scikit-learn#5511 from KamalakerDadi/sphinx_version_added

[MRG + 1] Version Added for All Classes in 0.17

Author: amueller

sklearn/cluster/dbscan_.py

@@ -174,6 +174,10 @@ class DBSCAN(BaseEstimator, ClusterMixin):
         If metric is "precomputed", X is assumed to be a distance matrix and
         must be square. X may be a sparse matrix, in which case only "nonzero"
         elements may be considered neighbors for DBSCAN.
+
+        .. versionadded:: 0.17
+           metric *precomputed* to accept precomputed sparse matrix.
+
     algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, optional
         The algorithm to be used by the NearestNeighbors module
         to compute pointwise distances and find nearest neighbors.

sklearn/cluster/mean_shift_.py

@@ -147,6 +147,9 @@ def mean_shift(X, bandwidth=None, seeds=None, bin_seeding=False,
         (n_cpus + 1 + n_jobs) are used. Thus for n_jobs = -2, all CPUs but one
         are used.
 
+        .. versionadded:: 0.17
+           Parallel Execution using *n_jobs*.
+
     Returns
     -------
 

sklearn/cross_validation.py

@@ -361,6 +361,8 @@ class LabelKFold(_BaseKFold):
     The folds are approximately balanced in the sense that the number of
     distinct labels is approximately the same in each fold.
 
+    .. versionadded:: 0.17
+
     Parameters
     ----------
     labels : array-like with shape (n_samples, )
@@ -1108,6 +1110,8 @@ class LabelShuffleSplit(ShuffleSplit):
     Note: The parameters ``test_size`` and ``train_size`` refer to labels, and
     not to samples, as in ShuffleSplit.
 
+    .. versionadded:: 0.17
+
     Parameters
     ----------
     labels :  array, [n_samples]
@@ -1828,6 +1832,9 @@ def train_test_split(*arrays, **options):
         If not None, data is split in a stratified fashion, using this as
         the labels array.
 
+        .. versionadded:: 0.17
+           *stratify* splitting
+
     Returns
     -------
     splitting : list, length = 2 * len(arrays),

sklearn/datasets/rcv1.py

@@ -51,6 +51,8 @@ def fetch_rcv1(data_home=None, subset='all', download_if_missing=True,
 
     Read more in the :ref:`User Guide <datasets>`.
 
+    .. versionadded:: 0.17
+
     Parameters
     ----------
     data_home : string, optional

sklearn/datasets/samples_generator.py

@@ -294,6 +294,9 @@ def make_multilabel_classification(n_samples=100, n_features=20, n_classes=5,
     sparse : bool, optional (default=False)
         If ``True``, return a sparse feature matrix
 
+        .. versionadded:: 0.17
+           parameter to allow *sparse* output.
+
     return_indicator : 'dense' (default) | 'sparse' | False
         If ``dense`` return ``Y`` in the dense binary indicator format. If
         ``'sparse'`` return ``Y`` in the sparse binary indicator format.

sklearn/datasets/svmlight_format.py

@@ -342,7 +342,7 @@ def dump_svmlight_file(X, y, f,  zero_based=True, comment=None, query_id=None,
         n_features is the number of features.
 
     y : array-like, shape = [n_samples] or [n_samples, n_labels]
-        Target values. Class labels must be an integer or float, or array-like 
+        Target values. Class labels must be an integer or float, or array-like
         objects of integer or float for multilabel classifications.
 
     f : string or file-like in binary mode
@@ -369,6 +369,9 @@ def dump_svmlight_file(X, y, f,  zero_based=True, comment=None, query_id=None,
     multilabel: boolean, optional
         Samples may have several labels each (see
         http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multilabel.html)
+
+        .. versionadded:: 0.17
+           parameter *multilabel* to support multilabel datasets.
     """
     if comment is not None:
         # Convert comment string to list of lines in UTF-8.

sklearn/decomposition/dict_learning.py

@@ -948,6 +948,9 @@ class DictionaryLearning(BaseEstimator, SparseCodingMixin):
         Lasso solution (linear_model.Lasso). Lars will be faster if
         the estimated components are sparse.
 
+        .. versionadded:: 0.17
+           *cd* coordinate descent method to improve speed.
+
     transform_algorithm : {'lasso_lars', 'lasso_cd', 'lars', 'omp', \
     'threshold'}
         Algorithm used to transform the data
@@ -960,6 +963,9 @@ class DictionaryLearning(BaseEstimator, SparseCodingMixin):
         threshold: squashes to zero all coefficients less than alpha from
         the projection ``dictionary * X'``
 
+        .. versionadded:: 0.17
+           *lasso_cd* coordinate descent method to improve speed.
+
     transform_n_nonzero_coefs : int, ``0.1 * n_features`` by default
         Number of nonzero coefficients to target in each column of the
         solution. This is only used by `algorithm='lars'` and `algorithm='omp'`

sklearn/decomposition/nmf.py

@@ -841,8 +841,14 @@ class NMF(BaseEstimator, TransformerMixin):
 
     solver : 'pg' | 'cd'
         Numerical solver to use:
-        'pg' is a (deprecated) Projected Gradient solver.
-        'cd' is a Coordinate Descent solver.
+        'pg' is a Projected Gradient solver (deprecated).
+        'cd' is a Coordinate Descent solver (recommended).
+
+        .. versionadded:: 0.17
+           Coordinate Descent solver.
+
+        .. versionchanged:: 0.17
+           Deprecated Projected Gradient solver.
 
     tol : double, default: 1e-4
         Tolerance value used in stopping conditions.
@@ -857,32 +863,57 @@ class NMF(BaseEstimator, TransformerMixin):
         Constant that multiplies the regularization terms. Set it to zero to
         have no regularization.
 
+        .. versionadded:: 0.17
+           *alpha* used in the Coordinate Descent solver.
+
     l1_ratio : double, default: 0.
         The regularization mixing parameter, with 0 <= l1_ratio <= 1.
         For l1_ratio = 0 the penalty is an elementwise L2 penalty
         (aka Frobenius Norm).
         For l1_ratio = 1 it is an elementwise L1 penalty.
         For 0 < l1_ratio < 1, the penalty is a combination of L1 and L2.
 
+        .. versionadded:: 0.17
+           Regularization parameter *l1_ratio* used in the Coordinate Descent solver.
+
     shuffle : boolean, default: False
         If true, randomize the order of coordinates in the CD solver.
 
+        .. versionadded:: 0.17
+           *shuffle* parameter used in the Coordinate Descent solver.
+
     nls_max_iter : integer, default: 2000
         Number of iterations in NLS subproblem.
         Used only in the deprecated 'pg' solver.
 
+        .. versionchanged:: 0.17
+           Deprecated Projected Gradient solver. Use Coordinate Descent solver
+           instead.
+
     sparseness : 'data' | 'components' | None, default: None
         Where to enforce sparsity in the model.
         Used only in the deprecated 'pg' solver.
 
+        .. versionchanged:: 0.17
+           Deprecated Projected Gradient solver. Use Coordinate Descent solver
+           instead.
+
     beta : double, default: 1
         Degree of sparseness, if sparseness is not None. Larger values mean
         more sparseness. Used only in the deprecated 'pg' solver.
 
+        .. versionchanged:: 0.17
+           Deprecated Projected Gradient solver. Use Coordinate Descent solver
+           instead.
+
     eta : double, default: 0.1
         Degree of correctness to maintain, if sparsity is not None. Smaller
         values mean larger error. Used only in the deprecated 'pg' solver.
 
+        .. versionchanged:: 0.17
+           Deprecated Projected Gradient solver. Use Coordinate Descent solver
+           instead.
+
     Attributes
     ----------
     components_ : array, [n_components, n_features]

sklearn/decomposition/online_lda.py

@@ -136,6 +136,8 @@ def _update_doc_distribution(X, exp_topic_word_distr, doc_topic_prior,
 class LatentDirichletAllocation(BaseEstimator, TransformerMixin):
     """Latent Dirichlet Allocation with online variational Bayes algorithm
 
+    .. versionadded:: 0.17
+
     Parameters
     ----------
     n_topics : int, optional (default=10)

sklearn/discriminant_analysis.py

@@ -140,6 +140,12 @@ class LinearDiscriminantAnalysis(BaseEstimator, LinearClassifierMixin,
     The fitted model can also be used to reduce the dimensionality of the input
     by projecting it to the most discriminative directions.
 
+    .. versionadded:: 0.17
+       *LinearDiscriminantAnalysis*.
+
+    .. versionchanged:: 0.17
+       Deprecated :class:`lda.LDA` have been moved to *LinearDiscriminantAnalysis*.
+
     Parameters
     ----------
     solver : string, optional
@@ -167,9 +173,13 @@ class LinearDiscriminantAnalysis(BaseEstimator, LinearClassifierMixin,
     store_covariance : bool, optional
         Additionally compute class covariance matrix (default False).
 
+        .. versionadded:: 0.17
+
     tol : float, optional
         Threshold used for rank estimation in SVD solver.
 
+        .. versionadded:: 0.17
+
     Attributes
     ----------
     coef_ : array, shape (n_features,) or (n_classes, n_features)
@@ -399,6 +409,12 @@ def fit(self, X, y, store_covariance=None, tol=None):
         """Fit LinearDiscriminantAnalysis model according to the given
            training data and parameters.
 
+           .. versionchanged:: 0.17
+              Deprecated *store_covariance* have been moved to main constructor.
+
+           .. versionchanged:: 0.17
+              Deprecated *tol* have been moved to main constructor.
+
         Parameters
         ----------
         X : array-like, shape (n_samples, n_features)
@@ -532,6 +548,12 @@ class QuadraticDiscriminantAnalysis(BaseEstimator, ClassifierMixin):
 
     The model fits a Gaussian density to each class.
 
+    .. versionadded:: 0.17
+       *QuadraticDiscriminantAnalysis*
+
+    .. versionchanged:: 0.17
+       Deprecated :class:`qda.QDA` have been moved to *QuadraticDiscriminantAnalysis*.
+
     Parameters
     ----------
     priors : array, optional, shape = [n_classes]
@@ -567,9 +589,13 @@ class QuadraticDiscriminantAnalysis(BaseEstimator, ClassifierMixin):
         If True the covariance matrices are computed and stored in the
         `self.covariances_` attribute.
 
+        .. versionadded:: 0.17
+
     tol : float, optional, default 1.0e-4
         Threshold used for rank estimation.
 
+        .. versionadded:: 0.17
+
     Examples
     --------
     >>> from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
@@ -600,6 +626,12 @@ def __init__(self, priors=None, reg_param=0., store_covariances=False,
     def fit(self, X, y, store_covariances=None, tol=None):
         """Fit the model according to the given training data and parameters.
 
+            .. versionchanged:: 0.17
+               Deprecated *store_covariance* have been moved to main constructor.
+
+            .. versionchanged:: 0.17
+               Deprecated *tol* have been moved to main constructor.
+
         Parameters
         ----------
         X : array-like, shape = [n_samples, n_features]