scikit-learn · alhewpl · Jan 25, 2020 · jnothman · Jan 26, 2020 · jnothman
diff --git a/.gitignore b/.gitignore
@@ -6,6 +6,7 @@
 *.lprof
 *.swp
 *.swo
+env/
 .DS_Store
 build
 sklearn/datasets/__config__.py

diff --git a/sklearn/cluster/_agglomerative.py b/sklearn/cluster/_agglomerative.py
@@ -755,6 +755,8 @@ class AgglomerativeClustering(ClusterMixin, BaseEstimator):
     n_connected_components_ : int
         The estimated number of connected components in the graph.
 
+        .. versionchanged:: 0.21
+
     children_ : array-like of shape (n_samples-1, 2)
         The children of each non-leaf node. Values less than `n_samples`
         correspond to leaves of the tree which are the original samples.

diff --git a/sklearn/cluster/_optics.py b/sklearn/cluster/_optics.py
@@ -51,6 +51,8 @@ class OPTICS(ClusterMixin, BaseEstimator):
         number or a fraction of the number of samples (rounded to be at least
         2).
 
+        .. versionadded:: 0.21
+
     max_eps : float, optional (default=np.inf)
         The maximum distance between two samples for one to be considered as
         in the neighborhood of the other. Default value of ``np.inf`` will
@@ -119,6 +121,8 @@ class OPTICS(ClusterMixin, BaseEstimator):
         at least 2). If ``None``, the value of ``min_samples`` is used instead.
         Used only when ``cluster_method='xi'``.
 
+        .. versionadded:: 0.21
+
     algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, optional
         Algorithm used to compute the nearest neighbors:
 

diff --git a/sklearn/compose/_column_transformer.py b/sklearn/compose/_column_transformer.py
@@ -110,6 +110,8 @@ class ColumnTransformer(TransformerMixin, _BaseComposition):
         If True, the time elapsed while fitting each transformer will be
         printed as it is completed.
 
+        .. versionadded:: 0.21
+
     Attributes
     ----------
     transformers_ : list
@@ -717,6 +719,8 @@ def make_column_transformer(*transformers, **kwargs):
         If True, the time elapsed while fitting each transformer will be
         printed as it is completed.
 
+        .. versionadded:: 0.21
+
     Returns
     -------
     ct : ColumnTransformer

diff --git a/sklearn/externals/_scipy_linalg.py b/sklearn/externals/_scipy_linalg.py
@@ -51,6 +51,8 @@ def pinvh(a, cond=None, rcond=None, lower=True, return_rank=False,
     using its eigenvalue decomposition and including all eigenvalues with
     'large' absolute value.
 
+    .. versionadded:: 0.21
+
     Parameters
     ----------
     a : (N, N) array_like

diff --git a/sklearn/pipeline.py b/sklearn/pipeline.py
@@ -70,6 +70,8 @@ class Pipeline(_BaseComposition):
         If True, the time elapsed while fitting each step will be printed as it
         is completed.
 
+        .. versionadded:: 0.21
+
     Attributes
     ----------
     named_steps : bunch object, a dictionary with attribute access
@@ -211,6 +213,9 @@ def _iter(self, with_final=True, filter_passthrough=True):
     def __len__(self):
         """
         Returns the length of the Pipeline
+
+        .. versionadded:: 0.21
+
         """
         return len(self.steps)
 
@@ -678,6 +683,8 @@ def make_pipeline(*steps, **kwargs):
         If True, the time elapsed while fitting each step will be printed as it
         is completed.
 
+        .. versionadded:: 0.21
+
     See Also
     --------
     sklearn.pipeline.Pipeline : Class for creating a pipeline of
@@ -787,6 +794,8 @@ class FeatureUnion(TransformerMixin, _BaseComposition):
         If True, the time elapsed while fitting each transformer will be
         printed as it is completed.
 
+        .. versionadded:: 0.21
+
     See Also
     --------
     sklearn.pipeline.make_union : Convenience function for simplified
@@ -1020,6 +1029,8 @@ def make_union(*transformers, **kwargs):
         If True, the time elapsed while fitting each transformer will be
         printed as it is completed.
 
+        .. versionadded:: 0.21
+
     Returns
     -------
     f : FeatureUnion

diff --git a/sklearn/preprocessing/_csr_polynomial_expansion.pyx b/sklearn/preprocessing/_csr_polynomial_expansion.pyx
@@ -83,6 +83,8 @@ def _csr_polynomial_expansion(ndarray[DATA_T, ndim=1] data,
     ----------
     "Leveraging Sparsity to Speed Up Polynomial Feature Expansions of CSR
     Matrices Using K-Simplex Numbers" by Andrew Nystrom and John Hughes.
+
+    .. versionadded:: 0.21
     """
 
     assert degree in (2, 3)

diff --git a/sklearn/preprocessing/_data.py b/sklearn/preprocessing/_data.py
@@ -2161,6 +2161,8 @@ class QuantileTransformer(TransformerMixin, BaseEstimator):
         a better approximation of the cumulative distribution function
         estimator.
 
+        .. versionchanged:: 0.21
+
     output_distribution : str, optional (default='uniform')
         Marginal distribution for the transformed data. The choices are
         'uniform' (default) or 'normal'.

diff --git a/sklearn/preprocessing/_encoders.py b/sklearn/preprocessing/_encoders.py
@@ -37,6 +37,8 @@ def _check_X(self, X):
           of pandas DataFrame columns, as otherwise information is lost
           and cannot be used, eg for the `categories_` attribute.
 
+        .. versionchanged:: 0.21
+
         """
         if not (hasattr(X, 'iloc') and getattr(X, 'ndim', 0) == 2):
             # if not a dataframe, do normal check_array validation
@@ -198,6 +200,8 @@ class OneHotEncoder(_BaseEncoder):
         - array : ``drop[i]`` is the category in feature ``X[:, i]`` that
           should be dropped.
 
+        .. versionadded:: 0.21
+
     sparse : bool, default=True
         Will return sparse matrix if set True else will return an array.
 

diff --git a/sklearn/preprocessing/_label.py b/sklearn/preprocessing/_label.py
@@ -950,6 +950,8 @@ def transform(self, y):
         return yt
 
     def _build_cache(self):
+        """ .. versionadded:: 0.21"""
+
         if self._cached_dict is None:
             self._cached_dict = dict(zip(self.classes_,
                                          range(len(self.classes_))))

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
@@ -118,6 +118,8 @@ def get_depth(self):
         The depth of a tree is the maximum distance between the root
         and any leaf.
 
+        .. versionadded:: 0.21
+
         Returns
         -------
         self.tree_.max_depth : int
@@ -129,6 +131,8 @@ def get_depth(self):
     def get_n_leaves(self):
         """Return the number of leaves of the decision tree.
 
+        .. versionadded:: 0.21
+
         Returns
         -------
         self.tree_.n_leaves : int

diff --git a/sklearn/tree/_export.py b/sklearn/tree/_export.py
@@ -809,6 +809,8 @@ def export_text(decision_tree, feature_names=None, max_depth=10,
 
     Note that backwards compatibility may not be supported.
 
+    .. versionadded:: 0.21
+
     Parameters
     ----------
     decision_tree : object

diff --git a/sklearn/utils/__init__.py b/sklearn/utils/__init__.py
@@ -486,6 +486,8 @@ def resample(*arrays, **options):
         If not None, data is split in a stratified fashion, using this as
         the class labels.
 
+    .. versionadded:: 0.21
+
     Returns
     -------
     resampled_arrays : sequence of indexable data-structures

diff --git a/sklearn/utils/estimator_checks.py b/sklearn/utils/estimator_checks.py
@@ -2787,12 +2787,17 @@ def check_fit_non_negative(name, estimator_orig):
 
 
 def check_fit_idempotent(name, estimator_orig):
-    # Check that est.fit(X) is the same as est.fit(X).fit(X). Ideally we would
-    # check that the estimated parameters during training (e.g. coefs_) are
-    # the same, but having a universal comparison function for those
-    # attributes is difficult and full of edge cases. So instead we check that
-    # predict(), predict_proba(), decision_function() and transform() return
-    # the same results.
+    """
+    Check that est.fit(X) is the same as est.fit(X).fit(X). Ideally we would
+    check that the estimated parameters during training (e.g. coefs_) are
+    the same, but having a universal comparison function for those
+    attributes is difficult and full of edge cases. So instead we check that
+    predict(), predict_proba(), decision_function() and transform() return
+    the same results.
+
+     .. versionadded:: 0.21
+
+     """
 
     check_methods = ["predict", "transform", "decision_function",
                      "predict_proba"]

diff --git a/sklearn/utils/fixes.py b/sklearn/utils/fixes.py
@@ -190,6 +190,9 @@ def _astype_copy_false(X):
     """Returns the copy=False parameter for
     {ndarray, csr_matrix, csc_matrix}.astype when possible,
     otherwise don't specify
+
+    .. versionadded:: 0.21
+
     """
     if sp_version >= (1, 1) or not sp.issparse(X):
         return {'copy': False}
-Original file line number
+Diff line change
@@ Expand Up / @@ -6,6 +6,7 @@ @@
     *.lprof
     *.swp
     *.swo
+    env/
     .DS_Store
     build
     sklearn/datasets/__config__.py
@@ Expand Down @@