diff --git a/doc/faq.rst b/doc/faq.rst
index d5d15a1ed024325d096a4a77807e2e490e58991a..16101bc5c9ba7ed767350c7b4c9de56c11677828 100644
--- a/doc/faq.rst
+++ b/doc/faq.rst
@@ -127,6 +127,7 @@ together with scikit-learn tools. You can implement your favorite algorithm in
a scikit-learn compatible way, upload it to github and let us know. We will
list it under :ref:`related_projects`.
+.. _selectiveness:
Why are you so selective on what algorithms you include in scikit-learn?
------------------------------------------------------------------------
@@ -313,7 +314,7 @@ not close your pull request or discontinue your work solely because of
this reason.
How do I set a ``random_state`` for an entire execution?
-----------------------------------------------------
+---------------------------------------------------------
For testing and replicability, it is often important to have the entire execution
controlled by a single seed for the pseudo-random number generator used in
diff --git a/doc/modules/model_evaluation.rst b/doc/modules/model_evaluation.rst
index 9f9e7ac19f87eaf528468cfeaaa336fbadfc5619..63e16932cf9af9316507128aeafed0277a4761e4 100644
--- a/doc/modules/model_evaluation.rst
+++ b/doc/modules/model_evaluation.rst
@@ -1101,7 +1101,7 @@ Here is a small example of usage of this function:::
.. topic:: Example:
- * See :ref:`sphx_glr_calibration_plot_calibration.py`
+ * See :ref:`sphx_glr_auto_examples_calibration_plot_calibration.py`
for an example of Brier score loss usage to perform probability
calibration of classifiers.
diff --git a/examples/ensemble/plot_random_forest_regression_multioutput.py b/examples/ensemble/plot_random_forest_regression_multioutput.py
index 5849833fef4bfe566c669e60345cf5180fbdb107..2b795ab3a92b2279a46d1c1139fa5e34f78aaf24 100644
--- a/examples/ensemble/plot_random_forest_regression_multioutput.py
+++ b/examples/ensemble/plot_random_forest_regression_multioutput.py
@@ -4,10 +4,10 @@ Comparing random forests and the multi-output meta estimator
============================================================
An example to compare multi-output regression with random forest and
-the :ref:`multioutput.MultiOutputRegressor <_multiclass>` meta-estimator.
+the :ref:`multioutput.MultiOutputRegressor <multiclass>` meta-estimator.
This example illustrates the use of the
-:ref:`multioutput.MultiOutputRegressor <_multiclass>` meta-estimator
+:ref:`multioutput.MultiOutputRegressor <multiclass>` meta-estimator
to perform multi-output regression. A random forest regressor is used,
which supports multi-output regression natively, so the results can be
compared.
diff --git a/sklearn/ensemble/iforest.py b/sklearn/ensemble/iforest.py
index 05ea557b58bd3471bd16974d074dd59fef7a31c3..c96622c95f1ba2e905c059dec018a01842ac591f 100644
--- a/sklearn/ensemble/iforest.py
+++ b/sklearn/ensemble/iforest.py
@@ -64,6 +64,7 @@ class IsolationForest(BaseBagging):
max_features : int or float, optional (default=1.0)
The number of features to draw from X to train each base estimator.
+
- If int, then draw `max_features` features.
- If float, then draw `max_features * X.shape[1]` features.
diff --git a/sklearn/mixture/bayesian_mixture.py b/sklearn/mixture/bayesian_mixture.py
index 97aaacb4564c1d00c8f17524d639c8cf8b2e5bb0..d22ba73691ad9cf3784828ef77613bc6c2fa45e6 100644
--- a/sklearn/mixture/bayesian_mixture.py
+++ b/sklearn/mixture/bayesian_mixture.py
@@ -90,13 +90,14 @@ class BayesianGaussianMixture(BaseMixture):
close to zero. The number of effective components is therefore smaller
than n_components.
- covariance_type : {'full', 'tied', 'diag', 'spherical'}, defaults to 'full'.
+ covariance_type : {'full', 'tied', 'diag', 'spherical'}, defaults to 'full'
String describing the type of covariance parameters to use.
Must be one of::
- 'full' (each component has its own general covariance matrix),
- 'tied' (all components share the same general covariance matrix),
- 'diag' (each component has its own diagonal covariance matrix),
- 'spherical' (each component has its own single variance).
+
+ 'full' (each component has its own general covariance matrix),
+ 'tied' (all components share the same general covariance matrix),
+ 'diag' (each component has its own diagonal covariance matrix),
+ 'spherical' (each component has its own single variance).
tol : float, defaults to 1e-3.
The convergence threshold. EM iterations will stop when the
@@ -118,14 +119,16 @@ class BayesianGaussianMixture(BaseMixture):
The method used to initialize the weights, the means and the
covariances.
Must be one of::
- 'kmeans' : responsibilities are initialized using kmeans.
- 'random' : responsibilities are initialized randomly.
+
+ 'kmeans' : responsibilities are initialized using kmeans.
+ 'random' : responsibilities are initialized randomly.
weight_concentration_prior_type : str, defaults to 'dirichlet_process'.
String describing the type of the weight concentration prior.
Must be one of::
- 'dirichlet_process' (using the Stick-breaking representation),
- 'dirichlet_distribution' (can favor more uniform weights).
+
+ 'dirichlet_process' (using the Stick-breaking representation),
+ 'dirichlet_distribution' (can favor more uniform weights).
weight_concentration_prior : float | None, optional.
The dirichlet concentration of each component on the weight
@@ -133,7 +136,7 @@ class BayesianGaussianMixture(BaseMixture):
the center and will lead to more components being active, while a lower
concentration parameter will lead to more mass at the edge of the
mixture weights simplex. The value of the parameter must be greater
- than 0. If it is None, it's set to `1. / n_components`.
+ than 0. If it is None, it's set to ``1. / n_components``.
mean_precision_prior : float | None, optional.
The precision prior on the mean distribution (Gaussian).
@@ -142,7 +145,7 @@ class BayesianGaussianMixture(BaseMixture):
The value of the parameter must be greater than 0.
If it is None, it's set to 1.
- mean_prior : array-like, shape (`n_features`,), optional
+ mean_prior : array-like, shape (n_features,), optional
The prior on the mean distribution (Gaussian).
If it is None, it's set to the mean of X.
@@ -154,10 +157,11 @@ class BayesianGaussianMixture(BaseMixture):
The prior on the covariance distribution (Wishart).
If it is None, the emiprical covariance prior is initialized using the
covariance of X. The shape depends on `covariance_type`::
- (`n_features`, `n_features`) if 'full',
- (`n_features`, `n_features`) if 'tied',
- (`n_features`) if 'diag',
- float if 'spherical'
+
+ (n_features, n_features) if 'full',
+ (n_features, n_features) if 'tied',
+ (n_features) if 'diag',
+ float if 'spherical'
random_state: RandomState or an int seed, defaults to None.
A random number generator instance.
@@ -178,15 +182,16 @@ class BayesianGaussianMixture(BaseMixture):
Attributes
----------
- weights_ : array-like, shape (`n_components`,)
+ weights_ : array-like, shape (n_components,)
The weights of each mixture components.
- means_ : array-like, shape (`n_components`, `n_features`)
+ means_ : array-like, shape (n_components, n_features)
The mean of each mixture component.
covariances_ : array-like
The covariance of each mixture component.
The shape depends on `covariance_type`::
+
(n_components,) if 'spherical',
(n_features, n_features) if 'tied',
(n_components, n_features) if 'diag',
@@ -199,7 +204,8 @@ class BayesianGaussianMixture(BaseMixture):
equivalently parameterized by the precision matrices. Storing the
precision matrices instead of the covariance matrices makes it more
efficient to compute the log-likelihood of new samples at test time.
- The shape depends on `covariance_type`::
+ The shape depends on ``covariance_type``::
+
(n_components,) if 'spherical',
(n_features, n_features) if 'tied',
(n_components, n_features) if 'diag',
@@ -212,7 +218,8 @@ class BayesianGaussianMixture(BaseMixture):
Gaussian can be equivalently parameterized by the precision matrices.
Storing the precision matrices instead of the covariance matrices makes
it more efficient to compute the log-likelihood of new samples at test
- time. The shape depends on `covariance_type`::
+ time. The shape depends on ``covariance_type``::
+
(n_components,) if 'spherical',
(n_features, n_features) if 'tied',
(n_components, n_features) if 'diag',
@@ -232,15 +239,17 @@ class BayesianGaussianMixture(BaseMixture):
weight_concentration_prior_ : tuple or float
The dirichlet concentration of each component on the weight
distribution (Dirichlet). The type depends on
- `weight_concentration_prior_type`::
+ ``weight_concentration_prior_type``::
+
(float, float) if 'dirichlet_process' (Beta parameters),
float if 'dirichlet_distribution' (Dirichlet parameters).
+
The higher concentration puts more mass in
the center and will lead to more components being active, while a lower
concentration parameter will lead to more mass at the edge of the
simplex.
- weight_concentration_ : array-like, shape (`n_components`, )
+ weight_concentration_ : array-like, shape (n_components,)
The dirichlet concentration of each component on the weight
distribution (Dirichlet).
@@ -250,26 +259,27 @@ class BayesianGaussianMixture(BaseMixture):
Smaller values concentrate the means of each clusters around
`mean_prior`.
- mean_precision_ : array-like, shape (`n_components`, )
+ mean_precision_ : array-like, shape (n_components,)
The precision of each components on the mean distribution (Gaussian).
- means_prior_ : array-like, shape (`n_features`,)
+ means_prior_ : array-like, shape (n_features,)
The prior on the mean distribution (Gaussian).
degrees_of_freedom_prior_ : float
The prior of the number of degrees of freedom on the covariance
distributions (Wishart).
- degrees_of_freedom_ : array-like, shape (`n_components`,)
+ degrees_of_freedom_ : array-like, shape (n_components,)
The number of degrees of freedom of each components in the model.
covariance_prior_ : float or array-like
The prior on the covariance distribution (Wishart).
The shape depends on `covariance_type`::
- (`n_features`, `n_features`) if 'full',
- (`n_features`, `n_features`) if 'tied',
- (`n_features`) if 'diag',
- float if 'spherical'
+
+ (n_features, n_features) if 'full',
+ (n_features, n_features) if 'tied',
+ (n_features) if 'diag',
+ float if 'spherical'
See Also
--------
diff --git a/sklearn/mixture/gaussian_mixture.py b/sklearn/mixture/gaussian_mixture.py
index 57fa24e891836ecb572d880895abe0c10e21e62a..f4a182a7c95672c42899ae26e9b9ce9431d6a013 100644
--- a/sklearn/mixture/gaussian_mixture.py
+++ b/sklearn/mixture/gaussian_mixture.py
@@ -450,13 +450,14 @@ class GaussianMixture(BaseMixture):
The number of mixture components.
covariance_type : {'full', 'tied', 'diag', 'spherical'},
- defaults to 'full'.
+ defaults to 'full'.
String describing the type of covariance parameters to use.
Must be one of::
- 'full' (each component has its own general covariance matrix),
- 'tied' (all components share the same general covariance matrix),
- 'diag' (each component has its own diagonal covariance matrix),
- 'spherical' (each component has its own single variance).
+
+ 'full' (each component has its own general covariance matrix),
+ 'tied' (all components share the same general covariance matrix),
+ 'diag' (each component has its own diagonal covariance matrix),
+ 'spherical' (each component has its own single variance).
tol : float, defaults to 1e-3.
The convergence threshold. EM iterations will stop when the
@@ -476,8 +477,9 @@ class GaussianMixture(BaseMixture):
The method used to initialize the weights, the means and the
precisions.
Must be one of::
- 'kmeans' : responsibilities are initialized using kmeans.
- 'random' : responsibilities are initialized randomly.
+
+ 'kmeans' : responsibilities are initialized using kmeans.
+ 'random' : responsibilities are initialized randomly.
weights_init : array-like, shape (n_components, ), optional
The user-provided initial weights, defaults to None.
@@ -492,6 +494,7 @@ class GaussianMixture(BaseMixture):
matrices), defaults to None.
If it None, precisions are initialized using the 'init_params' method.
The shape depends on 'covariance_type'::
+
(n_components,) if 'spherical',
(n_features, n_features) if 'tied',
(n_components, n_features) if 'diag',
@@ -525,6 +528,7 @@ class GaussianMixture(BaseMixture):
covariances_ : array-like
The covariance of each mixture component.
The shape depends on `covariance_type`::
+
(n_components,) if 'spherical',
(n_features, n_features) if 'tied',
(n_components, n_features) if 'diag',
@@ -538,6 +542,7 @@ class GaussianMixture(BaseMixture):
precision matrices instead of the covariance matrices makes it more
efficient to compute the log-likelihood of new samples at test time.
The shape depends on `covariance_type`::
+
(n_components,) if 'spherical',
(n_features, n_features) if 'tied',
(n_components, n_features) if 'diag',
@@ -551,6 +556,7 @@ class GaussianMixture(BaseMixture):
Storing the precision matrices instead of the covariance matrices makes
it more efficient to compute the log-likelihood of new samples at test
time. The shape depends on `covariance_type`::
+
(n_components,) if 'spherical',
(n_features, n_features) if 'tied',
(n_components, n_features) if 'diag',