DOC/TST Docstring checks for svm and covariance modules (scikit-learn#11405)

Author: NicolasHug

sklearn/covariance/elliptic_envelope.py

@@ -122,9 +122,9 @@ def decision_function(self, X, raw_values=None):
             decision function. Must be False (default) for compatibility
             with the others outlier detection tools.
 
-        .. deprecated:: 0.20
-            ``raw_values`` has been deprecated in 0.20 and will be removed
-            in 0.22.
+            .. deprecated:: 0.20
+                ``raw_values`` has been deprecated in 0.20 and will be removed
+                in 0.22.
 
         Returns
         -------

sklearn/covariance/graph_lasso_.py

@@ -383,6 +383,9 @@ def graphical_lasso_path(X, alphas, cov_init=None, X_test=None, mode='cd',
     alphas : list of positive floats
         The list of regularization parameters, decreasing order.
 
+    cov_init : 2D array (n_features, n_features), optional
+        The initial guess for the covariance.
+
     X_test : 2D array, shape (n_test_samples, n_features), optional
         Optional test matrix to measure generalisation error.
 

sklearn/covariance/robust_covariance.py

@@ -55,16 +55,16 @@ def c_step(X, n_support, remaining_iterations=30, initial_estimates=None,
     verbose : boolean, optional
         Verbose mode.
 
+    cov_computation_method : callable, default empirical_covariance
+        The function which will be used to compute the covariance.
+        Must return shape (n_features, n_features)
+
     random_state : int, RandomState instance or None, optional (default=None)
         If int, random_state is the seed used by the random number generator;
         If RandomState instance, random_state is the random number generator;
         If None, the random number generator is the RandomState instance used
         by `np.random`.
 
-    cov_computation_method : callable, default empirical_covariance
-        The function which will be used to compute the covariance.
-        Must return shape (n_features, n_features)
-
     Returns
     -------
     location : array-like, shape (n_features,)
@@ -200,9 +200,6 @@ def select_candidates(X, n_support, n_trials, select=1, n_iter=30,
     n_support : int, [(n + p + 1)/2] < n_support < n
         The number of samples the pure data set must contain.
 
-    select : int, int > 0
-        Number of best candidates results to return.
-
     n_trials : int, nb_trials > 0 or 2-tuple
         Number of different initial sets of observations from which to
         run the algorithm.
@@ -214,22 +211,25 @@ def select_candidates(X, n_support, n_trials, select=1, n_iter=30,
         - n_trials[1]: array-like, shape (n_trials, n_features, n_features)
           is the list of `n_trials` initial covariances estimates
 
+    select : int, int > 0
+        Number of best candidates results to return.
+
     n_iter : int, nb_iter > 0
         Maximum number of iterations for the c_step procedure.
         (2 is enough to be close to the final solution. "Never" exceeds 20).
 
-    random_state : int, RandomState instance or None, optional (default=None)
-        If int, random_state is the seed used by the random number generator;
-        If RandomState instance, random_state is the random number generator;
-        If None, the random number generator is the RandomState instance used
-        by `np.random`.
+    verbose : boolean, default False
+        Control the output verbosity.
 
     cov_computation_method : callable, default empirical_covariance
         The function which will be used to compute the covariance.
         Must return shape (n_features, n_features)
 
-    verbose : boolean, default False
-        Control the output verbosity.
+    random_state : int, RandomState instance or None, optional (default=None)
+        If int, random_state is the seed used by the random number generator;
+        If RandomState instance, random_state is the random number generator;
+        If None, the random number generator is the RandomState instance used
+        by `np.random`.
 
     See Also
     ---------

sklearn/svm/classes.py

@@ -260,26 +260,23 @@ class LinearSVR(LinearModel, RegressorMixin):
 
     Parameters
     ----------
-    C : float, optional (default=1.0)
-        Penalty parameter C of the error term. The penalty is a squared
-        l2 penalty. The bigger this parameter, the less regularization is used.
-
-    loss : string, 'epsilon_insensitive' or 'squared_epsilon_insensitive' (default='epsilon_insensitive')
-        Specifies the loss function. 'l1' is the epsilon-insensitive loss
-        (standard SVR) while 'l2' is the squared epsilon-insensitive loss.
-
     epsilon : float, optional (default=0.1)
         Epsilon parameter in the epsilon-insensitive loss function. Note
         that the value of this parameter depends on the scale of the target
         variable y. If unsure, set ``epsilon=0``.
 
-    dual : bool, (default=True)
-        Select the algorithm to either solve the dual or primal
-        optimization problem. Prefer dual=False when n_samples > n_features.
-
     tol : float, optional (default=1e-4)
         Tolerance for stopping criteria.
 
+    C : float, optional (default=1.0)
+        Penalty parameter C of the error term. The penalty is a squared
+        l2 penalty. The bigger this parameter, the less regularization is used.
+
+    loss : string, optional (default='epsilon_insensitive')
+        Specifies the loss function. The epsilon-insensitive loss
+        (standard SVR) is the L1 loss, while the squared epsilon-insensitive
+        loss ('squared_epsilon_insensitive') is the L2 loss.
+
     fit_intercept : boolean, optional (default=True)
         Whether to calculate the intercept for this model. If set
         to false, no intercept will be used in calculations
@@ -296,6 +293,10 @@ class LinearSVR(LinearModel, RegressorMixin):
         To lessen the effect of regularization on synthetic feature weight
         (and therefore on the intercept) intercept_scaling has to be increased.
 
+    dual : bool, (default=True)
+        Select the algorithm to either solve the dual or primal
+        optimization problem. Prefer dual=False when n_samples > n_features.
+
     verbose : int, (default=0)
         Enable verbose output. Note that this setting takes advantage of a
         per-process runtime setting in liblinear that, if enabled, may not work
@@ -473,13 +474,13 @@ class SVC(BaseSVC):
         Independent term in kernel function.
         It is only significant in 'poly' and 'sigmoid'.
 
+    shrinking : boolean, optional (default=True)
+        Whether to use the shrinking heuristic.
+
     probability : boolean, optional (default=False)
         Whether to enable probability estimates. This must be enabled prior
         to calling `fit`, and will slow down that method.
 
-    shrinking : boolean, optional (default=True)
-        Whether to use the shrinking heuristic.
-
     tol : float, optional (default=1e-3)
         Tolerance for stopping criterion.
 
@@ -639,13 +640,13 @@ class NuSVC(BaseSVC):
         Independent term in kernel function.
         It is only significant in 'poly' and 'sigmoid'.
 
+    shrinking : boolean, optional (default=True)
+        Whether to use the shrinking heuristic.
+
     probability : boolean, optional (default=False)
         Whether to enable probability estimates. This must be enabled prior
         to calling `fit`, and will slow down that method.
 
-    shrinking : boolean, optional (default=True)
-        Whether to use the shrinking heuristic.
-
     tol : float, optional (default=1e-3)
         Tolerance for stopping criterion.
 
@@ -769,15 +770,6 @@ class SVR(BaseLibSVM, RegressorMixin):
 
     Parameters
     ----------
-    C : float, optional (default=1.0)
-        Penalty parameter C of the error term.
-
-    epsilon : float, optional (default=0.1)
-         Epsilon in the epsilon-SVR model. It specifies the epsilon-tube
-         within which no penalty is associated in the training loss function
-         with points predicted within a distance epsilon from the actual
-         value.
-
     kernel : string, optional (default='rbf')
          Specifies the kernel type to be used in the algorithm.
          It must be one of 'linear', 'poly', 'rbf', 'sigmoid', 'precomputed' or
@@ -803,12 +795,21 @@ class SVR(BaseLibSVM, RegressorMixin):
         Independent term in kernel function.
         It is only significant in 'poly' and 'sigmoid'.
 
-    shrinking : boolean, optional (default=True)
-        Whether to use the shrinking heuristic.
-
     tol : float, optional (default=1e-3)
         Tolerance for stopping criterion.
 
+    C : float, optional (default=1.0)
+        Penalty parameter C of the error term.
+
+    epsilon : float, optional (default=0.1)
+         Epsilon in the epsilon-SVR model. It specifies the epsilon-tube
+         within which no penalty is associated in the training loss function
+         with points predicted within a distance epsilon from the actual
+         value.
+
+    shrinking : boolean, optional (default=True)
+        Whether to use the shrinking heuristic.
+
     cache_size : float, optional
         Specify the size of the kernel cache (in MB).
 
@@ -894,14 +895,14 @@ class NuSVR(BaseLibSVM, RegressorMixin):
 
     Parameters
     ----------
-    C : float, optional (default=1.0)
-        Penalty parameter C of the error term.
-
     nu : float, optional
         An upper bound on the fraction of training errors and a lower bound of
         the fraction of support vectors. Should be in the interval (0, 1].  By
         default 0.5 will be taken.
 
+    C : float, optional (default=1.0)
+        Penalty parameter C of the error term.
+
     kernel : string, optional (default='rbf')
          Specifies the kernel type to be used in the algorithm.
          It must be one of 'linear', 'poly', 'rbf', 'sigmoid', 'precomputed' or
@@ -1020,12 +1021,6 @@ class OneClassSVM(BaseLibSVM, OutlierMixin):
          If none is given, 'rbf' will be used. If a callable is given it is
          used to precompute the kernel matrix.
 
-    nu : float, optional
-        An upper bound on the fraction of training
-        errors and a lower bound of the fraction of support
-        vectors. Should be in the interval (0, 1]. By default 0.5
-        will be taken.
-
     degree : int, optional (default=3)
         Degree of the polynomial kernel function ('poly').
         Ignored by all other kernels.
@@ -1047,6 +1042,12 @@ class OneClassSVM(BaseLibSVM, OutlierMixin):
     tol : float, optional
         Tolerance for stopping criterion.
 
+    nu : float, optional
+        An upper bound on the fraction of training
+        errors and a lower bound of the fraction of support
+        vectors. Should be in the interval (0, 1]. By default 0.5
+        will be taken.
+
     shrinking : boolean, optional
         Whether to use the shrinking heuristic.
 

sklearn/tests/test_docstring_parameters.py

@@ -25,8 +25,6 @@
 # TODO Uncomment all modules and fix doc inconsistencies everywhere
 # The list of modules that are not tested for now
 IGNORED_MODULES = (
-    'cross_decomposition',
-    'covariance',
     'cluster',
     'datasets',
     'decomposition',
@@ -41,9 +39,7 @@
     'kernel_approximation',
     'model_selection',
     'multioutput',
-    'random_projection',
     'setup',
-    'svm',
     'utils',
     'neighbors',
     # Deprecated modules