DOC Added docstring checks for feature_selection, kernel_approximation and neighbors modules (scikit-learn#11421)

Author: NicolasHug

sklearn/feature_selection/rfe.py

@@ -262,16 +262,61 @@ def _get_support_mask(self):
 
  @if_delegate_has_method(delegate='estimator')
  def decision_function(self, X):
+ """Compute the decision function of ``X``.
+
+ Parameters
+ ----------
+ X : array-like or sparse matrix, shape = [n_samples, n_features]
+ The input samples. Internally, it will be converted to
+ ``dtype=np.float32`` and if a sparse matrix is provided
+ to a sparse ``csr_matrix``.
+
+ Returns
+ -------
+ score : array, shape = [n_samples, n_classes] or [n_samples]
+ The decision function of the input samples. The order of the
+ classes corresponds to that in the attribute `classes_`.
+ Regression and binary classification produce an array of shape
+ [n_samples].
+ """
  check_is_fitted(self, 'estimator_')
  return self.estimator_.decision_function(self.transform(X))
 
  @if_delegate_has_method(delegate='estimator')
  def predict_proba(self, X):
+ """Predict class probabilities for X.
+
+ Parameters
+ ----------
+ X : array-like or sparse matrix, shape = [n_samples, n_features]
+ The input samples. Internally, it will be converted to
+ ``dtype=np.float32`` and if a sparse matrix is provided
+ to a sparse ``csr_matrix``.
+
+ Returns
+ -------
+ p : array of shape = [n_samples, n_classes]
+ The class probabilities of the input samples. The order of the
+ classes corresponds to that in the attribute `classes_`.
+ """
  check_is_fitted(self, 'estimator_')
  return self.estimator_.predict_proba(self.transform(X))
 
  @if_delegate_has_method(delegate='estimator')
  def predict_log_proba(self, X):
+ """Predict class log-probabilities for X.
+
+ Parameters
+ ----------
+ X : array of shape [n_samples, n_features]
+ The input samples.
+
+ Returns
+ -------
+ p : array of shape = [n_samples, n_classes]
+ The class log-probabilities of the input samples. The order of the
+ classes corresponds to that in the attribute `classes_`.
+ """
  check_is_fitted(self, 'estimator_')
  return self.estimator_.predict_log_proba(self.transform(X))
 

sklearn/feature_selection/univariate_selection.py

@@ -50,8 +50,9 @@ def f_oneway(*args):
 
  Parameters
  ----------
- sample1, sample2, ... : array_like, sparse matrices
- The sample measurements should be given as arguments.
+ *args : array_like, sparse matrices
+ sample1, sample2... The sample measurements should be given as
+ arguments.
 
  Returns
  -------

sklearn/kernel_approximation.py

@@ -302,7 +302,19 @@ def __init__(self, sample_steps=2, sample_interval=None):
  self.sample_interval = sample_interval
 
  def fit(self, X, y=None):
- """Set parameters."""
+ """Set the parameters
+
+ Parameters
+ ----------
+ X : array-like, shape (n_samples, n_features)
+ Training data, where n_samples in the number of samples
+ and n_features is the number of features.
+
+ Returns
+ -------
+ self : object
+ Returns the transformer.
+ """
  X = check_array(X, accept_sparse='csr')
  if self.sample_interval is None:
  # See reference, figure 2 c)
@@ -420,27 +432,27 @@ class Nystroem(BaseEstimator, TransformerMixin):
  and the keyword arguments passed to this object as kernel_params, and
  should return a floating point number.
 
- n_components : int
- Number of features to construct.
- How many data points will be used to construct the mapping.
-
  gamma : float, default=None
  Gamma parameter for the RBF, laplacian, polynomial, exponential chi2
  and sigmoid kernels. Interpretation of the default value is left to
  the kernel; see the documentation for sklearn.metrics.pairwise.
  Ignored by other kernels.
 
- degree : float, default=None
- Degree of the polynomial kernel. Ignored by other kernels.
-
  coef0 : float, default=None
  Zero coefficient for polynomial and sigmoid kernels.
  Ignored by other kernels.
 
+ degree : float, default=None
+ Degree of the polynomial kernel. Ignored by other kernels.
+
  kernel_params : mapping of string to any, optional
  Additional parameters (keyword arguments) for kernel function passed
  as callable object.
 
+ n_components : int
+ Number of features to construct.
+ How many data points will be used to construct the mapping.
+
  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;

sklearn/neighbors/approximate.py

@@ -82,16 +82,53 @@ def _to_hash(projected):
  return out.reshape(projected.shape[0], -1)
 
  def fit_transform(self, X, y=None):
+ """
+ Parameters
+ ----------
+ X : array-like, shape = [n_samples, n_features]
+ Training vectors, where n_samples is the number of samples and
+ n_features is the number of predictors.
+ """
+
  self.fit(X)
  return self.transform(X)
 
  def transform(self, X):
+ """
+ Parameters
+ ----------
+ X : array-like, shape = [n_samples, n_features]
+ Training vectors, where n_samples is the number of samples and
+ n_features is the number of predictors.
+ """
  return self._to_hash(super(ProjectionToHashMixin, self).transform(X))
 
 
 class GaussianRandomProjectionHash(ProjectionToHashMixin,
  GaussianRandomProjection):
- """Use GaussianRandomProjection to produce a cosine LSH fingerprint"""
+ """Use GaussianRandomProjection to produce a cosine LSH fingerprint
+
+ Parameters
+ ----------
+
+ n_components : int or 'auto', optional (default = 32)
+ Dimensionality of the target projection space.
+
+ n_components can be automatically adjusted according to the
+ number of samples in the dataset and the bound given by the
+ Johnson-Lindenstrauss lemma. In that case the quality of the
+ embedding is controlled by the ``eps`` parameter.
+
+ It should be noted that Johnson-Lindenstrauss lemma can yield
+ very conservative estimated of the required number of components
+ as it makes no assumption on the structure of the dataset.
+
+ 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`.
+ """
  def __init__(self,
  n_components=32,
  random_state=None):

sklearn/neighbors/kde.py

@@ -121,7 +121,7 @@ def fit(self, X, y=None, sample_weight=None):
  X : array_like, shape (n_samples, n_features)
  List of n_features-dimensional data points. Each row
  corresponds to a single data point.
- sample_weight: array_like, shape (n_samples,), optional
+ sample_weight : array_like, shape (n_samples,), optional
  List of sample weights attached to the data X.
  """
  algorithm = self._choose_algorithm(self.algorithm, self.metric)

sklearn/tests/test_docstring_parameters.py

@@ -27,13 +27,10 @@
 IGNORED_MODULES = (
  'cluster',
  'datasets',
- 'feature_selection',
- 'kernel_approximation',
  'model_selection',
  'multioutput',
  'setup',
  'utils',
- 'neighbors',
  # Deprecated modules
  'cross_validation',
  'grid_search',