DOC clean up assorted type specifications

With thanks to the demo of numpy/numpydoc#150

Author: jnothman

sklearn/cluster/k_means_.py

@@ -55,7 +55,7 @@ def _k_init(X, n_clusters, x_squared_norms, random_state, n_local_trials=None):
     x_squared_norms : array, shape (n_samples,)
         Squared Euclidean norm of each data point.
 
-    random_state : numpy.RandomState
+    random_state : RandomState
         The generator used to initialize the centers.
 
     n_local_trials : integer, optional
@@ -1495,7 +1495,7 @@ def _labels_inertia_minibatch(self, X):
 
         Returns
         -------
-        labels : array, shap (n_samples,)
+        labels : array, shape (n_samples,)
             Cluster labels for each point.
 
         inertia : float

sklearn/covariance/empirical_covariance_.py

@@ -55,7 +55,7 @@ def empirical_covariance(X, assume_centered=False):
     X : ndarray, shape (n_samples, n_features)
         Data from which to compute the covariance estimate
 
-    assume_centered : Boolean
+    assume_centered : boolean
         If True, data are not centered before computation.
         Useful when working with data whose mean is almost, but not exactly
         zero.
@@ -142,7 +142,7 @@ def get_precision(self):
 
         Returns
         -------
-        precision_ : array-like,
+        precision_ : array-like
             The precision matrix associated to the current covariance object.
 
         """
@@ -162,12 +162,12 @@ def fit(self, X, y=None):
           Training data, where n_samples is the number of samples and
           n_features is the number of features.
 
-        y : not used, present for API consistence purpose.
+        y
+            not used, present for API consistence purpose.
 
         Returns
         -------
         self : object
-            Returns self.
 
         """
         X = check_array(X)
@@ -193,7 +193,8 @@ def score(self, X_test, y=None):
             X_test is assumed to be drawn from the same distribution than
             the data used in fit (including centering).
 
-        y : not used, present for API consistence purpose.
+        y
+            not used, present for API consistence purpose.
 
         Returns
         -------

sklearn/covariance/graph_lasso_.py

@@ -519,7 +519,7 @@ class GraphLassoCV(GraphLasso):
         If verbose is True, the objective function and duality gap are
         printed at each iteration.
 
-    assume_centered : Boolean
+    assume_centered : boolean
         If True, data are not centered before computation.
         Useful when working with data whose mean is almost, but not exactly
         zero.

sklearn/covariance/robust_covariance.py

@@ -523,7 +523,7 @@ class MinCovDet(EmpiricalCovariance):
     store_precision : bool
         Specify if the estimated precision is stored.
 
-    assume_centered : Boolean
+    assume_centered : bool
         If True, the support of the robust location and the covariance
         estimates is computed, and a covariance estimate is recomputed from
         it, without centering the data.
@@ -606,12 +606,12 @@ def fit(self, X, y=None):
             Training data, where n_samples is the number of samples
             and n_features is the number of features.
 
-        y : not used, present for API consistence purpose.
+        y
+            not used, present for API consistence purpose.
 
         Returns
         -------
         self : object
-            Returns self.
 
         """
         X = check_array(X, ensure_min_samples=2, estimator='MinCovDet')

sklearn/covariance/shrunk_covariance_.py

@@ -122,12 +122,12 @@ def fit(self, X, y=None):
             Training data, where n_samples is the number of samples
             and n_features is the number of features.
 
-        y : not used, present for API consistence purpose.
+        y
+            not used, present for API consistence purpose.
 
         Returns
         -------
         self : object
-            Returns self.
 
         """
         X = check_array(X)
@@ -157,7 +157,7 @@ def ledoit_wolf_shrinkage(X, assume_centered=False, block_size=1000):
     X : array-like, shape (n_samples, n_features)
         Data from which to compute the Ledoit-Wolf shrunk covariance shrinkage.
 
-    assume_centered : Boolean
+    assume_centered : bool
         If True, data are not centered before computation.
         Useful to work with data whose mean is significantly equal to
         zero but is not exactly zero.
@@ -380,12 +380,12 @@ def fit(self, X, y=None):
         X : array-like, shape = [n_samples, n_features]
             Training data, where n_samples is the number of samples
             and n_features is the number of features.
-        y : not used, present for API consistence purpose.
+        y
+            not used, present for API consistence purpose.
 
         Returns
         -------
         self : object
-            Returns self.
 
         """
         # Not calling the parent object to fit, to avoid computing the
@@ -537,12 +537,12 @@ def fit(self, X, y=None):
         X : array-like, shape = [n_samples, n_features]
             Training data, where n_samples is the number of samples
             and n_features is the number of features.
-        y : not used, present for API consistence purpose.
+        y
+            not used, present for API consistence purpose.
 
         Returns
         -------
         self : object
-            Returns self.
 
         """
         X = check_array(X)

sklearn/cross_decomposition/pls_.py

@@ -153,7 +153,8 @@ class _PLS(six.with_metaclass(ABCMeta), BaseEstimator, TransformerMixin,
         The algorithm used to estimate the weights. It will be called
         n_components times, i.e. once for each iteration of the outer loop.
 
-    max_iter : an integer, the maximum number of iterations (default 500)
+    max_iter : int (default 500)
+        The maximum number of iterations
         of the NIPALS inner loop (used only if algorithm="nipals")
 
     tol : non-negative real, default 1e-06

sklearn/datasets/base.py

@@ -212,8 +212,9 @@ def load_data(module_path, data_file_name):
 
     Parameters
     ----------
-    data_file_name : String. Name of csv file to be loaded from
-    module_path/data/data_file_name. For example 'wine_data.csv'.
+    data_file_name : String
+        Name of csv file to be loaded from
+        module_path/data/data_file_name. For example 'wine_data.csv'.
 
     Returns
     -------

sklearn/datasets/mlcomp.py

@@ -29,14 +29,17 @@ def load_mlcomp(name_or_id, set_="raw", mlcomp_root=None, **kwargs):
     Parameters
     ----------
 
-    name_or_id : the integer id or the string name metadata of the MLComp
-                 dataset to load
+    name_or_id : int or str
+        The integer id or the string name metadata of the MLComp
+        dataset to load
 
-    set_ : select the portion to load: 'train', 'test' or 'raw'
+    set_ : str, default='raw'
+        Select the portion to load: 'train', 'test' or 'raw'
 
-    mlcomp_root : the filesystem path to the root folder where MLComp datasets
-                  are stored, if mlcomp_root is None, the MLCOMP_DATASETS_HOME
-                  environment variable is looked up instead.
+    mlcomp_root : str, optional
+        The filesystem path to the root folder where MLComp datasets
+        are stored, if mlcomp_root is None, the MLCOMP_DATASETS_HOME
+        environment variable is looked up instead.
 
     **kwargs : domain specific kwargs to be passed to the dataset loader.
 

sklearn/dummy.py

@@ -104,7 +104,6 @@ def fit(self, X, y, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         if self.strategy not in ("most_frequent", "stratified", "uniform",
                                  "constant", "prior"):
@@ -386,7 +385,6 @@ def fit(self, X, y, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         if self.strategy not in ("mean", "median", "quantile", "constant"):
             raise ValueError("Unknown strategy type: %s, expected "

sklearn/ensemble/_gradient_boosting.pyx

@@ -376,7 +376,7 @@ def _random_sample_mask(np.npy_intp n_total_samples,
      n_total_in_bag : int
          The number of elements in the sample mask which are set to 1.
 
-     random_state : np.RandomState
+     random_state : RandomState
          A numpy ``RandomState`` object.
 
      Returns

sklearn/ensemble/bagging.py

@@ -242,7 +242,6 @@ def fit(self, X, y, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         return self._fit(X, y, self.max_samples, sample_weight=sample_weight)
 
@@ -275,7 +274,6 @@ def _fit(self, X, y, max_samples=None, max_depth=None, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         random_state = check_random_state(self.random_state)
 

sklearn/ensemble/forest.py

@@ -241,7 +241,6 @@ def fit(self, X, y, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         # Validate or convert input data
         X = check_array(X, accept_sparse="csc", dtype=DTYPE)
@@ -1895,7 +1894,6 @@ def fit(self, X, y=None, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
 
         """
         self.fit_transform(X, y, sample_weight=sample_weight)

sklearn/ensemble/gradient_boosting.py

@@ -987,7 +987,6 @@ def fit(self, X, y, sample_weight=None, monitor=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         # if not warmstart - clear the estimator state
         if not self.warm_start:
@@ -1412,7 +1411,7 @@ class GradientBoostingClassifier(BaseGradientBoosting, ClassifierMixin):
 
         .. versionadded:: 0.19
 
-    init : BaseEstimator, None, optional (default=None)
+    init : estimator, optional
         An estimator object that is used to compute the initial
         predictions. ``init`` has to provide ``fit`` and ``predict``.
         If None it uses ``loss.init_estimator``.
@@ -1493,7 +1492,7 @@ class GradientBoostingClassifier(BaseGradientBoosting, ClassifierMixin):
     loss_ : LossFunction
         The concrete ``LossFunction`` object.
 
-    init_ : BaseEstimator
+    init_ : estimator
         The estimator that provides the initial predictions.
         Set via the ``init`` argument or ``loss.init_estimator``.
 
@@ -1870,7 +1869,7 @@ class GradientBoostingRegressor(BaseGradientBoosting, RegressorMixin):
         The alpha-quantile of the huber loss function and the quantile
         loss function. Only if ``loss='huber'`` or ``loss='quantile'``.
 
-    init : BaseEstimator, None, optional (default=None)
+    init : estimator, optional (default=None)
         An estimator object that is used to compute the initial
         predictions. ``init`` has to provide ``fit`` and ``predict``.
         If None it uses ``loss.init_estimator``.
@@ -1945,7 +1944,7 @@ class GradientBoostingRegressor(BaseGradientBoosting, RegressorMixin):
     loss_ : LossFunction
         The concrete ``LossFunction`` object.
 
-    init_ : BaseEstimator
+    init_ : estimator
         The estimator that provides the initial predictions.
         Set via the ``init`` argument or ``loss.init_estimator``.
 

sklearn/ensemble/iforest.py

@@ -157,7 +157,6 @@ def fit(self, X, y=None, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         X = check_array(X, accept_sparse=['csc'])
         if issparse(X):

sklearn/ensemble/voting_classifier.py

@@ -316,7 +316,7 @@ def set_params(self, **params):
 
         Parameters
         ----------
-        params: keyword arguments
+        params : keyword arguments
             Specific parameters using e.g. set_params(parameter_name=new_value)
             In addition, to setting the parameters of the ``VotingClassifier``,
             the individual classifiers of the ``VotingClassifier`` can also be

sklearn/ensemble/weight_boosting.py

@@ -93,7 +93,6 @@ def fit(self, X, y, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         # Check parameters
         if self.learning_rate <= 0:
@@ -188,7 +187,7 @@ def _boost(self, iboost, X, y, sample_weight, random_state):
         sample_weight : array-like of shape = [n_samples]
             The current sample weights.
 
-        random_state : numpy.RandomState
+        random_state : RandomState
             The current random number generator
 
         Returns
@@ -403,7 +402,6 @@ def fit(self, X, y, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         # Check that algorithm is supported
         if self.algorithm not in ('SAMME', 'SAMME.R'):
@@ -452,7 +450,7 @@ def _boost(self, iboost, X, y, sample_weight, random_state):
         sample_weight : array-like of shape = [n_samples]
             The current sample weights.
 
-        random_state : numpy.RandomState
+        random_state : RandomState
             The current random number generator
 
         Returns
@@ -949,7 +947,6 @@ def fit(self, X, y, sample_weight=None):
         Returns
         -------
         self : object
-            Returns self.
         """
         # Check loss
         if self.loss not in ('linear', 'square', 'exponential'):
@@ -986,7 +983,7 @@ def _boost(self, iboost, X, y, sample_weight, random_state):
         sample_weight : array-like of shape = [n_samples]
             The current sample weights.
 
-        random_state : numpy.RandomState
+        random_state : RandomState
             The current random number generator
 
         Returns

sklearn/feature_selection/from_model.py

@@ -160,7 +160,6 @@ def fit(self, X, y=None, **fit_params):
         Returns
         -------
         self : object
-            Returns self.
         """
         if self.prefit:
             raise NotFittedError(
@@ -192,7 +191,6 @@ def partial_fit(self, X, y=None, **fit_params):
         Returns
         -------
         self : object
-            Returns self.
         """
         if self.prefit:
             raise NotFittedError(

sklearn/feature_selection/univariate_selection.py

@@ -336,7 +336,6 @@ def fit(self, X, y):
         Returns
         -------
         self : object
-            Returns self.
         """
         X, y = check_X_y(X, y, ['csr', 'csc'], multi_output=True)