DOC make documentation consistent with sklearn guideline

Author: glemaitre

doc/ensemble.rst

@@ -69,7 +69,7 @@ Forest of randomized trees
 :class:`BalancedRandomForestClassifier` is another ensemble method in which
 each tree of the forest will be provided a balanced bootstrap sample
 :cite:`chen2004using`. This class provides all functionality of the
-:class:`sklearn.ensemble.RandomForestClassifier` and notably the
+:class:`~sklearn.ensemble.RandomForestClassifier` and notably the
 `feature_importances_` attributes::
 
   >>> from imblearn.ensemble import BalancedRandomForestClassifier

doc/miscellaneous.rst

@@ -53,7 +53,7 @@ sampling for regression targets.
 
 We illustrate the use of such sampler to implement an outlier rejection
 estimator which can be easily used within a
-:class:`imblearn.pipeline.Pipeline`:
+:class:`~imblearn.pipeline.Pipeline`:
 :ref:`sphx_glr_auto_examples_plot_outlier_rejections.py`
 
 .. _generators:
@@ -158,7 +158,7 @@ Then, ``fit_generator`` can be called passing the generator and the step::
   ...                                        epochs=10, verbose=0)
 
 The second possibility is to use
-:class:`imblearn.keras.BalancedBatchGenerator`. Only an instance of this class
+:class:`~imblearn.keras.BalancedBatchGenerator`. Only an instance of this class
 will be passed to ``fit_generator``::
 
   >>> from imblearn.keras import BalancedBatchGenerator

doc/over_sampling.rst

@@ -203,18 +203,16 @@ other extra interpolation.
 ROSE (Random Over-Sampling Examples)
 ------------------------------------
 
-ROSE uses smoothed bootstrapping to draw artificial samples from the 
+ROSE uses smoothed bootstrapping to draw artificial samples from the
 feature space neighborhood around selected classes, using a multivariate
-Gaussian kernel around randomly selected samples. First, random samples are 
+Gaussian kernel around randomly selected samples. First, random samples are
 selected from original classes. Then the smoothing kernel distribution
-is computed around the samples: :math:`\hat f(x|y=Y_i) = \sum_i^{n_j} 
-p_i Pr(x|x_i)=\sum_i^{n_j} \frac{1}{n_j} Pr(x|x_i)=\sum_i^{n_j} 
+is computed around the samples: :math:`\hat f(x|y=Y_i) = \sum_i^{n_j}
+p_i Pr(x|x_i)=\sum_i^{n_j} \frac{1}{n_j} Pr(x|x_i)=\sum_i^{n_j}
 \frac{1}{n_j} K_{H_j}(x|x_i)`.
 
 Then new samples are drawn from the computed distribution.
 
-
-
 Mathematical formulation
 ========================
 

examples/applications/porto_seguro_keras_under_sampling.py

@@ -63,7 +63,7 @@ def convert_float64(X):
 ###############################################################################
 # We want to standard scale the numerical features while we want to one-hot
 # encode the categorical features. In this regard, we make use of the
-# :class:`sklearn.compose.ColumnTransformer`.
+# :class:`~sklearn.compose.ColumnTransformer`.
 
 numerical_columns = [name for name in X_train.columns
                      if '_calc_' in name and '_bin' not in name]

examples/plot_outlier_rejections.py

@@ -73,14 +73,14 @@ def plot_scatter(X, y, title):
 plot_scatter(X_test, y_test, 'Testing dataset')
 
 ##############################################################################
-# How to use the :class:`imblearn.FunctionSampler`
+# How to use the :class:`~imblearn.FunctionSampler`
 ##############################################################################
 
 ##############################################################################
 # We first define a function which will use
-# :class:`sklearn.ensemble.IsolationForest` to eliminate some outliers from
+# :class:`~sklearn.ensemble.IsolationForest` to eliminate some outliers from
 # our dataset during training. The function passed to the
-# :class:`imblearn.FunctionSampler` will be called when using the method
+# :class:`~imblearn.FunctionSampler` will be called when using the method
 # ``fit_resample``.
 
 

imblearn/combine/_smote_enn.py

@@ -36,15 +36,15 @@ class SMOTEENN(BaseSampler):
 
     {random_state}
 
-    smote : object, default=None
-        The :class:`imblearn.over_sampling.SMOTE` object to use. If not given,
-        a :class:`imblearn.over_sampling.SMOTE` object with default parameters
+    smote : sampler object, default=None
+        The :class:`~imblearn.over_sampling.SMOTE` object to use. If not given,
+        a :class:`~imblearn.over_sampling.SMOTE` object with default parameters
         will be given.
 
-    enn : object, default=None
-        The :class:`imblearn.under_sampling.EditedNearestNeighbours` object
+    enn : sampler object, default=None
+        The :class:`~imblearn.under_sampling.EditedNearestNeighbours` object
         to use. If not given, a
-        :class:`imblearn.under_sampling.EditedNearestNeighbours` object with
+        :class:`~imblearn.under_sampling.EditedNearestNeighbours` object with
         sampling strategy='all' will be given.
 
     {n_jobs}

imblearn/combine/_smote_tomek.py

@@ -37,14 +37,14 @@ class SMOTETomek(BaseSampler):
 
     {random_state}
 
-    smote : object, default=None
-        The :class:`imblearn.over_sampling.SMOTE` object to use. If not given,
-        a :class:`imblearn.over_sampling.SMOTE` object with default parameters
+    smote : sampler object, default=None
+        The :class:`~imblearn.over_sampling.SMOTE` object to use. If not given,
+        a :class:`~imblearn.over_sampling.SMOTE` object with default parameters
         will be given.
 
-    tomek : object, default=None
-        The :class:`imblearn.under_sampling.TomekLinks` object to use. If not
-        given, a :class:`imblearn.under_sampling.TomekLinks` object with
+    tomek : sampler object, default=None
+        The :class:`~imblearn.under_sampling.TomekLinks` object to use. If not
+        given, a :class:`~imblearn.under_sampling.TomekLinks` object with
         sampling strategy='all' will be given.
 
     {n_jobs}

imblearn/datasets/_imbalance.py

@@ -26,13 +26,13 @@ def make_imbalance(
 
     Parameters
     ----------
-    X : {array-like, dataframe}, shape (n_samples, n_features)
+    X : {array-like, dataframe} of shape (n_samples, n_features)
         Matrix containing the data to be imbalanced.
 
-    y : ndarray, shape (n_samples, )
+    y : ndarray of shape (n_samples,)
         Corresponding label for each sample in X.
 
-    sampling_strategy : dict, or callable,
+    sampling_strategy : dict or callable,
         Ratio to use for resampling the data set.
 
         - When ``dict``, the keys correspond to the targeted classes. The
@@ -43,25 +43,25 @@ def make_imbalance(
           correspond to the targeted classes. The values correspond to the
           desired number of samples for each class.
 
-    random_state : int, RandomState instance or None, optional (default=None)
+    random_state : int, RandomState instance or None, 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 : bool, optional (default=False)
+    verbose : bool, default=False
         Show information regarding the sampling.
 
-    kwargs : dict, optional
+    kwargs : dict
         Dictionary of additional keyword arguments to pass to
         ``sampling_strategy``.
 
     Returns
     -------
-    X_resampled : {ndarray, dataframe}, shape (n_samples_new, n_features)
+    X_resampled : {ndarray, dataframe} of shape (n_samples_new, n_features)
         The array containing the imbalanced data.
 
-    y_resampled : ndarray, shape (n_samples_new)
+    y_resampled : ndarray of shape (n_samples_new)
         The corresponding label of `X_resampled`
 
     Notes
@@ -86,7 +86,6 @@ def make_imbalance(
     ...                               random_state=42)
     >>> print('Distribution after imbalancing: {}'.format(Counter(y_res)))
     Distribution after imbalancing: Counter({2: 30, 1: 20, 0: 10})
-
     """
     target_stats = Counter(y)
     # restrict ratio to be a dict or a callable

imblearn/datasets/_zenodo.py

@@ -117,42 +117,42 @@ def fetch_datasets(
 
     Parameters
     ----------
-    data_home : string, optional (default=None)
+    data_home : str, default=None
         Specify another download and cache folder for the datasets. By default
         all scikit-learn data is stored in '~/scikit_learn_data' subfolders.
 
-    filter_data : tuple of str/int or None, optional (default=None)
+    filter_data : tuple of str/int, default=None
         A tuple containing the ID or the name of the datasets to be returned.
         Refer to the above table to get the ID and name of the datasets.
 
-    download_if_missing : boolean, optional (default=True)
+    download_if_missing : bool, default=True
         If False, raise a IOError if the data is not locally available
         instead of trying to download the data from the source site.
 
-    random_state : int, RandomState instance or None, optional (default=None)
+    random_state : int, RandomState instance or None, default=None
         Random state for shuffling the dataset.
         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`.
 
-    shuffle : bool, optional (default=False)
+    shuffle : bool, default=False
         Whether to shuffle dataset.
 
-    verbose : bool, optional (default=False)
+    verbose : bool, default=False
         Show information regarding the fetching.
 
     Returns
     -------
     datasets : OrderedDict of Bunch object,
         The ordered is defined by ``filter_data``. Each Bunch object ---
-        refered as dataset --- have the following attributes:
+        referred as dataset --- have the following attributes:
 
-    dataset.data : ndarray, shape (n_samples, n_features)
+    dataset.data : ndarray of shape (n_samples, n_features)
 
-    dataset.target : ndarray, shape (n_samples, )
+    dataset.target : ndarray of shape (n_samples,)
 
-    dataset.DESCR : string
+    dataset.DESCR : str
         Description of the each dataset.
 
     Notes

imblearn/ensemble/_bagging.py

@@ -37,7 +37,7 @@ class BalancedBaggingClassifier(BaggingClassifier):
 
     Parameters
     ----------
-    base_estimator : object, default=None
+    base_estimator : estimator object, default=None
         The base estimator to fit on random subsets of the dataset.
         If None, then the base estimator is a decision tree.
 
@@ -130,7 +130,7 @@ class BalancedBaggingClassifier(BaggingClassifier):
     Notes
     -----
     This is possible to turn this classifier into a balanced random forest [5]_
-    by passing a :class:`sklearn.tree.DecisionTreeClassifier` with
+    by passing a :class:`~sklearn.tree.DecisionTreeClassifier` with
     `max_features='auto'` as a base estimator.
 
     See
@@ -157,7 +157,6 @@ class BalancedBaggingClassifier(BaggingClassifier):
 
     Examples
     --------
-
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from sklearn.model_selection import train_test_split

imblearn/ensemble/_easy_ensemble.py

@@ -42,7 +42,7 @@ class EasyEnsembleClassifier(BaggingClassifier):
     n_estimators : int, default=10
         Number of AdaBoost learners in the ensemble.
 
-    base_estimator : object, default=AdaBoostClassifier()
+    base_estimator : estimator object, default=AdaBoostClassifier()
         The base AdaBoost classifier used in the inner ensemble. Note that you
         can set the number of inner learner by passing your own instance.
 
@@ -60,7 +60,7 @@ class EasyEnsembleClassifier(BaggingClassifier):
 
     {random_state}
 
-    verbose : int, optional (default=0)
+    verbose : int, default=0
         Controls the verbosity of the building process.
 
     Attributes
@@ -103,7 +103,6 @@ class EasyEnsembleClassifier(BaggingClassifier):
 
     Examples
     --------
-
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from sklearn.model_selection import train_test_split

imblearn/ensemble/_forest.py

@@ -91,7 +91,7 @@ class BalancedRandomForestClassifier(RandomForestClassifier):
     n_estimators : int, default=100
         The number of trees in the forest.
 
-    criterion : str, default="gini"
+    criterion : {"gini", "entropy"}, default="gini"
         The function to measure the quality of a split. Supported criteria are
         "gini" for the Gini impurity and "entropy" for the information gain.
         Note: this parameter is tree-specific.
@@ -101,15 +101,15 @@ class BalancedRandomForestClassifier(RandomForestClassifier):
         all leaves are pure or until all leaves contain less than
         min_samples_split samples.
 
-    min_samples_split : int, float, default=2
+    min_samples_split : int or float, default=2
         The minimum number of samples required to split an internal node:
 
         - If int, then consider `min_samples_split` as the minimum number.
         - If float, then `min_samples_split` is a percentage and
           `ceil(min_samples_split * n_samples)` are the minimum
           number of samples for each split.
 
-    min_samples_leaf : int, float, default=1
+    min_samples_leaf : int or float, default=1
         The minimum number of samples required to be at a leaf node:
 
         - If int, then consider ``min_samples_leaf`` as the minimum number.

imblearn/ensemble/_weight_boosting.py

@@ -29,7 +29,7 @@ class RUSBoostClassifier(AdaBoostClassifier):
 
     Parameters
     ----------
-    base_estimator : object, default=None
+    base_estimator : estimator object, default=None
         The base estimator from which the boosted ensemble is built.
         Support for sample weighting is required, as well as proper
         ``classes_`` and ``n_classes_`` attributes. If ``None``, then