iter

Author: glemaitre

imblearn/base.py

@@ -140,6 +140,13 @@ def _identity(X, y):
     return X, y
 
 
+def is_sampler(estimator):
+    """Return True if the given estimator is a sampler, False otherwise."""
+    if estimator._estimator_type == "sampler":
+        return True
+    return False
+
+
 class FunctionSampler(BaseSampler):
     """Construct a sampler from calling an arbitrary callable.
 
@@ -166,9 +173,20 @@ class FunctionSampler(BaseSampler):
 
         .. versionadded:: 0.6
 
+    Attributes
+    ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
-
     sklearn.preprocessing.FunctionTransfomer : Stateless transformer.
 
     Notes

imblearn/combine/_smote_enn.py

@@ -49,6 +49,25 @@ class SMOTEENN(BaseSampler):
 
     {n_jobs}
 
+    Attributes
+    ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
+    smote_ : sampler object
+        The validated :class:`~imblearn.over_sampling.SMOTE` instance.
+
+    enn_ : sampler object
+        The validated :class:`~imblearn.under_sampling.EditedNearestNeighbours`
+        instance.
+
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     SMOTETomek : Over-sample using SMOTE followed by under-sampling removing

imblearn/combine/_smote_tomek.py

@@ -49,6 +49,24 @@ class SMOTETomek(BaseSampler):
 
     {n_jobs}
 
+    Attributes
+    ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
+    smote_ : sampler object
+        The validated :class:`~imblearn.over_sampling.SMOTE` instance.
+
+    tomek_ : sampler object
+        The validated :class:`~imblearn.under_sampling.TomekLinks` instance.
+
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     SMOTEENN : Over-sample using SMOTE followed by under-sampling using Edited

imblearn/ensemble/_bagging.py

@@ -111,6 +111,9 @@ class BalancedBaggingClassifier(BaggingClassifier):
     estimators_ : list of estimators
         The collection of fitted base estimators.
 
+    sampler_ : sampler object
+        The validate sampler created from the `sampler` parameter.
+
     estimators_samples_ : list of ndarray
         The subset of drawn samples (i.e., the in-bag samples) for each base
         estimator. Each subset is defined by a boolean mask.
@@ -133,6 +136,11 @@ class BalancedBaggingClassifier(BaggingClassifier):
         was never left out during the bootstrap. In this case,
         ``oob_decision_function_`` might contain NaN.
 
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     BalancedRandomForestClassifier : Random forest applying random-under

imblearn/ensemble/_easy_ensemble.py

@@ -73,12 +73,23 @@ class EasyEnsembleClassifier(BaggingClassifier):
     estimators_ : list of estimators
         The collection of fitted base estimators.
 
+    estimators_samples_ : list of arrays
+        The subset of drawn samples for each base estimator.
+
+    estimators_features_ : list of arrays
+        The subset of drawn features for each base estimator.
+
     classes_ : array, shape (n_classes,)
         The classes labels.
 
     n_classes_ : int or list
         The number of classes.
 
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     BalancedBaggingClassifier : Bagging classifier for which each base

imblearn/ensemble/_forest.py

@@ -230,10 +230,17 @@ class BalancedRandomForestClassifier(RandomForestClassifier):
 
     Attributes
     ----------
-    estimators_ : list of DecisionTreeClassifier
+    base_estimator_ : :class:`~sklearn.tree.DecisionTreeClassifier` instance
+        The child estimator template used to create the collection of fitted
+        sub-estimators.
+
+    estimators_ : list of :class:`~sklearn.tree.DecisionTreeClassifier`
         The collection of fitted sub-estimators.
 
-    samplers_ : list of RandomUnderSampler
+    base_sampler_ : :class:`~imblearn.under_sampling.RandomUnderSampler`
+        The base sampler used to construct the subsequent list of samplers.
+
+    samplers_ : list of :class:`~imblearn.under_sampling.RandomUnderSampler`
         The collection of fitted samplers.
 
     pipelines_ : list of Pipeline.
@@ -250,6 +257,11 @@ class labels (multi-output problem).
     n_features_ : int
         The number of features when ``fit`` is performed.
 
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     n_outputs_ : int
         The number of outputs when ``fit`` is performed.
 
@@ -628,7 +640,7 @@ def _set_oob_score(self, X, y):
     @property
     def n_features_(self):
         """Number of features when fitting the estimator."""
-        return getattr(self.n_features_in_, self._n_features)
+        return getattr(self.n_features_in_, "n_features_", self._n_features)
 
     def _more_tags(self):
         return {

imblearn/ensemble/_weight_boosting.py

@@ -68,7 +68,10 @@ class RUSBoostClassifier(AdaBoostClassifier):
     estimators_ : list of classifiers
         The collection of fitted sub-estimators.
 
-    samplers_ : list of RandomUnderSampler
+    base_sampler_ : :class:`~imblearn.under_sampling.RandomUnderSampler`
+        The base sampler used to generate the subsequent samplers.
+
+    samplers_ : list of :class:`~imblearn.under_sampling.RandomUnderSampler`
         The collection of fitted samplers.
 
     pipelines_ : list of Pipeline
@@ -90,6 +93,11 @@ class RUSBoostClassifier(AdaBoostClassifier):
     feature_importances_ : ndarray of shape (n_features,)
         The feature importances if supported by the ``base_estimator``.
 
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     BalancedBaggingClassifier : Bagging classifier for which each base

imblearn/over_sampling/_adasyn.py

@@ -46,6 +46,21 @@ class ADASYN(BaseOverSampler):
 
     {n_jobs}
 
+    Attributes
+    ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
+    nn_ : estimator object
+        Validated K-nearest Neighbours estimator linked to the parameter `n_neighbors`.
+
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     SMOTE : Over-sample using SMOTE.

imblearn/over_sampling/_random_over_sampler.py

@@ -57,6 +57,11 @@ class RandomOverSampler(BaseOverSampler):
 
     Attributes
     ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
     sample_indices_ : ndarray of shape (n_new_samples,)
         Indices of the samples selected.
 
@@ -68,6 +73,11 @@ class RandomOverSampler(BaseOverSampler):
 
         .. versionadded:: 0.8
 
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     BorderlineSMOTE : Over-sample using the borderline-SMOTE variant.

imblearn/over_sampling/_smote/base.py

@@ -231,6 +231,21 @@ class SMOTE(BaseSMOTE):
 
     {n_jobs}
 
+    Attributes
+    ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
+    nn_k_ : estimator object
+        Validated k-nearest neighbours created from the `k_neighbors` parameter.
+
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     SMOTENC : Over-sample using SMOTE for continuous and categorical features.
@@ -628,6 +643,21 @@ class SMOTEN(SMOTE):
 
     {n_jobs}
 
+    Attributes
+    ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
+    nn_k_ : estimator object
+        Validated k-nearest neighbours created from the `k_neighbors` parameter.
+
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     SMOTE : Over-sample using SMOTE.

imblearn/over_sampling/_smote/cluster.py

@@ -69,6 +69,11 @@ class KMeansSMOTE(BaseSMOTE):
 
     Attributes
     ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
     kmeans_estimator_ : estimator
         The fitted clustering method used before to apply SMOTE.
 
@@ -78,6 +83,11 @@ class KMeansSMOTE(BaseSMOTE):
     cluster_balance_threshold_ : float
         The threshold used during ``fit`` for calling a cluster balanced.
 
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     SMOTE : Over-sample using SMOTE.

imblearn/over_sampling/_smote/filter.py

@@ -65,6 +65,24 @@ class BorderlineSMOTE(BaseSMOTE):
         The type of SMOTE algorithm to use one of the following options:
         ``'borderline-1'``, ``'borderline-2'``.
 
+    Attributes
+    ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
+    nn_k_ : estimator object
+        Validated k-nearest neighbours created from the `k_neighbors` parameter.
+
+    nn_m_ : estimator object
+        Validated m-nearest neighbours created from the `m_neighbors` parameter.
+
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     SMOTE : Over-sample using SMOTE.
@@ -264,6 +282,28 @@ class SVMSMOTE(BaseSMOTE):
     out_step : float, default=0.5
         Step size when extrapolating.
 
+    Attributes
+    ----------
+    sampling_strategy_ : dict
+        Dictionary containing the information to sample the dataset. The keys
+        corresponds to the class labels from which to sample and the values
+        are the number of samples to sample.
+
+    nn_k_ : estimator object
+        Validated k-nearest neighbours created from the `k_neighbors` parameter.
+
+    nn_m_ : estimator object
+        Validated m-nearest neighbours created from the `m_neighbors` parameter.
+
+    svm_estimator_ : estimator object
+        The validated SVM classifier used to detect samples from which to
+        generate new synthetic samples.
+
+    n_features_in_ : int
+        Number of features in the input dataset.
+
+        .. versionadded:: 0.9
+
     See Also
     --------
     SMOTE : Over-sample using SMOTE.

imblearn/pipeline.py

@@ -67,6 +67,12 @@ class Pipeline(pipeline.Pipeline):
         Read-only attribute to access any step parameter by user given name.
         Keys are step names and values are steps parameters.
 
+    classes_ : ndarray of shape (n_classes,)
+        The classes labels.
+
+    n_features_in_ : int
+        Number of features seen during first step `fit` method.
+
     See Also
     --------
     make_pipeline : Helper function to make pipeline.