[WIP] Fix a bug in ClusterCentroids when using the hard voting strategy

[lixiilu]

Related Issue: #738

[pep8speaks]

Hello @tangxi1227! Thanks for opening this PR. We checked the lines you've touched for PEP 8 issues, and found:

• In the file imblearn/under_sampling/_prototype_generation/_cluster_centroids.py:

Line 174:89: E501 line too long (110 > 88 characters)

[chkoar]

Thanks for the PR. Please fix the pep8 issue and add a test.

[lixiilu]

file: imbalanced-learn/imblearn/under_sampling/_prototype_generation/_cluster_centroids.py
function : _fit_resample
line: 174

def _fit_resample(self, X, y):
self._validate_estimator()

    if self.voting == "auto":
        if sparse.issparse(X):
            self.voting_ = "hard"
        else:
            self.voting_ = "soft"
    else:
        if self.voting in VOTING_KIND:
            self.voting_ = self.voting
        else:
            raise ValueError(
                "'voting' needs to be one of {}. Got {}"
                " instead.".format(VOTING_KIND, self.voting)
            )

    X_resampled, y_resampled = [], []
    for target_class in np.unique(y):
        if target_class in self.sampling_strategy_.keys():
            n_samples = self.sampling_strategy_[target_class]
            self.estimator_.set_params(**{"n_clusters": n_samples})
            self.estimator_.fit(X[y == target_class])
            X_new, y_new = self._generate_sample(
                X[y == target_class], y[y == target_class], self.estimator_.cluster_centers_, target_class
            )
            X_resampled.append(X_new)
            y_resampled.append(y_new)
        else:
            target_class_indices = np.flatnonzero(y == target_class)
            X_resampled.append(_safe_indexing(X, target_class_indices))
            y_resampled.append(_safe_indexing(y, target_class_indices))

    if sparse.issparse(X):
        X_resampled = sparse.vstack(X_resampled)
    else:
        X_resampled = np.vstack(X_resampled)
    y_resampled = np.hstack(y_resampled)

    return X_resampled, np.array(y_resampled, dtype=y.dtype)

[glemaitre]

A potential test would be to check that there is no minority sample once you resample in the majority part. This could be quite easy to implement. We would also need an entry in what's new since it is affecting end-user.