"""Class to perform under-sampling using easy ensemble."""
# Authors: Guillaume Lemaitre <g.lemaitre58@gmail.com>
# Christos Aridas
# License: MIT
import numpy as np
from sklearn.utils import check_random_state
from .base import BaseEnsembleSampler
from ..under_sampling import RandomUnderSampler
MAX_INT = np.iinfo(np.int32).max
[docs]class EasyEnsemble(BaseEnsembleSampler):
"""Create an ensemble sets by iteratively applying random under-sampling.
This method iteratively select a random subset and make an ensemble of the
different sets.
Parameters
----------
ratio : str, dict, or callable, optional (default='auto')
Ratio to use for resampling the data set.
- If ``str``, has to be one of: (i) ``'minority'``: resample the
minority class; (ii) ``'majority'``: resample the majority class,
(iii) ``'not minority'``: resample all classes apart of the minority
class, (iv) ``'all'``: resample all classes, and (v) ``'auto'``:
correspond to ``'all'`` with for over-sampling methods and ``'not
minority'`` for under-sampling methods. The classes targeted will be
over-sampled or under-sampled to achieve an equal number of sample
with the majority or minority class.
- If ``dict``, the keys correspond to the targeted classes. The values
correspond to the desired number of samples.
- If callable, function taking ``y`` and returns a ``dict``. The keys
correspond to the targeted classes. The values correspond to the
desired number of samples.
return_indices : bool, optional (default=False)
Whether or not to return the indices of the samples randomly
selected from the majority class.
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``.
replacement : bool, optional (default=False)
Whether or not to sample randomly with replacement or not.
n_subsets : int, optional (default=10)
Number of subsets to generate.
Notes
-----
The method is described in [1]_.
Supports mutli-class resampling.
Examples
--------
>>> from collections import Counter
>>> from sklearn.datasets import make_classification
>>> from imblearn.ensemble import \
EasyEnsemble # doctest: +NORMALIZE_WHITESPACE
>>> X, y = make_classification(n_classes=2, class_sep=2,
... weights=[0.1, 0.9], n_informative=3, n_redundant=1, flip_y=0,
... n_features=20, n_clusters_per_class=1, n_samples=1000, random_state=10)
>>> print('Original dataset shape {}'.format(Counter(y)))
Original dataset shape Counter({1: 900, 0: 100})
>>> ee = EasyEnsemble(random_state=42)
>>> X_res, y_res = ee.fit_sample(X, y)
>>> print('Resampled dataset shape {}'.format(Counter(y_res[0])))
Resampled dataset shape Counter({0: 100, 1: 100})
References
----------
.. [1] X. Y. Liu, J. Wu and Z. H. Zhou, "Exploratory Undersampling for
Class-Imbalance Learning," in IEEE Transactions on Systems, Man, and
Cybernetics, Part B (Cybernetics), vol. 39, no. 2, pp. 539-550,
April 2009.
"""
[docs] def __init__(self,
ratio='auto',
return_indices=False,
random_state=None,
replacement=False,
n_subsets=10):
super(EasyEnsemble, self).__init__(ratio=ratio,
random_state=random_state)
self.return_indices = return_indices
self.replacement = replacement
self.n_subsets = n_subsets
def _sample(self, X, y):
"""Resample the dataset.
Parameters
----------
X : ndarray, shape (n_samples, n_features)
Matrix containing the data which have to be sampled.
y : ndarray, shape (n_samples, )
Corresponding label for each sample in X.
Returns
-------
X_resampled : ndarray, shape (n_subset, n_samples_new, n_features)
The array containing the resampled data.
y_resampled : ndarray, shape (n_subset, n_samples_new)
The corresponding label of `X_resampled`
idx_under : ndarray, shape (n_subset, n_samples, )
If `return_indices` is `True`, a boolean array will be returned
containing the which samples have been selected.
"""
random_state = check_random_state(self.random_state)
X_resampled = []
y_resampled = []
if self.return_indices:
idx_under = []
for _ in range(self.n_subsets):
rus = RandomUnderSampler(
ratio=self.ratio_, return_indices=True,
random_state=random_state.randint(MAX_INT),
replacement=self.replacement)
sel_x, sel_y, sel_idx = rus.fit_sample(X, y)
X_resampled.append(sel_x)
y_resampled.append(sel_y)
if self.return_indices:
idx_under.append(sel_idx)
if self.return_indices:
return (np.array(X_resampled), np.array(y_resampled),
np.array(idx_under))
else:
return np.array(X_resampled), np.array(y_resampled)