"""Class to perform random under-sampling."""
# Authors: Guillaume Lemaitre <g.lemaitre58@gmail.com>
# Christos Aridas
# License: MIT
from __future__ import division
import numpy as np
from sklearn.utils import check_array
from sklearn.utils import check_consistent_length
from sklearn.utils import check_random_state
from sklearn.utils import safe_indexing
from ..base import BaseUnderSampler
from ...utils import check_target_type
from ...utils import Substitution
from ...utils.deprecation import deprecate_parameter
from ...utils._docstring import _random_state_docstring
[docs]@Substitution(
sampling_strategy=BaseUnderSampler._sampling_strategy_docstring,
random_state=_random_state_docstring)
class RandomUnderSampler(BaseUnderSampler):
"""Class to perform random under-sampling.
Under-sample the majority class(es) by randomly picking samples
with or without replacement.
Read more in the :ref:`User Guide <controlled_under_sampling>`.
Parameters
----------
{sampling_strategy}
return_indices : bool, optional (default=False)
Whether or not to return the indices of the samples randomly selected.
.. deprecated:: 0.4
``return_indices`` is deprecated. Use the attribute
``sample_indices_`` instead.
{random_state}
replacement : boolean, optional (default=False)
Whether the sample is with or without replacement.
ratio : str, dict, or callable
.. deprecated:: 0.4
Use the parameter ``sampling_strategy`` instead. It will be removed
in 0.6.
Attributes
----------
sample_indices_ : ndarray, shape (n_new_samples)
Indices of the samples selected.
.. versionadded:: 0.4
``sample_indices_`` used instead of ``return_indices=True``.
Notes
-----
Supports multi-class resampling by sampling each class independently.
Supports heterogeneous data as object array containing string and numeric
data.
Examples
--------
>>> from collections import Counter
>>> from sklearn.datasets import make_classification
>>> from imblearn.under_sampling import \
RandomUnderSampler # 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 %s' % Counter(y))
Original dataset shape Counter({{1: 900, 0: 100}})
>>> rus = RandomUnderSampler(random_state=42)
>>> X_res, y_res = rus.fit_resample(X, y)
>>> print('Resampled dataset shape %s' % Counter(y_res))
Resampled dataset shape Counter({{0: 100, 1: 100}})
"""
[docs] def __init__(self,
sampling_strategy='auto',
return_indices=False,
random_state=None,
replacement=False,
ratio=None):
super(RandomUnderSampler, self).__init__(
sampling_strategy=sampling_strategy, ratio=ratio)
self.random_state = random_state
self.return_indices = return_indices
self.replacement = replacement
@staticmethod
def _check_X_y(X, y):
y, binarize_y = check_target_type(y, indicate_one_vs_all=True)
X = check_array(X, accept_sparse=['csr', 'csc'], dtype=None)
y = check_array(y, accept_sparse=['csr', 'csc'], dtype=None,
ensure_2d=False)
check_consistent_length(X, y)
return X, y, binarize_y
def _fit_resample(self, X, y):
if self.return_indices:
deprecate_parameter(self, '0.4', 'return_indices',
'sample_indices_')
random_state = check_random_state(self.random_state)
idx_under = np.empty((0, ), dtype=int)
for target_class in np.unique(y):
if target_class in self.sampling_strategy_.keys():
n_samples = self.sampling_strategy_[target_class]
index_target_class = random_state.choice(
range(np.count_nonzero(y == target_class)),
size=n_samples,
replace=self.replacement)
else:
index_target_class = slice(None)
idx_under = np.concatenate(
(idx_under,
np.flatnonzero(y == target_class)[index_target_class]),
axis=0)
self.sample_indices_ = idx_under
if self.return_indices:
return (safe_indexing(X, idx_under), safe_indexing(y, idx_under),
idx_under)
return safe_indexing(X, idx_under), safe_indexing(y, idx_under)