У меня проблемы с использованием StratifiedShuffleSplit из sklearn для некоторых данных с несколькими метками.Следующий автономный пример лучше всего объясняет проблему:
import numpy as np
from sklearn.model_selection import StratifiedShuffleSplit
# Generate some data
np.random.seed(0)
n_samples = 10
n_features = 40
n_labels = 20
x = np.random.rand(n_samples, n_features)
y = np.zeros((n_samples, n_labels))
for col in range(n_labels):
n_instances = np.random.randint(5)
indices = np.random.permutation(n_samples)[:n_instances]
y[indices,col] = 1
print('Features training set shape:', x.shape)
print('Labels from training set shape:', y.shape)
print('Are there any labels with fewer than two instances?', np.any(y.sum(axis=0) < 2), '\n')
print(y, '\n')
# Remove labels which are represented fewer than two times in the training set,
# since this messes with StratifiedShuffleSplit below.
label_indices_rm = np.where(y.sum(axis=0) < 2)[0]
y = np.delete(y, label_indices_rm, axis=1)
print(len(label_indices_rm), ' labels had fewer than two instances and were removed.')
print('Features from training set shape:', x.shape)
print('Labels from training set shape:', y.shape)
print('Are there any labels with fewer than two instances?', np.any(y.sum(axis=0) < 2), '\n')
print(y, '\n')
sss = StratifiedShuffleSplit(n_splits=1, train_size=0.5)
indices,_ = sss.split(x, y) # gives the training indices
Это дает следующий вывод:
Features from training set shape: (10, 40)
Labels from training set shape: (10, 20)
Are there any labels with fewer than two instances? True
[[0. 1. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 1. 1.]
[0. 1. 0. 0. 0. 0. 1. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 1. 0.]
[0. 0. 1. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 0. 1. 1. 1. 0. 0. 0. 0. 0.]
[0. 0. 1. 1. 0. 0. 1. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 1. 0. 0.]
[0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 1. 1. 0. 1. 0. 0. 0. 0. 1. 0.]
[0. 0. 0. 1. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0.]
[1. 0. 1. 0. 0. 0. 0. 0. 0. 1. 1. 1. 0. 1. 0. 0. 0. 1. 0. 0.]
[0. 0. 0. 0. 0. 0. 1. 0. 0. 1. 0. 0. 1. 0. 0. 0. 0. 1. 0. 0.]
[0. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 0. 1. 1. 0. 0. 0. 0. 0.]]
7 labels had fewer than two instances and were removed.
Features from training set shape: (10, 40)
Labels from training set shape: (10, 13)
Are there any labels with fewer than two instances? False
[[1. 1. 0. 0. 0. 0. 0. 0. 0. 0. 1. 0. 1.]
[1. 0. 0. 1. 0. 1. 0. 0. 0. 0. 0. 1. 1.]
[0. 1. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 1. 0. 1. 1. 1. 0. 0.]
[0. 1. 1. 1. 0. 0. 0. 1. 0. 0. 0. 1. 0.]
[1. 0. 0. 0. 0. 1. 1. 1. 0. 1. 0. 0. 1.]
[0. 0. 1. 0. 1. 0. 0. 0. 0. 0. 1. 0. 0.]
[0. 1. 0. 0. 0. 1. 1. 1. 0. 1. 0. 1. 0.]
[0. 0. 0. 1. 0. 1. 0. 0. 1. 0. 0. 1. 0.]
[0. 0. 1. 0. 0. 0. 0. 1. 0. 1. 1. 0. 0.]]
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-45-a490e96dd0e0> in <module>()
32
33 sss = StratifiedShuffleSplit(n_splits=1, train_size=0.5)
---> 34 indices,_ = sss.split(x, y) # gives the training indices
~/miniconda3/lib/python3.6/site-packages/sklearn/model_selection/_split.py in split(self, X, y, groups)
1202 """
1203 X, y, groups = indexable(X, y, groups)
-> 1204 for train, test in self._iter_indices(X, y, groups):
1205 yield train, test
1206
~/miniconda3/lib/python3.6/site-packages/sklearn/model_selection/_split.py in _iter_indices(self, X, y, groups)
1544 class_counts = np.bincount(y_indices)
1545 if np.min(class_counts) < 2:
-> 1546 raise ValueError("The least populated class in y has only 1"
1547 " member, which is too few. The minimum"
1548 " number of groups for any class cannot"
ValueError: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2.
Я убедился, что нет меток, которые представлены только менее чем двумяраз.Почему я все еще получаю эту ошибку?