标题说明了一切。我正在呼叫np.linalg.eig并收到此错误消息，但是如果我呼叫np.isnan(X).any()或np.isinf(X).any()这些都将返回False
我用于进行特征分解的类如下：
class LDA():
def __init__(self, n_discriminants=None, centered=False):
self.n_discriminants = n_discriminants
self.centered = centered
def scatter_matrix_col(self, X, y, val):
matrix_col = X[y == val].mean(0)
return matrix_col
def build_scatter_matrix(self, X, y):
y_vals = np.unique(y)
scatter_matrix = np.hstack((self.scatter_matrix_col(X, y, val)[:, np.newaxis] for val in y_vals))
return scatter_matrix
def within_class_matrix(self, X, y):
m_features = X.shape[1]
y_vals = np.unique(y)
S_w = np.zeros((m_features, m_features))
for val in y_vals:
scat_matrix = np.cov(X[y == val].T)
S_w += scat_matrix
return S_w
def between_class_matrix(self, X, y):
col_means = X.mean(0)[:, np.newaxis]
mean_vecs = self.build_scatter_matrix(X, y)
y_vals = np.unique(y)
m_features = X.shape[1]
S_b = np.zeros((m_features, m_features))
for i, val in enumerate(y_vals):
n = np.sum(y == val)
val = mean_vecs[:, i][:, np.newaxis] - col_means
scat_matrix = val @ val.T * n
S_b += scat_matrix
return S_b
def fit(self, X, y):
if self.n_discriminants is None:
self.n_discriminants = X.shape[1]
if self.centered:
X_fit = standardize(X)
else:
X_fit = X
S_b = self.between_class_matrix(X_fit, y)
S_w = self.within_class_matrix(X_fit, y)
inv_Sw = np.linalg.inv(S_w)
eigen_vals, eigen_vecs = np.linalg.eig(inv_Sw @ S_b)
eigen_pairs = [(eigen_vals[i], eigen_vecs[:, i]) for i in range(len(eigen_vals))]
sorted_pairs = sorted(eigen_pairs, key=lambda x: x[0], reverse=True)
self.discriminants_ = np.hstack((sorted_pairs[i][1][:, np.newaxis].real for i in range(self.n_discriminants)))
self.variance_ratios_ = [np.abs(pair[0].real)/np.sum(eigen_vals.real) for pair in sorted_pairs[:self.n_discriminants]]
return self
我在SKLearn中使用了预安装的数据集：
from sklearn.datasets import load_boston
from sklearn.preprocessing import StandardScaler
boston = load_boston()
sc = StandardScaler()
X_std = sc.fit_transform(boston.data)
y = boston.target
LDA的调用方式如下：lda = LDA()
lda.fit(X_std, y)
然后给出以下回溯：
__main__:65: RuntimeWarning: Degrees of freedom <= 0 for slice
C:\Users\Jonat\Anaconda\lib\site-packages\numpy\lib\function_base.py:2326:
RuntimeWarning: divide by zero encountered in true_divide
c *= np.true_divide(1, fact)
C:\Users\Jonat\Anaconda\lib\site-packages\numpy\lib\function_base.py:2326:
RuntimeWarning: invalid value encountered in multiply
c *= np.true_divide(1, fact)
Traceback (most recent call last):
File "<ipython-input-172-1c94e8f13082>", line 1, in <module>
lda.fit(X_std, y)
File "C:/Users/Jonat/OneDrive/Dokumentumok/Python
Scripts/easyml/easyml/algorithms/VarianceReduction/lda.py", line 114, in fit
eigen_vals, eigen_vecs = np.linalg.eig(inv_Sw @ S_b)
File "C:\Users\Jonat\Anaconda\lib\site-packages\numpy\linalg\linalg.py", line 1262, in eig
_assertFinite(a)
File "C:\Users\Jonat\Anaconda\lib\site-packages\numpy\linalg\linalg.py", line 220, in _assertFinite
raise LinAlgError("Array must not contain infs or NaNs")
LinAlgError: Array must not contain infs or NaNs
这个问题以前曾提过，但从来没有警告过，有问题的ndarray没有任何
nan或inf。我不知道这是一个错误，还是它指向我为获取特征值而正在做的事情。
最佳答案
好吧，我意识到自己做错了。
问题是within_class_matrix方法，该方法返回以下回溯：
__main__:65: RuntimeWarning: Degrees of freedom <= 0 for slice
C:\Users\Jonat\Anaconda\lib\site-packages\numpy\lib\function_base.py:2326:
RuntimeWarning: divide by zero encountered in true_divide
c *= np.true_divide(1, fact)
C:\Users\Jonat\Anaconda\lib\site-packages\numpy\lib\function_base.py:2326:
RuntimeWarning: invalid value encountered in multiply
c *= np.true_divide(1, fact)
我认为这里最大的问题是我在回归数据集上使用了
LDA，并且y的不同值数量导致矩阵计算不正确。关于python - LinAlgError:数组不能包含infs或NaN，但不能包含NaN的infs，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/56632418/