参考:https://www.zhihu.com/question/270451437/answer/405814593
https://www.cnpython.com/qa/38203
import numpy as np
import scipy as sp
a = [1, 1, 2, 3, 4]
b = [2, 2, 3, 2, 1]
c = [4, 6, 7, 8, 9]
d = [4, 3, 4, 5, 4]
ck = np.column_stack([a, b, c, d])
cc = sp.corrcoef(ck, rowvar=False)
VIF = np.linalg.inv(cc)
VIF.diagonal()
from statsmodels.stats.outliers_influence import variance_inflation_factor
from statsmodels.tools.tools import add_constant
df = pd.DataFrame(
{'a': [1, 1, 2, 3, 4],
'b': [2, 2, 3, 2, 1],
'c': [4, 6, 7, 8, 9],
'd': [4, 3, 4, 5, 4]}
)
X = add_constant(df)
>>> pd.Series([variance_inflation_factor(X.values, i)
for i in range(X.shape[1])],