Suppose I have a set of feature columns that I select to check for correlations with the target feature 'is_Star'; which is of binary values and the former consists of numeric values
Why do i end up getting an array of NAN values? Also, I have accounted for missing values, if any.
from sklearn.feature_selection import f_classif
X = star_data.drop(['class', 'is_Star'], axis=1)
y = star_data['is_Star']
anova = f_classif(X, y)
anova
The output given is as below
(array([nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]),
array([nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]))
