LinAlgError: singular matrix
js185529 opened this issue · 3 comments
Just trying to simply pass the dataframe into create_report() and receive this error
LinAlgError: singular matrix
C:...\Python\Python39\site-packages\scipy\stats\stats.py:4812: RuntimeWarning: overflow encountered in longlong_scalars
(2 * xtie * ytie) / m + x0 * y0 / (9 * m * (size - 2)))
C:...\Python\Python39\site-packages\scipy\stats\stats.py:4814: RuntimeWarning: invalid value encountered in sqrt
np.sqrt(var) / np.sqrt(2)))
Pretty big dataset of features. If I knew the column, I could deal with it (but it is a 170 or so columns so I imagine it's not just 1 column). I read this was potentially fixed on later versions? I'm using the latest version 0.4.3
Hi @js185529 , not sure how the error happens. Is it possible to share with us a dataset that can reproduce the error so I can take a look?
Sure. When I run it on a sample of the data, it works, when I try to run on the full dataset, I get that error. Let me work out the sample that raises the error (and anonymize the data) and I will share.
@jinglinpeng , here is a dataset where I get the error. https://www.dropbox.com/s/ea1cii2ihqzujyi/sample.csv?dl=0