spent a solid 1/2 day trying to figure out why my structural model was giving me garbage output, eventually reverted to good ol ((X'X)^-1)X'y and lo! coherence
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I got to use Matlab as my main at my first job, it was dreamy
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I just use statsmodels out of habit. You can also do the linalg directly yourself for something so simple. Other sklearn linear models I've used have always worked fine for me as well.
-
Doing it myself was what led me to see the problem Like How do you fuck up ((X'X)^-1)X'y In your release In a stats module
End of conversation
New conversation -
-
-
wait, what? what's wrong with it?
-
garbage coefficient output will send you code snippet when coherent
-
oh yea, never understood the way sklearn did linreg... always used statsmodels instead.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.