UnboundLocalError: local variable 'pool' referenced before assignment

[muthumula19]

lgt = LGT( response_col="Sales", date_col="Date", estimator='stan-mcmc', seasonality=12, seed=8888 ) lgt.fit(df)

When i using it in ipynb file i didn't get any error but when i am using in .py file i getting error as UnboundLocalError: local variable 'pool' referenced before assignment i try to change few things in _map_parallel function but it won't work can you help to achive mcmc

[edwinnglabs]

could you also provide python version and os you are using?

[muthumula19]

i am using Python 3.8.12 and windows 10

[brandoncbryant]

I experienced the same issue on Windows 10, Python 3.9.6, orbit-ml 1.1.1dev0.

Placing the code inside a main() function and using if __name__ == '__main__': main() seemed to work.

[ghost]

How did you format this code so that it would run and work? I am receiving the same error.

[brandoncbryant]

I can't share the code because it's work related, but the format was:

import ...

def main():

    df = ...

    model = LGT(
        response_col=response_col,
        date_col=date_col,
        estimator='stan-mcmc',
        seasonality=52,
    )

    model.fit(df)

if __name__ == '__main__':
    main()

[edwinnglabs]

How did you format this code so that it would run and work? I am receiving the same error.

are you using the version from dev or from pypi ?

[wangzhishi]

The problem happens in jupyter notebook and it's due to the varied behaviors of multiprocessing across different operating systems and python versions.

For solutions, please refer to this thread https://github.com/uber/orbit/issues/520#issuecomment-1077937181.

Also, execute the code via __main__ block might also dodge this issue.