New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[MOMM] add weighting to calculation #298
Comments
Add in optional coverage_threshold to calculate MOMM. |
Hi @BiancaMorandi , I have gone through your pull request #384 and have the below comments. I also made some small edits mostly to the doc strings and pushed.
|
@stephenholleran you can find below answers to your questions:
|
@stephenholleran we had an internal discussion today and agreed to include the input |
@stephenholleran I have updated the results may be incorrect when you use an insufficient data coverage threshold, i.e. below our recommended value of 0.8. Some months may have very little data coverage and so may skew the statistics. |
Hi @BiancaMorandi, Running the I updated the doc string text but I think it is still not good. Not sure what to do with it though. It is probably as good as we can make it. Can you add an example in the docstring to cover the situation when the seasonal adj is True and the user needs to set the coverage threshold to 0 for it not to take effect? |
@stephenholleran Yes, I understand that this behaviour might be confusing but this is the only way to not create a breaking change for I have added an example in the docstring to cover the situation when the seasonal adj is True and the user needs to set the coverage threshold to 0 for it not to take effect. This case was already part of tests. |
Once the mean of January is calculated from all 10-min timestamps that occur in January's, then this is given a weighting of 31 days when averaging all 12 months.
If only half of January is available it is still given a 31 day weighting.
If no data available for a month then return an error. It is not appropriate to calculate a MOMM where a timeseries mean is more appropriate. Even if you have 2 years of data but just so happen to be missing all data for January it still returns nothing.
Should return the coverage of all the months to show the wind analyst if a month has minimal coverage and therefore be cautious of the result.
The text was updated successfully, but these errors were encountered: