search

ECMWFCode4Earth / ml_drought

Machine learning to better predict and understand drought. Moving github.com/ml-clim
https://ml-clim.github.io/drought-prediction/
89 stars 18 forks source link

exporters/split s5 by year #129

Closed tommylees112 closed 3 years ago

tommylees112 commented 4 years ago

Update the s5 exporter to download PER YEAR rather than splitting up by month (groups API calls into more reasonable sizes ...

Also update the s5 preprocessors to:

            # select first 25 ensemble members (complete dataset)
            ds = self.select_n_ensemble_members(ds, n=25)

            # calculate mean/std over 'number'
            ds = self.get_variance_and_mean_over_number(ds)

            # calculate n_timestep ahead variables
            ds = self.create_variables_for_n_timesteps_predictions(ds)