load_data_for_year_hdf5.py

import h5py

def load_data_for_year(year) -> pd.DataFrame:
    if year > 2016:
        filename = f'GFED4.1s_{year}_beta.hdf5'
    else:
        filename = f'GFED4.1s_{year}.hdf5'
    filepath = os.path.join(data_dir, filename)
    data = h5py.File(filepath, 'r')
    df = pd.DataFrame({
        'lat': data['lat'][:].flatten(),
        'lon': data['lon'][:].flatten(), 
    })
    keys = ['burned_area/{:02}/burned_fraction',
           'emissions/{:02}/DM',
           'emissions/{:02}/C',
           'emissions/{:02}/small_fire_fraction',
           'biosphere/{:02}/NPP',
           'biosphere/{:02}/Rh',
           'biosphere/{:02}/BB']
    for month in range(1,13):
        for key in keys:
            key_str = key.format(month)
            df[key_str] = data[key_str][:].flatten()
    df = filter_to_west_us_region(df)
    return df