def update_time_in_NetCDF2save(ds, convert_time2dt=False):
"""
Update time of monthly output to be in NetCDF saveable format
Parameters
-------
convert_time2dt (bool): convert the time into a datetime.datetime format
"""
# Climate model time
sdate = datetime.datetime(1985, 1, 1)
# Convert / setup time dim?
if convert_time2dt:
months = np.arange(1, 13)
ds['time'] = [AC.add_months(sdate, i - 1) for i in months]
# Update to hours since X
hours = [(AC.dt64_2_dt([i])[0] - sdate).days * 24.
for i in ds['time'].values]
ds['time'] = hours
attrs_dict = {'units': 'hours since 1985-01-01 00:00:00'}
ds['time'].attrs = attrs_dict
return ds
def mk_NetCDF_from_productivity_data():
"""
Convert productivity .csv file (Behrenfeld and Falkowski, 1997) into a NetCDF file
"""
# Location of data (update to use public facing host)
folder = utils.get_file_locations('data_root') + '/Productivity/'
# Which file to use?
filename = 'productivity_behrenfeld_and_falkowski_1997_extrapolated.csv'
# Setup coordinates
lon = np.arange(-180, 180, 1/6.)
lat = np.arange(-90, 90, 1/6.)
lat = np.append(lat, [90])
# Setup time
varname = 'vgpm'
months = np.arange(1, 13)
# Extract data
df = pd.read_csv(folder+filename, header=None)
print(df.shape)
# Extract data by month
da_l = []
for n in range(12):
# Assume the data is in blocks by longitude?
arr = df.values[:, n*1081: (n+1)*1081].T[None, ...]
print(arr.shape)
da_l += [xr.Dataset(
data_vars={varname: (['time', 'lat', 'lon', ], arr)},
coords={'lat': lat, 'lon': lon, 'time': [n]})]
# Concatenate to data xr.Dataset
ds = xr.concat(da_l, dim='time')
# Update time ...
sdate = datetime.datetime(1985, 1, 1) # Climate model tiem
ds['time'] = [AC.add_months(sdate, i-1) for i in months]
# Update to hours since X
hours = [(AC.dt64_2_dt([i])[0] - sdate).days *
24. for i in ds['time'].values]
ds['time'] = hours
# Add units
attrs_dict = {'units': 'hours since 1985-01-01 00:00:00'}
ds['time'].attrs = attrs_dict
# Add attributes for variable
attrs_dict = {
'long_name': "net primary production",
'units': "mg C / m**2 / day",
}
ds[varname].attrs = attrs_dict
# For latitude...
attrs_dict = {
'long_name': "latitude",
'units': "degrees_north",
"standard_name": "latitude",
"axis": "Y",
}
ds['lat'].attrs = attrs_dict
# And longitude...
attrs_dict = {
'long_name': "longitude",
'units': "degrees_east",
"standard_name": "longitude",
"axis": "X",
}
ds['lon'].attrs = attrs_dict
# Add extra global attributes
global_attribute_dictionary = {
'Title': 'Sea-surface productivity (Behrenfeld and Falkowski, 1997)',
'Author': 'Tomas Sherwen ([email protected])',
'Notes': "Data extracted from OCRA and extrapolated to poles by Martin Wadley. NetCDF contructed using xarray (xarray.pydata.org) by Tomas Sherwen. \n NOTES from oringal site (http://orca.science.oregonstate.edu/) from 'based on the standard vgpm algorithm. npp is based on the standard vgpm, using modis chl, sst4, and par as input; clouds have been filled in the input data using our own gap-filling software. For citation, please reference the original vgpm paper by Behrenfeld and Falkowski, 1997a as well as the Ocean Productivity site for the data.' ",
'History': 'Last Modified on:' + strftime("%B %d %Y", gmtime()),
'Conventions': "COARDS",
}
ds.attrs = global_attribute_dictionary
# Save to NetCDF
filename = 'productivity_behrenfeld_and_falkowski_1997_extrapolated.nc'
ds.to_netcdf(filename, unlimited_dims={'time': True})