# path to 7zip if using windows
processor.path_to_7z = r'C:/Program Files/7-Zip/7z.exe'
# download the data; this step will be skipped if this has already been done
# (from the last example) but is necessary to set the metadata
processor.download(bbox, start, end, output, datasets=['GSOD'])
# let's use the processor to aggregate the GSOD data together, including
# tmin, tmax, dewpoint, and wind speed. The GSOD database contains dew point
# and seems to be more complete than GHCND. It doesn't have snow or pan
# evaporation though--this is why they are both included.
tmax = processor.aggregate('GSOD', 'tmax', start, end)
tmin = processor.aggregate('GSOD', 'tmin', start, end)
dewpoint = processor.aggregate('GSOD', 'dewpoint', start, end)
wind = processor.aggregate('GSOD', 'wind', start, end)
# now these time series can be saved for later consistent with the structure
# used by PyHSPF's HSPFModel class (start date, time step in minutes, data)
# this way the data are easy to access later
for n, dataset in zip(('tmax', 'tmin', 'dewpoint', 'wind'),
(tmax, tmin, dewpoint, wind)):
name = '{}/GSOD_aggregated_{}'.format(output, n)
ts = start, 1440, dataset
# dump it in a pickled file to use later
if not os.path.isfile(filename + '.shp'):
print('error: file {} does not exist!'.format(filename))
raise
# make an instance of the ClimateProcessor to fetch the climate data
processor = ClimateProcessor()
# the Penman-Monteith Equation requires temperature, humidity of dewpoint,
# wind speed, and solar radiation, which can be obtained from the processor
processor.download_shapefile(filename, start, end, output, space=0.)
# let's get the daily tmin, tmax, dewpoint, and wind speed from GSOD
tmax = processor.aggregate('GSOD', 'tmax', start, end)
tmin = processor.aggregate('GSOD', 'tmin', start, end)
dewt = processor.aggregate('GSOD', 'dewpoint', start, end)
wind = processor.aggregate('GSOD', 'wind', start, end)
# let's use the hourly METSTAT data from the NSRDB for solar radiation
solar = processor.aggregate('NSRDB', 'metstat', start, end)
# since the solar data are hourly and this example uses daily ET, the time
# series has to be aggregated to an average daily value (use a different
# variable for daily and hourly)
dsolar = [
sum(solar[i:i + 24]) / 24 for i in range(0, 24 * (end - start).days, 24)
]
# path to 7zip if using windows
processor.path_to_7z = r'C:/Program Files/7-Zip/7z.exe'
# download the data; this step will be skipped if this has already been done
# (from the last example); alternatively it will set the metadata
processor.download(bbox, start, end, output, datasets = ['precip3240'])
# aggregate the data -- it's important to keep in mind missing data at many
# of these stations and the high degree of spatial variability associated with
# precipitation. in this example, all the data are aggregating into one series;
# however, it may make sense to aggregate more specifically to capture this
# variability to some degree (lots of papers on this subject).
precip = processor.aggregate('precip3240', 'precip', start, end)
# now these time series can be saved for later consistent with the structure
# used by PyHSPF's HSPFModel class (start date, time step in minutes, data)
# this way the data are easy to access later
name = '{}/precip3240_aggregated_precip'.format(output)
ts = start, 60, precip
# dump it in a pickled file to use later
with open(name, 'wb') as f: pickle.dump(ts, f)
# change the start and end dates for plotting up some hourly results
# (just look at a few months to highlight the concept)
# iterate through the shapefile records and aggregate the timeseries
for i in range(len(sf.records())):
record = sf.record(i)
comid = record[comid_index]
lon = record[lon_index]
lat = record[lat_index]
i = comid, lon, lat
print('aggregating timeseries for comid {} at {}, {}\n'.format(*i))
precipitation = processor.aggregate('precip3240',
'precip',
start,
end,
method='IDWA',
longitude=lon,
latitude=lat)
mean = sum(precipitation) / (end - start).days * 365.25
print('aggregated annual average precipitation: {:.1f} in\n'.format(mean))
# dump the result in PyHSPF timeseries format into a pickle file for later
ts = start, 60, precipitation
# use the unique common identifiers for the files
p = '{}/{}'.format(directory, comid)
lat_index = [f[0] for f in sf.fields].index('CenY') - 1
# iterate through the shapefile records and aggregate the timeseries
for i in range(len(sf.records())):
record = sf.record(i)
comid = record[comid_index]
lon = record[lon_index]
lat = record[lat_index]
i = comid, lon, lat
print('aggregating timeseries for comid {} at {}, {}\n'.format(*i))
precipitation = processor.aggregate('precip3240', 'precip', start, end,
method = 'IDWA', longitude = lon,
latitude = lat)
mean = sum(precipitation) / (end - start).days * 365.25
print('aggregated annual average precipitation: {:.1f} in\n'.format(mean))
# dump the result in PyHSPF timeseries format into a pickle file for later
ts = start, 60, precipitation
# use the unique common identifiers for the files
p = '{}/{}'.format(directory, comid)
with open(p, 'wb') as f: pickle.dump(ts, f)
# path to 7zip if using windows
processor.path_to_7z = r'C:/Program Files/7-Zip/7z.exe'
# download the data; this step will be skipped if this has already been done
# (from the last example) but is necessary to set the metadata
processor.download(bbox, start, end, output, datasets=['GHCND'])
# let's use the processor to aggregate the GHCND data together, including
# tmin, tmax, snowdepth, and snowfall. The GHNCD extraction tool also has
# wind and pan evaporation, but the wind data are sparse and pan evaporation
# isn't needed as an input to HSPF so there is not much reason to aggregate
# those data together.
tmax = processor.aggregate('GHCND', 'tmax', start, end)
tmin = processor.aggregate('GHCND', 'tmin', start, end)
snowdepth = processor.aggregate('GHCND', 'snowdepth', start, end)
snowfall = processor.aggregate('GHCND', 'snowfall', start, end)
# now these time series can be saved for later consistent with the structure
# used by PyHSPF's HSPFModel class (start date, time step in minutes, data)
# this way the data are easy to access later
for n, dataset in zip(('tmax', 'tmin', 'snowdepth', 'snowfall'),
(tmax, tmin, snowdepth, snowfall)):
name = '{}/GHCND_aggregated_{}'.format(output, n)
ts = start, 1440, dataset
# dump it in a pickled file to use later
end = datetime.datetime(2011, 1, 1)
# path to 7zip if using windows
processor.path_to_7z = r'C:/Program Files/7-Zip/7z.exe'
# download the data; this step will be skipped if this has already been done
# (from the last example); alternatively it will set the metadata
processor.download(bbox, start, end, output, datasets=['NSRDB'])
# aggregate the data -- worth noting that prior to 1991 is a separate database
# that corresponds more closely to METSTAT than SUNY; requesting data prior
# to 1991 will give the same values either way.
metstat = processor.aggregate('NSRDB', 'metstat', start, end)
suny = processor.aggregate('NSRDB', 'suny', start, end)
# now these time series can be saved for later consistent with the structure
# used by PyHSPF's HSPFModel class (start date, time step in minutes, data)
# this way the data are easy to access later
for n, dataset in zip(('metstat', 'suny'), (metstat, suny)):
name = '{}/NSRDB_aggregated_{}'.format(output, n)
ts = start, 60, dataset
# dump it in a pickled file to use later
with open(name, 'wb') as f:
pickle.dump(ts, f)
if not os.path.isfile(filename + '.shp'):
print('error: file {} does not exist!'.format(filename))
raise
# make an instance of the ClimateProcessor to fetch the climate data
processor = ClimateProcessor()
# the Penman-Monteith Equation requires temperature, humidity of dewpoint,
# wind speed, and solar radiation, which can be obtained from the processor
processor.download_shapefile(filename, start, end, output, space = 0.)
# let's get the daily tmin, tmax, dewpoint, and wind speed from GSOD
tmax = processor.aggregate('GSOD', 'tmax', start, end)
tmin = processor.aggregate('GSOD', 'tmin', start, end)
dewt = processor.aggregate('GSOD', 'dewpoint', start, end)
wind = processor.aggregate('GSOD', 'wind', start, end)
# let's use the hourly METSTAT data from the NSRDB for solar radiation
solar = processor.aggregate('NSRDB', 'metstat', start, end)
# since the solar data are hourly and this example uses daily ET, the time
# series has to be aggregated to an average daily value
solar = [sum(solar[i:i+24]) / 24 for i in range(0, 24 * (end-start).days, 24)]
# let's parse the GHCND data and see if there are any pan evaporation
# observations (only available from GHCND) to compare with estimated PET
if not os.path.isfile(filename + ".shp"):
print("error: file {} does not exist!".format(filename))
raise
# make an instance of the ClimateProcessor to fetch the climate data
processor = ClimateProcessor()
# the Penman-Monteith Equation requires temperature, humidity of dewpoint,
# wind speed, and solar radiation, which can be obtained from the processor
processor.download_shapefile(filename, start, end, output, space=0.0)
# let's get the daily tmin, tmax, dewpoint, wind speed and solar
tmax = processor.aggregate("GSOD", "tmax", start, end)
tmin = processor.aggregate("GSOD", "tmin", start, end)
dewt = processor.aggregate("GSOD", "dewpoint", start, end)
wind = processor.aggregate("GSOD", "wind", start, end)
solar = processor.aggregate("NSRDB", "metstat", start, end)
# use the ETCalculator to estimate the evapotranspiration time series
calculator = ETCalculator()
# some of the parameters in the Penman-Monteith Equation depend on the
# geographic location so get the average longitude, latitude, and elevation
sf = Reader(filename)
# make a list of the fields for each shape
# path to 7zip if using windows
processor.path_to_7z = r'C:/Program Files/7-Zip/7z.exe'
# download the data; this step will be skipped if this has already been done
# (from the last example) but is necessary to set the metadata
processor.download(bbox, start, end, output, datasets = ['GSOD'])
# let's use the processor to aggregate the GSOD data together, including
# tmin, tmax, dewpoint, and wind speed. The GSOD database contains dew point
# and seems to be more complete than GHCND. It doesn't have snow or pan
# evaporation though--this is why they are both included.
tmax = processor.aggregate('GSOD', 'tmax', start, end)
tmin = processor.aggregate('GSOD', 'tmin', start, end)
dewpoint = processor.aggregate('GSOD', 'dewpoint', start, end)
wind = processor.aggregate('GSOD', 'wind', start, end)
# now these time series can be saved for later consistent with the structure
# used by PyHSPF's HSPFModel class (start date, time step in minutes, data)
# this way the data are easy to access later
for n, dataset in zip(('tmax', 'tmin', 'dewpoint', 'wind'),
(tmax, tmin, dewpoint, wind)):
name = '{}/GSOD_aggregated_{}'.format(output, n)
ts = start, 1440, dataset
# dump it in a pickled file to use later
# path to 7zip if using windows
processor.path_to_7z = r'C:/Program Files/7-Zip/7z.exe'
# download the data; this step will be skipped if this has already been done
# (from the last example) but is necessary to set the metadata
processor.download(bbox, start, end, output, datasets = ['GHCND'])
# let's use the processor to aggregate the GHCND data together, including
# tmin, tmax, snowdepth, and snowfall. The GHNCD extraction tool also has
# wind and pan evaporation, but the wind data are sparse and pan evaporation
# isn't needed as an input to HSPF so there is not much reason to aggregate
# those data together.
tmax = processor.aggregate('GHCND', 'tmax', start, end)
tmin = processor.aggregate('GHCND', 'tmin', start, end)
snowdepth = processor.aggregate('GHCND', 'snowdepth', start, end)
snowfall = processor.aggregate('GHCND', 'snowfall', start, end)
# now these time series can be saved for later consistent with the structure
# used by PyHSPF's HSPFModel class (start date, time step in minutes, data)
# this way the data are easy to access later
for n, dataset in zip(('tmax', 'tmin', 'snowdepth', 'snowfall'),
(tmax, tmin, snowdepth, snowfall)):
name = '{}/GHCND_aggregated_{}'.format(output, n)
ts = start, 1440, dataset
# dump it in a pickled file to use later
end = datetime.datetime(2011, 1, 1)
# path to 7zip if using windows
processor.path_to_7z = r'C:/Program Files/7-Zip/7z.exe'
# download the data; this step will be skipped if this has already been done
# (from the last example); alternatively it will set the metadata
processor.download(bbox, start, end, output, datasets = ['NSRDB'])
# aggregate the data -- worth noting that prior to 1991 is a separate database
# that corresponds more closely to METSTAT than SUNY; requesting data prior
# to 1991 will give the same values either way.
metstat = processor.aggregate('NSRDB', 'metstat', start, end)
suny = processor.aggregate('NSRDB', 'suny', start, end)
# now these time series can be saved for later consistent with the structure
# used by PyHSPF's HSPFModel class (start date, time step in minutes, data)
# this way the data are easy to access later
for n, dataset in zip(('metstat','suny'), (metstat, suny)):
name = '{}/NSRDB_aggregated_{}'.format(output, n)
ts = start, 60, dataset
# dump it in a pickled file to use later
with open(name, 'wb') as f: pickle.dump(ts, f)