def test_get_airmass():
tus = Location(32.2, -111, 'US/Arizona', 700, 'Tucson')
times = pd.DatetimeIndex(start='20160101T0600-0700',
end='20160101T1800-0700',
freq='3H')
airmass = tus.get_airmass(times)
expected = pd.DataFrame(data=np.array(
[[ nan, nan],
[ 3.61046506, 3.32072602],
[ 1.76470864, 1.62309115],
[ 2.45582153, 2.25874238],
[ nan, nan]]),
columns=['airmass_relative', 'airmass_absolute'],
index=times)
assert_frame_equal(expected, airmass)
airmass = tus.get_airmass(times, model='young1994')
expected = pd.DataFrame(data=np.array(
[[ nan, nan],
[ 3.6075018 , 3.31800056],
[ 1.7641033 , 1.62253439],
[ 2.45413091, 2.25718744],
[ nan, nan]]),
columns=['airmass_relative', 'airmass_absolute'],
index=times)
assert_frame_equal(expected, airmass)
def test_get_airmass():
tus = Location(32.2, -111, 'US/Arizona', 700, 'Tucson')
times = pd.DatetimeIndex(start='20160101T0600-0700',
end='20160101T1800-0700',
freq='3H')
airmass = tus.get_airmass(times)
expected = pd.DataFrame(data=np.array(
[[ nan, nan],
[ 3.61046506, 3.32072602],
[ 1.76470864, 1.62309115],
[ 2.45582153, 2.25874238],
[ nan, nan]]),
columns=['airmass_relative', 'airmass_absolute'],
index=times)
assert_frame_equal(expected, airmass)
airmass = tus.get_airmass(times, model='young1994')
expected = pd.DataFrame(data=np.array(
[[ nan, nan],
[ 3.6075018 , 3.31800056],
[ 1.7641033 , 1.62253439],
[ 2.45413091, 2.25718744],
[ nan, nan]]),
columns=['airmass_relative', 'airmass_absolute'],
index=times)
assert_frame_equal(expected, airmass)
def test_get_airmass_valueerror():
tus = Location(32.2, -111, 'US/Arizona', 700, 'Tucson')
times = pd.DatetimeIndex(start='20160101T0600-0700',
end='20160101T1800-0700',
freq='3H')
with pytest.raises(ValueError):
clearsky = tus.get_airmass(times, model='invalid_model')
def test_get_airmass_valueerror():
tus = Location(32.2, -111, 'US/Arizona', 700, 'Tucson')
times = pd.DatetimeIndex(start='20160101T0600-0700',
end='20160101T1800-0700',
freq='3H')
with pytest.raises(ValueError):
clearsky = tus.get_airmass(times, model='invalid_model')
class ForecastModel(object):
"""
An object for querying and holding forecast model information for
use within the pvlib library.
Simplifies use of siphon library on a THREDDS server.
Parameters
----------
model_type: string
UNIDATA category in which the model is located.
model_name: string
Name of the UNIDATA forecast model.
set_type: string
Model dataset type.
Attributes
----------
access_url: string
URL specifying the dataset from data will be retrieved.
base_tds_url : string
The top level server address
catalog_url : string
The url path of the catalog to parse.
data: pd.DataFrame
Data returned from the query.
data_format: string
Format of the forecast data being requested from UNIDATA.
dataset: Dataset
Object containing information used to access forecast data.
dataframe_variables: list
Model variables that are present in the data.
datasets_list: list
List of all available datasets.
fm_models: Dataset
TDSCatalog object containing all available
forecast models from UNIDATA.
fm_models_list: list
List of all available forecast models from UNIDATA.
latitude: list
A list of floats containing latitude values.
location: Location
A pvlib Location object containing geographic quantities.
longitude: list
A list of floats containing longitude values.
lbox: boolean
Indicates the use of a location bounding box.
ncss: NCSS object
NCSS
model_name: string
Name of the UNIDATA forecast model.
model: Dataset
A dictionary of Dataset object, whose keys are the name of the
dataset's name.
model_url: string
The url path of the dataset to parse.
modelvariables: list
Common variable names that correspond to queryvariables.
query: NCSS query object
NCSS object used to complete the forecast data retrival.
queryvariables: list
Variables that are used to query the THREDDS Data Server.
time: DatetimeIndex
Time range.
variables: dict
Defines the variables to obtain from the weather
model and how they should be renamed to common variable names.
units: dict
Dictionary containing the units of the standard variables
and the model specific variables.
vert_level: float or integer
Vertical altitude for query data.
"""
access_url_key = 'NetcdfSubset'
catalog_url = 'https://thredds.ucar.edu/thredds/catalog.xml'
base_tds_url = catalog_url.split('/thredds/')[0]
data_format = 'netcdf'
units = {
'temp_air': 'C',
'wind_speed': 'm/s',
'ghi': 'W/m^2',
'ghi_raw': 'W/m^2',
'dni': 'W/m^2',
'dhi': 'W/m^2',
'total_clouds': '%',
'low_clouds': '%',
'mid_clouds': '%',
'high_clouds': '%'
}
def __init__(self, model_type, model_name, set_type, vert_level=None):
self.model_type = model_type
self.model_name = model_name
self.set_type = set_type
self.connected = False
self.vert_level = vert_level
def connect_to_catalog(self):
self.catalog = TDSCatalog(self.catalog_url)
self.fm_models = TDSCatalog(
self.catalog.catalog_refs[self.model_type].href)
self.fm_models_list = sorted(list(self.fm_models.catalog_refs.keys()))
try:
model_url = self.fm_models.catalog_refs[self.model_name].href
except ParseError:
raise ParseError(self.model_name + ' model may be unavailable.')
try:
self.model = TDSCatalog(model_url)
except HTTPError:
try:
self.model = TDSCatalog(model_url)
except HTTPError:
raise HTTPError(self.model_name + ' model may be unavailable.')
self.datasets_list = list(self.model.datasets.keys())
self.set_dataset()
self.connected = True
def __repr__(self):
return '{}, {}'.format(self.model_name, self.set_type)
def set_dataset(self):
'''
Retrieves the designated dataset, creates NCSS object, and
creates a NCSS query object.
'''
keys = list(self.model.datasets.keys())
labels = [item.split()[0].lower() for item in keys]
if self.set_type == 'best':
self.dataset = self.model.datasets[keys[labels.index('best')]]
elif self.set_type == 'latest':
self.dataset = self.model.datasets[keys[labels.index('latest')]]
elif self.set_type == 'full':
self.dataset = self.model.datasets[keys[labels.index('full')]]
self.access_url = self.dataset.access_urls[self.access_url_key]
self.ncss = NCSS(self.access_url)
self.query = self.ncss.query()
def set_query_time_range(self, start, end):
"""
Parameters
----------
start : datetime.datetime, pandas.Timestamp
Must be tz-localized.
end : datetime.datetime, pandas.Timestamp
Must be tz-localized.
Notes
-----
Assigns ``self.start``, ``self.end``. Modifies ``self.query``
"""
self.start = pd.Timestamp(start)
self.end = pd.Timestamp(end)
if self.start.tz is None or self.end.tz is None:
raise TypeError('start and end must be tz-localized')
self.query.time_range(self.start, self.end)
def set_query_latlon(self):
'''
Sets the NCSS query location latitude and longitude.
'''
if (isinstance(self.longitude, list)
and isinstance(self.latitude, list)):
self.lbox = True
# west, east, south, north
self.query.lonlat_box(self.longitude[0], self.longitude[1],
self.latitude[0], self.latitude[1])
else:
self.lbox = False
self.query.lonlat_point(self.longitude, self.latitude)
def set_location(self, tz, latitude, longitude):
'''
Sets the location for the query.
Parameters
----------
tz: tzinfo
Timezone of the query
latitude: float
Latitude of the query
longitude: float
Longitude of the query
Notes
-----
Assigns ``self.location``.
'''
self.location = Location(latitude, longitude, tz=tz)
def get_data(self,
latitude,
longitude,
start,
end,
vert_level=None,
query_variables=None,
close_netcdf_data=True,
**kwargs):
"""
Submits a query to the UNIDATA servers using Siphon NCSS and
converts the netcdf data to a pandas DataFrame.
Parameters
----------
latitude: float
The latitude value.
longitude: float
The longitude value.
start: datetime or timestamp
The start time.
end: datetime or timestamp
The end time.
vert_level: None, float or integer, default None
Vertical altitude of interest.
query_variables: None or list, default None
If None, uses self.variables.
close_netcdf_data: bool, default True
Controls if the temporary netcdf data file should be closed.
Set to False to access the raw data.
**kwargs:
Additional keyword arguments are silently ignored.
Returns
-------
forecast_data : DataFrame
column names are the weather model's variable names.
"""
if not self.connected:
self.connect_to_catalog()
if vert_level is not None:
self.vert_level = vert_level
if query_variables is None:
self.query_variables = list(self.variables.values())
else:
self.query_variables = query_variables
self.set_query_time_range(start, end)
self.latitude = latitude
self.longitude = longitude
self.set_query_latlon() # modifies self.query
self.set_location(self.start.tz, latitude, longitude)
if self.vert_level is not None:
self.query.vertical_level(self.vert_level)
self.query.variables(*self.query_variables)
self.query.accept(self.data_format)
self.netcdf_data = self.ncss.get_data(self.query)
# might be better to go to xarray here so that we can handle
# higher dimensional data for more advanced applications
self.data = self._netcdf2pandas(self.netcdf_data, self.query_variables,
self.start, self.end)
if close_netcdf_data:
self.netcdf_data.close()
return self.data
def process_data(self, data, **kwargs):
"""
Defines the steps needed to convert raw forecast data
into processed forecast data. Most forecast models implement
their own version of this method which also call this one.
Parameters
----------
data: DataFrame
Raw forecast data
Returns
-------
data: DataFrame
Processed forecast data.
"""
data = self.rename(data)
return data
def get_processed_data(self, *args, **kwargs):
"""
Get and process forecast data.
Parameters
----------
*args: positional arguments
Passed to get_data
**kwargs: keyword arguments
Passed to get_data and process_data
Returns
-------
data: DataFrame
Processed forecast data
"""
return self.process_data(self.get_data(*args, **kwargs), **kwargs)
def rename(self, data, variables=None):
"""
Renames the columns according the variable mapping.
Parameters
----------
data: DataFrame
variables: None or dict, default None
If None, uses self.variables
Returns
-------
data: DataFrame
Renamed data.
"""
if variables is None:
variables = self.variables
return data.rename(columns={y: x for x, y in variables.items()})
def _netcdf2pandas(self, netcdf_data, query_variables, start, end):
"""
Transforms data from netcdf to pandas DataFrame.
Parameters
----------
data: netcdf
Data returned from UNIDATA NCSS query.
query_variables: list
The variables requested.
start: Timestamp
The start time
end: Timestamp
The end time
Returns
-------
pd.DataFrame
"""
# set self.time
try:
time_var = 'time'
self.set_time(netcdf_data.variables[time_var])
except KeyError:
# which model does this dumb thing?
time_var = 'time1'
self.set_time(netcdf_data.variables[time_var])
data_dict = {}
for key, data in netcdf_data.variables.items():
# if accounts for possibility of extra variable returned
if key not in query_variables:
continue
squeezed = data[:].squeeze()
if squeezed.ndim == 1:
data_dict[key] = squeezed
elif squeezed.ndim == 2:
for num, data_level in enumerate(squeezed.T):
data_dict[key + '_' + str(num)] = data_level
else:
raise ValueError('cannot parse ndim > 2')
data = pd.DataFrame(data_dict, index=self.time)
# sometimes data is returned as hours since T0
# where T0 is before start. Then the hours between
# T0 and start are added *after* end. So sort and slice
# to remove the garbage
data = data.sort_index().loc[start:end]
return data
def set_time(self, time):
'''
Converts time data into a pandas date object.
Parameters
----------
time: netcdf
Contains time information.
Returns
-------
pandas.DatetimeIndex
'''
times = num2date(time[:].squeeze(),
time.units,
only_use_cftime_datetimes=False,
only_use_python_datetimes=True)
self.time = pd.DatetimeIndex(pd.Series(times), tz=self.location.tz)
def cloud_cover_to_ghi_linear(self,
cloud_cover,
ghi_clear,
offset=35,
**kwargs):
"""
Convert cloud cover to GHI using a linear relationship.
0% cloud cover returns ghi_clear.
100% cloud cover returns offset*ghi_clear.
Parameters
----------
cloud_cover: numeric
Cloud cover in %.
ghi_clear: numeric
GHI under clear sky conditions.
offset: numeric, default 35
Determines the minimum GHI.
kwargs
Not used.
Returns
-------
ghi: numeric
Estimated GHI.
References
----------
Larson et. al. "Day-ahead forecasting of solar power output from
photovoltaic plants in the American Southwest" Renewable Energy
91, 11-20 (2016).
"""
offset = offset / 100.
cloud_cover = cloud_cover / 100.
ghi = (offset + (1 - offset) * (1 - cloud_cover)) * ghi_clear
return ghi
def cloud_cover_to_irradiance_clearsky_scaling(self,
cloud_cover,
method='linear',
**kwargs):
"""
Estimates irradiance from cloud cover in the following steps:
1. Determine clear sky GHI using Ineichen model and
climatological turbidity.
2. Estimate cloudy sky GHI using a function of
cloud_cover e.g.
:py:meth:`~ForecastModel.cloud_cover_to_ghi_linear`
3. Estimate cloudy sky DNI using the DISC model.
4. Calculate DHI from DNI and GHI.
Parameters
----------
cloud_cover : Series
Cloud cover in %.
method : str, default 'linear'
Method for converting cloud cover to GHI.
'linear' is currently the only option.
**kwargs
Passed to the method that does the conversion
Returns
-------
irrads : DataFrame
Estimated GHI, DNI, and DHI.
"""
solpos = self.location.get_solarposition(cloud_cover.index)
cs = self.location.get_clearsky(cloud_cover.index,
model='ineichen',
solar_position=solpos)
method = method.lower()
if method == 'linear':
ghi = self.cloud_cover_to_ghi_linear(cloud_cover, cs['ghi'],
**kwargs)
else:
raise ValueError('invalid method argument')
dni = disc(ghi, solpos['zenith'], cloud_cover.index)['dni']
dhi = ghi - dni * np.cos(np.radians(solpos['zenith']))
irrads = pd.DataFrame({'ghi': ghi, 'dni': dni, 'dhi': dhi}).fillna(0)
return irrads
def cloud_cover_to_transmittance_linear(self,
cloud_cover,
offset=0.75,
**kwargs):
"""
Convert cloud cover to atmospheric transmittance using a linear
model.
0% cloud cover returns offset.
100% cloud cover returns 0.
Parameters
----------
cloud_cover : numeric
Cloud cover in %.
offset : numeric, default 0.75
Determines the maximum transmittance.
kwargs
Not used.
Returns
-------
ghi : numeric
Estimated GHI.
"""
transmittance = ((100.0 - cloud_cover) / 100.0) * offset
return transmittance
def cloud_cover_to_irradiance_liujordan(self, cloud_cover, **kwargs):
"""
Estimates irradiance from cloud cover in the following steps:
1. Determine transmittance using a function of cloud cover e.g.
:py:meth:`~ForecastModel.cloud_cover_to_transmittance_linear`
2. Calculate GHI, DNI, DHI using the
:py:func:`pvlib.irradiance.liujordan` model
Parameters
----------
cloud_cover : Series
Returns
-------
irradiance : DataFrame
Columns include ghi, dni, dhi
"""
# in principle, get_solarposition could use the forecast
# pressure, temp, etc., but the cloud cover forecast is not
# accurate enough to justify using these minor corrections
solar_position = self.location.get_solarposition(cloud_cover.index)
dni_extra = get_extra_radiation(cloud_cover.index)
airmass = self.location.get_airmass(cloud_cover.index)
transmittance = self.cloud_cover_to_transmittance_linear(
cloud_cover, **kwargs)
irrads = liujordan(solar_position['apparent_zenith'],
transmittance,
airmass['airmass_absolute'],
dni_extra=dni_extra)
irrads = irrads.fillna(0)
return irrads
def cloud_cover_to_irradiance(self,
cloud_cover,
how='clearsky_scaling',
**kwargs):
"""
Convert cloud cover to irradiance. A wrapper method.
Parameters
----------
cloud_cover : Series
how : str, default 'clearsky_scaling'
Selects the method for conversion. Can be one of
clearsky_scaling or liujordan.
**kwargs
Passed to the selected method.
Returns
-------
irradiance : DataFrame
Columns include ghi, dni, dhi
"""
how = how.lower()
if how == 'clearsky_scaling':
irrads = self.cloud_cover_to_irradiance_clearsky_scaling(
cloud_cover, **kwargs)
elif how == 'liujordan':
irrads = self.cloud_cover_to_irradiance_liujordan(
cloud_cover, **kwargs)
else:
raise ValueError('invalid how argument')
return irrads
def kelvin_to_celsius(self, temperature):
"""
Converts Kelvin to celsius.
Parameters
----------
temperature: numeric
Returns
-------
temperature: numeric
"""
return temperature - 273.15
def isobaric_to_ambient_temperature(self, data):
"""
Calculates temperature from isobaric temperature.
Parameters
----------
data: DataFrame
Must contain columns pressure, temperature_iso,
temperature_dew_iso. Input temperature in K.
Returns
-------
temperature : Series
Temperature in K
"""
P = data['pressure'] / 100.0 # noqa: N806
Tiso = data['temperature_iso'] # noqa: N806
Td = data['temperature_dew_iso'] - 273.15 # noqa: N806
# saturation water vapor pressure
e = 6.11 * 10**((7.5 * Td) / (Td + 273.3))
# saturation water vapor mixing ratio
w = 0.622 * (e / (P - e))
temperature = Tiso - ((2.501 * 10.**6) / 1005.7) * w
return temperature
def uv_to_speed(self, data):
"""
Computes wind speed from wind components.
Parameters
----------
data : DataFrame
Must contain the columns 'wind_speed_u' and 'wind_speed_v'.
Returns
-------
wind_speed : Series
"""
wind_speed = np.sqrt(data['wind_speed_u']**2 + data['wind_speed_v']**2)
return wind_speed
def gust_to_speed(self, data, scaling=1 / 1.4):
"""
Computes standard wind speed from gust.
Very approximate and location dependent.
Parameters
----------
data : DataFrame
Must contain the column 'wind_speed_gust'.
Returns
-------
wind_speed : Series
"""
wind_speed = data['wind_speed_gust'] * scaling
return wind_speed
def test_get_airmass_valueerror(times):
tus = Location(32.2, -111, 'US/Arizona', 700, 'Tucson')
with pytest.raises(ValueError):
tus.get_airmass(times, model='invalid_model')
class ForecastModel(object):
"""
An object for querying and holding forecast model information for
use within the pvlib library.
Simplifies use of siphon library on a THREDDS server.
Parameters
----------
model_type: string
UNIDATA category in which the model is located.
model_name: string
Name of the UNIDATA forecast model.
set_type: string
Model dataset type.
Attributes
----------
access_url: string
URL specifying the dataset from data will be retrieved.
base_tds_url : string
The top level server address
catalog_url : string
The url path of the catalog to parse.
data: pd.DataFrame
Data returned from the query.
data_format: string
Format of the forecast data being requested from UNIDATA.
dataset: Dataset
Object containing information used to access forecast data.
dataframe_variables: list
Model variables that are present in the data.
datasets_list: list
List of all available datasets.
fm_models: Dataset
TDSCatalog object containing all available
forecast models from UNIDATA.
fm_models_list: list
List of all available forecast models from UNIDATA.
latitude: list
A list of floats containing latitude values.
location: Location
A pvlib Location object containing geographic quantities.
longitude: list
A list of floats containing longitude values.
lbox: boolean
Indicates the use of a location bounding box.
ncss: NCSS object
NCSS
model_name: string
Name of the UNIDATA forecast model.
model: Dataset
A dictionary of Dataset object, whose keys are the name of the
dataset's name.
model_url: string
The url path of the dataset to parse.
modelvariables: list
Common variable names that correspond to queryvariables.
query: NCSS query object
NCSS object used to complete the forecast data retrival.
queryvariables: list
Variables that are used to query the THREDDS Data Server.
time: DatetimeIndex
Time range.
variables: dict
Defines the variables to obtain from the weather
model and how they should be renamed to common variable names.
units: dict
Dictionary containing the units of the standard variables
and the model specific variables.
vert_level: float or integer
Vertical altitude for query data.
"""
access_url_key = 'NetcdfSubset'
catalog_url = 'http://thredds.ucar.edu/thredds/catalog.xml'
base_tds_url = catalog_url.split('/thredds/')[0]
data_format = 'netcdf'
vert_level = 100000
units = {
'temp_air': 'C',
'wind_speed': 'm/s',
'ghi': 'W/m^2',
'ghi_raw': 'W/m^2',
'dni': 'W/m^2',
'dhi': 'W/m^2',
'total_clouds': '%',
'low_clouds': '%',
'mid_clouds': '%',
'high_clouds': '%'}
def __init__(self, model_type, model_name, set_type):
self.model_type = model_type
self.model_name = model_name
self.set_type = set_type
self.catalog = TDSCatalog(self.catalog_url)
self.fm_models = TDSCatalog(self.catalog.catalog_refs[model_type].href)
self.fm_models_list = sorted(list(self.fm_models.catalog_refs.keys()))
try:
model_url = self.fm_models.catalog_refs[model_name].href
except ParseError:
raise ParseError(self.model_name + ' model may be unavailable.')
try:
self.model = TDSCatalog(model_url)
except HTTPError:
try:
self.model = TDSCatalog(model_url)
except HTTPError:
raise HTTPError(self.model_name + ' model may be unavailable.')
self.datasets_list = list(self.model.datasets.keys())
self.set_dataset()
def __repr__(self):
return '{}, {}'.format(self.model_name, self.set_type)
def set_dataset(self):
'''
Retrieves the designated dataset, creates NCSS object, and
creates a NCSS query object.
'''
keys = list(self.model.datasets.keys())
labels = [item.split()[0].lower() for item in keys]
if self.set_type == 'best':
self.dataset = self.model.datasets[keys[labels.index('best')]]
elif self.set_type == 'latest':
self.dataset = self.model.datasets[keys[labels.index('latest')]]
elif self.set_type == 'full':
self.dataset = self.model.datasets[keys[labels.index('full')]]
self.access_url = self.dataset.access_urls[self.access_url_key]
self.ncss = NCSS(self.access_url)
self.query = self.ncss.query()
def set_query_latlon(self):
'''
Sets the NCSS query location latitude and longitude.
'''
if (isinstance(self.longitude, list) and
isinstance(self.latitude, list)):
self.lbox = True
# west, east, south, north
self.query.lonlat_box(self.latitude[0], self.latitude[1],
self.longitude[0], self.longitude[1])
else:
self.lbox = False
self.query.lonlat_point(self.longitude, self.latitude)
def set_location(self, time, latitude, longitude):
'''
Sets the location for the query.
Parameters
----------
time: datetime or DatetimeIndex
Time range of the query.
'''
if isinstance(time, datetime.datetime):
tzinfo = time.tzinfo
else:
tzinfo = time.tz
if tzinfo is None:
self.location = Location(latitude, longitude)
else:
self.location = Location(latitude, longitude, tz=tzinfo)
def get_data(self, latitude, longitude, start, end,
vert_level=None, query_variables=None,
close_netcdf_data=True):
"""
Submits a query to the UNIDATA servers using Siphon NCSS and
converts the netcdf data to a pandas DataFrame.
Parameters
----------
latitude: float
The latitude value.
longitude: float
The longitude value.
start: datetime or timestamp
The start time.
end: datetime or timestamp
The end time.
vert_level: None, float or integer
Vertical altitude of interest.
variables: None or list
If None, uses self.variables.
close_netcdf_data: bool
Controls if the temporary netcdf data file should be closed.
Set to False to access the raw data.
Returns
-------
forecast_data : DataFrame
column names are the weather model's variable names.
"""
if vert_level is not None:
self.vert_level = vert_level
if query_variables is None:
self.query_variables = list(self.variables.values())
else:
self.query_variables = query_variables
self.latitude = latitude
self.longitude = longitude
self.set_query_latlon() # modifies self.query
self.set_location(start, latitude, longitude)
self.start = start
self.end = end
self.query.time_range(self.start, self.end)
self.query.vertical_level(self.vert_level)
self.query.variables(*self.query_variables)
self.query.accept(self.data_format)
self.netcdf_data = self.ncss.get_data(self.query)
# might be better to go to xarray here so that we can handle
# higher dimensional data for more advanced applications
self.data = self._netcdf2pandas(self.netcdf_data, self.query_variables)
if close_netcdf_data:
self.netcdf_data.close()
return self.data
def process_data(self, data, **kwargs):
"""
Defines the steps needed to convert raw forecast data
into processed forecast data. Most forecast models implement
their own version of this method which also call this one.
Parameters
----------
data: DataFrame
Raw forecast data
Returns
-------
data: DataFrame
Processed forecast data.
"""
data = self.rename(data)
return data
def get_processed_data(self, *args, **kwargs):
"""
Get and process forecast data.
Parameters
----------
*args: positional arguments
Passed to get_data
**kwargs: keyword arguments
Passed to get_data and process_data
Returns
-------
data: DataFrame
Processed forecast data
"""
return self.process_data(self.get_data(*args, **kwargs), **kwargs)
def rename(self, data, variables=None):
"""
Renames the columns according the variable mapping.
Parameters
----------
data: DataFrame
variables: None or dict
If None, uses self.variables
Returns
-------
data: DataFrame
Renamed data.
"""
if variables is None:
variables = self.variables
return data.rename(columns={y: x for x, y in variables.items()})
def _netcdf2pandas(self, netcdf_data, query_variables):
"""
Transforms data from netcdf to pandas DataFrame.
Parameters
----------
data: netcdf
Data returned from UNIDATA NCSS query.
query_variables: list
The variables requested.
Returns
-------
pd.DataFrame
"""
# set self.time
try:
time_var = 'time'
self.set_time(netcdf_data.variables[time_var])
except KeyError:
# which model does this dumb thing?
time_var = 'time1'
self.set_time(netcdf_data.variables[time_var])
data_dict = {key: data[:].squeeze() for key, data in
netcdf_data.variables.items() if key in query_variables}
return pd.DataFrame(data_dict, index=self.time)
def set_time(self, time):
'''
Converts time data into a pandas date object.
Parameters
----------
time: netcdf
Contains time information.
Returns
-------
pandas.DatetimeIndex
'''
times = num2date(time[:].squeeze(), time.units)
self.time = pd.DatetimeIndex(pd.Series(times), tz=self.location.tz)
def cloud_cover_to_ghi_linear(self, cloud_cover, ghi_clear, offset=35,
**kwargs):
"""
Convert cloud cover to GHI using a linear relationship.
0% cloud cover returns ghi_clear.
100% cloud cover returns offset*ghi_clear.
Parameters
----------
cloud_cover: numeric
Cloud cover in %.
ghi_clear: numeric
GHI under clear sky conditions.
offset: numeric
Determines the minimum GHI.
kwargs
Not used.
Returns
-------
ghi: numeric
Estimated GHI.
References
----------
Larson et. al. "Day-ahead forecasting of solar power output from
photovoltaic plants in the American Southwest" Renewable Energy
91, 11-20 (2016).
"""
offset = offset / 100.
cloud_cover = cloud_cover / 100.
ghi = (offset + (1 - offset) * (1 - cloud_cover)) * ghi_clear
return ghi
def cloud_cover_to_irradiance_clearsky_scaling(self, cloud_cover,
method='linear',
**kwargs):
"""
Estimates irradiance from cloud cover in the following steps:
1. Determine clear sky GHI using Ineichen model and
climatological turbidity.
2. Estimate cloudy sky GHI using a function of
cloud_cover e.g.
:py:meth:`~ForecastModel.cloud_cover_to_ghi_linear`
3. Estimate cloudy sky DNI using the DISC model.
4. Calculate DHI from DNI and DHI.
Parameters
----------
cloud_cover : Series
Cloud cover in %.
method : str
Method for converting cloud cover to GHI.
'linear' is currently the only option.
**kwargs
Passed to the method that does the conversion
Returns
-------
irrads : DataFrame
Estimated GHI, DNI, and DHI.
"""
solpos = self.location.get_solarposition(cloud_cover.index)
cs = self.location.get_clearsky(cloud_cover.index, model='ineichen',
solar_position=solpos)
method = method.lower()
if method == 'linear':
ghi = self.cloud_cover_to_ghi_linear(cloud_cover, cs['ghi'],
**kwargs)
else:
raise ValueError('invalid method argument')
dni = disc(ghi, solpos['zenith'], cloud_cover.index)['dni']
dhi = ghi - dni * np.cos(np.radians(solpos['zenith']))
irrads = pd.DataFrame({'ghi': ghi, 'dni': dni, 'dhi': dhi}).fillna(0)
return irrads
def cloud_cover_to_transmittance_linear(self, cloud_cover, offset=0.75,
**kwargs):
"""
Convert cloud cover to atmospheric transmittance using a linear
model.
0% cloud cover returns offset.
100% cloud cover returns 0.
Parameters
----------
cloud_cover : numeric
Cloud cover in %.
offset : numeric
Determines the maximum transmittance.
kwargs
Not used.
Returns
-------
ghi : numeric
Estimated GHI.
"""
transmittance = ((100.0 - cloud_cover) / 100.0) * 0.75
return transmittance
def cloud_cover_to_irradiance_liujordan(self, cloud_cover, **kwargs):
"""
Estimates irradiance from cloud cover in the following steps:
1. Determine transmittance using a function of cloud cover e.g.
:py:meth:`~ForecastModel.cloud_cover_to_transmittance_linear`
2. Calculate GHI, DNI, DHI using the
:py:func:`pvlib.irradiance.liujordan` model
Parameters
----------
cloud_cover : Series
Returns
-------
irradiance : DataFrame
Columns include ghi, dni, dhi
"""
# in principle, get_solarposition could use the forecast
# pressure, temp, etc., but the cloud cover forecast is not
# accurate enough to justify using these minor corrections
solar_position = self.location.get_solarposition(cloud_cover.index)
dni_extra = extraradiation(cloud_cover.index)
airmass = self.location.get_airmass(cloud_cover.index)
transmittance = self.cloud_cover_to_transmittance_linear(cloud_cover,
**kwargs)
irrads = liujordan(solar_position['apparent_zenith'],
transmittance, airmass['airmass_absolute'],
dni_extra=dni_extra)
irrads = irrads.fillna(0)
return irrads
def cloud_cover_to_irradiance(self, cloud_cover, how='clearsky_scaling',
**kwargs):
"""
Convert cloud cover to irradiance. A wrapper method.
Parameters
----------
cloud_cover : Series
how : str
Selects the method for conversion. Can be one of
clearsky_scaling or liujordan.
**kwargs
Passed to the selected method.
Returns
-------
irradiance : DataFrame
Columns include ghi, dni, dhi
"""
how = how.lower()
if how == 'clearsky_scaling':
irrads = self.cloud_cover_to_irradiance_clearsky_scaling(
cloud_cover, **kwargs)
elif how == 'liujordan':
irrads = self.cloud_cover_to_irradiance_liujordan(
cloud_cover, **kwargs)
else:
raise ValueError('invalid how argument')
return irrads
def kelvin_to_celsius(self, temperature):
"""
Converts Kelvin to celsius.
Parameters
----------
temperature: numeric
Returns
-------
temperature: numeric
"""
return temperature - 273.15
def isobaric_to_ambient_temperature(self, data):
"""
Calculates temperature from isobaric temperature.
Parameters
----------
data: DataFrame
Must contain columns pressure, temperature_iso,
temperature_dew_iso. Input temperature in K.
Returns
-------
temperature : Series
Temperature in K
"""
P = data['pressure'] / 100.0
Tiso = data['temperature_iso']
Td = data['temperature_dew_iso'] - 273.15
# saturation water vapor pressure
e = 6.11 * 10**((7.5 * Td) / (Td + 273.3))
# saturation water vapor mixing ratio
w = 0.622 * (e / (P - e))
T = Tiso - ((2.501 * 10.**6) / 1005.7) * w
return T
def uv_to_speed(self, data):
"""
Computes wind speed from wind components.
Parameters
----------
data : DataFrame
Must contain the columns 'wind_speed_u' and 'wind_speed_v'.
Returns
-------
wind_speed : Series
"""
wind_speed = np.sqrt(data['wind_speed_u']**2 + data['wind_speed_v']**2)
return wind_speed
def gust_to_speed(self, data, scaling=1/1.4):
"""
Computes standard wind speed from gust.
Very approximate and location dependent.
Parameters
----------
data : DataFrame
Must contain the column 'wind_speed_gust'.
Returns
-------
wind_speed : Series
"""
wind_speed = data['wind_speed_gust'] * scaling
return wind_speed
def test_get_airmass_valueerror(times):
tus = Location(32.2, -111, 'US/Arizona', 700, 'Tucson')
with pytest.raises(ValueError):
clearsky = tus.get_airmass(times, model='invalid_model')