def test_img2ts_daily_no_resampling_missing_day():
"""
Test resampling over missing day 2016-01-01 (see reader above)
"""
input_grid = BasicGrid(
np.array([0.5, 0.5, -0.5, -0.5]),
np.array([1, -1, 1, -1]),
)
outputpath = tempfile.mkdtemp()
start = datetime(2015, 12, 5)
end = datetime(2016, 1, 10)
ds_in = TestMultiTemporalImageDatasetDaily()
img2ts = Img2Ts(ds_in,
outputpath,
start,
end,
imgbuffer=15,
input_grid=input_grid)
ts_should = np.concatenate(
[np.arange(5, 32, dtype=np.float),
np.arange(2, 11, dtype=np.float)])
dates_should = ds_in.tstamps_for_daterange(start, end)
dates_should.remove(datetime(2016, 1, 1))
img2ts.calc()
ts_file = os.path.join(outputpath, '0000.nc')
with OrthoMultiTs(ts_file) as ds:
ts = ds.read_ts('var1', 0)
nptest.assert_allclose(ts['var1'], ts_should)
assert dates_should == list(ts['time'])
nptest.assert_allclose(ds.dataset.variables['location_id'][:],
np.array([0, 1, 2, 3]))
def reshuffle(input_root, outputpath,
startdate, enddate,
parameters, land_points=True,
imgbuffer=50):
"""
Reshuffle method applied to GLDAS data.
Parameters
----------
input_root: string
input path where gldas data was downloaded
outputpath : string
Output path.
startdate : datetime
Start date.
enddate : datetime
End date.
parameters: list
parameters to read and convert
imgbuffer: int, optional
How many images to read at once before writing time series.
"""
if land_points:
landgrid = GLDAS025LandGrid()
else:
landgrid = None
if get_filetype(input_root) == 'grib':
input_dataset = GLDAS_Noah_v1_025Ds(input_root, parameters,
array_1D=True)
if land_points:
warnings.warn('Land Grid is fit to GLDAS 2.x netCDF data')
else:
input_dataset = GLDAS_Noah_v21_025Ds(input_root, parameters, landgrid,
array_1D=True)
if not os.path.exists(outputpath):
os.makedirs(outputpath)
global_attr = {'product': 'GLDAS'}
# get time series attributes from first day of data.
data = input_dataset.read(startdate)
ts_attributes = data.metadata
if landgrid:
grid = landgrid
else:
grid = BasicGrid(data.lon, data.lat)
reshuffler = Img2Ts(input_dataset=input_dataset, outputpath=outputpath,
startdate=startdate, enddate=enddate, input_grid=grid,
imgbuffer=imgbuffer, cellsize_lat=5.0,
cellsize_lon=5.0, global_attr=global_attr, zlib=True,
unlim_chunksize=1000, ts_attributes=ts_attributes)
reshuffler.calc()
def EASE25CellGrid():
ease25 = EASE2_grid(25000)
lons, lats = np.meshgrid(ease25.londim, ease25.latdim)
lats = np.flipud(lats) # flip lats, so that origin in bottom left
grid = BasicGrid(lons.flatten(),
lats.flatten(),
shape=(ease25.londim.size,
ease25.latdim.size)).to_cell_grid(5., 5.)
return grid
def __init__(self, networks):
"""
Create network collection from previously created Networks.
Parameters
----------
networks : list[Network]
List of Networks that build the collection from.
"""
self.networks = OrderedDict([])
lons = []
lats = []
for net in networks:
self.networks[net.name] = net
net_lons, net_lats = net.coords
lons += net_lons
lats += net_lats
self.grid = BasicGrid(lons, lats) if (len(lons) > 0
and len(lats) > 0) else None
def reshuffle(input_root,
outputpath,
startdate,
enddate,
parameters,
imgbuffer=50):
"""
Reshuffle method applied to ESACCI SM v0.42 data.
Parameters
----------
input_root: string
input path where era interim data was downloaded
outputpath : string
Output path.
startdate : datetime
Start date.
enddate : datetime
End date.
parameters: list
parameters to read and convert
imgbuffer: int, optional
How many images to read at once before writing time series.
"""
input_dataset = CCI_SM_v042_025Ds(input_root, parameters, array_1D=True)
if not os.path.exists(outputpath):
os.makedirs(outputpath)
global_attr = {'product': 'ESACCI'}
# get time series attributes from first day of data.
data = input_dataset.read(startdate)
ts_attributes = data.metadata
grid = BasicGrid(data.lon, data.lat)
reshuffler = Img2Ts(input_dataset=input_dataset,
outputpath=outputpath,
startdate=startdate,
enddate=enddate,
input_grid=grid,
imgbuffer=imgbuffer,
cellsize_lat=5.0,
cellsize_lon=5.0,
global_attr=global_attr,
zlib=True,
unlim_chunksize=1000,
ts_attributes=ts_attributes)
reshuffler.calc()
def reshuffle(input_root, outputpath, startdate, enddate,
parameters, overpass=None, crid=None, imgbuffer=50):
"""
Reshuffle method applied to ERA-Interim data.
Parameters
----------
input_root: string
input path where era interim data was downloaded
outputpath : string
Output path.
startdate : datetime
Start date.
enddate : datetime
End date.
parameters: list
parameters to read and convert
overpass : str
Select 'AM' for the descending overpass or 'PM' for the ascending one.
If the version data does not contain multiple overpasses, this must be None
crid : int, optional (default: None)
Search for files with this Composite Release ID for reshuffling only.
See also https://nsidc.org/data/smap/data_versions#CRID
imgbuffer: int, optional
How many images to read at once before writing time series.
"""
input_dataset = SPL3SMP_Ds(input_root, parameter=parameters,
overpass=overpass, crid=crid, flatten=True)
global_attr = {'product': 'SPL3SMP'}
if overpass:
global_attr['overpass'] = overpass
if not os.path.exists(outputpath):
os.makedirs(outputpath)
# get time series attributes from first day of data.
data = input_dataset.read(startdate)
ts_attributes = data.metadata
ease36 = EASE2_grid(36000)
lons, lats = np.meshgrid(ease36.londim, ease36.latdim)
grid = BasicGrid(lons.flatten(), lats.flatten())
reshuffler = Img2Ts(input_dataset=input_dataset, outputpath=outputpath,
startdate=startdate, enddate=enddate, input_grid=grid,
imgbuffer=imgbuffer, cellsize_lat=5.0, cellsize_lon=5.0,
global_attr=global_attr, ts_attributes=ts_attributes)
reshuffler.calc()
def reshuffle(input_root,
outputpath,
startdate,
enddate,
parameters,
imgbuffer=50):
"""
Reshuffle method applied to ERA-Interim data.
Parameters
----------
input_root: string
input path where era interim data was downloaded
outputpath : string
Output path.
startdate : datetime
Start date.
enddate : datetime
End date.
parameters: list
parameters to read and convert
imgbuffer: int, optional
How many images to read at once before writing time series.
"""
input_dataset = ERAInterimDs(parameters, input_root, expand_grid=False)
if not os.path.exists(outputpath):
os.makedirs(outputpath)
global_attr = {'product': 'ERA Interim'}
# get time series attributes from first day of data.
data = input_dataset.read(startdate)
ts_attributes = data.metadata
grid = BasicGrid(data.lon, data.lat)
reshuffler = Img2Ts(input_dataset=input_dataset,
outputpath=outputpath,
startdate=startdate,
enddate=enddate,
input_grid=grid,
imgbuffer=imgbuffer,
cellsize_lat=5.0,
cellsize_lon=5.0,
ts_dtypes=np.dtype('float32'),
global_attr=global_attr,
ts_attributes=ts_attributes)
reshuffler.calc()
def reshuffle(input_root, outputpath,
startdate, enddate,
parameters,
imgbuffer=50):
"""
Reshuffle method applied to ERA-Interim data.
Parameters
----------
input_root: string
input path where era interim data was downloaded
outputpath : string
Output path.
startdate : datetime
Start date.
enddate : datetime
End date.
parameters: list
parameters to read and convert
imgbuffer: int, optional
How many images to read at once before writing time series.
"""
input_dataset = SPL3SMP_Ds(input_root, parameter=parameters, flatten=True)
if not os.path.exists(outputpath):
os.makedirs(outputpath)
global_attr = {'product': 'SPL3SMP'}
# get time series attributes from first day of data.
data = input_dataset.read(startdate)
ts_attributes = data.metadata
ease36 = EASE2_grid(36000)
lons, lats = np.meshgrid(ease36.londim, ease36.latdim)
grid = BasicGrid(lons.flatten(), lats.flatten())
reshuffler = Img2Ts(input_dataset=input_dataset, outputpath=outputpath,
startdate=startdate, enddate=enddate,
input_grid=grid,
imgbuffer=imgbuffer, cellsize_lat=5.0, cellsize_lon=5.0,
global_attr=global_attr,
ts_attributes=ts_attributes)
reshuffler.calc()
def load_grid(filename,
subset_flag='subset_flag',
subset_value=1,
location_var_name='gpi'):
"""
load a grid from netCDF file
Parameters
----------
filename : string
filename
subset_flag : string, optional (default: 'subset_flag')
name of the subset to load.
subset_value : int or list, optional (default: 1)
Value(s) of the subset variable that points are loaded for.
location_var_name: string, optional (default: 'gpi')
variable name under which the grid point locations
are stored
Returns
-------
grid : BasicGrid or CellGrid instance
grid instance initialized with the loaded data
"""
with Dataset(filename, 'r') as nc_data:
# determine if it is a cell grid or a basic grid
arrcell = None
if 'cell' in nc_data.variables.keys():
arrcell = nc_data.variables['cell'][:].flatten()
gpis = nc_data.variables[location_var_name][:].flatten()
shape = None
if hasattr(nc_data, 'shape'):
try:
shape = tuple(nc_data.shape)
except TypeError as e:
try:
length = len(nc_data.shape)
except TypeError:
length = nc_data.shape.size
if length == 1:
shape = tuple([nc_data.shape])
else:
raise e
subset = None
# some old grid do not have a shape attribute
# this meant that they had shape of len 1
if shape is None:
shape = tuple([len(nc_data.variables['lon'][:])])
# check if grid has regular shape
if len(shape) == 2:
lons, lats = np.meshgrid(nc_data.variables['lon'][:],
nc_data.variables['lat'][:])
lons = lons.flatten()
lats = lats.flatten()
if subset_flag in nc_data.variables.keys():
subset = np.where(
np.isin(nc_data.variables[subset_flag][:].flatten(),
subset_value))[0]
elif len(shape) == 1:
lons = nc_data.variables['lon'][:]
lats = nc_data.variables['lat'][:]
# determine if it has a subset
if subset_flag in nc_data.variables.keys():
subset = np.where(
np.isin(nc_data.variables[subset_flag][:].flatten(),
subset_value))[0]
if 'crs' in nc_data.variables:
geodatumName = nc_data.variables['crs'].getncattr('ellipsoid_name')
else:
# ellipsoid information is missing, use WGS84 by default
geodatumName = 'WGS84'
if arrcell is None:
# BasicGrid
return BasicGrid(lons,
lats,
gpis=gpis,
geodatum=geodatumName,
subset=subset,
shape=shape)
else:
# CellGrid
return CellGrid(lons,
lats,
arrcell,
gpis=gpis,
geodatum=geodatumName,
subset=subset,
shape=shape)
def reshuffle(in_path,
out_path,
start_date,
end_date,
parameters,
temporal_sampling=6,
img_buffer=50):
"""
Reshuffle method applied to MERRA2 data.
Parameters
----------
in_path: string
input path where merra2 data was downloaded
out_path : string
Output path.
start_date : datetime
Start date.
end_date : datetime
End date.
parameters: list
parameters to read and convert
temporal_sampling: int in range [1, 24]
Get an image every n hours where n=temporal_sampling. For example:
if 1: return hourly sampled data -> hourly sampling
if 6: return an image every 6 hours -> 6 hourly sampling
if 24: return the 00:30 image of each day -> daily sampling
img_buffer: int, optional
How many images to read at once before writing the time series.
"""
# define input dataset
# the img_bulk class in img2ts iterates through every nth
# timestamp as specified by temporal_sampling
input_dataset = MerraImageStack(data_path=in_path,
parameter=parameters,
temporal_sampling=temporal_sampling,
array_1d=True)
product = 'MERRA2_hourly'
# create out_path directory if it does not exist yet
if not os.path.exists(out_path):
os.makedirs(out_path)
# set global attribute
global_attributes = {'product': product}
# get ts attributes from fist day of data
data = input_dataset.read(start_date)
ts_attributes = data.metadata
# define grid
grid = BasicGrid(data.lon, data.lat)
# define reshuffler
reshuffler = Img2Ts(input_dataset=input_dataset,
outputpath=out_path,
startdate=start_date,
enddate=end_date,
input_grid=grid,
imgbuffer=img_buffer,
cellsize_lat=5.0,
cellsize_lon=6.25,
global_attr=global_attributes,
zlib=True,
unlim_chunksize=1000,
ts_attributes=ts_attributes)
reshuffler.calc()
class NetworkCollection(IsmnComponent):
"""
A NetworkCollection holds multiple networks and provides functionality
to perform access to components from multiple networks.
A grid is added that contains all stations to perform spatial searches.
Attributes
----------
networks : OrderedDict
Collection of network names and Networks
grid : BasicGrid
Grid that contains one point for each station in all networks.
"""
def __init__(self, networks):
"""
Create network collection from previously created Networks.
Parameters
----------
networks : list[Network]
List of Networks that build the collection from.
"""
self.networks = OrderedDict([])
lons = []
lats = []
for net in networks:
self.networks[net.name] = net
net_lons, net_lats = net.coords
lons += net_lons
lats += net_lats
self.grid = BasicGrid(lons, lats) if (len(lons) > 0
and len(lats) > 0) else None
def __repr__(self, indent=''):
return ',\n'.join([
f"{indent}{net.name}: {list(net.stations.keys())}"
for net in self.networks.values()
])
def __getitem__(self, item: Union[int, str]):
# shortcut to access networks directly
if isinstance(item, int):
item = list(self.networks.keys())[item]
return self.networks[item]
def iter_networks(self) -> Network:
"""
Iterate through all networks in the Collection.
"""
for nw in self.networks.values():
yield nw
def iter_stations(self, **filter_kwargs) -> (Network, Station):
"""
Iterate through Networks in the Collection and get (all/filtered)
Stations.
"""
for nw in self.networks.values():
for stat in nw.iter_stations(**filter_kwargs):
yield nw, stat
def iter_sensors(self, **filter_kwargs) -> (Network, Station, Sensor):
"""
Iterate through Networks in the Collection and get (all/filtered)
Stations and Sensors at each Station.
"""
for nw in self.networks.values():
for stat, sen in nw.iter_sensors(**filter_kwargs):
yield nw, stat, sen
def station4gpi(self, gpi):
"""
Get the Station for the passed gpi in the grid.
Parameters
----------
gpi : int or List[int]
Point index or multiple indices in self.grid.
Returns
-------
station : Station or list[Station]
Station(s) at gpi(s).
"""
idxs = np.atleast_1d(gpi)
in_grid = np.isin(idxs, self.grid.activegpis)
if not all(in_grid):
raise ValueError(
f"Index not found in loaded grid: {idxs[~in_grid]}")
lon, lat = self.grid.gpi2lonlat(idxs)
stations = []
for net, stat in self.iter_stations():
if (stat.lon == lon) and (stat.lat == lat):
stations.append(stat)
if len(stations) == len(idxs):
break # stop when all indices are found
return stations[0] if len(stations) == 1 else stations
def get_nearest_station(self, lon, lat, max_dist=np.inf):
"""
Get nearest station for given longitude/latitude coordinates.
Parameters
----------
lon : float or List[float]
Longitude coordinate(s).
lat : float or List[float]
Latitude coordinate(s).
max_dist : float, optional (default: np.Inf)
Maximum search distance.
Returns
-------
station : Station or List[Station]
The nearest Station(s) to the passed coordinates.
dist : float
Distance in meter between the passed coordinates and the
actual location of the station.
"""
gpi, dist = self.grid.find_nearest_gpi(lon, lat, max_dist=max_dist)
station = self.station4gpi(gpi)
return station, dist
def grid(self) -> BasicGrid:
"""
Get grid for all Stations in Network
"""
return BasicGrid(*self.coords)
def reshuffle(
input_root,
outputpath,
startdate,
enddate,
variables,
mask_seapoints=False,
h_steps=(0, 6, 12, 18),
imgbuffer=50,
):
"""
Reshuffle method applied to ERA images for conversion into netcdf time
series format.
Parameters
----------
input_root: str
Input path where ERA image data was downloaded to.
outputpath : str
Output path, where the reshuffled netcdf time series are stored.
startdate : datetime
Start date, from which images are read and time series are generated.
enddate : datetime
End date, from which images are read and time series are generated.
variables: list or str or tuple
Variables to read from the passed images and convert into time
series format.
mask_seapoints: bool, optional (default: False)
Mask points over sea, replace them with nan.
h_steps: tuple, optional (default: (0,6,12,18))
Full hours for which images are available.
imgbuffer: int, optional (default: 50)
How many images to read at once before writing time series. This number
affects how many images are stored in memory and should be chosen according
to the available amount of memory and the size of a single image.
"""
filetype = parse_filetype(input_root)
if filetype == "grib":
input_dataset = ERAIntGrbDs(
root_path=input_root,
parameter=variables,
subgrid=None,
array_1D=True,
mask_seapoints=mask_seapoints,
h_steps=h_steps,
)
elif filetype == "netcdf":
input_dataset = ERAIntNcDs(
root_path=input_root,
parameter=variables,
subgrid=None,
array_1D=True,
mask_seapoints=mask_seapoints,
h_steps=h_steps,
)
else:
raise Exception("Unknown file format")
if not os.path.exists(outputpath):
os.makedirs(outputpath)
global_attr = {"product": "ERA Interim (from {})".format(filetype)}
# get time series attributes from first day of data.
first_date_time = datetime.combine(startdate.date(), time(h_steps[0], 0))
data = input_dataset.read(first_date_time)
ts_attributes = data.metadata
grid = BasicGrid(data.lon, data.lat)
reshuffler = Img2Ts(
input_dataset=input_dataset,
outputpath=outputpath,
startdate=startdate,
enddate=enddate,
input_grid=grid,
imgbuffer=imgbuffer,
cellsize_lat=5.0,
cellsize_lon=5.0,
ts_dtypes=np.dtype("float32"),
global_attr=global_attr,
zlib=True,
unlim_chunksize=1000,
ts_attributes=ts_attributes,
)
reshuffler.calc()
def reshuffle(input_root,
outputpath,
startdate,
enddate,
parameters=None,
ignore_meta=False,
imgbuffer=200):
"""
Reshuffle method applied to ESA CCI SM images.
Parameters
----------
input_root: string
input path where era interim data was downloaded
outputpath : string
Output path.
startdate : datetime
Start date.
enddate : datetime
End date.
parameters: list, optional (default: None)
parameters to read and convert
If none are passed, we read an image in the root path and use vars from
the image.
imgbuffer: int, optional
How many images to read at once before writing time series.
"""
if not os.path.exists(outputpath):
os.makedirs(outputpath)
file_args, file_vars = parse_filename(input_root)
if parameters is None:
parameters = [p for p in file_vars if p not in ['lat', 'lon', 'time']]
input_dataset = CCI_SM_025Ds(input_root, parameters, array_1D=True)
data = input_dataset.read(startdate)
grid = BasicGrid(data.lon, data.lat)
if not ignore_meta:
global_attr, ts_attributes = read_metadata(
sensortype=file_args['sensor_type'],
version=int(file_args['version']),
varnames=parameters,
subversion=file_args['sub_version'])
else:
global_attr = {'product': 'ESA CCI SM'}
ts_attributes = None
reshuffler = Img2Ts(input_dataset=input_dataset,
outputpath=outputpath,
startdate=startdate,
enddate=enddate,
input_grid=grid,
imgbuffer=imgbuffer,
cellsize_lat=5.0,
cellsize_lon=5.0,
global_attr=global_attr,
zlib=True,
unlim_chunksize=1000,
ts_attributes=ts_attributes)
reshuffler.calc()
def reshuffle(input_root,
outputpath,
startdate,
enddate,
parameters,
land_points=False,
imgbuffer=50):
"""
Reshuffle method applied to ERA-Interim data.
Parameters
----------
input_root: string
input path where era interim data was downloaded
outputpath : string
Output path.
startdate : datetime
Start date.
enddate : datetime
End date.
parameters: list
parameters to read and convert
landpoints: bool
reshuffle land points only (not implemented yet)
imgbuffer: int, optional
How many images to read at once before writing time series.
"""
filetype = get_filetype(input_root)
if filetype == 'grib':
input_dataset = ERAGrbDs(input_root, parameters, expand_grid=False)
elif filetype == 'netcdf':
input_dataset = ERANcDs(input_root,
parameters,
subgrid=False,
array_1D=True)
else:
raise Exception('Unknown file format')
if not os.path.exists(outputpath):
os.makedirs(outputpath)
global_attr = {'product': 'ECMWF Reanalysis from {}'.format(filetype)}
# get time series attributes from first day of data.
data = input_dataset.read(startdate)
ts_attributes = data.metadata
grid = BasicGrid(data.lon, data.lat)
reshuffler = Img2Ts(input_dataset=input_dataset,
outputpath=outputpath,
startdate=startdate,
enddate=enddate,
input_grid=grid,
imgbuffer=imgbuffer,
cellsize_lat=5.0,
cellsize_lon=5.0,
ts_dtypes=np.dtype('float32'),
global_attr=global_attr,
zlib=True,
unlim_chunksize=1000,
ts_attributes=ts_attributes)
reshuffler.calc()
def reshuffle(input_root,
outputpath,
startdate,
enddate,
parameters,
imgbuffer=50):
"""
Reshuffle method applied to ERA-Interim data.
Parameters
----------
input_root: string
input path where era interim data was downloaded
outputpath : string
Output path.
startdate : datetime
Start date.
enddate : datetime
End date.
parameters: list
parameters to read and convert
imgbuffer: int, optional
How many images to read at once before writing time series.
"""
input_dataset = ECMWF_ERA5_025Ds(input_root, parameters, array_1D=True)
if not os.path.exists(outputpath):
os.makedirs(outputpath)
global_attr = {'product': 'ERA5'}
# get time series attributes from first day of data.
data = input_dataset.read(startdate)
ts_attributes = data.metadata
grid = BasicGrid(data.lon, data.lat)
# test
test_data = data['skt']
#test_data_res = np.reshape(test_data, (720,1440))
#test_lon_res = np.reshape(data.lon, (720, 1440))
#test_lat_res = np.reshape(data.lat, (720, 1440))
#test_data_res[test_data_res > 100] = np.nan
#plt.figure(1)
#plt.pcolor(test_lon_res, test_lat_res, test_data_res)
#plt.show()
reshuffler = Img2Ts(input_dataset=input_dataset,
outputpath=outputpath,
startdate=startdate,
enddate=enddate,
input_grid=grid,
imgbuffer=imgbuffer,
cellsize_lat=5.0,
cellsize_lon=5.0,
global_attr=global_attr,
zlib=True,
unlim_chunksize=1000,
ts_attributes=ts_attributes)
reshuffler.calc()
