def test_aggregating_over_time_with_default_times(self):
from datetime import datetime, timedelta
from cis.time_util import cis_standard_time_unit as tunit
data = make_regular_2d_with_time_ungridded_data()
data.time.convert_to_std_time()
output = data.aggregate(t=slice(None, None, timedelta(days=30)))
expected_t_bounds = [[tunit.date2num(datetime(1984, 8, 27)), tunit.date2num(datetime(1984, 9, 10))]]
assert_arrays_equal(output[0].coord('time').bounds, expected_t_bounds)
assert_arrays_equal(output[0].data, [[[7.5]]])
def test_aggregating_over_time_with_partial_datetime(self):
from cis.time_util import PartialDateTime, cis_standard_time_unit as tunit
from datetime import datetime, timedelta
data = make_regular_2d_with_time_ungridded_data()
data.time.convert_to_std_time()
output = data.aggregate(t=[PartialDateTime(1984,9), timedelta(days=30)])
expected_t_bounds = [[tunit.date2num(datetime(1984, 9, 1)), tunit.date2num(datetime(1984, 10, 1))]]
assert_arrays_almost_equal(output[0].coord('time').bounds, expected_t_bounds)
assert_arrays_almost_equal(output[0].data, [[[10.5]]])
def test_aeronet_time_parsing(self):
# 1.8s
from datetime import datetime
from cis.time_util import cis_standard_time_unit as ct
aeronet_data = load_aeronet(valid_aeronet_filename, [valid_aeronet_variable])
assert_almost_equal(aeronet_data['datetime'][0], ct.date2num(datetime(2003, 9, 25, 6, 47, 9)))
assert_almost_equal(aeronet_data['datetime'][5], ct.date2num(datetime(2003, 9, 25, 7, 10, 37)))
assert_almost_equal(aeronet_data['datetime'][76], ct.date2num(datetime(2003, 9, 27, 13, 28, 2)))
def test_aggregating_over_time_with_default_times(self):
from datetime import datetime, timedelta
from cis.time_util import cis_standard_time_unit as tunit
data = make_regular_2d_with_time_ungridded_data()
data.time.convert_to_std_time()
output = data.aggregate(t=slice(None, None, timedelta(days=30)))
expected_t_bounds = [[
tunit.date2num(datetime(1984, 8, 27)),
tunit.date2num(datetime(1984, 9, 10))
]]
assert_arrays_equal(output[0].coord('time').bounds, expected_t_bounds)
assert_arrays_equal(output[0].data, [[[7.5]]])
def test_aggregating_over_time_with_partial_datetime(self):
from cis.time_util import PartialDateTime, cis_standard_time_unit as tunit
from datetime import datetime, timedelta
data = make_regular_2d_with_time_ungridded_data()
data.time.convert_to_std_time()
output = data.aggregate(
t=[PartialDateTime(1984, 9),
timedelta(days=30)])
expected_t_bounds = [[
tunit.date2num(datetime(1984, 9, 1)),
tunit.date2num(datetime(1984, 10, 1))
]]
assert_arrays_almost_equal(output[0].coord('time').bounds,
expected_t_bounds)
assert_arrays_almost_equal(output[0].data, [[[10.5]]])
def test_pressure_constraint_in_4d(self):
from cis.collocation.col_implementations import SepConstraintKdtree
import datetime as dt
import numpy as np
ug_data = mock.make_regular_4d_ungridded_data()
ug_data_points = ug_data.as_data_frame(time_index=False,
name='vals').dropna(axis=1)
sample_point = pd.Series({
'longitude': [0.0],
'latitude': [0.0],
'altitude': [50.0],
'air_pressure': [24.0],
'time':
[cis_standard_time_unit.date2num(dt.datetime(1984, 8, 29))]
})
constraint = SepConstraintKdtree(p_sep=2)
# This should leave us with 20 points: [ 6. 7. 8. 9. 10.]
# [ 11. 12. 13. 14. 15.]
# [ 16. 17. 18. 19. 20.]
# [ 21. 22. 23. 24. 25.]
ref_vals = np.array([
6., 7., 8., 9., 10., 11., 12., 13., 14., 15., 16., 17., 18., 19.,
20., 21., 22., 23., 24., 25.
])
new_points = constraint.constrain_points(sample_point, ug_data_points)
new_vals = new_points.vals
eq_(ref_vals.size, new_vals.size)
assert (np.equal(ref_vals, new_vals).all())
def test_time_constraint_in_4d(self):
from cis.collocation.col_implementations import SepConstraintKdtree
import datetime as dt
import numpy as np
ug_data = mock.make_regular_4d_ungridded_data()
ug_data_points = ug_data.as_data_frame(time_index=False,
name='vals').dropna(axis=1)
sample_point = pd.Series({
'longitude': [0.0],
'latitude': [0.0],
'altitude': [50.0],
'time':
[cis_standard_time_unit.date2num(dt.datetime(1984, 8, 29))]
})
# 1 day (and a little bit) time seperation
constraint = SepConstraintKdtree(t_sep='P1dT1M')
# This should leave us with 30 points
ref_vals = np.reshape(np.arange(50) + 1.0, (10, 5))[:, 1:4].flatten()
new_points = constraint.constrain_points(sample_point, ug_data_points)
new_vals = new_points.vals
eq_(ref_vals.size, new_vals.size)
assert (np.equal(ref_vals, new_vals).all())
def test_alt_constraint_in_4d(self):
from cis.collocation.col_implementations import SepConstraintKdtree
import datetime as dt
import numpy as np
ug_data = mock.make_regular_4d_ungridded_data()
ug_data_points = ug_data.as_data_frame(time_index=False,
name='vals').dropna(axis=1)
sample_point = pd.Series({
'longitude': [0.0],
'latitude': [0.0],
'altitude': [50.0],
'time':
[cis_standard_time_unit.date2num(dt.datetime(1984, 8, 29))]
})
# 15m altitude separation
a_sep = 15
constraint = SepConstraintKdtree(a_sep=a_sep)
# This should leave us with 15 points: [ 21. 22. 23. 24. 25.]
# [ 26. 27. 28. 29. 30.]
# [ 31. 32. 33. 34. 35.]
ref_vals = np.array([
21., 22., 23., 24., 25., 26., 27., 28., 29., 30., 31., 32., 33.,
34., 35.
])
new_points = constraint.constrain_points(sample_point, ug_data_points)
new_vals = new_points.vals
eq_(ref_vals.size, new_vals.size)
assert (np.equal(ref_vals, new_vals).all())
def test_all_constraints_in_4d(self):
ug_data = mock.make_regular_4d_ungridded_data()
ug_data_points = ug_data.as_data_frame(time_index=False, name='vals').dropna(axis=1)
sample_point = pd.DataFrame(data={'longitude': [0.0], 'latitude': [0.0], 'altitude': [50.0],
'air_pressure': [50.0],
'time': [cis_standard_time_unit.date2num(dt.datetime(1984, 8, 29))]}).iloc[0]
# One degree near 0, 0 is about 110km in latitude and longitude, so 300km should keep us to within 3 degrees
# in each direction
h_sep = 1000
# 15m altitude separation
a_sep = 15
# 1 day (and a little bit) time separation
t_sep = 'P1dT1M'
# Pressure constraint is 50/40 < p_sep < 60/50
p_sep = 1.22
constraint = SepConstraintKdtree(h_sep=h_sep, a_sep=a_sep, p_sep=p_sep, t_sep=t_sep)
index = HaversineDistanceKDTreeIndex()
index.index_data(None, ug_data_points, None)
constraint.haversine_distance_kd_tree_index = index
# This should leave us with 9 points: [[ 22, 23, 24]
# [ 27, 28, 29]
# [ 32, 33, 34]]
ref_vals = np.array([27., 28., 29., 32., 33., 34.])
new_points = constraint.constrain_points(sample_point, ug_data_points)
new_vals = np.sort(new_points.vals)
eq_(ref_vals.size, new_vals.size)
assert (np.equal(ref_vals, new_vals).all())
def parse_as_number_or_standard_time(string):
"""
Parse a string as a number from the command line, or if that fails, as a datetime in standard cis units
:param in_string: String to parse
:return: int, float (possibly representing a time in CIS standard time units)
"""
from datetime import datetime
res = parse_as_number_or_datetime(string)
if isinstance(res, datetime):
res = cis_standard_time_unit.date2num(res)
return res
def parse_as_number_or_standard_time(string):
"""
Parse a string as a number from the command line, or if that fails, as a datetime in standard cis units
:param in_string: String to parse
:return: int, float (possibly representing a time in CIS standard time units)
"""
from datetime import datetime
res = parse_as_number_or_datetime(string)
if isinstance(res, datetime):
res = cis_standard_time_unit.date2num(res)
return res
def load_aeronet(filename, variables=None):
"""
Loads aeronet csv file.
:param filename: data file name
:param variables: A list of variables to return
:return: A dictionary of variables names and numpy arrays containing the data for that variable
"""
from cis.exceptions import InvalidVariableError
from cis.time_util import cis_standard_time_unit
from numpy.ma import masked_invalid
from pandas import read_csv, to_datetime
version = get_aeronet_version(filename)
ordered_vars = get_aeronet_file_variables(filename, version)
if len(ordered_vars) == 0:
return {}
# Load all available geolocation information and any requested variables
cols = [var for var in ("date", "time", "latitude", "longitude", "altitude") if var in ordered_vars]
if cols is not None and variables is not None:
cols.extend(variables)
dtypes = {var:'str' if var in ("date", "time") else "float" for var in cols}
try:
rawd = read_csv(filename, sep=",", header=AERONET_HEADER_LENGTH[version]-1, names=ordered_vars,
index_col=False, usecols=cols, na_values=AERONET_MISSING_VALUE[version], dtype=dtypes,
parse_dates={"datetime":["date", "time"]}, infer_datetime_format=True, dayfirst=True,
error_bad_lines=False, warn_bad_lines=True, #low_memory="All_Sites_Times_All_Points" in filename
)
except ValueError:
raise InvalidVariableError("{} not available in {}".format(variables, filename))
# Empty file
if rawd.shape[0] == 0:
return {"datetime":[], "latitude":[], "longitude":[], "altitude":[]}
# Convert pandas Timestamps into CIS standard numbers
rawd["datetime"] = [cis_standard_time_unit.date2num(timestamp.to_pydatetime())
for timestamp in to_datetime(rawd["datetime"], format='%d:%m:%Y %H:%M:%S')]
# Add position metadata that isn't listed in every line for some formats
if version.startswith("MAN"):
rawd["altitude"] = 0.
elif version.endswith("2"):
metadata = get_file_metadata(filename)
rawd["longitude"] = float(metadata.misc[2][1].split("=")[1])
rawd["latitude"] = float(metadata.misc[2][2].split("=")[1])
rawd["altitude"] = float(metadata.misc[2][3].split("=")[1])
return {var : masked_invalid(arr) for var, arr in rawd.items()}
def make_regular_2d_with_time_ungridded_data():
"""
Makes a well defined ungridded data object of shape 5x3 with data as follows
array([[1,2,3],
[4,5,6],
[7,8,9],
[10,11,12],
[13,14,15]])
and coordinates in latitude:
array([[-10,-10,-10],
[-5,-5,-5],
[0,0,0],
[5,5,5],
[10,10,10]])
longitude:
array([[-5,0,5],
[-5,0,5],
[-5,0,5],
[-5,0,5],
[-5,0,5]])
time: np.array( [ 15 day increments from 27th August 1984 ] )
They are different lengths to make it easier to distinguish. Note the latitude increases
as you step through the array in order - so downwards as it's written above
"""
import numpy as np
from cis.data_io.Coord import CoordList, Coord
from cis.data_io.ungridded_data import UngriddedData, Metadata
import datetime
from cis.time_util import cis_standard_time_unit
x_points = np.arange(-10, 11, 5)
y_points = np.arange(-5, 6, 5)
y, x = np.meshgrid(y_points, x_points)
t0 = datetime.datetime(1984, 8, 27)
times = np.reshape(np.array([t0 + datetime.timedelta(days=d) for d in range(15)]), (5, 3))
x = Coord(x, Metadata(standard_name='latitude', units='degrees'))
y = Coord(y, Metadata(standard_name='longitude', units='degrees'))
t = Coord(cis_standard_time_unit.date2num(times), Metadata(standard_name='time', units=cis_standard_time_unit))
data = np.reshape(np.arange(15) + 1.0, (5, 3))
coords = CoordList([x, y, t])
return UngriddedData(data, Metadata(name='rain', standard_name='rainfall_flux', long_name="TOTAL RAINFALL RATE: LS+CONV KG/M2/S",
units="kg m-2 s-1", missing_value=-999), coords)
def test_all_constraints_in_4d(self):
ug_data = mock.make_regular_4d_ungridded_data()
ug_data_points = ug_data.as_data_frame(time_index=False,
name='vals').dropna(axis=1)
sample_point = pd.DataFrame(
data={
'longitude': [0.0],
'latitude': [0.0],
'altitude': [50.0],
'air_pressure': [50.0],
'time':
[cis_standard_time_unit.date2num(dt.datetime(1984, 8, 29))]
}).iloc[0]
# One degree near 0, 0 is about 110km in latitude and longitude, so 300km should keep us to within 3 degrees
# in each direction
h_sep = 1000
# 15m altitude separation
a_sep = 15
# 1 day (and a little bit) time separation
t_sep = 'P1dT1M'
# Pressure constraint is 50/40 < p_sep < 60/50
p_sep = 1.22
constraint = SepConstraintKdtree(h_sep=h_sep,
a_sep=a_sep,
p_sep=p_sep,
t_sep=t_sep)
index = HaversineDistanceKDTreeIndex()
index.index_data(None, ug_data_points, None)
constraint.haversine_distance_kd_tree_index = index
# This should leave us with 9 points: [[ 22, 23, 24]
# [ 27, 28, 29]
# [ 32, 33, 34]]
ref_vals = np.array([27., 28., 29., 32., 33., 34.])
new_points = constraint.constrain_points(sample_point, ug_data_points)
new_vals = np.sort(new_points.vals)
eq_(ref_vals.size, new_vals.size)
assert (np.equal(ref_vals, new_vals).all())
def test_time_constraint_in_4d(self):
from cis.collocation.col_implementations import SepConstraintKdtree
import datetime as dt
import numpy as np
ug_data = mock.make_regular_4d_ungridded_data()
ug_data_points = ug_data.as_data_frame(time_index=False, name='vals').dropna(axis=1)
sample_point = pd.Series({'longitude': [0.0], 'latitude': [0.0], 'altitude':[50.0],
'time': [cis_standard_time_unit.date2num(dt.datetime(1984, 8, 29))]})
# 1 day (and a little bit) time seperation
constraint = SepConstraintKdtree(t_sep='P1dT1M')
# This should leave us with 30 points
ref_vals = np.reshape(np.arange(50) + 1.0, (10, 5))[:, 1:4].flatten()
new_points = constraint.constrain_points(sample_point, ug_data_points)
new_vals = new_points.vals
eq_(ref_vals.size, new_vals.size)
assert (np.equal(ref_vals, new_vals).all())
def make_dummy_ungridded_data_time_series(len=10):
"""
Create a time series of ungridded data of length len, with a single lat/lon coordinate (65.2, -12.1)
:param len: length of teh time series and associated data
:return:
"""
from datetime import datetime, timedelta
from cis.time_util import cis_standard_time_unit
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import UngriddedData, Metadata
t0 = datetime(1984, 8, 27)
times = np.array([t0 + timedelta(days=d) for d in range(len)])
x = Coord(np.zeros(len) + 65.2, Metadata(standard_name='latitude', units='degrees'))
y = Coord(np.zeros(len) - 12.1, Metadata(standard_name='longitude', units='degrees'))
t = Coord(cis_standard_time_unit.date2num(times),
Metadata(standard_name='time', units=cis_standard_time_unit), axis='x')
data = np.arange(len) + 1.0
return UngriddedData(data, Metadata(standard_name='rainfall_flux', long_name="TOTAL RAINFALL RATE: LS+CONV KG/M2/S",
units="kg m-2 s-1", missing_value=-999), CoordList([x, y, t]))
def test_pressure_constraint_in_4d(self):
from cis.collocation.col_implementations import SepConstraintKdtree
import datetime as dt
import numpy as np
ug_data = mock.make_regular_4d_ungridded_data()
ug_data_points = ug_data.as_data_frame(time_index=False, name='vals').dropna(axis=1)
sample_point = pd.Series({'longitude': [0.0], 'latitude': [0.0], 'altitude':[50.0], 'air_pressure': [24.0],
'time': [cis_standard_time_unit.date2num(dt.datetime(1984, 8, 29))]})
constraint = SepConstraintKdtree(p_sep=2)
# This should leave us with 20 points: [ 6. 7. 8. 9. 10.]
# [ 11. 12. 13. 14. 15.]
# [ 16. 17. 18. 19. 20.]
# [ 21. 22. 23. 24. 25.]
ref_vals = np.array([6., 7., 8., 9., 10., 11., 12., 13., 14., 15., 16., 17., 18., 19., 20., 21., 22., 23.,
24., 25.])
new_points = constraint.constrain_points(sample_point, ug_data_points)
new_vals = new_points.vals
eq_(ref_vals.size, new_vals.size)
assert (np.equal(ref_vals, new_vals).all())
def test_alt_constraint_in_4d(self):
from cis.collocation.col_implementations import SepConstraintKdtree
import datetime as dt
import numpy as np
ug_data = mock.make_regular_4d_ungridded_data()
ug_data_points = ug_data.as_data_frame(time_index=False, name='vals').dropna(axis=1)
sample_point = pd.Series({'longitude': [0.0], 'latitude': [0.0], 'altitude':[50.0],
'time': [cis_standard_time_unit.date2num(dt.datetime(1984, 8, 29))]})
# 15m altitude separation
a_sep = 15
constraint = SepConstraintKdtree(a_sep=a_sep)
# This should leave us with 15 points: [ 21. 22. 23. 24. 25.]
# [ 26. 27. 28. 29. 30.]
# [ 31. 32. 33. 34. 35.]
ref_vals = np.array([21., 22., 23., 24., 25., 26., 27., 28., 29., 30., 31., 32., 33., 34., 35.])
new_points = constraint.constrain_points(sample_point, ug_data_points)
new_vals = new_points.vals
eq_(ref_vals.size, new_vals.size)
assert (np.equal(ref_vals, new_vals).all())
def parse_as_number_or_datetime(in_string, name, parser):
"""Parse a string as a number from the command line, or if that fails, as a datetime, reporting parse errors.
The string should be in an ISO 8601 format except that the date and time
parts may be separated by a space or colon instead of T.
:param in_string: String to parse
:param name: A description of the argument used for error messages
:param parser: The parser used to report errors
:return: int, or float value (possibly converted to the standard time from a time string)
"""
import dateutil.parser as du
try:
ret = int(in_string)
except ValueError:
try:
ret = float(in_string)
except ValueError:
try:
ret = cis_standard_time_unit.date2num(du.parse(in_string))
except ValueError:
parser.error("'" + in_string + "' is not a valid " + name)
ret = None
return ret
def create_data_object(self, filenames, variable, index_offset=1):
from cis.data_io.hdf_vd import get_data
from cis.data_io.hdf_vd import VDS
from pyhdf.error import HDF4Error
from cis.data_io import hdf_sd
from iris.coords import DimCoord, AuxCoord
from iris.cube import Cube, CubeList
from cis.data_io.gridded_data import GriddedData
from cis.time_util import cis_standard_time_unit
from datetime import datetime
from iris.util import new_axis
import numpy as np
logging.debug("Creating data object for variable " + variable)
variables = ["Pressure_Mean"]
logging.info("Listing coordinates: " + str(variables))
variables.append(variable)
# reading data from files
sdata = {}
for filename in filenames:
try:
sds_dict = hdf_sd.read(filename, variables)
except HDF4Error as e:
raise IOError(str(e))
for var in list(sds_dict.keys()):
utils.add_element_to_list_in_dict(sdata, var, sds_dict[var])
# work out size of data arrays
# the coordinate variables will be reshaped to match that.
# NOTE: This assumes that all Caliop_L1 files have the same altitudes.
# If this is not the case, then the following line will need to be changed
# to concatenate the data from all the files and not just arbitrarily pick
# the altitudes from the first file.
alt_data = self._get_calipso_data(hdf_sd.HDF_SDS(filenames[0], 'Altitude_Midpoint'))[0, :]
alt_coord = DimCoord(alt_data, standard_name='altitude', units='km')
alt_coord.convert_units('m')
lat_data = self._get_calipso_data(hdf_sd.HDF_SDS(filenames[0], 'Latitude_Midpoint'))[0, :]
lat_coord = DimCoord(lat_data, standard_name='latitude', units='degrees_north')
lon_data = self._get_calipso_data(hdf_sd.HDF_SDS(filenames[0], 'Longitude_Midpoint'))[0, :]
lon_coord = DimCoord(lon_data, standard_name='longitude', units='degrees_east')
cubes = CubeList()
for f in filenames:
t = get_data(VDS(f, "Nominal_Year_Month"), True)[0]
time_data = cis_standard_time_unit.date2num(datetime(int(t[0:4]), int(t[4:6]), 15))
time_coord = AuxCoord(time_data, long_name='Profile_Time', standard_name='time',
units=cis_standard_time_unit)
# retrieve data + its metadata
var = sdata[variable]
metadata = hdf.read_metadata(var, "SD")
data = self._get_calipso_data(hdf_sd.HDF_SDS(f, variable))
pres_data = self._get_calipso_data(hdf_sd.HDF_SDS(f, 'Pressure_Mean'))
pres_coord = AuxCoord(pres_data, standard_name='air_pressure', units='hPa')
if data.ndim == 2:
# pres_coord = new_axis()
cube = Cube(data, long_name=metadata.long_name or variable, units=self.clean_units(metadata.units),
dim_coords_and_dims=[(lat_coord, 0), (lon_coord, 1)],
aux_coords_and_dims=[(time_coord, ())])
# Promote the time scalar coord to a length one dimension
new_cube = new_axis(cube, 'time')
cubes.append(new_cube)
elif data.ndim == 3:
# pres_coord = new_axis()
cube = Cube(data, long_name=metadata.long_name or variable, units=self.clean_units(metadata.units),
dim_coords_and_dims=[(lat_coord, 0), (lon_coord, 1), (alt_coord, 2)],
aux_coords_and_dims=[(time_coord, ())])
# Promote the time scalar coord to a length one dimension
new_cube = new_axis(cube, 'time')
# Then add the (extended) pressure coord so that it is explicitly a function of time
new_cube.add_aux_coord(pres_coord[np.newaxis, ...], (0, 1, 2, 3))
cubes.append(new_cube)
else:
raise ValueError("Unexpected number of dimensions for CALIOP data: {}".format(data.ndim))
# Concatenate the cubes from each file into a single GriddedData object
gd = GriddedData.make_from_cube(cubes.concatenate_cube())
return gd
def parse_datetimestr_to_std_time(s):
import dateutil.parser as du
return cis_standard_time_unit.date2num(du.parse(s))
def create_data_object(self, filenames, variable):
from netCDF4 import Dataset
from biggus import OrthoArrayAdapter
from iris.cube import Cube, CubeList
from iris.coords import DimCoord
from iris.fileformats.netcdf import NetCDFDataProxy
from datetime import datetime
from os.path import basename
from cis.time_util import cis_standard_time_unit
from cis.data_io.gridded_data import make_from_cube
import numpy as np
cubes = CubeList()
for f in filenames:
# Open the file
ds = Dataset(f)
# E.g. 'NO2.COLUMN.VERTICAL.TROPOSPHERIC.CS30_BACKSCATTER.SOLAR'
v = ds.variables[variable]
# Get the coords
lat = ds.variables['LATITUDE']
lon = ds.variables['LONGITUDE']
# Create a biggus adaptor over the data
scale_factor = getattr(v, 'scale_factor', None)
add_offset = getattr(v, 'add_offset', None)
if scale_factor is None and add_offset is None:
v_dtype = v.datatype
elif scale_factor is not None:
v_dtype = scale_factor.dtype
else:
v_dtype = add_offset.dtype
# proxy = NetCDFDataProxy(v.shape, v_dtype, f, variable, float(v.VAR_FILL_VALUE))
# a = OrthoArrayAdapter(proxy)
# Mask out all invalid values (NaN, Inf, etc)
a = np.ma.masked_invalid(v[:])
# Set everything negative to NaN
a = np.ma.masked_less(a, 0.0)
# Just read the lat and lon in directly
lat_coord = DimCoord(lat[:], standard_name='latitude', units='degrees', long_name=lat.VAR_DESCRIPTION)
lon_coord = DimCoord(lon[:], standard_name='longitude', units='degrees', long_name=lon.VAR_DESCRIPTION)
# Pull the date out of the filename
fname = basename(f)
dt = datetime.strptime(fname[:10], "%Y_%m_%d")
t_coord = DimCoord(cis_standard_time_unit.date2num(dt), standard_name='time', units=cis_standard_time_unit)
c = Cube(a, long_name=getattr(v, "VAR_DESCRIPTION", None), units=getattr(v, "VAR_UNITS", None),
dim_coords_and_dims=[(lat_coord, 0), (lon_coord, 1)])
c.add_aux_coord(t_coord)
# Close the file
ds.close()
cubes.append(c)
# We have a scalar time coord and no conflicting metadata so this should just create one cube...
merged = cubes.merge_cube()
# Return as a CIS GriddedData object
return make_from_cube(merged)
def create_data_object(self, filenames, variable, index_offset=1):
from cis.data_io.hdf_vd import get_data
from cis.data_io.hdf_vd import VDS
from pyhdf.error import HDF4Error
from cis.data_io import hdf_sd
from iris.coords import DimCoord, AuxCoord
from iris.cube import Cube, CubeList
from cis.data_io.gridded_data import GriddedData
from cis.time_util import cis_standard_time_unit
from datetime import datetime
from iris.util import new_axis
import numpy as np
logging.debug("Creating data object for variable " + variable)
variables = ["Pressure_Mean"]
logging.info("Listing coordinates: " + str(variables))
variables.append(variable)
# reading data from files
sdata = {}
for filename in filenames:
try:
sds_dict = hdf_sd.read(filename, variables)
except HDF4Error as e:
raise IOError(str(e))
for var in list(sds_dict.keys()):
utils.add_element_to_list_in_dict(sdata, var, sds_dict[var])
# work out size of data arrays
# the coordinate variables will be reshaped to match that.
# NOTE: This assumes that all Caliop_L1 files have the same altitudes.
# If this is not the case, then the following line will need to be changed
# to concatenate the data from all the files and not just arbitrarily pick
# the altitudes from the first file.
alt_data = self._get_calipso_data(
hdf_sd.HDF_SDS(filenames[0], 'Altitude_Midpoint'))[0, :]
alt_coord = DimCoord(alt_data, standard_name='altitude', units='km')
alt_coord.convert_units('m')
lat_data = self._get_calipso_data(
hdf_sd.HDF_SDS(filenames[0], 'Latitude_Midpoint'))[0, :]
lat_coord = DimCoord(lat_data,
standard_name='latitude',
units='degrees_north')
lon_data = self._get_calipso_data(
hdf_sd.HDF_SDS(filenames[0], 'Longitude_Midpoint'))[0, :]
lon_coord = DimCoord(lon_data,
standard_name='longitude',
units='degrees_east')
cubes = CubeList()
for f in filenames:
t = get_data(VDS(f, "Nominal_Year_Month"), True)[0]
time_data = cis_standard_time_unit.date2num(
datetime(int(t[0:4]), int(t[4:6]), 15))
time_coord = AuxCoord(time_data,
long_name='Profile_Time',
standard_name='time',
units=cis_standard_time_unit)
# retrieve data + its metadata
var = sdata[variable]
metadata = hdf.read_metadata(var, "SD")
data = self._get_calipso_data(hdf_sd.HDF_SDS(f, variable))
pres_data = self._get_calipso_data(
hdf_sd.HDF_SDS(f, 'Pressure_Mean'))
pres_coord = AuxCoord(pres_data,
standard_name='air_pressure',
units='hPa')
if data.ndim == 2:
# pres_coord = new_axis()
cube = Cube(data,
long_name=metadata.long_name or variable,
units=self.clean_units(metadata.units),
dim_coords_and_dims=[(lat_coord, 0),
(lon_coord, 1)],
aux_coords_and_dims=[(time_coord, ())])
# Promote the time scalar coord to a length one dimension
new_cube = new_axis(cube, 'time')
cubes.append(new_cube)
elif data.ndim == 3:
# pres_coord = new_axis()
cube = Cube(data,
long_name=metadata.long_name or variable,
units=self.clean_units(metadata.units),
dim_coords_and_dims=[(lat_coord, 0),
(lon_coord, 1),
(alt_coord, 2)],
aux_coords_and_dims=[(time_coord, ())])
# Promote the time scalar coord to a length one dimension
new_cube = new_axis(cube, 'time')
# Then add the (extended) pressure coord so that it is explicitly a function of time
new_cube.add_aux_coord(pres_coord[np.newaxis, ...],
(0, 1, 2, 3))
cubes.append(new_cube)
else:
raise ValueError(
"Unexpected number of dimensions for CALIOP data: {}".
format(data.ndim))
# Concatenate the cubes from each file into a single GriddedData object
gd = GriddedData.make_from_cube(cubes.concatenate_cube())
return gd
def parse_datetimestr_to_std_time(s):
import dateutil.parser as du
return cis_standard_time_unit.date2num(du.parse(s))
def parse_as_number_or_datetime_can_parse_date_as_datetime():
from datetime import datetime
from cis.time_util import cis_standard_time_unit
parser = MockParser()
dt = parse_as_number_or_datetime('2010-07-01', 'date/time arg', parser)
assert (dt == cis_standard_time_unit.date2num(datetime(2010, 7, 1)))
