def _create_coord_list(self):
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import Metadata
from cis.time_util import cis_standard_time_unit as cstu
# These implement a lot of what is necessary, but aren't in CIS style
from acp_utils import rolling_window
from orbit import ATSR
lat_data = []
lon_data = []
time_data = []
for fname in self.filenames:
prod = ATSR(fname)
lat_data.append(prod.lat)
lon_data.append(prod.lon)
time_data.append(prod.get_time())
# TODO: Properly define metadata
lat_meta = Metadata(standard_name="latitude", units="degrees")
lon_meta = Metadata(standard_name="longitude", units="degrees")
time_meta = Metadata(standard_name="time", units=cstu)
lat = Coord(concatenate(lat_data), lat_meta, "Y")
lat.update_shape()
lat.update_range()
lon = Coord(concatenate(lon_data), lon_meta, "Y")
lon.update_shape()
lon.update_range()
time = Coord(concatenate(time_data), time_meta, "T")
time.update_shape()
time.update_range()
return CoordList([lat, lon, time])
def _create_coord_list(self, filenames):
from cis.data_io.netcdf import read_many_files_individually, get_metadata
from cis.data_io.Coord import Coord
from cis.exceptions import InvalidVariableError
try:
variables = ["lon", "lat", "time"]
data = read_many_files_individually(filenames, variables)
except InvalidVariableError:
variables = ["longitude", "latitude", "time"]
data = read_many_files_individually(filenames, variables)
logging.info("Listing coordinates: " + str(variables))
coords = CoordList()
coords.append(
Coord(data[variables[0]], get_metadata(data[variables[0]][0]),
"X"))
coords.append(
Coord(data[variables[1]], get_metadata(data[variables[1]][0]),
"Y"))
coords.append(
self._fix_time(
Coord(data[variables[2]], get_metadata(data[variables[2]][0]),
"T")))
return coords
def setUp(self):
x_points = np.arange(-10, 11, 5)
y_points = np.arange(-5, 6, 5)
y, x = np.meshgrid(y_points, x_points)
x = Coord(
x, Metadata(name='lat', standard_name='latitude', units='degrees'))
y = Coord(
y, Metadata(name='lon', standard_name='longitude',
units='degrees'))
data = np.reshape(np.arange(15) + 1.0, (5, 3))
self.coords = CoordList([x, y])
ug1 = 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), self.coords)
ug2 = UngriddedData(
data * 0.1,
Metadata(standard_name='snowfall_flux',
long_name="TOTAL SNOWFALL RATE: LS+CONV KG/M2/S",
units="kg m-2 s-1",
missing_value=-999), self.coords)
self.ungridded_data_list = UngriddedDataList([ug1, ug2])
def create_coords(self, filenames, usr_variable=None):
from cis.data_io.netcdf import read_many_files_individually, get_metadata
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import UngriddedCoordinates, UngriddedData
from cis.exceptions import InvalidVariableError
variables = [("longitude", "x"), ("latitude", "y")]
# if usr_variable is not None:
# variables.append((usr_variable, ''))
logging.info("Listing coordinates: " + str(variables))
coords = CoordList()
var_data = read_many_files_individually(filenames,
[v[0] for v in variables])
for var, (name, axis) in zip(var_data.values(), variables):
try:
coords.append(Coord(var, get_metadata(var[0]), axis=axis))
except InvalidVariableError:
pass
# Note - We don't need to convert this time coord as it should have been written in our
# 'standard' time unit
if usr_variable is None:
res = UngriddedCoordinates(coords)
else:
usr_var_data = read_many_files_individually(
filenames, usr_variable)[usr_variable]
res = UngriddedData(usr_var_data, get_metadata(usr_var_data[0]),
coords)
return res
def create_coords(self, filenames, variable=None):
"""
Reads the coordinates and data if required from the files
:param filenames: List of filenames to read coordinates from
:param variable: load a variable for the data
:return: Coordinates
"""
from cis.data_io.netcdf import read_many_files_individually
from cis.data_io.Coord import Coord, CoordList
from cis.exceptions import InvalidVariableError
variables = [("longitude", "x"), ("latitude", "y"), ("altitude", "z"), ("time", "t"), ("air_pressure", "p")]
dim_coords = CoordList()
for v in variables:
try:
var_data = read_many_files_individually(filenames, v[0])[v[0]]
dim_coords.append(Coord(var_data, get_metadata(var_data[0]), axis=v[1]))
except InvalidVariableError:
pass
if variable is None:
return UngriddedCoordinates(dim_coords)
else:
all_coords = self._add_aux_coordinate(dim_coords, filenames[0], 'DP_MID',
dim_coords.get_coord(standard_name='time').data.size)
usr_var_data = read_many_files_individually(filenames, variable)[variable]
return UngriddedData(usr_var_data, get_metadata(usr_var_data[0]), all_coords)
def _create_coord_list(self):
"""Read file coordinates into a CIS object"""
from cis.data_io.Coord import Coord, CoordList
from reame.utils import ncdf_read
try:
lon_data, lon_metadata = ncdf_read(self.filenames, "longitude")
lat_data, lat_metadata = ncdf_read(self.filenames, "latitude")
except IndexError:
lon_data, lon_metadata = ncdf_read(self.filenames, "lon")
lat_data, lat_metadata = ncdf_read(self.filenames, "lat")
lat = Coord(lat_data, lat_metadata, "Y")
lat.update_shape()
lat.update_range()
lon = Coord(lon_data, lon_metadata, "X")
lon.update_shape()
lat.update_range()
time_data, time_metadata = ncdf_read(self.filenames, "time")
# Ensure the standard name is set
time_metadata.standard_name = "time"
time = Coord(time_data, time_metadata, "T")
time.convert_TAI_time_to_std_time(ATSR_REFERENCE_TIME)
time.update_shape()
time.update_range()
return CoordList([lat, lon, time])
def _create_coord_list(self, filename):
import numpy as np
coords = CoordList()
time_data = read(filename, 'time')['time']
try:
alt_data = read(filename, 'altitude')['altitude']
except InvalidVariableError:
alt_data = read(filename, 'range')['range']
len_y = alt_data.shape[1]
time_arr = utils.expand_1d_to_2d_array(time_data[:], len_y, axis=1)
t_coord = Coord(time_arr, get_metadata(time_data), axis='x')
t_coord.convert_to_std_time()
coords.append(t_coord)
#alt_arr = utils.expand_1d_to_2d_array(alt_data[:], len_x, axis=0)
alt_arr = alt_data[:, :, 0] #eliminate "angle" axis
#alt_arr = alt_data #eliminate "angle" axis
coords.append(Coord(alt_arr, get_metadata(alt_data), axis='y'))
lat_data = read(filename, 'latitude')['latitude']
lat_arr = np.ones(alt_arr.shape) * lat_data[:]
coords.append(Coord(lat_arr, get_metadata(lat_data)))
lon_data = read(filename, 'longitude')['longitude']
lon_arr = np.ones(alt_arr.shape) * lon_data[:]
coords.append(Coord(lon_arr, get_metadata(lon_data)))
return coords
def __init__(self, data, metadata, coords):
from cis.data_io.Coord import CoordList
from cis.utils import listify
def getmask(arr):
mask = np.ma.getmaskarray(arr)
try:
mask |= np.isnan(arr)
except ValueError:
pass
return mask
data = listify(data)
metadata = listify(metadata)
if isinstance(coords, list):
self._coords = CoordList(coords)
elif isinstance(coords, CoordList):
self._coords = coords
elif isinstance(coords, Coord):
self._coords = CoordList([coords])
else:
raise ValueError("Invalid Coords type")
# Throw out points where any coordinate is masked
combined_mask = np.zeros(data[0].shape, dtype=bool)
for coord in self._coords:
combined_mask |= getmask(coord.data)
for bound in np.moveaxis(coord.bounds, -1, 0):
combined_mask |= getmask(bound)
coord.update_shape()
coord.update_range()
if combined_mask.any():
keep = np.logical_not(combined_mask)
data = [variable[keep] for variable in data]
for coord in self._coords:
coord.data = coord.data[keep]
new_bounds = np.array([
bound[keep]
for bound in np.moveaxis(coord.bounds, -1, 0)
])
coord.bounds = np.moveaxis(new_bounds, 0, -1)
coord.update_shape()
coord.update_range()
super(UngriddedCube, self).__init__(zip(data, metadata))
def create_dummy_coordinates_list():
coord1 = Coord(numpy.array([5, 4]),
Metadata(standard_name='grid_latitude'),
axis='Y')
coord2 = Coord(numpy.array([5, 4]),
Metadata(standard_name='grid_longitude'),
axis='X')
return CoordList([coord1, coord2])
def create_coords(self, filenames, usr_variable=None):
from cis.data_io.netcdf import read_many_files_individually, get_metadata, get_netcdf_file_variables
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import UngriddedCoordinates, UngriddedData
from cis.exceptions import InvalidVariableError
# We have to read it once first to find out which variables are in there. We assume the set of coordinates in
# all the files are the same
file_variables = get_netcdf_file_variables(filenames[0])
def get_axis_std_name(var):
axis=None
lvar = var.lower()
if lvar == 'longitude':
axis = 'x', 'longitude'
if lvar == 'latitude':
axis = 'y', 'latitude'
if lvar == 'G_ALT' or lvar == 'altitude' or lvar == 'pressure_altitude':
axis = 'z', 'altitude'
if lvar == 'time':
axis = 't', 'time'
if lvar == 'p' or lvar == 'pressure' or lvar == 'static_pressure':
axis = 'p', 'air_pressure'
return axis
all_coord_variables = [(v, get_axis_std_name(v)) for v in file_variables if get_axis_std_name(v) is not None]
# Get rid of any duplicates
coord_variables = []
for v in all_coord_variables:
if v is None or v[1][1] not in [x[1][1] for x in coord_variables]:
coord_variables.append(v)
all_variables = coord_variables.copy()
if usr_variable is not None:
all_variables.append((usr_variable, ''))
logging.info("Listing coordinates: " + str(all_variables))
coords = CoordList()
var_data = read_many_files_individually(filenames, [v[0] for v in all_variables])
for name, axis_std_name in coord_variables:
try:
meta = get_metadata(var_data[name][0])
if meta.standard_name is None:
meta.standard_name = axis_std_name[1]
coords.append(Coord(var_data[name], meta, axis=axis_std_name[0]))
except InvalidVariableError:
pass
# Note - We don't need to convert this time coord as it should have been written in our
# 'standard' time unit
if usr_variable is None:
res = UngriddedCoordinates(coords)
else:
res = UngriddedData(var_data[usr_variable], get_metadata(var_data[usr_variable][0]), coords)
return res
def _create_coord_list(self):
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import Metadata
from cis.time_util import convert_sec_since_to_std_time
from os.path import basename
lat_all = []
lon_all = []
time_all = []
for fname in self.filenames:
var_name = self.gdal_variable_name(fname, "Optical_Depth_055")
if self.grid_path:
granule = basename(fname).split(".")[2]
lat_data, lon_data = self._read_grid_centres(granule)
else:
lat_data, lon_data = self._calculate_grid_centres(var_name)
time_data = self._calculate_grid_time(var_name, lat_data, lon_data)
# Workaround files containing only one day
sh = (-1, ) + lat_data.shape
time_data = time_data.reshape(sh)
keep = np.logical_not(self._read_qcmask(fname)).reshape(sh)
for time_slice, keep_slice in zip(time_data, keep):
lat_all.extend(lat_data[keep_slice])
lon_all.extend(lon_data[keep_slice])
time_all.extend(time_slice[keep_slice])
if len(lat_all) == 0:
raise NotImplementedError("It's empty!")
lat = Coord(
np.ma.array(lat_all),
Metadata(name="lat",
standard_name="latitude",
units="degrees",
range=(-90., 90.)), "Y")
lat.update_shape()
lon = Coord(
np.ma.array(lon_all),
Metadata(name="lon",
standard_name="longitude",
units="degrees",
range=(-180., 180.)), "X")
lon.update_shape()
time = Coord(
np.ma.array(time_all),
Metadata(name="time",
standard_name="time",
units="Seconds since 1993-1-1 00:00:00.0 0"), "T")
time.convert_TAI_time_to_std_time(MODIS_REFERENCE_TIME)
time.update_shape()
# Set the QC mask as we now know how many points we have
self._qcmask = np.full(lat.shape, False)
return CoordList([lat, lon, time])
def _create_coordinates_list(self, data_variables, variable_selector):
"""
Create a co-ordinate list for the data
:param data_variables: the load data
:param variable_selector: the variable selector for the data
:return: a list of coordinates
"""
coords = CoordList()
# Time
time_coord = self._create_time_coord(
variable_selector.time_stamp_info,
variable_selector.time_variable_name, data_variables)
coords.append(time_coord)
# Lat and Lon
# Multiple points counts for multiple files
points_count = [
np.product(var.shape)
for var in data_variables[variable_selector.time_variable_name]
]
if variable_selector.station:
lat_coord = self._create_fixed_value_coord(
"Y", variable_selector.station_latitude, "degrees_north",
points_count, "latitude")
lon_coord = self._create_fixed_value_coord(
"X", variable_selector.station_longitude, "degrees_east",
points_count, "longitude")
else:
lat_coord = self._create_coord(
"Y", variable_selector.latitude_variable_name, data_variables,
"latitude")
lon_coord = self._create_coord(
"X", variable_selector.longitude_variable_name, data_variables,
"longitude")
coords.append(lat_coord)
coords.append(lon_coord)
# Altitude
if variable_selector.altitude is None:
altitude_coord = self._create_coord(
"Z", variable_selector.altitude_variable_name, data_variables,
"altitude")
else:
altitude_coord = self._create_fixed_value_coord(
"Z", variable_selector.altitude, "meters", points_count,
"altitude")
coords.append(altitude_coord)
# Pressure
if variable_selector.pressure_variable_name is not None:
coords.append(
self._create_coord("P",
variable_selector.pressure_variable_name,
data_variables, "air_pressure"))
return coords
def setUp(self):
x_points = np.arange(-10, 11, 5)
y_points = np.arange(-5, 6, 5)
y, x = np.meshgrid(y_points, x_points)
self.x = Coord(x, Metadata(standard_name='latitude', units='degrees'))
self.y = Coord(y, Metadata(standard_name='longitude', units='degrees'))
coords = CoordList([self.x, self.y])
self.ug = UngriddedCoordinates(coords)
def _create_one_dimensional_coord_list(self, filenames, index_offset=1):
"""
Create a set of coordinates appropriate for a ond-dimensional (column integrated) variable
:param filenames:
:param int index_offset: For 5km products this will choose the coordinates which represent the start (0),
middle (1) and end (2) of the 15 shots making up each column retrieval.
:return:
"""
from pyhdf.error import HDF4Error
from cis.data_io import hdf_sd
import datetime as dt
from cis.time_util import convert_sec_since_to_std_time, cis_standard_time_unit
variables = ['Latitude', 'Longitude', "Profile_Time"]
logging.info("Listing coordinates: " + str(variables))
# 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])
# latitude
lat_data = hdf.read_data(sdata['Latitude'], self._get_calipso_data)[:, index_offset]
lat_metadata = hdf.read_metadata(sdata['Latitude'], "SD")
lat_coord = Coord(lat_data, lat_metadata, 'Y')
# longitude
lon = sdata['Longitude']
lon_data = hdf.read_data(lon, self._get_calipso_data)[:, index_offset]
lon_metadata = hdf.read_metadata(lon, "SD")
lon_coord = Coord(lon_data, lon_metadata, 'X')
# profile time, x
time = sdata['Profile_Time']
time_data = hdf.read_data(time, self._get_calipso_data)[:, index_offset]
time_data = convert_sec_since_to_std_time(time_data, dt.datetime(1993, 1, 1, 0, 0, 0))
time_coord = Coord(time_data, Metadata(name='Profile_Time', standard_name='time', shape=time_data.shape,
units=cis_standard_time_unit), "T")
# create the object containing all coordinates
coords = CoordList()
coords.append(lat_coord)
coords.append(lon_coord)
coords.append(time_coord)
return coords
def create_coords(self, filenames):
from cis.data_io.netcdf import read_many_files_individually, get_metadata
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import UngriddedCoordinates
var_data = read_many_files_individually(filenames, ["longitude", "latitude", "time"])
lon = Coord(var_data["longitude"], get_metadata(var_data["longitude"][0]), axis="x")
lat = Coord(var_data["latitude"], get_metadata(var_data["latitude"][0]), axis="y")
time = Coord(var_data["time"], get_metadata(var_data["time"][0]), axis="t")
coords = CoordList([lat, lon, time])
return UngriddedCoordinates(coords)
def create_coords(self, filenames, usr_variable=None):
from cis.data_io.netcdf import read_many_files_individually, get_metadata, get_netcdf_file_variables
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import UngriddedCoordinates, UngriddedData
from cis.exceptions import InvalidVariableError
# We have to read it once first to find out which variables are in there. We assume the set of coordinates in
# all the files are the same
file_variables = get_netcdf_file_variables(filenames[0])
axis_lookup = {
"longitude": "x",
'latitude': 'y',
'altitude': 'z',
'time': 't',
'air_pressure': 'p'
}
coord_variables = [(v, axis_lookup[v]) for v in file_variables
if v in axis_lookup]
# Create a copy to contain all the variables to read
all_variables = list(coord_variables)
if usr_variable is not None:
all_variables.append((usr_variable, ''))
logging.info("Listing coordinates: " + str(all_variables))
coords = CoordList()
var_data = read_many_files_individually(filenames,
[v[0] for v in all_variables])
for name, axis in coord_variables:
try:
coords.append(
Coord(var_data[name],
get_metadata(var_data[name][0]),
axis=axis))
except InvalidVariableError:
pass
# Note - We don't need to convert this time coord as it should have been written in our
# 'standard' time unit
if usr_variable is None:
res = UngriddedCoordinates(coords)
else:
res = UngriddedData(var_data[usr_variable],
get_metadata(var_data[usr_variable][0]),
coords)
return res
def _create_bounded_coord_list(self):
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import Metadata
from cis.time_util import cis_standard_time_unit as cstu
# These implement a lot of what is necessary, but aren't in CIS style
from acp_utils import rolling_window
from orbit import MODIS
lat_data = []
lat_bounds = []
lon_data = []
lon_bounds = []
time_data = []
time_bounds = []
for fname in self.filenames:
prod = MODIS(fname)
lat_data.append(prod.lat)
lon_data.append(prod.lon)
lat_c = rolling_window(prod.lat_corner, (2, 2))
lat_bounds.append(lat_c.reshape(prod.shape + (4, )))
lon_c = rolling_window(prod.lon_corner, (2, 2))
lon_bounds.append(lon_c.reshape(prod.shape + (4, )))
t = prod.get_time()
time_data.append(t)
b = np.stack([t, np.roll(t, -1)], axis=2)
b[-1, :, 1] = 2 * t[-1, :] - t[-2, :]
time_bounds.append(b)
# TODO: Properly define metadata
lat_meta = Metadata(standard_name="latitude", units="degrees")
lon_meta = Metadata(standard_name="longitude", units="degrees")
time_meta = Metadata(standard_name="time", units=cstu)
lat = Coord(concatenate(lat_data), lat_meta, "Y")
lat.update_shape()
lat.update_range()
lat.bounds = concatenate(lat_bounds).reshape(lat.shape + (4, ))
lat.bounds[..., 2:4] = lat.bounds[..., [3, 2]]
lon = Coord(concatenate(lon_data), lon_meta, "Y")
lon.update_shape()
lon.update_range()
lon.bounds = concatenate(lon_bounds).reshape(lon.shape + (4, ))
lon.bounds[..., 2:4] = lon.bounds[..., [3, 2]]
time = Coord(concatenate(time_data), time_meta, "T")
time.update_shape()
time.update_range()
time.bounds = concatenate(time_bounds)
return CoordList([lat, lon, time])
def _create_coord_list(self, filenames, data=None):
if data is None:
data = {} #initialise data dictionary
inData = netCDF4.Dataset(filenames[0]) #open netCDF file
data['longitude'] = np.array(
inData.variables['longitude']) #extract longitudes
data['latitude'] = np.array(
inData.variables['latitude']) #extract latitudes
origTimes = np.array(inData.variables['time']) #extract times
#convert to days since 1600-01-01 (cis col doesn't work otherwise - not sure why...):
niceDateTime = cf_units.num2date(origTimes,
'days since 1990-01-01 00:00:00',
'gregorian')
data['time'] = cf_units.date2num(niceDateTime,
'days since 1600-01-01 00:00:00',
'gregorian')
inData.close() #close netCDF file
coords = CoordList() #initialise coordinate list
#Append latitudes and longitudes to coordinate list:
coords.append(
Coord(
data['longitude'],
Metadata(name="longitude",
long_name='longitude',
standard_name='longitude',
shape=(len(data), ),
missing_value=-999.0,
units="degrees_east",
range=(-180, 180)), "x"))
coords.append(
Coord(
data['latitude'],
Metadata(name="latitude",
long_name='latitude',
standard_name='latitude',
shape=(len(data), ),
missing_value=-999.0,
units="degrees_north",
range=(-90, 90)), "y"))
coords.append(
Coord(
data['time'],
Metadata(name="time",
long_name='time',
standard_name='time',
shape=(len(data), ),
missing_value=-999.0,
units="days since 1600-01-01 00:00:00"), "t"))
return coords
def create_data_object(self, filenames, variable):
from cis.data_io.netcdf import read_many_files_individually, get_metadata
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import UngriddedData
var_data = read_many_files_individually(filenames, ["longitude", "latitude", "time", variable])
lon = Coord(var_data["longitude"], get_metadata(var_data["longitude"][0]), axis="x")
lat = Coord(var_data["latitude"], get_metadata(var_data["latitude"][0]), axis="y")
time = Coord(var_data["time"], get_metadata(var_data["time"][0]), axis="t")
coords = CoordList([lat, lon, time])
usr_var_data = var_data[variable]
return UngriddedData(usr_var_data, get_metadata(usr_var_data[0]), coords)
def _create_coord_list(self, filenames, variable=None):
import datetime as dt
from cis.time_util import convert_time_since_to_std_time, cis_standard_time_unit
from cis.utils import concatenate
from cf_units import Unit
from geotiepoints import modis5kmto1km
variables = ['Latitude', 'Longitude', 'View_time']
logging.info("Listing coordinates: " + str(variables))
sdata, vdata = hdf.read(filenames, variables)
apply_interpolation = False
if variable is not None:
scale = self.__get_data_scale(filenames[0], variable)
apply_interpolation = True if scale is "1km" else False
lat_data = hdf.read_data(sdata['Latitude'], _get_MODIS_SDS_data)
lat_metadata = hdf.read_metadata(sdata['Latitude'], "SD")
lon_data = hdf.read_data(sdata['Longitude'], _get_MODIS_SDS_data)
lon_metadata = hdf.read_metadata(sdata['Longitude'], "SD")
if apply_interpolation:
lon_data, lat_data = modis5kmto1km(lon_data, lat_data)
lat_coord = Coord(lat_data, lat_metadata, 'Y')
lon_coord = Coord(lon_data, lon_metadata, 'X')
time = sdata['View_time']
time_metadata = hdf.read_metadata(time, "SD")
# Ensure the standard name is set
time_metadata.standard_name = 'time'
time_metadata.units = cis_standard_time_unit
t_arrays = []
for f, d in zip(filenames, time):
time_start = self._get_start_date(f)
t_data = _get_MODIS_SDS_data(
d) / 24.0 # Convert hours since to days since
t_offset = time_start - dt.datetime(1600, 1,
1) # Convert to CIS time
t_arrays.append(t_data + t_offset.days)
time_coord = Coord(concatenate(t_arrays), time_metadata, "T")
return CoordList([lat_coord, lon_coord, time_coord])
def test_GIVEN_missing_coord_values_WHEN_coords_THEN_missing_values_removed(
self):
x_points = np.arange(-10, 11, 5)
y_points = np.arange(-5, 6, 5)
y, x = np.meshgrid(y_points, x_points)
y = np.ma.masked_array(y, np.zeros(y.shape, dtype=bool))
y.mask[1, 2] = True
x = Coord(x, Metadata(standard_name='latitude', units='degrees'))
y = Coord(y, Metadata(standard_name='longitude', units='degrees'))
coords = CoordList([x, y])
ug = UngriddedCoordinates(coords)
coords = ug.coords()
for coord in coords:
assert_that(len(coord.data), is_(14))
def test_GIVEN_missing_coord_values_WHEN_data_flattened_THEN_missing_values_removed(
self):
x_points = np.arange(-10, 11, 5)
y_points = np.arange(-5, 6, 5)
y, x = np.meshgrid(y_points, x_points)
y = np.ma.masked_array(y, np.zeros(y.shape, dtype=bool))
y.mask[1, 2] = True
x = Coord(x, Metadata(standard_name='latitude', units='degrees'))
y = Coord(y, Metadata(standard_name='longitude', units='degrees'))
coords = CoordList([x, y])
data = np.reshape(np.arange(15) + 1.0, (5, 3))
ug = UngriddedData(None, Metadata(), coords, lambda x: data)
data = ug.data_flattened
assert_that(len(data), is_(14))
def _create_coord_list(self, filenames, data=None):
from cis.data_io.ungridded_data import Metadata
from cis.data_io.aeronet import load_multiple_aeronet
from cis.time_util import cis_standard_time_unit as ct
if data is None:
data = load_multiple_aeronet(filenames)
coords = CoordList()
coords.append(Coord(data['longitude'], Metadata(name="Longitude", shape=(len(data),),
units="degrees_east", range=(-180, 180))))
coords.append(Coord(data['latitude'], Metadata(name="Latitude", shape=(len(data),),
units="degrees_north", range=(-90, 90))))
coords.append(Coord(data['altitude'], Metadata(name="Altitude", shape=(len(data),), units="meters")))
coords.append(Coord(data["datetime"], Metadata(name="DateTime", standard_name='time', shape=(len(data),),
units=ct), "X"))
return coords
def _create_one_dimensional_coord_list(self, filenames):
from cis.time_util import cis_standard_time_unit
# list of coordinate variables we are interested in
variables = [
'MODIS_latitude', 'MODIS_longitude', 'TAI_start', 'Profile_time'
]
# reading the various files
logging.info("Listing coordinates: " + str(variables))
sdata, vdata = hdf.read(filenames, variables)
# latitude
lat = sdata['MODIS_latitude']
lat_data = hdf.read_data(lat, self._get_cloudsat_sds_data)
lat_metadata = hdf.read_metadata(lat, "SD")
lat_metadata.shape = lat_data.shape
lat_metadata.standard_name = 'latitude'
lat_coord = Coord(lat_data, lat_metadata)
# longitude
lon = sdata['MODIS_longitude']
lon_data = hdf.read_data(lon, self._get_cloudsat_sds_data)
lon_metadata = hdf.read_metadata(lon, "SD")
lon_metadata.shape = lon_data.shape
lon_metadata.standard_name = 'longitude'
lon_coord = Coord(lon_data, lon_metadata)
# time coordinate
time_data = self._generate_time_array(vdata)
time_coord = Coord(
time_data,
Metadata(name='Profile_time',
standard_name='time',
shape=time_data.shape,
units=cis_standard_time_unit), "X")
# create object containing list of coordinates
coords = CoordList()
coords.append(lat_coord)
coords.append(lon_coord)
coords.append(time_coord)
return coords
def create_coords(self, filenames):
from cis.data_io.Coord import Coord, CoordList
from cis.data_io.ungridded_data import UngriddedCoordinates, Metadata
# FIXME
var_data = None
lon = Coord(var_data["longitude"],
get_metadata(var_data["longitude"][0]),
axis="x")
lat = Coord(var_data["latitude"],
get_metadata(var_data["latitude"][0]),
axis="y")
time = Coord(var_data["time"],
get_metadata(var_data["time"][0]),
axis="t")
coords = CoordList([lon, lat, time])
return UngriddedCoordinates(coords)
def create_coords(self, filenames, variable=None):
from cis.data_io.ungridded_data import Metadata
from numpy import genfromtxt, NaN
from cis.exceptions import InvalidVariableError
from cis.time_util import convert_datetime_to_std_time
import dateutil.parser as du
array_list = []
for filename in filenames:
try:
array_list.append(genfromtxt(filename, dtype="f8,f8,f8,O,f8",
names=['latitude', 'longitude', 'altitude', 'time', 'value'],
delimiter=',', missing_values='', usemask=True, invalid_raise=True,
converters={"time": du.parse}))
except:
raise IOError('Unable to read file ' + filename)
data_array = utils.concatenate(array_list)
n_elements = len(data_array['latitude'])
coords = CoordList()
coords.append(Coord(data_array["latitude"],
Metadata(standard_name="latitude", shape=(n_elements,), units="degrees_north")))
coords.append(Coord(data_array["longitude"],
Metadata(standard_name="longitude", shape=(n_elements,), units="degrees_east")))
coords.append(
Coord(data_array["altitude"], Metadata(standard_name="altitude", shape=(n_elements,), units="meters")))
time_arr = convert_datetime_to_std_time(data_array["time"])
time = Coord(time_arr,
Metadata(standard_name="time", shape=(n_elements,), units="days since 1600-01-01 00:00:00"))
coords.append(time)
if variable:
try:
data = UngriddedData(data_array['value'], Metadata(name="value", shape=(n_elements,), units="unknown",
missing_value=NaN), coords)
except:
InvalidVariableError("Value column does not exist in file " + filenames)
return data
else:
return UngriddedCoordinates(coords)
def _create_coord_list(self, filenames, data=None):
from cis.data_io.ungridded_data import Metadata
from cis.time_util import cis_standard_time_unit as ct
import numpy as np
if data is None:
data = load_multiple_hysplit(filenames) # TODO error handling
coords = CoordList()
#print(data['DATETIMES'])
latM = Metadata(standard_name="latitude",
shape=(len(data['LAT']), ),
units="degrees_north",
range=(-90, 90))
lonM = Metadata(standard_name="longitude",
shape=(len(data['LON']), ),
units="degrees_east",
range=(-180, 180))
altM = Metadata(standard_name="altitude",
shape=(len(data['ALT']), ),
units="m")
timeM = Metadata(standard_name="time",
shape=(len(data['DATETIMES']), ),
units=str(ct))
#timeM = Metadata(name="DateTime", standard_name="time", shape=(len(data['DATETIMES']),), units=str(ct))
pressM = Metadata(standard_name="air_pressure",
shape=(len(data['PRESSURE']), ),
units="Pa")
#start_timeM = Metadata(name="start_time", standard_name="forecast_reference_time", shape=(len(data['STARTING_TIME']),), units=str(ct))
#start_heightM = Metadata(name="start_height", shape=(len(data['STARTING_HEIGHT']),), units="meters")
#station_noM = Metadata(name="station_no", standard_name="institution", shape=(len(data['STATION_NO']),))
coords.append(Coord(data['DATETIMES'], timeM))
coords.append(Coord(data['PRESSURE'], pressM))
coords.append(Coord(data['LAT'], latM))
coords.append(Coord(data['LON'], lonM))
coords.append(Coord(data['ALT'], altM))
#coords.append(Coord(data['STARTING_TIME'], start_timeM))
#coords.append(Coord(data['STARTING_HEIGHT'], start_heightM))
#coords.append(Coord(data['STATION_NO'], station_noM))
return coords
def create_coords(self, filenames, usr_variable=None):
from cis.data_io.netcdf import read_many_files_individually, get_metadata
from cis.data_io.ungridded_data import UngriddedCoordinates, UngriddedData
from cis.data_io.Coord import Coord, CoordList
from cis.exceptions import InvalidVariableError
variables = [("lon", "x", 'longitude'), ("lat", "y", 'latitude'),
("alt", "z", 'altitude'), ("time", "t", 'time'),
("p", "p", 'air_pressure')]
logging.info("Listing coordinates: " + str(variables))
coords = CoordList()
for variable in variables:
try:
var_data = read_many_files_individually(
filenames, variable[0])[variable[0]]
meta = get_metadata(var_data[0])
meta.standard_name = variable[2]
# Some of the variables have an illegal name attribute...
meta.misc.pop('name', None)
c = Coord(var_data, meta, axis=variable[1])
if variable[1] == 'z':
c.convert_units('m')
coords.append(c)
except InvalidVariableError:
pass
# Note - We don't need to convert this time coord as it should have been written in our
# 'standard' time unit
if usr_variable is None:
res = UngriddedCoordinates(coords)
else:
usr_var_data = read_many_files_individually(
filenames, usr_variable)[usr_variable]
meta = get_metadata(usr_var_data[0])
# Some of the variables have an illegal name attribute...
meta.misc.pop('name', None)
res = UngriddedData(usr_var_data, meta, coords)
return res
def create_coords(self, filenames):
logging.info("gathering coordinates")
for filename in filenames:
data1 = []
data2 = []
data3 = []
logging.info("gathering coordinates metadata")
metadata1 = Metadata()
metadata2 = Metadata()
metadata3 = Metadata()
coord1 = Coord(
data1, metadata1,
'X') # this coordinate will be used as the 'X' axis when plotting
coord2 = Coord(
data2, metadata2,
'Y') # this coordinate will be used as the 'Y' axis when plotting
coord3 = Coord(data3, metadata3)
return CoordList([coord1, coord2, coord3])
def _create_coord_list(self, filenames, variable=None):
import datetime as dt
variables = ['Latitude', 'Longitude', 'Scan_Start_Time']
logging.info("Listing coordinates: " + str(variables))
sdata, vdata = hdf.read(filenames, variables)
apply_interpolation = False
if variable is not None:
scale = self.__get_data_scale(filenames[0], variable)
apply_interpolation = True if scale is "1km" else False
lat = sdata['Latitude']
sd_lat = hdf.read_data(lat, _get_MODIS_SDS_data)
lat_data = self.__field_interpolate(
sd_lat) if apply_interpolation else sd_lat
lat_metadata = hdf.read_metadata(lat, "SD")
lat_coord = Coord(lat_data, lat_metadata, 'Y')
lon = sdata['Longitude']
if apply_interpolation:
lon_data = self.__field_interpolate(
hdf.read_data(lon, _get_MODIS_SDS_data))
else:
lon_data = hdf.read_data(lon, _get_MODIS_SDS_data)
lon_metadata = hdf.read_metadata(lon, "SD")
lon_coord = Coord(lon_data, lon_metadata, 'X')
time = sdata['Scan_Start_Time']
time_metadata = hdf.read_metadata(time, "SD")
# Ensure the standard name is set
time_metadata.standard_name = 'time'
time_coord = Coord(time, time_metadata, "T", _get_MODIS_SDS_data)
time_coord.convert_TAI_time_to_std_time(
dt.datetime(1993, 1, 1, 0, 0, 0))
return CoordList([lat_coord, lon_coord, time_coord])
