def setUp(self):
#print 'Creating temporary file: ', filename
self.filename = tempfile.mktemp(prefix="test_", suffix=".nc")
do_setup(self.filename)
opt = Nio.options()
opt.MaskedArrayMode = 'MaskedAlways'
self.f = Nio.open_file(self.filename, options=opt)
def create_file(self, new_file_name, ncformat, hist_string=None):
"""
Create a NetCDF file for writing.
Parameters:
new_file_name (str): Name, including full path, of the new
NetCDF file to create.
ncformat (str): Type of NetCDF file to create.
Options:
'netcdf4c': NetCDF4 with Level 1 compression
'NetCDF4Classic': NetCDF4 Classic
'Classic': NetCDF3
'netcdfLarge': NetCDF 64bit Offset
hist_string (str): Optional. A string to append to the histroy attribute.
Returns:
new_file (NioFile): A pointer to a NioFile object.
"""
# Set pyNIO netcdf file options
opt = Nio.options()
# The netcdf output format
if "netcdf4c" in ncformat:
opt.Format = "NetCDF4Classic"
if ncformat[-1].isdigit():
opt.CompressionLevel = ncformat[-1]
elif ncformat == "netcdf4":
opt.Format = "NetCDF4Classic"
elif ncformat == "netcdf":
opt.Format = "Classic"
elif ncformat == "netcdfLarge":
opt.Format = "64BitOffset"
else:
print(
"WARNING: Selected netcdf file format (",
ncformat,
") is not recongnized.",
)
print("Defaulting to netcdf4Classic format.")
opt.Format = "NetCDF4Classic"
opt.PreFill = False
if hist_string is None:
hist_string = "clim-convert" + new_file_name
# Open new output file
new_file = Nio.open_file(new_file_name, "w", options=opt, history=hist_string)
return new_file
def test_large(self):
#
# Creating a file
#
#init_time = time.clock()
opt = Nio.options()
opt.Format = "LargeFile"
opt.PreFill = False
f = Nio.open_file(self.filename, 'w', options=opt)
f.title = "Testing large files and dimensions"
f.create_dimension('big', 2500000000)
bigvar = f.create_variable('bigvar', "b", ('big',))
#print("created bigvar")
# note it is incredibly slow to write a scalar to a large file variable
# so create an temporary variable x that will get assigned in steps
x = np.empty(1000000,dtype = 'int8')
#print x
x[:] = 42
t = list(range(0,2500000000,1000000))
ii = 0
for i in t:
if (i == 0):
continue
#print(t[ii],i)
bigvar[t[ii]:i] = x[:]
ii += 1
x[:] = 84
bigvar[2499000000:2500000000] = x[:]
bigvar[-1] = 84
bigvar.units = "big var units"
#print bigvar[-1]
#print(bigvar.dimensions)
# check unlimited status
#print(f)
nt.assert_equal(bigvar.dimensions, ('big',))
nt.assert_equal(f.unlimited('big'), False)
nt.assert_equal(f.attributes, {'title': 'Testing large files and dimensions'})
nt.assert_equal(f.dimensions, {'big': 2500000000})
nt.assert_equal(list(f.variables.keys()), ['bigvar'])
#print("closing file")
#print('elapsed time: ',time.clock() - init_time)
f.close()
#quit()
#
# Reading a file
#
#print('opening file for read')
#print('elapsed time: ',time.clock() - init_time)
f = Nio.open_file(self.filename, 'r')
#print('file is open')
#print('elapsed time: ',time.clock() - init_time)
nt.assert_equal(f.attributes, {'title': 'Testing large files and dimensions'})
nt.assert_equal(f.dimensions, {'big': 2500000000})
nt.assert_equal(list(f.variables.keys()), ['bigvar'])
#print(f.dimensions)
#print(list(f.variables.keys()))
#print(f)
#print("reading variable")
#print('elapsed time: ',time.clock() - init_time)
x = f.variables['bigvar']
#print(x[0],x[1000000],x[249000000],x[2499999999])
nt.assert_equal((x[0],x[1000000],x[249000000],x[2499999999]), (42, 42, 42, 84))
#print("max and min")
min = x[:].min()
max = x[:].max()
nt.assert_equal((x[:].min(), x[:].max()), (42, 84))
# check unlimited status
nt.assert_equal(f.variables['bigvar'].dimensions, ('big',))
nt.assert_equal(f.unlimited('big'), False)
#print("closing file")
#print('elapsed time: ',time.clock() - init_time)
f.close()
def __init__(self, specifier, serial=False, verbosity=1,
skip_existing=False, overwrite=False,
once=False, simplecomm=None):
"""
Constructor
Parameters:
specifier (Specifier): An instance of the Specifier class,
defining the input specification for this reshaper operation.
Keyword Arguments:
serial (bool): True or False, indicating whether the operation
should be performed in serial (True) or parallel
(False). The default is to assume parallel operation
(but serial will be chosen if the mpi4py cannot be
found when trying to initialize decomposition.
verbosity(int): Level of printed output (stdout). A value of 0
means no output, and a higher value means more output. The
default value is 1.
skip_existing (bool): Flag specifying whether to skip the generation
of time-series for variables with time-series files that already
exist. Default is False.
overwrite (bool): Flag specifying whether to forcefully overwrite
output files if they already exist. Default is False.
once (bool): True or False, indicating whether the Reshaper should
write all metadata to a 'once' file (separately).
simplecomm (SimpleComm): A SimpleComm object to handle the parallel
communication, if necessary
"""
# Type checking (or double-checking)
if not isinstance(specifier, Specifier):
err_msg = "Input must be given in the form of a Specifier object"
raise TypeError(err_msg)
if type(serial) is not bool:
err_msg = "Serial indicator must be True or False."
raise TypeError(err_msg)
if type(verbosity) is not int:
err_msg = "Verbosity level must be an integer."
raise TypeError(err_msg)
if type(skip_existing) is not bool:
err_msg = "Skip_existing flag must be True or False."
raise TypeError(err_msg)
if type(once) is not bool:
err_msg = "Once-file indicator must be True or False."
raise TypeError(err_msg)
if simplecomm is not None:
if not (isinstance(simplecomm, SimpleComm) or \
isinstance(simplecomm, SimpleCommMPI)):
err_msg = ("Simple communicator object is not a SimpleComm or ",
"SimpleCommMPI")
raise TypeError(err_msg)
# Whether to write a once file
self._use_once_file = once
# Internal timer data
self._timer = TimeKeeper()
# Dictionary storing read/write data amounts
self.assumed_block_size = float(4 * 1024 * 1024)
self._byte_counts = {}
self._timer.start('Initializing Simple Communicator')
if simplecomm is None:
simplecomm = create_comm(serial=serial)
# Reference to the simple communicator
self._simplecomm = simplecomm
self._timer.stop('Initializing Simple Communicator')
# Contruct the print header
header = ''.join(['[', str(self._simplecomm.get_rank()),
'/', str(self._simplecomm.get_size()), '] '])
# Reference to the verbose printer tool
self._vprint = VPrinter(header=header, verbosity=verbosity)
# Debug output starting
if self._simplecomm.is_manager():
self._vprint('Initializing Reshaper', verbosity=1)
# Validate the user input data
self._timer.start('Specifier Validation')
specifier.validate()
self._timer.stop('Specifier Validation')
if self._simplecomm.is_manager():
self._vprint('Specifier validated', verbosity=1)
# Setup PyNIO options (including disabling the default PreFill option)
opt = Nio.options()
opt.PreFill = False
# Determine the Format and CompressionLevel options
# from the NetCDF format string in the Specifier
if specifier.netcdf_format == 'netcdf':
opt.Format = 'Classic'
elif specifier.netcdf_format == 'netcdf4':
opt.Format = 'NetCDF4Classic'
opt.CompressionLevel = 0
elif specifier.netcdf_format == 'netcdf4c':
opt.Format = 'NetCDF4Classic'
opt.CompressionLevel = specifier.netcdf_deflate
if self._simplecomm.is_manager():
self._vprint('PyNIO compression level: {0}'.format(\
specifier.netcdf_deflate), verbosity=2)
self._nio_options = opt
if self._simplecomm.is_manager():
self._vprint('PyNIO options set', verbosity=2)
# Open all of the input files
self._timer.start('Open Input Files')
self._input_files = []
for filename in specifier.input_file_list:
self._input_files.append(Nio.open_file(filename, "r"))
self._timer.stop('Open Input Files')
if self._simplecomm.is_manager():
self._vprint('Input files opened', verbosity=2)
# Validate the input files themselves
self._timer.start('Input File Validation')
self._validate_input_files(specifier)
self._timer.stop('Input File Validation')
if self._simplecomm.is_manager():
self._vprint('Input files validated', verbosity=2)
# Sort the input files by time
self._timer.start('Sort Input Files')
self._sort_input_files_by_time(specifier)
self._timer.stop('Sort Input Files')
if self._simplecomm.is_manager():
self._vprint('Input files sorted', verbosity=2)
# Retrieve and sort the variables in each time-slice file
# (To determine if it is time-invariant metadata, time-variant
# metadata, or if it is a time-series variable)
self._timer.start('Sort Variables')
self._sort_variables(specifier)
self._timer.stop('Sort Variables')
if self._simplecomm.is_manager():
self._vprint('Variables sorted', verbosity=2)
# Validate the output files
self._timer.start('Output File Validation')
self._validate_output_files(specifier, skip_existing, overwrite)
self._timer.stop('Output File Validation')
if self._simplecomm.is_manager():
self._vprint('Output files validated', verbosity=2)
# Helpful debugging message
if self._simplecomm.is_manager():
self._vprint('Reshaper initialized.', verbosity=1)
# Sync before continuing..
self._simplecomm.sync()
def setUp(self):
do_setup(filename)
opt = Nio.options()
opt.UseAxisAttribute = True
self.f = Nio.open_file(filename, options=opt)
def setUp(self):
# print 'Creating temporary file: ', filename
do_setup(filename)
opt = Nio.options()
opt.MaskedArrayMode = "MaskedAlways"
self.f = Nio.open_file(filename, options=opt)
def setUp(self):
do_setup(filename)
opt = Nio.options()
opt.MaskedArrayMode = "MaskedExplicit"
self.f = Nio.open_file(filename, options=opt)
def setUp(self):
self.filename = tempfile.mktemp(prefix="test_", suffix=".nc")
do_setup(self.filename)
opt = Nio.options()
opt.MaskedArrayMode = 'MaskedExplicit'
self.f = Nio.open_file(self.filename, options=opt)
def open_new_file(self,
file_name,
z_values=numpy.arange(10),
z_units='m',
var_names=['X'],
long_names=[None],
units_names=['None'],
dtypes=['float64'],
time_units='minutes',
comment=''):
#----------------------------------------------------
# Notes: It might be okay to have "nz" be an
# unlimited dimension, like "time". This
# would mean replacing "int(profile_length)"
# with "None".
#----------------------------------------------------
#--------------------------------------------------
# Try to import the Nio module from PyNIO package
#--------------------------------------------------
Nio = self.import_nio()
if not (Nio): return False
#----------------------------
# Does file already exist ?
#----------------------------
file_name = file_utils.check_overwrite(file_name)
self.file_name = file_name
#---------------------------------------
# Check and store the time series info
#---------------------------------------
self.format = 'ncps'
self.file_name = file_name
self.time_index = 0
if (long_names[0] is None):
long_names = var_names
#-------------------------------------------
self.z_values = z_values
self.z_units = z_units
nz = numpy.size(z_values)
#-------------------------------------------
# We may not need to save these in self.
# I don't think they're used anywhere yet.
#-------------------------------------------
self.var_names = var_names
self.long_names = long_names
self.units_names = units_names
self.dtypes = dtypes
#---------------------------------------------
# Create array of Nio type codes from dtypes
#---------------------------------------------
nio_type_map = self.get_nio_type_map()
nio_type_codes = []
if (len(dtypes) == len(var_names)):
for dtype in dtypes:
nio_type_code = nio_type_map[dtype.lower()]
nio_type_codes.append(nio_type_code)
else:
dtype = dtypes[0]
nio_type_code = nio_type_map[dtype.lower()]
for k in xrange(len(var_names)):
nio_type_codes.append(nio_type_code)
self.nio_type_codes = nio_type_codes
#-------------------------------------
# Open a new netCDF file for writing
#-------------------------------------
# Sample output from time.asctime():
# "Thu Oct 8 17:10:18 2009"
#-------------------------------------
opt = Nio.options()
opt.PreFill = False # (for efficiency)
opt.HeaderReserveSpace = 4000 # (4000 bytes, for efficiency)
history = "Created using PyNIO " + Nio.__version__ + " on "
history = history + time.asctime() + ". "
history = history + comment
try:
ncps_unit = Nio.open_file(file_name,
mode="w",
options=opt,
history=history)
OK = True
except:
OK = False
return OK
#------------------------------------------------
# Create an unlimited time dimension (via None)
#------------------------------------------------
# Without using "int()" here, we get this:
# TypeError: size must be None or integer
#------------------------------------------------
ncps_unit.create_dimension("nz", int(nz))
ncps_unit.create_dimension("time", None)
#-------------------------
# Create a time variable
#---------------------------------------------------
#('f' = float32; must match in add_values_at_IDs()
#---------------------------------------------------
# NB! Can't use "time" vs. "tvar" here unless we
# add "import time" inside this function.
#---------------------------------------------------
tvar = ncps_unit.create_variable('time', 'd', ("time", ))
ncps_unit.variables['time'].units = time_units
#--------------------------------------
# Create a distance/depth variable, z
#--------------------------------------
zvar = ncps_unit.create_variable('z', 'd', ("nz", ))
zvar[:] = z_values # (store the z-values)
ncps_unit.variables['z'].units = z_units
#-----------------------------------
# Create variables using var_names
#-----------------------------------
# Returns "var" as a PyNIO object
#---------------------------------------------------
# NB! The 3rd argument here (dimension), must be a
# tuple. If there is only one dimension, then
# we need to add a comma, as shown.
#---------------------------------------------------
for k in xrange(len(var_names)):
var_name = var_names[k]
var = ncps_unit.create_variable(var_name, nio_type_codes[k],
("time", "nz"))
#------------------------------------
# Create attributes of the variable
#------------------------------------
ncps_unit.variables[var_name].long_name = long_names[k]
ncps_unit.variables[var_name].units = units_names[k]
#----------------------------------
# Specify a "nodata" fill value ?
#----------------------------------
var._FillValue = -9999.0 ## Does this jive with Prefill above ??
self.ncps_unit = ncps_unit
return OK
def var_nc2d(parameters=['AREA', 'HEFF'],
ofile='MIT_output_2d',
bswap=1,
sstart_date="seconds since 2002-10-01 07:00",
deltaT=1800,
FillValue=-1.0e+23,
dump='no'):
'''
Convert 2d fields produced by MITgcm to netCDF format with use of Nio module.
Names of the files should be defined in form of the list, even if we have only one variable.
I put everything on the C grid!
You have to have following files in the the directory where you run your code:
XC.data
XC.meta
YC.data
YC.meta
maskCtrlC.data
maskCtrlC.meta
Input:
parameters - list with names of the variables (like AREA or AREAtave).
ofile - name of the output file.
bswap - do we need a byte swap? Yes (1) or no (0) [default 1]
sstart_date - should be "seconds since", [default "seconds since 2002-10-01 07:00"
deltaT - time step in seconds
FillValue - missing value
dump - if dump='yes' will return numpy array with data
'''
lon = mitbin2('XC.data', bswap)[0, 0, :, :]
lat = mitbin2('YC.data', bswap)[0, 0, :, :]
lsmask = mitbin2('maskCtrlC.data', bswap)[:, 0, :, :]
fileList = glob.glob(parameters[0] + "*.data")
if os.path.exists(ofile + ".nc") == True:
os.system("rm " + ofile + ".nc")
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(
fileList[0][:-4] + "meta")
ttime = numpy.zeros((len(fileList)))
#ttime[0] = timeStepNumber*deltaT
opt = Nio.options()
opt.PreFill = False
opt.HeaderReserveSpace = 4000
f = Nio.open_file(ofile + ".nc", "w", opt)
f.title = "MITgcm variables in netCDF format"
f.create_dimension('x', xdim)
f.create_dimension('y', ydim)
f.create_dimension('time', ttime.shape[0])
f.create_variable('time', 'd', ('time', ))
f.variables['time'].units = sstart_date
f.create_variable('latitude', 'd', ('x', 'y'))
f.variables['latitude'].long_name = "latitude"
f.variables['latitude'].units = "degrees_north"
f.variables['latitude'].standard_name = "grid_latitude"
f.variables['latitude'][:] = lat[:]
f.create_variable('longitude', 'd', ('x', 'y'))
f.variables['longitude'].long_name = "longitude"
f.variables['longitude'].units = "degrees_east"
f.variables['longitude'].standard_name = "grid_longitude"
f.variables['longitude'][:] = lon[:]
for parameter in parameters:
f.create_variable(parameter, 'd', ('time', 'x', 'y'))
f.variables[parameter].long_name = gatrib(parameter)[0]
f.variables[parameter].units = gatrib(parameter)[1]
f.variables[parameter]._FillValue = FillValue
f.variables[parameter].missing_value = FillValue
adatemp_final = numpy.zeros((len(fileList), xdim, ydim))
iterator = 0
for fileName in fileList:
adatemp = mitbin2(parameter + fileName[-16:], bswap=bswap)[0,
0, :, :]
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(
fileName[:-4] + "meta")
adatemp = numpy.where(adatemp[:] < -1.0e+20, FillValue, adatemp[:])
adatemp = numpy.where(lsmask[:] == 0, FillValue, adatemp[:])
adatemp_final[iterator, :, :] = adatemp
ttime[iterator] = timeStepNumber * deltaT
iterator = iterator + 1
f.variables[parameter][:] = adatemp_final
f.variables['time'][:] = ttime
f.close()
if dump == 'yes':
return adatemp
def nc3d(parameters=['adxx_atemp'],
ofile='adxx',
iteration='0',
bswap=1,
sstart_date="seconds since 2002-10-01 07:00",
deltaT=1200,
xx_period=240000.0,
FillValue=-1.0e+23,
meta=None,
dump="no"):
'''
Convert 3d fields from adxx* and xx* fles to netCDF format with use of Nio module.
Names of the files should be defined in form of the list, even if we have only one variable.
I put everything on the C grid!
You have to have following files in the the directory where you run your code:
XC.data
XC.meta
YC.data
YC.meta
DRC.data
DRC.meta
maskCtrlC.data
maskCtrlC.meta
Input:
parameters - list with names of the variables.
ofile - name of the output file.
iteration - iteration of optimisation, should be STRING!
bswap - do we need a byte swap? Yes (1) or no (0) [default 1]
sstart_date - should be "seconds since", [default "seconds since 2002-10-01 07:00"
deltaT - time step in seconds
xx_period - xx_*period
FillValue - missing value
meta - flag to fix problem with wrong adxx*.meta files.
If meta = 'xx', use .meta file from xx files
dump - if dump='yes' will return numpy array with data
'''
lon = mitbin2('XC.data', bswap)[0, 0, :, :]
lat = mitbin2('YC.data', bswap)[0, 0, :, :]
lev = mitbin2('DRC.data', bswap)[0, :, 0, 0]
lev = numpy.cumsum(lev)
lsmask = mitbin2('maskCtrlC.data', bswap)[:, :, :, :]
if os.path.exists(ofile + ".nc") == True:
os.system("rm " + ofile + ".nc")
if meta == None:
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(
parameters[0] + "." + iteration.zfill(10) + ".meta")
elif meta == 'xx':
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(
parameters[0][2:] + "." + iteration.zfill(10) + ".meta")
if nrecords == 1:
ttime = numpy.zeros((nrecords))
ttime[0] = timeStepNumber * deltaT
elif nrecords > 1:
ttime = numpy.zeros((nrecords))
for i in range(nrecords):
ttime[i] = xx_period * i
opt = Nio.options()
opt.PreFill = False
opt.HeaderReserveSpace = 4000
f = Nio.open_file(ofile + ".nc", "w", opt)
f.title = "MITgcm variables in netCDF format"
f.create_dimension('x', xdim)
f.create_dimension('y', ydim)
f.create_dimension('z', zdim)
f.create_dimension('time', ttime.shape[0])
f.create_variable('time', 'd', ('time', ))
f.variables['time'].units = sstart_date
f.variables['time'][:] = ttime
f.create_variable('z', 'd', ('z', ))
f.variables['z'].units = "meters"
f.variables['z'][:] = lev[:]
f.create_variable('latitude', 'd', ('x', 'y'))
f.variables['latitude'].long_name = "latitude"
f.variables['latitude'].units = "degrees_north"
f.variables['latitude'].standard_name = "grid_latitude"
f.variables['latitude'][:] = lat[:]
f.create_variable('longitude', 'd', ('x', 'y'))
f.variables['longitude'].long_name = "longitude"
f.variables['longitude'].units = "degrees_east"
f.variables['longitude'].standard_name = "grid_longitude"
f.variables['longitude'][:] = lon[:]
#vvariables = ["atemp","aqh", "uwind", "vwind", ]
#vvariables = ["atemp"]
for parameter in parameters:
adatemp = mitbin2(parameter + "." + iteration.zfill(10) + ".data",
bswap=bswap,
meta=meta)[:, :, :, :]
# adatemp = numpy.where(adatemp[:] > 1.0e+12, 0, adatemp[:])
adatemp = numpy.where(adatemp[:] < -1.0e+20, FillValue, adatemp[:])
adatemp = numpy.where(lsmask[:] == 0, FillValue, adatemp[:])
f.create_variable(parameter, 'd', ('time', 'z', 'x', 'y'))
nname, unit, grid = gatrib(parameter)
f.variables[parameter].long_name = nname
f.variables[parameter].units = unit
f.variables[parameter].grid = grid
f.variables[parameter]._FillValue = FillValue
#print(adatemp.shape())
f.variables[parameter][:] = adatemp
f.close()
if dump == 'yes':
return adatemp
def nc3d(parameters=['adxx_atemp'], ofile='adxx', iteration='0', bswap=1, sstart_date = "seconds since 2002-10-01 07:00", deltaT=1200, xx_period=240000.0, FillValue=-1.0e+23, meta=None, dump="no"):
'''
Convert 3d fields from adxx* and xx* fles to netCDF format with use of Nio module.
Names of the files should be defined in form of the list, even if we have only one variable.
I put everything on the C grid!
You have to have following files in the the directory where you run your code:
XC.data
XC.meta
YC.data
YC.meta
DRC.data
DRC.meta
maskCtrlC.data
maskCtrlC.meta
Input:
parameters - list with names of the variables.
ofile - name of the output file.
iteration - iteration of optimisation, should be STRING!
bswap - do we need a byte swap? Yes (1) or no (0) [default 1]
sstart_date - should be "seconds since", [default "seconds since 2002-10-01 07:00"
deltaT - time step in seconds
xx_period - xx_*period
FillValue - missing value
meta - flag to fix problem with wrong adxx*.meta files.
If meta = 'xx', use .meta file from xx files
dump - if dump='yes' will return numpy array with data
'''
lon = mitbin2('XC.data',bswap)[0,0,:,:]
lat = mitbin2('YC.data',bswap)[0,0,:,:]
lev = mitbin2('DRC.data',bswap)[0,:,0,0]
lev = numpy.cumsum(lev)
lsmask = mitbin2('maskCtrlC.data',bswap)[:,:,:,:]
if os.path.exists(ofile+".nc") == True:
os.system("rm "+ofile+".nc")
if meta == None:
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(parameters[0]+"."+iteration.zfill(10)+".meta")
elif meta == 'xx':
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(parameters[0][2:]+"."+iteration.zfill(10)+".meta")
if nrecords == 1:
ttime = numpy.zeros((nrecords))
ttime[0] = timeStepNumber*deltaT
elif nrecords > 1:
ttime = numpy.zeros((nrecords))
for i in range (nrecords):
ttime[i] = xx_period*i
opt = Nio.options()
opt.PreFill = False
opt.HeaderReserveSpace = 4000
f = Nio.open_file(ofile+".nc","w",opt)
f.title = "MITgcm variables in netCDF format"
f.create_dimension('x',xdim)
f.create_dimension('y',ydim)
f.create_dimension('z',zdim)
f.create_dimension('time',ttime.shape[0])
f.create_variable('time','d',('time',))
f.variables['time'].units = sstart_date
f.variables['time'][:] = ttime
f.create_variable('z','d',('z',))
f.variables['z'].units = "meters"
f.variables['z'][:] = lev[:]
f.create_variable('latitude','d',('x','y'))
f.variables['latitude'].long_name = "latitude"
f.variables['latitude'].units = "degrees_north"
f.variables['latitude'].standard_name = "grid_latitude"
f.variables['latitude'][:] = lat[:]
f.create_variable('longitude','d',('x','y'))
f.variables['longitude'].long_name = "longitude"
f.variables['longitude'].units = "degrees_east"
f.variables['longitude'].standard_name = "grid_longitude"
f.variables['longitude'][:] = lon[:]
#vvariables = ["atemp","aqh", "uwind", "vwind", ]
#vvariables = ["atemp"]
for parameter in parameters:
adatemp = mitbin2(parameter+"."+iteration.zfill(10)+".data", bswap=bswap, meta=meta)[:,:,:,:]
# adatemp = numpy.where(adatemp[:] > 1.0e+12, 0, adatemp[:])
adatemp = numpy.where(adatemp[:] < -1.0e+20, FillValue, adatemp[:])
adatemp = numpy.where(lsmask[:]==0, FillValue, adatemp[:])
f.create_variable(parameter,'d',('time','z','x','y'))
nname, unit, grid = gatrib(parameter)
f.variables[parameter].long_name = nname
f.variables[parameter].units = unit
f.variables[parameter].grid = grid
f.variables[parameter]._FillValue = FillValue
#print(adatemp.shape())
f.variables[parameter][:] = adatemp
f.close()
if dump == 'yes':
return adatemp
def var_nc3d(parameters=['Ttave'], ofile='MIT_output_3d', bswap=1, sstart_date = "seconds since 2002-10-01 07:00", deltaT=1200, FillValue=-1.0e+23, dump="no"):
'''
Convert 3d fields produced by MITgcm to netCDF format with use of Nio module.
Names of the files should be defined in form of the list, even if we have only one variable.
I put everything on the C grid!
You have to have following files in the the directory where you run your code:
XC.data
XC.meta
YC.data
YC.meta
DRC.data
DRC.meta
maskCtrlC.data
maskCtrlC.meta
Input:
parameters - list with names of the variables.
ofile - name of the output file.
iteration - iteration of optimisation, should be STRING!
bswap - do we need a byte swap? Yes (1) or no (0) [default 1]
sstart_date - should be "seconds since", [default "seconds since 2002-10-01 07:00"
deltaT - time step in seconds
xx_period - xx_*period
FillValue - missing value
meta - flag to fix problem with wrong adxx*.meta files.
If meta = 'xx', use .meta file from xx files
dump - if dump='yes' will return numpy array with data
'''
lon = mitbin2('XC.data',bswap)[0,0,:,:]
lat = mitbin2('YC.data',bswap)[0,0,:,:]
lev = mitbin2('DRC.data',bswap)[0,:,0,0]
lev = numpy.cumsum(lev)
lsmask = mitbin2('maskCtrlC.data',bswap)[:,:,:,:]
fileList = glob.glob(parameters[0]+"*.data")
if os.path.exists(ofile+".nc") == True:
os.system("rm "+ofile+".nc")
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(fileList[0][:-4]+"meta")
ttime = numpy.zeros((len(fileList)))
opt = Nio.options()
opt.PreFill = False
opt.HeaderReserveSpace = 4000
f = Nio.open_file(ofile+".nc","w",opt)
f.title = "MITgcm variables in netCDF format"
f.create_dimension('x',xdim)
f.create_dimension('y',ydim)
f.create_dimension('z',zdim)
f.create_dimension('time',ttime.shape[0])
f.create_variable('time','d',('time',))
f.variables['time'].units = sstart_date
f.create_variable('z','d',('z',))
f.variables['z'].units = "meters"
f.variables['z'][:] = lev[:]
f.create_variable('latitude','d',('x','y'))
f.variables['latitude'].long_name = "latitude"
f.variables['latitude'].units = "degrees_north"
f.variables['latitude'].standard_name = "grid_latitude"
f.variables['latitude'][:] = lat[:]
f.create_variable('longitude','d',('x','y'))
f.variables['longitude'].long_name = "longitude"
f.variables['longitude'].units = "degrees_east"
f.variables['longitude'].standard_name = "grid_longitude"
f.variables['longitude'][:] = lon[:]
#vvariables = ["atemp","aqh", "uwind", "vwind", ]
#vvariables = ["atemp"]
for parameter in parameters:
f.create_variable(parameter,'d',('time','z','x','y'))
f.variables[parameter].long_name = gatrib(parameter)[0]
f.variables[parameter].units = gatrib(parameter)[1]
f.variables[parameter]._FillValue = FillValue
f.variables[parameter].missing_value = FillValue
adatemp_final = numpy.zeros((len(fileList), zdim, xdim, ydim))
for ind, fileName in enumerate(fileList):
adatemp = mitbin2(parameter+fileName[-16:], bswap=bswap)[:,:,:,:]
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(fileName[:-4]+"meta")
# adatemp = numpy.where(adatemp[:] > 1.0e+12, 0, adatemp[:])
adatemp = numpy.where(adatemp[:] < -1.0e+20, FillValue, adatemp[:])
adatemp = numpy.where(lsmask[:]==0, FillValue, adatemp[:])
adatemp_final[ind,:,:,:] = adatemp
ttime[ind] = timeStepNumber*deltaT
f.variables[parameter][:] = adatemp
f.close()
if dump == 'yes':
return adatemp
def var_nc2d(parameters=['AREA','HEFF'], ofile='MIT_output_2d', bswap=1, sstart_date = "seconds since 2002-10-01 07:00", deltaT=1800, FillValue=-1.0e+23, dump='no'):
'''
Convert 2d fields produced by MITgcm to netCDF format with use of Nio module.
Names of the files should be defined in form of the list, even if we have only one variable.
I put everything on the C grid!
You have to have following files in the the directory where you run your code:
XC.data
XC.meta
YC.data
YC.meta
maskCtrlC.data
maskCtrlC.meta
Input:
parameters - list with names of the variables (like AREA or AREAtave).
ofile - name of the output file.
bswap - do we need a byte swap? Yes (1) or no (0) [default 1]
sstart_date - should be "seconds since", [default "seconds since 2002-10-01 07:00"
deltaT - time step in seconds
FillValue - missing value
dump - if dump='yes' will return numpy array with data
'''
lon = mitbin2('XC.data',bswap)[0,0,:,:]
lat = mitbin2('YC.data',bswap)[0,0,:,:]
lsmask = mitbin2('maskCtrlC.data',bswap)[:,0,:,:]
fileList = glob.glob(parameters[0]+"*.data")
if os.path.exists(ofile+".nc") == True:
os.system("rm "+ofile+".nc")
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(fileList[0][:-4]+"meta")
ttime = numpy.zeros((len(fileList)))
#ttime[0] = timeStepNumber*deltaT
opt = Nio.options()
opt.PreFill = False
opt.HeaderReserveSpace = 4000
f = Nio.open_file(ofile+".nc","w",opt)
f.title = "MITgcm variables in netCDF format"
f.create_dimension('x',xdim)
f.create_dimension('y',ydim)
f.create_dimension('time',ttime.shape[0])
f.create_variable('time','d',('time',))
f.variables['time'].units = sstart_date
f.create_variable('latitude','d',('x','y'))
f.variables['latitude'].long_name = "latitude"
f.variables['latitude'].units = "degrees_north"
f.variables['latitude'].standard_name = "grid_latitude"
f.variables['latitude'][:] = lat[:]
f.create_variable('longitude','d',('x','y'))
f.variables['longitude'].long_name = "longitude"
f.variables['longitude'].units = "degrees_east"
f.variables['longitude'].standard_name = "grid_longitude"
f.variables['longitude'][:] = lon[:]
for parameter in parameters:
f.create_variable(parameter,'d',('time','x','y'))
f.variables[parameter].long_name = gatrib(parameter)[0]
f.variables[parameter].units = gatrib(parameter)[1]
f.variables[parameter]._FillValue = FillValue
f.variables[parameter].missing_value = FillValue
adatemp_final = numpy.zeros((len(fileList), xdim, ydim))
iterator = 0
for fileName in fileList:
adatemp = mitbin2(parameter+fileName[-16:], bswap=bswap)[0,0,:,:]
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(fileName[:-4]+"meta")
adatemp = numpy.where(adatemp[:] < -1.0e+20, FillValue, adatemp[:])
adatemp = numpy.where(lsmask[:]==0, FillValue, adatemp[:])
adatemp_final[iterator,:,:] = adatemp
ttime[iterator] = timeStepNumber*deltaT
iterator = iterator + 1
f.variables[parameter][:] = adatemp_final
f.variables['time'][:] = ttime
f.close()
if dump == 'yes':
return adatemp
def open_new_file(self, file_name,
z_values=numpy.arange(10),
z_units='m',
var_names=['X'],
long_names=[None],
units_names=['None'],
dtypes=['float64'],
time_units='minutes',
comment=''):
#----------------------------------------------------
# Notes: It might be okay to have "nz" be an
# unlimited dimension, like "time". This
# would mean replacing "int(profile_length)"
# with "None".
#----------------------------------------------------
#--------------------------------------------------
# Try to import the Nio module from PyNIO package
#--------------------------------------------------
Nio = self.import_nio()
if not(Nio): return False
#----------------------------
# Does file already exist ?
#----------------------------
file_name = file_utils.check_overwrite( file_name )
self.file_name = file_name
#---------------------------------------
# Check and store the time series info
#---------------------------------------
self.format = 'ncps'
self.file_name = file_name
self.time_index = 0
if (long_names[0] == None):
long_names = var_names
#-------------------------------------------
self.z_values = z_values
self.z_units = z_units
nz = numpy.size(z_values)
#-------------------------------------------
# We may not need to save these in self.
# I don't think they're used anywhere yet.
#-------------------------------------------
self.var_names = var_names
self.long_names = long_names
self.units_names = units_names
self.dtypes = dtypes
#---------------------------------------------
# Create array of Nio type codes from dtypes
#---------------------------------------------
nio_type_map = self.get_nio_type_map()
nio_type_codes = []
if (len(dtypes) == len(var_names)):
for dtype in dtypes:
nio_type_code = nio_type_map[ dtype.lower() ]
nio_type_codes.append( nio_type_code )
else:
dtype = dtypes[0]
nio_type_code = nio_type_map[ dtype.lower() ]
for k in xrange(len(var_names)):
nio_type_codes.append( nio_type_code )
self.nio_type_codes = nio_type_codes
#-------------------------------------
# Open a new netCDF file for writing
#-------------------------------------
# Sample output from time.asctime():
# "Thu Oct 8 17:10:18 2009"
#-------------------------------------
opt = Nio.options()
opt.PreFill = False # (for efficiency)
opt.HeaderReserveSpace = 4000 # (4000 bytes, for efficiency)
history = "Created using PyNIO " + Nio.__version__ + " on "
history = history + time.asctime() + ". "
history = history + comment
try:
ncps_unit = Nio.open_file(file_name, mode="w",
options=opt, history=history )
OK = True
except:
OK = False
return OK
#------------------------------------------------
# Create an unlimited time dimension (via None)
#------------------------------------------------
# Without using "int()" here, we get this:
# TypeError: size must be None or integer
#------------------------------------------------
ncps_unit.create_dimension("nz", int(nz))
ncps_unit.create_dimension("time", None)
#-------------------------
# Create a time variable
#---------------------------------------------------
#('f' = float32; must match in add_values_at_IDs()
#---------------------------------------------------
# NB! Can't use "time" vs. "tvar" here unless we
# add "import time" inside this function.
#---------------------------------------------------
tvar = ncps_unit.create_variable('time', 'd', ("time",))
ncps_unit.variables['time'].units = time_units
#--------------------------------------
# Create a distance/depth variable, z
#--------------------------------------
zvar = ncps_unit.create_variable('z', 'd', ("nz",))
zvar[ : ] = z_values # (store the z-values)
ncps_unit.variables['z'].units = z_units
#-----------------------------------
# Create variables using var_names
#-----------------------------------
# Returns "var" as a PyNIO object
#---------------------------------------------------
# NB! The 3rd argument here (dimension), must be a
# tuple. If there is only one dimension, then
# we need to add a comma, as shown.
#---------------------------------------------------
for k in xrange(len(var_names)):
var_name = var_names[k]
var = ncps_unit.create_variable(var_name, nio_type_codes[k],
("time", "nz"))
#------------------------------------
# Create attributes of the variable
#------------------------------------
ncps_unit.variables[var_name].long_name = long_names[k]
ncps_unit.variables[var_name].units = units_names[k]
#----------------------------------
# Specify a "nodata" fill value ?
#----------------------------------
var._FillValue = -9999.0 ## Does this jive with Prefill above ??
self.ncps_unit = ncps_unit
return OK
def main(argv):
print('Running pyEnsSum!')
# Get command line stuff and store in a dictionary
s = 'tag= compset= esize= tslice= res= sumfile= indir= sumfiledir= mach= verbose jsonfile= mpi_enable maxnorm gmonly popens cumul regx= startMon= endMon= fIndex='
optkeys = s.split()
try:
opts, args = getopt.getopt(argv, "h", optkeys)
except getopt.GetoptError:
pyEnsLib.EnsSum_usage()
sys.exit(2)
# Put command line options in a dictionary - also set defaults
opts_dict={}
# Defaults
opts_dict['tag'] = ''
opts_dict['compset'] = ''
opts_dict['mach'] = ''
opts_dict['esize'] = 151
opts_dict['tslice'] = 0
opts_dict['res'] = ''
opts_dict['sumfile'] = 'ens.summary.nc'
opts_dict['indir'] = './'
opts_dict['sumfiledir'] = './'
opts_dict['jsonfile'] = ''
opts_dict['verbose'] = True
opts_dict['mpi_enable'] = False
opts_dict['maxnorm'] = False
opts_dict['gmonly'] = False
opts_dict['popens'] = False
opts_dict['cumul'] = False
opts_dict['regx'] = 'test'
opts_dict['startMon'] = 1
opts_dict['endMon'] = 1
opts_dict['fIndex'] = 151
# This creates the dictionary of input arguments
opts_dict = pyEnsLib.getopt_parseconfig(opts,optkeys,'ES',opts_dict)
verbose = opts_dict['verbose']
st = opts_dict['esize']
esize = int(st)
if (verbose == True):
print(opts_dict)
print('Ensemble size for summary = ', esize)
if not (opts_dict['tag'] and opts_dict['compset'] and opts_dict['mach'] or opts_dict['res']):
print('Please specify --tag, --compset, --mach and --res options')
sys.exit()
# Now find file names in indir
input_dir = opts_dict['indir']
# The var list that will be excluded
ex_varlist=[]
# Create a mpi simplecomm object
if opts_dict['mpi_enable']:
me=simplecomm.create_comm()
else:
me=simplecomm.create_comm(not opts_dict['mpi_enable'])
if me.get_rank() == 0:
if opts_dict['jsonfile']:
# Read in the excluded var list
ex_varlist=pyEnsLib.read_jsonlist(opts_dict['jsonfile'],'ES')
# Broadcast the excluded var list to each processor
if opts_dict['mpi_enable']:
ex_varlist=me.partition(ex_varlist,func=Duplicate(),involved=True)
in_files=[]
if(os.path.exists(input_dir)):
# Get the list of files
in_files_temp = os.listdir(input_dir)
in_files=sorted(in_files_temp)
#print in_files
# Make sure we have enough
num_files = len(in_files)
if (verbose == True):
print('Number of files in input directory = ', num_files)
if (num_files < esize):
print('Number of files in input directory (',num_files,
') is less than specified ensemble size of ', esize)
sys.exit(2)
if (num_files > esize):
print('NOTE: Number of files in ', input_dir,
'is greater than specified ensemble size of ', esize,
'\nwill just use the first ', esize, 'files')
else:
print('Input directory: ',input_dir,' not found')
sys.exit(2)
if opts_dict['cumul']:
if opts_dict['regx']:
in_files_list=get_cumul_filelist(opts_dict,opts_dict['indir'],opts_dict['regx'])
in_files=me.partition(in_files_list,func=EqualLength(),involved=True)
if me.get_rank()==0:
print('in_files=',in_files)
# Open the files in the input directory
o_files=[]
for onefile in in_files[0:esize]:
if (os.path.isfile(input_dir+'/' + onefile)):
o_files.append(Nio.open_file(input_dir+'/' + onefile,"r"))
else:
print("COULD NOT LOCATE FILE "+ input_dir + onefile + "! EXITING....")
sys.exit()
# Store dimensions of the input fields
if (verbose == True):
print("Getting spatial dimensions")
nlev = -1
ncol = -1
nlat = -1
nlon = -1
lonkey=''
latkey=''
# Look at first file and get dims
input_dims = o_files[0].dimensions
ndims = len(input_dims)
for key in input_dims:
if key == "lev":
nlev = input_dims["lev"]
elif key == "ncol":
ncol = input_dims["ncol"]
elif (key == "nlon") or (key =="lon"):
nlon = input_dims[key]
lonkey=key
elif (key == "nlat") or (key == "lat"):
nlat = input_dims[key]
latkey=key
if (nlev == -1) :
print("COULD NOT LOCATE valid dimension lev => EXITING....")
sys.exit()
if (( ncol == -1) and ((nlat == -1) or (nlon == -1))):
print("Need either lat/lon or ncol => EXITING....")
sys.exit()
# Check if this is SE or FV data
if (ncol != -1):
is_SE = True
else:
is_SE = False
# Make sure all files have the same dimensions
if (verbose == True):
print("Checking dimensions across files....")
print('lev = ', nlev)
if (is_SE == True):
print('ncol = ', ncol)
else:
print('nlat = ', nlat)
print('nlon = ', nlon)
for count, this_file in enumerate(o_files):
input_dims = this_file.dimensions
if (is_SE == True):
if ( nlev != int(input_dims["lev"]) or ( ncol != int(input_dims["ncol"]))):
print("Dimension mismatch between ", in_files[0], 'and', in_files[0], '!!!')
sys.exit()
else:
if ( nlev != int(input_dims["lev"]) or ( nlat != int(input_dims[latkey]))\
or ( nlon != int(input_dims[lonkey]))):
print("Dimension mismatch between ", in_files[0], 'and', in_files[0], '!!!')
sys.exit()
# Get 2d vars, 3d vars and all vars (For now include all variables)
vars_dict = o_files[0].variables
# Remove the excluded variables (specified in json file) from variable dictionary
if ex_varlist:
for i in ex_varlist:
if i in vars_dict:
del vars_dict[i]
num_vars = len(vars_dict)
if (verbose == True):
print('Number of variables (including metadata) found = ', num_vars)
str_size = 0
d2_var_names = []
d3_var_names = []
num_2d = 0
num_3d = 0
# Which are 2d, which are 3d and max str_size
for k,v in vars_dict.iteritems():
var = k
vd = v.dimensions # all the variable's dimensions (names)
vr = v.rank # num dimension
vs = v.shape # dim values
is_2d = False
is_3d = False
if (is_SE == True): # (time, lev, ncol) or (time, ncol)
if ((vr == 2) and (vs[1] == ncol)):
is_2d = True
num_2d += 1
elif ((vr == 3) and (vs[2] == ncol and vs[1] == nlev )):
is_3d = True
num_3d += 1
else: # (time, lev, nlon, nlon) or (time, nlat, nlon)
if ((vr == 3) and (vs[1] == nlat and vs[2] == nlon)):
is_2d = True
num_2d += 1
elif ((vr == 4) and (vs[2] == nlat and vs[3] == nlon and vs[1] == nlev )):
is_3d = True
num_3d += 1
if (is_3d == True) :
str_size = max(str_size, len(k))
d3_var_names.append(k)
elif (is_2d == True):
str_size = max(str_size, len(k))
d2_var_names.append(k)
# Now sort these and combine (this sorts caps first, then lower case -
# which is what we want)
d2_var_names.sort()
d3_var_names.sort()
# All vars is 3d vars first (sorted), the 2d vars
all_var_names = list(d3_var_names)
all_var_names += d2_var_names
n_all_var_names = len(all_var_names)
if (verbose == True):
print('num vars = ', n_all_var_names, '(3d = ', num_3d, ' and 2d = ', num_2d, ")")
# Create new summary ensemble file
this_sumfile = opts_dict["sumfile"]
if (verbose == True):
print("Creating ", this_sumfile, " ...")
if(me.get_rank() ==0 | opts_dict["popens"]):
if os.path.exists(this_sumfile):
os.unlink(this_sumfile)
opt = Nio.options()
opt.PreFill = False
opt.Format = 'NetCDF4Classic'
nc_sumfile = Nio.open_file(this_sumfile, 'w', options=opt)
# Set dimensions
if (verbose == True):
print("Setting dimensions .....")
if (is_SE == True):
nc_sumfile.create_dimension('ncol', ncol)
else:
nc_sumfile.create_dimension('nlat', nlat)
nc_sumfile.create_dimension('nlon', nlon)
nc_sumfile.create_dimension('nlev', nlev)
nc_sumfile.create_dimension('ens_size', esize)
nc_sumfile.create_dimension('nvars', num_3d + num_2d)
nc_sumfile.create_dimension('nvars3d', num_3d)
nc_sumfile.create_dimension('nvars2d', num_2d)
nc_sumfile.create_dimension('str_size', str_size)
# Set global attributes
now = time.strftime("%c")
if (verbose == True):
print("Setting global attributes .....")
setattr(nc_sumfile, 'creation_date',now)
setattr(nc_sumfile, 'title', 'CAM verification ensemble summary file')
setattr(nc_sumfile, 'tag', opts_dict["tag"])
setattr(nc_sumfile, 'compset', opts_dict["compset"])
setattr(nc_sumfile, 'resolution', opts_dict["res"])
setattr(nc_sumfile, 'machine', opts_dict["mach"])
# Create variables
if (verbose == True):
print("Creating variables .....")
v_lev = nc_sumfile.create_variable("lev", 'f', ('nlev',))
v_vars = nc_sumfile.create_variable("vars", 'S1', ('nvars', 'str_size'))
v_var3d = nc_sumfile.create_variable("var3d", 'S1', ('nvars3d', 'str_size'))
v_var2d = nc_sumfile.create_variable("var2d", 'S1', ('nvars2d', 'str_size'))
if not opts_dict['gmonly']:
if (is_SE == True):
v_ens_avg3d = nc_sumfile.create_variable("ens_avg3d", 'f', ('nvars3d', 'nlev', 'ncol'))
v_ens_stddev3d = nc_sumfile.create_variable("ens_stddev3d", 'f', ('nvars3d', 'nlev', 'ncol'))
v_ens_avg2d = nc_sumfile.create_variable("ens_avg2d", 'f', ('nvars2d', 'ncol'))
v_ens_stddev2d = nc_sumfile.create_variable("ens_stddev2d", 'f', ('nvars2d', 'ncol'))
else:
v_ens_avg3d = nc_sumfile.create_variable("ens_avg3d", 'f', ('nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_stddev3d = nc_sumfile.create_variable("ens_stddev3d", 'f', ('nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_avg2d = nc_sumfile.create_variable("ens_avg2d", 'f', ('nvars2d', 'nlat', 'nlon'))
v_ens_stddev2d = nc_sumfile.create_variable("ens_stddev2d", 'f', ('nvars2d', 'nlat', 'nlon'))
v_RMSZ = nc_sumfile.create_variable("RMSZ", 'f', ('nvars', 'ens_size'))
v_gm = nc_sumfile.create_variable("global_mean", 'f', ('nvars', 'ens_size'))
v_loadings_gm = nc_sumfile.create_variable('loadings_gm','f',('nvars','nvars'))
v_mu_gm = nc_sumfile.create_variable('mu_gm','f',('nvars',))
v_sigma_gm = nc_sumfile.create_variable('sigma_gm','f',('nvars',))
v_sigma_scores_gm = nc_sumfile.create_variable('sigma_scores_gm','f',('nvars',))
# Assign vars, var3d and var2d
if (verbose == True):
print("Assigning vars, var3d, and var2d .....")
eq_all_var_names =[]
eq_d3_var_names = []
eq_d2_var_names = []
l_eq = len(all_var_names)
for i in range(l_eq):
tt = list(all_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ')*(str_size - l_tt)
tt.extend(extra)
eq_all_var_names.append(tt)
l_eq = len(d3_var_names)
for i in range(l_eq):
tt = list(d3_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ')*(str_size - l_tt)
tt.extend(extra)
eq_d3_var_names.append(tt)
l_eq = len(d2_var_names)
for i in range(l_eq):
tt = list(d2_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ')*(str_size - l_tt)
tt.extend(extra)
eq_d2_var_names.append(tt)
v_vars[:] = eq_all_var_names[:]
v_var3d[:] = eq_d3_var_names[:]
v_var2d[:] = eq_d2_var_names[:]
# Time-invarient metadata
if (verbose == True):
print("Assigning time invariant metadata .....")
lev_data = vars_dict["lev"]
v_lev = lev_data
# Form ensembles, each missing one member; compute RMSZs and global means
#for each variable, we also do max norm also (currently done in pyStats)
tslice = opts_dict['tslice']
if not opts_dict['cumul']:
# Partition the var list
var3_list_loc=me.partition(d3_var_names,func=EqualStride(),involved=True)
var2_list_loc=me.partition(d2_var_names,func=EqualStride(),involved=True)
else:
var3_list_loc=d3_var_names
var2_list_loc=d2_var_names
# Calculate global means #
if (verbose == True):
print("Calculating global means .....")
if not opts_dict['cumul']:
gm3d,gm2d = pyEnsLib.generate_global_mean_for_summary(o_files,var3_list_loc,var2_list_loc , is_SE, False,opts_dict)
if (verbose == True):
print("Finish calculating global means .....")
# Calculate RMSZ scores
if (verbose == True):
print("Calculating RMSZ scores .....")
if (not opts_dict['gmonly']) | (opts_dict['cumul']):
zscore3d,zscore2d,ens_avg3d,ens_stddev3d,ens_avg2d,ens_stddev2d,temp1,temp2=pyEnsLib.calc_rmsz(o_files,var3_list_loc,var2_list_loc,is_SE,opts_dict)
# Calculate max norm ensemble
if opts_dict['maxnorm']:
if (verbose == True):
print("Calculating max norm of ensembles .....")
pyEnsLib.calculate_maxnormens(opts_dict,var3_list_loc)
pyEnsLib.calculate_maxnormens(opts_dict,var2_list_loc)
if opts_dict['mpi_enable'] & ( not opts_dict['popens']):
if not opts_dict['cumul']:
# Gather the 3d variable results from all processors to the master processor
slice_index=get_stride_list(len(d3_var_names),me)
# Gather global means 3d results
gm3d=gather_npArray(gm3d,me,slice_index,(len(d3_var_names),len(o_files)))
if not opts_dict['gmonly']:
# Gather zscore3d results
zscore3d=gather_npArray(zscore3d,me,slice_index,(len(d3_var_names),len(o_files)))
# Gather ens_avg3d and ens_stddev3d results
shape_tuple3d=get_shape(ens_avg3d.shape,len(d3_var_names),me.get_rank())
ens_avg3d=gather_npArray(ens_avg3d,me,slice_index,shape_tuple3d)
ens_stddev3d=gather_npArray(ens_stddev3d,me,slice_index,shape_tuple3d)
# Gather 2d variable results from all processors to the master processor
slice_index=get_stride_list(len(d2_var_names),me)
# Gather global means 2d results
gm2d=gather_npArray(gm2d,me,slice_index,(len(d2_var_names),len(o_files)))
if not opts_dict['gmonly']:
# Gather zscore2d results
zscore2d=gather_npArray(zscore2d,me,slice_index,(len(d2_var_names),len(o_files)))
# Gather ens_avg3d and ens_stddev2d results
shape_tuple2d=get_shape(ens_avg2d.shape,len(d2_var_names),me.get_rank())
ens_avg2d=gather_npArray(ens_avg2d,me,slice_index,shape_tuple2d)
ens_stddev2d=gather_npArray(ens_stddev2d,me,slice_index,shape_tuple2d)
else:
gmall=np.concatenate((temp1,temp2),axis=0)
gmall=pyEnsLib.gather_npArray_pop(gmall,me,(me.get_size(),len(d3_var_names)+len(d2_var_names)))
# Assign to file:
if me.get_rank() == 0 | opts_dict['popens'] :
if not opts_dict['cumul']:
gmall=np.concatenate((gm3d,gm2d),axis=0)
if not opts_dict['gmonly']:
Zscoreall=np.concatenate((zscore3d,zscore2d),axis=0)
v_RMSZ[:,:]=Zscoreall[:,:]
if not opts_dict['gmonly']:
if (is_SE == True):
v_ens_avg3d[:,:,:]=ens_avg3d[:,:,:]
v_ens_stddev3d[:,:,:]=ens_stddev3d[:,:,:]
v_ens_avg2d[:,:]=ens_avg2d[:,:]
v_ens_stddev2d[:,:]=ens_stddev2d[:,:]
else:
v_ens_avg3d[:,:,:,:]=ens_avg3d[:,:,:,:]
v_ens_stddev3d[:,:,:,:]=ens_stddev3d[:,:,:,:]
v_ens_avg2d[:,:,:]=ens_avg2d[:,:,:]
v_ens_stddev2d[:,:,:]=ens_stddev2d[:,:,:]
else:
gmall_temp=np.transpose(gmall[:,:])
gmall=gmall_temp
mu_gm,sigma_gm,standardized_global_mean,loadings_gm,scores_gm=pyEnsLib.pre_PCA(gmall)
v_gm[:,:]=gmall[:,:]
v_mu_gm[:]=mu_gm[:]
v_sigma_gm[:]=sigma_gm[:].astype(np.float32)
v_loadings_gm[:,:]=loadings_gm[:,:]
v_sigma_scores_gm[:]=scores_gm[:]
print("All Done")
def get_cumul_filelist(opts_dict,indir,regx):
if not opts_dict['indir']:
print('input dir is not specified')
sys.exit(2)
#regx='(pgi(.)*-(01|02))'
regx_list=["mon","gnu","pgi"]
all_files=[]
for prefix in regx_list:
for i in range(opts_dict['fIndex'],opts_dict['fIndex']+opts_dict['esize']/3):
for j in range(opts_dict['startMon'],opts_dict['endMon']+1):
mon_str=str(j).zfill(2)
regx='(^'+prefix+'(.)*'+str(i)+'(.)*-('+mon_str+'))'
print('regx=',regx)
res=[f for f in os.listdir(indir) if re.search(regx,f)]
in_files=sorted(res)
all_files.extend(in_files)
print("all_files=",all_files)
#in_files=res
return all_files
#
# Get the shape of all variable list in tuple for all processor
#
def get_shape(shape_tuple,shape1,rank):
lst=list(shape_tuple)
lst[0]=shape1
shape_tuple=tuple(lst)
return shape_tuple
#
# Get the mpi partition list for each processor
#
def get_stride_list(len_of_list,me):
slice_index=[]
for i in range(me.get_size()):
index_arr=np.arange(len_of_list)
slice_index.append(index_arr[i::me.get_size()])
return slice_index
#
# Gather arrays from each processor by the var_list to the master processor and make it an array
#
def gather_npArray(npArray,me,slice_index,array_shape):
the_array=np.zeros(array_shape,dtype=np.float32)
if me.get_rank()==0:
k=0
for j in slice_index[me.get_rank()]:
the_array[j,:]=npArray[k,:]
k=k+1
for i in range(1,me.get_size()):
if me.get_rank() == 0:
rank,npArray=me.collect()
k=0
for j in slice_index[rank]:
the_array[j,:]=npArray[k,:]
k=k+1
if me.get_rank() != 0:
message={"from_rank":me.get_rank(),"shape":npArray.shape}
me.collect(npArray)
me.sync()
return the_array
if __name__ == "__main__":
main(sys.argv[1:])
def main(argv):
print 'Running pyEnsSumPop!'
# Get command line stuff and store in a dictionary
s = 'nyear= nmonth= npert= tag= res= mach= compset= sumfile= indir= tslice= verbose jsonfile= mpi_enable zscoreonly nrand= rand seq= jsondir='
optkeys = s.split()
try:
opts, args = getopt.getopt(argv, "h", optkeys)
except getopt.GetoptError:
pyEnsLib.EnsSumPop_usage()
sys.exit(2)
# Put command line options in a dictionary - also set defaults
opts_dict = {}
# Defaults
opts_dict['tag'] = 'cesm1_2_0'
opts_dict['compset'] = 'FC5'
opts_dict['mach'] = 'yellowstone'
opts_dict['tslice'] = 0
opts_dict['nyear'] = 3
opts_dict['nmonth'] = 12
opts_dict['npert'] = 40
opts_dict['nbin'] = 40
opts_dict['minrange'] = 0.0
opts_dict['maxrange'] = 4.0
opts_dict['res'] = 'ne30_ne30'
opts_dict['sumfile'] = 'ens.pop.summary.nc'
opts_dict['indir'] = './'
opts_dict['jsonfile'] = ''
opts_dict['verbose'] = True
opts_dict['mpi_enable'] = False
opts_dict['zscoreonly'] = False
opts_dict['popens'] = True
opts_dict['nrand'] = 40
opts_dict['rand'] = False
opts_dict['seq'] = 0
opts_dict['jsondir'] = '/glade/scratch/haiyingx/'
# This creates the dictionary of input arguments
print "before parseconfig"
opts_dict = pyEnsLib.getopt_parseconfig(opts, optkeys, 'ESP', opts_dict)
verbose = opts_dict['verbose']
nbin = opts_dict['nbin']
if verbose:
print opts_dict
# Now find file names in indir
input_dir = opts_dict['indir']
# Create a mpi simplecomm object
if opts_dict['mpi_enable']:
me = simplecomm.create_comm()
else:
me = simplecomm.create_comm(not opts_dict['mpi_enable'])
if opts_dict['jsonfile']:
# Read in the included var list
Var2d, Var3d = pyEnsLib.read_jsonlist(opts_dict['jsonfile'], 'ESP')
str_size = 0
for str in Var3d:
if str_size < len(str):
str_size = len(str)
for str in Var2d:
if str_size < len(str):
str_size = len(str)
in_files = []
if (os.path.exists(input_dir)):
# Pick up the 'nrand' random number of input files to generate summary files
if opts_dict['rand']:
in_files = pyEnsLib.Random_pickup_pop(input_dir, opts_dict,
opts_dict['nrand'])
else:
# Get the list of files
in_files_temp = os.listdir(input_dir)
in_files = sorted(in_files_temp)
# Make sure we have enough
num_files = len(in_files)
else:
print 'Input directory: ', input_dir, ' not found'
sys.exit(2)
# Create a mpi simplecomm object
if opts_dict['mpi_enable']:
me = simplecomm.create_comm()
else:
me = simplecomm.create_comm(not opts_dict['mpi_enable'])
#Partition the input file list
in_file_list = me.partition(in_files, func=EqualStride(), involved=True)
# Open the files in the input directory
o_files = []
for onefile in in_file_list:
if (os.path.isfile(input_dir + '/' + onefile)):
o_files.append(Nio.open_file(input_dir + '/' + onefile, "r"))
else:
print "COULD NOT LOCATE FILE " + input_dir + onefile + "! EXITING...."
sys.exit()
print in_file_list
# Store dimensions of the input fields
if (verbose == True):
print "Getting spatial dimensions"
nlev = -1
nlat = -1
nlon = -1
# Look at first file and get dims
input_dims = o_files[0].dimensions
ndims = len(input_dims)
# Make sure all files have the same dimensions
for key in input_dims:
if key == "z_t":
nlev = input_dims["z_t"]
elif key == "nlon":
nlon = input_dims["nlon"]
elif key == "nlat":
nlat = input_dims["nlat"]
for count, this_file in enumerate(o_files):
input_dims = this_file.dimensions
if ( nlev != int(input_dims["z_t"]) or ( nlat != int(input_dims["nlat"]))\
or ( nlon != int(input_dims["nlon"]))):
print "Dimension mismatch between ", in_file_list[
0], 'and', in_file_list[count], '!!!'
sys.exit()
# Create new summary ensemble file
this_sumfile = opts_dict["sumfile"]
if verbose:
print "Creating ", this_sumfile, " ..."
if (me.get_rank() == 0):
if os.path.exists(this_sumfile):
os.unlink(this_sumfile)
opt = Nio.options()
opt.PreFill = False
opt.Format = 'NetCDF4Classic'
nc_sumfile = Nio.open_file(this_sumfile, 'w', options=opt)
# Set dimensions
if (verbose == True):
print "Setting dimensions ....."
nc_sumfile.create_dimension('nlat', nlat)
nc_sumfile.create_dimension('nlon', nlon)
nc_sumfile.create_dimension('nlev', nlev)
nc_sumfile.create_dimension('time', None)
nc_sumfile.create_dimension('ens_size', opts_dict['npert'])
nc_sumfile.create_dimension('nbin', opts_dict['nbin'])
nc_sumfile.create_dimension('nvars', len(Var3d) + len(Var2d))
nc_sumfile.create_dimension('nvars3d', len(Var3d))
nc_sumfile.create_dimension('nvars2d', len(Var2d))
nc_sumfile.create_dimension('str_size', str_size)
# Set global attributes
now = time.strftime("%c")
if (verbose == True):
print "Setting global attributes ....."
setattr(nc_sumfile, 'creation_date', now)
setattr(nc_sumfile, 'title', 'POP verification ensemble summary file')
setattr(nc_sumfile, 'tag', opts_dict["tag"])
setattr(nc_sumfile, 'compset', opts_dict["compset"])
setattr(nc_sumfile, 'resolution', opts_dict["res"])
setattr(nc_sumfile, 'machine', opts_dict["mach"])
# Create variables
if (verbose == True):
print "Creating variables ....."
v_lev = nc_sumfile.create_variable("lev", 'f', ('nlev', ))
v_vars = nc_sumfile.create_variable("vars", 'S1',
('nvars', 'str_size'))
v_var3d = nc_sumfile.create_variable("var3d", 'S1',
('nvars3d', 'str_size'))
v_var2d = nc_sumfile.create_variable("var2d", 'S1',
('nvars2d', 'str_size'))
v_time = nc_sumfile.create_variable("time", 'd', ('time', ))
v_ens_avg3d = nc_sumfile.create_variable(
"ens_avg3d", 'f', ('time', 'nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_stddev3d = nc_sumfile.create_variable(
"ens_stddev3d", 'f', ('time', 'nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_avg2d = nc_sumfile.create_variable(
"ens_avg2d", 'f', ('time', 'nvars2d', 'nlat', 'nlon'))
v_ens_stddev2d = nc_sumfile.create_variable(
"ens_stddev2d", 'f', ('time', 'nvars2d', 'nlat', 'nlon'))
v_RMSZ = nc_sumfile.create_variable(
"RMSZ", 'f', ('time', 'nvars', 'ens_size', 'nbin'))
if not opts_dict['zscoreonly']:
v_gm = nc_sumfile.create_variable("global_mean", 'f',
('time', 'nvars', 'ens_size'))
# Assign vars, var3d and var2d
if (verbose == True):
print "Assigning vars, var3d, and var2d ....."
eq_all_var_names = []
eq_d3_var_names = []
eq_d2_var_names = []
all_var_names = list(Var3d)
all_var_names += Var2d
l_eq = len(all_var_names)
for i in range(l_eq):
tt = list(all_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ') * (str_size - l_tt)
tt.extend(extra)
eq_all_var_names.append(tt)
l_eq = len(Var3d)
for i in range(l_eq):
tt = list(Var3d[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ') * (str_size - l_tt)
tt.extend(extra)
eq_d3_var_names.append(tt)
l_eq = len(Var2d)
for i in range(l_eq):
tt = list(Var2d[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ') * (str_size - l_tt)
tt.extend(extra)
eq_d2_var_names.append(tt)
v_vars[:] = eq_all_var_names[:]
v_var3d[:] = eq_d3_var_names[:]
v_var2d[:] = eq_d2_var_names[:]
# Time-invarient metadata
if (verbose == True):
print "Assigning time invariant metadata ....."
vars_dict = o_files[0].variables
lev_data = vars_dict["z_t"]
v_lev = lev_data
# Time-varient metadata
if verbose:
print "Assigning time variant metadata ....."
vars_dict = o_files[0].variables
time_value = vars_dict['time']
time_array = np.array([time_value])
time_array = pyEnsLib.gather_npArray_pop(time_array, me, (me.get_size(), ))
if me.get_rank() == 0:
v_time[:] = time_array[:]
# Calculate global mean, average, standard deviation
if verbose:
print "Calculating global means ....."
is_SE = False
tslice = 0
if not opts_dict['zscoreonly']:
gm3d, gm2d = pyEnsLib.generate_global_mean_for_summary(
o_files, Var3d, Var2d, is_SE, False, opts_dict)
if verbose:
print "Finish calculating global means ....."
# Calculate RMSZ scores
if (verbose == True):
print "Calculating RMSZ scores ....."
zscore3d, zscore2d, ens_avg3d, ens_stddev3d, ens_avg2d, ens_stddev2d, temp1, temp2 = pyEnsLib.calc_rmsz(
o_files, Var3d, Var2d, is_SE, opts_dict)
# Collect from all processors
if opts_dict['mpi_enable']:
# Gather the 3d variable results from all processors to the master processor
# Gather global means 3d results
if not opts_dict['zscoreonly']:
gmall = np.concatenate((gm3d, gm2d), axis=0)
#print "before gather, gmall.shape=",gmall.shape
gmall = pyEnsLib.gather_npArray_pop(
gmall, me,
(me.get_size(), len(Var3d) + len(Var2d), len(o_files)))
zmall = np.concatenate((zscore3d, zscore2d), axis=0)
zmall = pyEnsLib.gather_npArray_pop(
zmall, me,
(me.get_size(), len(Var3d) + len(Var2d), len(o_files), nbin))
#print 'zmall=',zmall
#print "after gather, gmall.shape=",gmall.shape
ens_avg3d = pyEnsLib.gather_npArray_pop(
ens_avg3d, me, (me.get_size(), len(Var3d), nlev, (nlat), nlon))
ens_avg2d = pyEnsLib.gather_npArray_pop(ens_avg2d, me,
(me.get_size(), len(Var2d),
(nlat), nlon))
ens_stddev3d = pyEnsLib.gather_npArray_pop(
ens_stddev3d, me, (me.get_size(), len(Var3d), nlev, (nlat), nlon))
ens_stddev2d = pyEnsLib.gather_npArray_pop(ens_stddev2d, me,
(me.get_size(), len(Var2d),
(nlat), nlon))
# Assign to file:
if me.get_rank() == 0:
#Zscoreall=np.concatenate((zscore3d,zscore2d),axis=0)
v_RMSZ[:, :, :, :] = zmall[:, :, :, :]
v_ens_avg3d[:, :, :, :, :] = ens_avg3d[:, :, :, :, :]
v_ens_stddev3d[:, :, :, :, :] = ens_stddev3d[:, :, :, :, :]
v_ens_avg2d[:, :, :, :] = ens_avg2d[:, :, :, :]
v_ens_stddev2d[:, :, :, :] = ens_stddev2d[:, :, :, :]
if not opts_dict['zscoreonly']:
v_gm[:, :, :] = gmall[:, :, :]
print "All done"
def var_nc3d(parameters=['Ttave'],
ofile='MIT_output_3d',
bswap=1,
sstart_date="seconds since 2002-10-01 07:00",
deltaT=1200,
FillValue=-1.0e+23,
dump="no"):
'''
Convert 3d fields produced by MITgcm to netCDF format with use of Nio module.
Names of the files should be defined in form of the list, even if we have only one variable.
I put everything on the C grid!
You have to have following files in the the directory where you run your code:
XC.data
XC.meta
YC.data
YC.meta
DRC.data
DRC.meta
maskCtrlC.data
maskCtrlC.meta
Input:
parameters - list with names of the variables.
ofile - name of the output file.
iteration - iteration of optimisation, should be STRING!
bswap - do we need a byte swap? Yes (1) or no (0) [default 1]
sstart_date - should be "seconds since", [default "seconds since 2002-10-01 07:00"
deltaT - time step in seconds
xx_period - xx_*period
FillValue - missing value
meta - flag to fix problem with wrong adxx*.meta files.
If meta = 'xx', use .meta file from xx files
dump - if dump='yes' will return numpy array with data
'''
lon = mitbin2('XC.data', bswap)[0, 0, :, :]
lat = mitbin2('YC.data', bswap)[0, 0, :, :]
lev = mitbin2('DRC.data', bswap)[0, :, 0, 0]
lev = numpy.cumsum(lev)
lsmask = mitbin2('maskCtrlC.data', bswap)[:, :, :, :]
fileList = glob.glob(parameters[0] + "*.data")
if os.path.exists(ofile + ".nc") == True:
os.system("rm " + ofile + ".nc")
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(
fileList[0][:-4] + "meta")
ttime = numpy.zeros((len(fileList)))
opt = Nio.options()
opt.PreFill = False
opt.HeaderReserveSpace = 4000
f = Nio.open_file(ofile + ".nc", "w", opt)
f.title = "MITgcm variables in netCDF format"
f.create_dimension('x', xdim)
f.create_dimension('y', ydim)
f.create_dimension('z', zdim)
f.create_dimension('time', ttime.shape[0])
f.create_variable('time', 'd', ('time', ))
f.variables['time'].units = sstart_date
f.create_variable('z', 'd', ('z', ))
f.variables['z'].units = "meters"
f.variables['z'][:] = lev[:]
f.create_variable('latitude', 'd', ('x', 'y'))
f.variables['latitude'].long_name = "latitude"
f.variables['latitude'].units = "degrees_north"
f.variables['latitude'].standard_name = "grid_latitude"
f.variables['latitude'][:] = lat[:]
f.create_variable('longitude', 'd', ('x', 'y'))
f.variables['longitude'].long_name = "longitude"
f.variables['longitude'].units = "degrees_east"
f.variables['longitude'].standard_name = "grid_longitude"
f.variables['longitude'][:] = lon[:]
#vvariables = ["atemp","aqh", "uwind", "vwind", ]
#vvariables = ["atemp"]
for parameter in parameters:
f.create_variable(parameter, 'd', ('time', 'z', 'x', 'y'))
f.variables[parameter].long_name = gatrib(parameter)[0]
f.variables[parameter].units = gatrib(parameter)[1]
f.variables[parameter]._FillValue = FillValue
f.variables[parameter].missing_value = FillValue
adatemp_final = numpy.zeros((len(fileList), zdim, xdim, ydim))
for ind, fileName in enumerate(fileList):
adatemp = mitbin2(parameter + fileName[-16:],
bswap=bswap)[:, :, :, :]
ndim, xdim, ydim, zdim, datatype, nrecords, timeStepNumber = rmeta(
fileName[:-4] + "meta")
# adatemp = numpy.where(adatemp[:] > 1.0e+12, 0, adatemp[:])
adatemp = numpy.where(adatemp[:] < -1.0e+20, FillValue, adatemp[:])
adatemp = numpy.where(lsmask[:] == 0, FillValue, adatemp[:])
adatemp_final[ind, :, :, :] = adatemp
ttime[ind] = timeStepNumber * deltaT
f.variables[parameter][:] = adatemp
f.close()
if dump == 'yes':
return adatemp
import numpy as np
import Nio
fn = "MSG3-SEVI-MSG15-0100-NA-20130521001244.164000000Z-1074164.h5"
opt = Nio.options()
opt.FileStructure = "advanced"
f = Nio.open_file(fn, "r", options=opt)
# f = Nio.open_file(fn)
print f.variables.keys()
# print f.groups
# n = 0
# for key in f.groups.keys():
# n += 1
# print "groun %d: <%s>" %(n, key)
# g = f.groups['/U_MARF/MSG/Level1_5/DATA/Channel_07']
g = f.groups["U-MARF/MSG/Level1.5/DATA/Channel 07"]
print g
palette = g.variables["Palette"]
print palette
print "\nLineSideInfo_DESCR:"
lsid = g.variables["LineSideInfo_DESCR"][:]
print lsid[:]
dims = lsid.shape
for n in xrange(dims[0]):
name = str(lsid[:][n][0])
value = str(lsid[:][n][1])
def create_ave_file(my_file,
outfile,
hist_string,
ncformat,
years,
collapse_dim=''):
'''
Opens up/Creates a new file to put the computed averages into.
@param my_file A sampled input file pointer.
@param outfile Filename of the new output/average file.
@param hist_string A string that contains the file history for the history attribute
@param ncformat Format to write the NetCDF file out as.
@param collapse_dim Dimension to collapse across
@return new_file Returns a file pointer to the newly opened file.
'''
dims = my_file.dimensions
attr = my_file.attributes
vars = {}
new_file_name = outfile
# Set pyNIO netcdf file options
opt = Nio.options()
# The netcdf output format
if (ncformat == 'netcdf4c'):
opt.Format = 'NetCDF4Classic'
opt.CompressionLevel = 1
elif (ncformat == 'netcdf4'):
opt.Format = 'NetCDF4Classic'
elif (ncformat == 'netcdf'):
opt.Format = 'Classic'
elif (ncformat == 'netcdfLarge'):
opt.Format = '64BitOffset'
else:
print "WARNING: Seltected netcdf file format (", ncformat, ") is not recongnized."
print "Defaulting to netcdf3Classic format."
opt.Format = 'Classic'
opt.PreFill = False
new_file = Nio.open_file(new_file_name,
"w",
options=opt,
history=hist_string)
#setattr(new_file,'yrs_averaged',years)
# Create attributes, dimensions, and variables
for n, v in attr.items():
if n == 'history':
v = hist_string + '\n' + v
setattr(new_file, n, v)
for var_d, l in dims.items():
if var_d == "time":
if "time" not in collapse_dim:
new_file.create_dimension(var_d, None)
else:
if var_d not in collapse_dim:
new_file.create_dimension(var_d, l)
setattr(new_file, 'yrs_averaged', years)
return new_file
def setUp(self):
do_setup(filename)
opt = Nio.options()
opt.MaskedArrayMode = 'MaskedExplicit'
self.f = Nio.open_file(filename, options=opt)
def main(argv):
# Get command line stuff and store in a dictionary
s = 'tag= compset= esize= tslice= res= sumfile= indir= sumfiledir= mach= verbose jsonfile= mpi_enable maxnorm gmonly popens cumul regx= startMon= endMon= fIndex='
optkeys = s.split()
try:
opts, args = getopt.getopt(argv, "h", optkeys)
except getopt.GetoptError:
pyEnsLib.EnsSum_usage()
sys.exit(2)
# Put command line options in a dictionary - also set defaults
opts_dict={}
# Defaults
opts_dict['tag'] = 'cesm2_0_beta08'
opts_dict['compset'] = 'F2000'
opts_dict['mach'] = 'cheyenne'
opts_dict['esize'] = 350
opts_dict['tslice'] = 1
opts_dict['res'] = 'f19_f19'
opts_dict['sumfile'] = 'ens.summary.nc'
opts_dict['indir'] = './'
opts_dict['sumfiledir'] = './'
opts_dict['jsonfile'] = 'exclude_empty.json'
opts_dict['verbose'] = False
opts_dict['mpi_enable'] = False
opts_dict['maxnorm'] = False
opts_dict['gmonly'] = True
opts_dict['popens'] = False
opts_dict['cumul'] = False
opts_dict['regx'] = 'test'
opts_dict['startMon'] = 1
opts_dict['endMon'] = 1
opts_dict['fIndex'] = 151
# This creates the dictionary of input arguments
opts_dict = pyEnsLib.getopt_parseconfig(opts,optkeys,'ES',opts_dict)
verbose = opts_dict['verbose']
st = opts_dict['esize']
esize = int(st)
if not (opts_dict['tag'] and opts_dict['compset'] and opts_dict['mach'] or opts_dict['res']):
print 'Please specify --tag, --compset, --mach and --res options'
sys.exit()
# Now find file names in indir
input_dir = opts_dict['indir']
# The var list that will be excluded
ex_varlist=[]
inc_varlist=[]
# Create a mpi simplecomm object
if opts_dict['mpi_enable']:
me=simplecomm.create_comm()
else:
me=simplecomm.create_comm(not opts_dict['mpi_enable'])
if me.get_rank() == 0:
print 'Running pyEnsSum!'
if me.get_rank() ==0 and (verbose == True):
print opts_dict
print 'Ensemble size for summary = ', esize
exclude=False
if me.get_rank() == 0:
if opts_dict['jsonfile']:
inc_varlist=[]
# Read in the excluded or included var list
ex_varlist,exclude=pyEnsLib.read_jsonlist(opts_dict['jsonfile'],'ES')
if exclude == False:
inc_varlist=ex_varlist
ex_varlist=[]
# Read in the included var list
#inc_varlist=pyEnsLib.read_jsonlist(opts_dict['jsonfile'],'ES')
# Broadcast the excluded var list to each processor
#if opts_dict['mpi_enable']:
# ex_varlist=me.partition(ex_varlist,func=Duplicate(),involved=True)
# Broadcast the excluded var list to each processor
if opts_dict['mpi_enable']:
exclude=me.partition(exclude,func=Duplicate(),involved=True)
if exclude:
ex_varlist=me.partition(ex_varlist,func=Duplicate(),involved=True)
else:
inc_varlist=me.partition(inc_varlist,func=Duplicate(),involved=True)
in_files=[]
if(os.path.exists(input_dir)):
# Get the list of files
in_files_temp = os.listdir(input_dir)
in_files=sorted(in_files_temp)
# Make sure we have enough
num_files = len(in_files)
if me.get_rank()==0 and (verbose == True):
print 'Number of files in input directory = ', num_files
if (num_files < esize):
if me.get_rank()==0 and (verbose == True):
print 'Number of files in input directory (',num_files,\
') is less than specified ensemble size of ', esize
sys.exit(2)
if (num_files > esize):
if me.get_rank()==0 and (verbose == True):
print 'NOTE: Number of files in ', input_dir, \
'is greater than specified ensemble size of ', esize ,\
'\nwill just use the first ', esize, 'files'
else:
if me.get_rank()==0:
print 'Input directory: ',input_dir,' not found'
sys.exit(2)
if opts_dict['cumul']:
if opts_dict['regx']:
in_files_list=get_cumul_filelist(opts_dict,opts_dict['indir'],opts_dict['regx'])
in_files=me.partition(in_files_list,func=EqualLength(),involved=True)
if me.get_rank()==0 and (verbose == True):
print 'in_files=',in_files
# Open the files in the input directory
o_files=[]
if me.get_rank() == 0 and opts_dict['verbose']:
print 'Input files are: '
print "\n".join(in_files)
#for i in in_files:
# print "in_files =",i
for onefile in in_files[0:esize]:
if (os.path.isfile(input_dir+'/' + onefile)):
o_files.append(Nio.open_file(input_dir+'/' + onefile,"r"))
else:
if me.get_rank()==0:
print "COULD NOT LOCATE FILE "+ input_dir + onefile + "! EXITING...."
sys.exit()
# Store dimensions of the input fields
if me.get_rank()==0 and (verbose == True):
print "Getting spatial dimensions"
nlev = -1
nilev = -1
ncol = -1
nlat = -1
nlon = -1
lonkey=''
latkey=''
# Look at first file and get dims
input_dims = o_files[0].dimensions
ndims = len(input_dims)
for key in input_dims:
if key == "lev":
nlev = input_dims["lev"]
elif key == "ilev":
nilev = input_dims["ilev"]
elif key == "ncol":
ncol = input_dims["ncol"]
elif (key == "nlon") or (key =="lon"):
nlon = input_dims[key]
lonkey=key
elif (key == "nlat") or (key == "lat"):
nlat = input_dims[key]
latkey=key
if (nlev == -1) :
if me.get_rank()==0:
print "COULD NOT LOCATE valid dimension lev => EXITING...."
sys.exit()
if (( ncol == -1) and ((nlat == -1) or (nlon == -1))):
if me.get_rank()==0:
print "Need either lat/lon or ncol => EXITING...."
sys.exit()
# Check if this is SE or FV data
if (ncol != -1):
is_SE = True
else:
is_SE = False
# Make sure all files have the same dimensions
if me.get_rank()==0 and (verbose == True):
print "Checking dimensions across files...."
print 'lev = ', nlev
if (is_SE == True):
print 'ncol = ', ncol
else:
print 'nlat = ', nlat
print 'nlon = ', nlon
for count, this_file in enumerate(o_files):
input_dims = this_file.dimensions
if (is_SE == True):
if ( nlev != int(input_dims["lev"]) or ( ncol != int(input_dims["ncol"]))):
if me.get_rank() == 0:
print "Dimension mismatch between ", in_files[0], 'and', in_files[0], '!!!'
sys.exit()
else:
if ( nlev != int(input_dims["lev"]) or ( nlat != int(input_dims[latkey]))\
or ( nlon != int(input_dims[lonkey]))):
if me.get_rank() == 0:
print "Dimension mismatch between ", in_files[0], 'and', in_files[0], '!!!'
sys.exit()
# Get 2d vars, 3d vars and all vars (For now include all variables)
vars_dict_all = o_files[0].variables
# Remove the excluded variables (specified in json file) from variable dictionary
#print len(vars_dict_all)
if exclude:
vars_dict=vars_dict_all
for i in ex_varlist:
if i in vars_dict:
del vars_dict[i]
#Given an included var list, remove all float var that are not on the list
else:
vars_dict=vars_dict_all.copy()
for k,v in vars_dict_all.iteritems():
if (k not in inc_varlist) and (vars_dict_all[k].typecode()=='f'):
#print vars_dict_all[k].typecode()
#print k
del vars_dict[k]
num_vars = len(vars_dict)
#print num_vars
#if me.get_rank() == 0:
# for k,v in vars_dict.iteritems():
# print 'vars_dict',k,vars_dict[k].typecode()
str_size = 0
d2_var_names = []
d3_var_names = []
num_2d = 0
num_3d = 0
# Which are 2d, which are 3d and max str_size
for k,v in vars_dict.iteritems():
var = k
vd = v.dimensions # all the variable's dimensions (names)
vr = v.rank # num dimension
vs = v.shape # dim values
is_2d = False
is_3d = False
if (is_SE == True): # (time, lev, ncol) or (time, ncol)
if ((vr == 2) and (vs[1] == ncol)):
is_2d = True
num_2d += 1
elif ((vr == 3) and (vs[2] == ncol and vs[1] == nlev )):
is_3d = True
num_3d += 1
else: # (time, lev, nlon, nlon) or (time, nlat, nlon)
if ((vr == 3) and (vs[1] == nlat and vs[2] == nlon)):
is_2d = True
num_2d += 1
elif ((vr == 4) and (vs[2] == nlat and vs[3] == nlon and (vs[1] == nlev or vs[1]==nilev ))):
is_3d = True
num_3d += 1
if (is_3d == True) :
str_size = max(str_size, len(k))
d3_var_names.append(k)
elif (is_2d == True):
str_size = max(str_size, len(k))
d2_var_names.append(k)
#else:
# print 'var=',k
if me.get_rank() == 0 and (verbose == True):
print 'Number of variables found: ', num_3d+num_2d
print '3D variables: '+str(num_3d)+', 2D variables: '+str(num_2d)
# Now sort these and combine (this sorts caps first, then lower case -
# which is what we want)
d2_var_names.sort()
d3_var_names.sort()
if esize<num_2d+num_3d:
if me.get_rank()==0:
print "************************************************************************************************************************************"
print " Error: the total number of 3D and 2D variables "+str(num_2d+num_3d)+" is larger than the number of ensemble files "+str(esize)
print " Cannot generate ensemble summary file, please remove more variables from your included variable list,"
print " or add more varaibles in your excluded variable list!!!"
print "************************************************************************************************************************************"
sys.exit()
# All vars is 3d vars first (sorted), the 2d vars
all_var_names = list(d3_var_names)
all_var_names += d2_var_names
n_all_var_names = len(all_var_names)
#if me.get_rank() == 0 and (verbose == True):
# print 'num vars = ', n_all_var_names, '(3d = ', num_3d, ' and 2d = ', num_2d, ")"
# Create new summary ensemble file
this_sumfile = opts_dict["sumfile"]
if me.get_rank() == 0 and (verbose == True):
print "Creating ", this_sumfile, " ..."
if(me.get_rank() ==0 | opts_dict["popens"]):
if os.path.exists(this_sumfile):
os.unlink(this_sumfile)
opt = Nio.options()
opt.PreFill = False
opt.Format = 'NetCDF4Classic'
nc_sumfile = Nio.open_file(this_sumfile, 'w', options=opt)
# Set dimensions
if me.get_rank() == 0 and (verbose == True):
print "Setting dimensions ....."
if (is_SE == True):
nc_sumfile.create_dimension('ncol', ncol)
else:
nc_sumfile.create_dimension('nlat', nlat)
nc_sumfile.create_dimension('nlon', nlon)
nc_sumfile.create_dimension('nlev', nlev)
nc_sumfile.create_dimension('ens_size', esize)
nc_sumfile.create_dimension('nvars', num_3d + num_2d)
nc_sumfile.create_dimension('nvars3d', num_3d)
nc_sumfile.create_dimension('nvars2d', num_2d)
nc_sumfile.create_dimension('str_size', str_size)
# Set global attributes
now = time.strftime("%c")
if me.get_rank() == 0 and (verbose == True):
print "Setting global attributes ....."
setattr(nc_sumfile, 'creation_date',now)
setattr(nc_sumfile, 'title', 'CAM verification ensemble summary file')
setattr(nc_sumfile, 'tag', opts_dict["tag"])
setattr(nc_sumfile, 'compset', opts_dict["compset"])
setattr(nc_sumfile, 'resolution', opts_dict["res"])
setattr(nc_sumfile, 'machine', opts_dict["mach"])
# Create variables
if me.get_rank() == 0 and (verbose == True):
print "Creating variables ....."
v_lev = nc_sumfile.create_variable("lev", 'f', ('nlev',))
v_vars = nc_sumfile.create_variable("vars", 'S1', ('nvars', 'str_size'))
v_var3d = nc_sumfile.create_variable("var3d", 'S1', ('nvars3d', 'str_size'))
v_var2d = nc_sumfile.create_variable("var2d", 'S1', ('nvars2d', 'str_size'))
if not opts_dict['gmonly']:
if (is_SE == True):
v_ens_avg3d = nc_sumfile.create_variable("ens_avg3d", 'f', ('nvars3d', 'nlev', 'ncol'))
v_ens_stddev3d = nc_sumfile.create_variable("ens_stddev3d", 'f', ('nvars3d', 'nlev', 'ncol'))
v_ens_avg2d = nc_sumfile.create_variable("ens_avg2d", 'f', ('nvars2d', 'ncol'))
v_ens_stddev2d = nc_sumfile.create_variable("ens_stddev2d", 'f', ('nvars2d', 'ncol'))
else:
v_ens_avg3d = nc_sumfile.create_variable("ens_avg3d", 'f', ('nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_stddev3d = nc_sumfile.create_variable("ens_stddev3d", 'f', ('nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_avg2d = nc_sumfile.create_variable("ens_avg2d", 'f', ('nvars2d', 'nlat', 'nlon'))
v_ens_stddev2d = nc_sumfile.create_variable("ens_stddev2d", 'f', ('nvars2d', 'nlat', 'nlon'))
v_RMSZ = nc_sumfile.create_variable("RMSZ", 'f', ('nvars', 'ens_size'))
v_gm = nc_sumfile.create_variable("global_mean", 'f', ('nvars', 'ens_size'))
v_standardized_gm=nc_sumfile.create_variable("standardized_gm",'f',('nvars','ens_size'))
v_loadings_gm = nc_sumfile.create_variable('loadings_gm','f',('nvars','nvars'))
v_mu_gm = nc_sumfile.create_variable('mu_gm','f',('nvars',))
v_sigma_gm = nc_sumfile.create_variable('sigma_gm','f',('nvars',))
v_sigma_scores_gm = nc_sumfile.create_variable('sigma_scores_gm','f',('nvars',))
# Assign vars, var3d and var2d
if me.get_rank() == 0 and (verbose == True):
print "Assigning vars, var3d, and var2d ....."
eq_all_var_names =[]
eq_d3_var_names = []
eq_d2_var_names = []
l_eq = len(all_var_names)
for i in range(l_eq):
tt = list(all_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ')*(str_size - l_tt)
tt.extend(extra)
eq_all_var_names.append(tt)
l_eq = len(d3_var_names)
for i in range(l_eq):
tt = list(d3_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ')*(str_size - l_tt)
tt.extend(extra)
eq_d3_var_names.append(tt)
l_eq = len(d2_var_names)
for i in range(l_eq):
tt = list(d2_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ')*(str_size - l_tt)
tt.extend(extra)
eq_d2_var_names.append(tt)
v_vars[:] = eq_all_var_names[:]
v_var3d[:] = eq_d3_var_names[:]
v_var2d[:] = eq_d2_var_names[:]
# Time-invarient metadata
if me.get_rank() == 0 and (verbose == True):
print "Assigning time invariant metadata ....."
lev_data = vars_dict["lev"]
v_lev = lev_data
# Form ensembles, each missing one member; compute RMSZs and global means
#for each variable, we also do max norm also (currently done in pyStats)
tslice = opts_dict['tslice']
if not opts_dict['cumul']:
# Partition the var list
var3_list_loc=me.partition(d3_var_names,func=EqualStride(),involved=True)
var2_list_loc=me.partition(d2_var_names,func=EqualStride(),involved=True)
else:
var3_list_loc=d3_var_names
var2_list_loc=d2_var_names
# Calculate global means #
if me.get_rank() == 0 and (verbose == True):
print "Calculating global means ....."
if not opts_dict['cumul']:
gm3d,gm2d,var_list = pyEnsLib.generate_global_mean_for_summary(o_files,var3_list_loc,var2_list_loc , is_SE, False,opts_dict)
if me.get_rank() == 0 and (verbose == True):
print "Finish calculating global means ....."
# Calculate RMSZ scores
if (not opts_dict['gmonly']) | (opts_dict['cumul']):
if me.get_rank() == 0 and (verbose == True):
print "Calculating RMSZ scores ....."
zscore3d,zscore2d,ens_avg3d,ens_stddev3d,ens_avg2d,ens_stddev2d,temp1,temp2=pyEnsLib.calc_rmsz(o_files,var3_list_loc,var2_list_loc,is_SE,opts_dict)
# Calculate max norm ensemble
if opts_dict['maxnorm']:
if me.get_rank() == 0 and (verbose == True):
print "Calculating max norm of ensembles ....."
pyEnsLib.calculate_maxnormens(opts_dict,var3_list_loc)
pyEnsLib.calculate_maxnormens(opts_dict,var2_list_loc)
if opts_dict['mpi_enable'] & ( not opts_dict['popens']):
if not opts_dict['cumul']:
# Gather the 3d variable results from all processors to the master processor
slice_index=get_stride_list(len(d3_var_names),me)
# Gather global means 3d results
gm3d=gather_npArray(gm3d,me,slice_index,(len(d3_var_names),len(o_files)))
if not opts_dict['gmonly']:
# Gather zscore3d results
zscore3d=gather_npArray(zscore3d,me,slice_index,(len(d3_var_names),len(o_files)))
# Gather ens_avg3d and ens_stddev3d results
shape_tuple3d=get_shape(ens_avg3d.shape,len(d3_var_names),me.get_rank())
ens_avg3d=gather_npArray(ens_avg3d,me,slice_index,shape_tuple3d)
ens_stddev3d=gather_npArray(ens_stddev3d,me,slice_index,shape_tuple3d)
# Gather 2d variable results from all processors to the master processor
slice_index=get_stride_list(len(d2_var_names),me)
# Gather global means 2d results
gm2d=gather_npArray(gm2d,me,slice_index,(len(d2_var_names),len(o_files)))
var_list=gather_list(var_list,me)
if not opts_dict['gmonly']:
# Gather zscore2d results
zscore2d=gather_npArray(zscore2d,me,slice_index,(len(d2_var_names),len(o_files)))
# Gather ens_avg3d and ens_stddev2d results
shape_tuple2d=get_shape(ens_avg2d.shape,len(d2_var_names),me.get_rank())
ens_avg2d=gather_npArray(ens_avg2d,me,slice_index,shape_tuple2d)
ens_stddev2d=gather_npArray(ens_stddev2d,me,slice_index,shape_tuple2d)
else:
gmall=np.concatenate((temp1,temp2),axis=0)
gmall=pyEnsLib.gather_npArray_pop(gmall,me,(me.get_size(),len(d3_var_names)+len(d2_var_names)))
# Assign to file:
if me.get_rank() == 0 | opts_dict['popens'] :
if not opts_dict['cumul']:
gmall=np.concatenate((gm3d,gm2d),axis=0)
if not opts_dict['gmonly']:
Zscoreall=np.concatenate((zscore3d,zscore2d),axis=0)
v_RMSZ[:,:]=Zscoreall[:,:]
if not opts_dict['gmonly']:
if (is_SE == True):
v_ens_avg3d[:,:,:]=ens_avg3d[:,:,:]
v_ens_stddev3d[:,:,:]=ens_stddev3d[:,:,:]
v_ens_avg2d[:,:]=ens_avg2d[:,:]
v_ens_stddev2d[:,:]=ens_stddev2d[:,:]
else:
v_ens_avg3d[:,:,:,:]=ens_avg3d[:,:,:,:]
v_ens_stddev3d[:,:,:,:]=ens_stddev3d[:,:,:,:]
v_ens_avg2d[:,:,:]=ens_avg2d[:,:,:]
v_ens_stddev2d[:,:,:]=ens_stddev2d[:,:,:]
else:
gmall_temp=np.transpose(gmall[:,:])
gmall=gmall_temp
mu_gm,sigma_gm,standardized_global_mean,loadings_gm,scores_gm=pyEnsLib.pre_PCA(gmall,all_var_names,var_list,me)
v_gm[:,:]=gmall[:,:]
v_standardized_gm[:,:]=standardized_global_mean[:,:]
v_mu_gm[:]=mu_gm[:]
v_sigma_gm[:]=sigma_gm[:].astype(np.float32)
v_loadings_gm[:,:]=loadings_gm[:,:]
v_sigma_scores_gm[:]=scores_gm[:]
if me.get_rank() == 0:
print "All Done"
def main(argv):
print "Running pyEnsSum!"
# Get command line stuff and store in a dictionary
s = "tag= compset= esize= tslice= res= sumfile= indir= sumfiledir= mach= verbose jsonfile= mpi_enable maxnorm gmonly popens cumul regx= startMon= endMon= fIndex="
optkeys = s.split()
try:
opts, args = getopt.getopt(argv, "h", optkeys)
except getopt.GetoptError:
pyEnsLib.EnsSum_usage()
sys.exit(2)
# Put command line options in a dictionary - also set defaults
opts_dict = {}
# Defaults
opts_dict["tag"] = ""
opts_dict["compset"] = ""
opts_dict["mach"] = ""
opts_dict["esize"] = 151
opts_dict["tslice"] = 0
opts_dict["res"] = ""
opts_dict["sumfile"] = "ens.summary.nc"
opts_dict["indir"] = "./"
opts_dict["sumfiledir"] = "./"
opts_dict["jsonfile"] = ""
opts_dict["verbose"] = True
opts_dict["mpi_enable"] = False
opts_dict["maxnorm"] = False
opts_dict["gmonly"] = False
opts_dict["popens"] = False
opts_dict["cumul"] = False
opts_dict["regx"] = "test"
opts_dict["startMon"] = 1
opts_dict["endMon"] = 1
opts_dict["fIndex"] = 151
# This creates the dictionary of input arguments
opts_dict = pyEnsLib.getopt_parseconfig(opts, optkeys, "ES", opts_dict)
verbose = opts_dict["verbose"]
st = opts_dict["esize"]
esize = int(st)
if verbose == True:
print opts_dict
print "Ensemble size for summary = ", esize
if not (opts_dict["tag"] and opts_dict["compset"] and opts_dict["mach"] or opts_dict["res"]):
print "Please specify --tag, --compset, --mach and --res options"
sys.exit()
# Now find file names in indir
input_dir = opts_dict["indir"]
# The var list that will be excluded
ex_varlist = []
# Create a mpi simplecomm object
if opts_dict["mpi_enable"]:
me = simplecomm.create_comm()
else:
me = simplecomm.create_comm(not opts_dict["mpi_enable"])
if me.get_rank() == 0:
if opts_dict["jsonfile"]:
# Read in the excluded var list
ex_varlist = pyEnsLib.read_jsonlist(opts_dict["jsonfile"], "ES")
# Broadcast the excluded var list to each processor
if opts_dict["mpi_enable"]:
ex_varlist = me.partition(ex_varlist, func=Duplicate(), involved=True)
in_files = []
if os.path.exists(input_dir):
# Get the list of files
in_files_temp = os.listdir(input_dir)
in_files = sorted(in_files_temp)
# Make sure we have enough
num_files = len(in_files)
if verbose == True:
print "Number of files in input directory = ", num_files
if num_files < esize:
print "Number of files in input directory (", num_files, ") is less than specified ensemble size of ", esize
sys.exit(2)
if num_files > esize:
print "NOTE: Number of files in ", input_dir, "is greater than specified ensemble size of ", esize, "\nwill just use the first ", esize, "files"
else:
print "Input directory: ", input_dir, " not found"
sys.exit(2)
if opts_dict["cumul"]:
if opts_dict["regx"]:
in_files_list = get_cumul_filelist(opts_dict, opts_dict["indir"], opts_dict["regx"])
in_files = me.partition(in_files_list, func=EqualLength(), involved=True)
if me.get_rank() == 0:
print "in_files=", in_files
# Open the files in the input directory
o_files = []
for onefile in in_files[0:esize]:
if os.path.isfile(input_dir + "/" + onefile):
o_files.append(Nio.open_file(input_dir + "/" + onefile, "r"))
else:
print "COULD NOT LOCATE FILE " + input_dir + onefile + "! EXITING...."
sys.exit()
# Store dimensions of the input fields
if verbose == True:
print "Getting spatial dimensions"
nlev = -1
ncol = -1
nlat = -1
nlon = -1
lonkey = ""
latkey = ""
# Look at first file and get dims
input_dims = o_files[0].dimensions
ndims = len(input_dims)
for key in input_dims:
if key == "lev":
nlev = input_dims["lev"]
elif key == "ncol":
ncol = input_dims["ncol"]
elif (key == "nlon") or (key == "lon"):
nlon = input_dims[key]
lonkey = key
elif (key == "nlat") or (key == "lat"):
nlat = input_dims[key]
latkey = key
if nlev == -1:
print "COULD NOT LOCATE valid dimension lev => EXITING...."
sys.exit()
if (ncol == -1) and ((nlat == -1) or (nlon == -1)):
print "Need either lat/lon or ncol => EXITING...."
sys.exit()
# Check if this is SE or FV data
if ncol != -1:
is_SE = True
else:
is_SE = False
# Make sure all files have the same dimensions
if verbose == True:
print "Checking dimensions across files...."
print "lev = ", nlev
if is_SE == True:
print "ncol = ", ncol
else:
print "nlat = ", nlat
print "nlon = ", nlon
for count, this_file in enumerate(o_files):
input_dims = this_file.dimensions
if is_SE == True:
if nlev != int(input_dims["lev"]) or (ncol != int(input_dims["ncol"])):
print "Dimension mismatch between ", in_files[0], "and", in_files[0], "!!!"
sys.exit()
else:
if nlev != int(input_dims["lev"]) or (nlat != int(input_dims[latkey])) or (nlon != int(input_dims[lonkey])):
print "Dimension mismatch between ", in_files[0], "and", in_files[0], "!!!"
sys.exit()
# Get 2d vars, 3d vars and all vars (For now include all variables)
vars_dict = o_files[0].variables
# Remove the excluded variables (specified in json file) from variable dictionary
if ex_varlist:
for i in ex_varlist:
del vars_dict[i]
num_vars = len(vars_dict)
if verbose == True:
print "Number of variables (including metadata) found = ", num_vars
str_size = 0
d2_var_names = []
d3_var_names = []
num_2d = 0
num_3d = 0
# Which are 2d, which are 3d and max str_size
for k, v in vars_dict.iteritems():
var = k
vd = v.dimensions # all the variable's dimensions (names)
vr = v.rank # num dimension
vs = v.shape # dim values
is_2d = False
is_3d = False
if is_SE == True: # (time, lev, ncol) or (time, ncol)
if (vr == 2) and (vs[1] == ncol):
is_2d = True
num_2d += 1
elif (vr == 3) and (vs[2] == ncol and vs[1] == nlev):
is_3d = True
num_3d += 1
else: # (time, lev, nlon, nlon) or (time, nlat, nlon)
if (vr == 3) and (vs[1] == nlat and vs[2] == nlon):
is_2d = True
num_2d += 1
elif (vr == 4) and (vs[2] == nlat and vs[3] == nlon and vs[1] == nlev):
is_3d = True
num_3d += 1
if is_3d == True:
str_size = max(str_size, len(k))
d3_var_names.append(k)
elif is_2d == True:
str_size = max(str_size, len(k))
d2_var_names.append(k)
# Now sort these and combine (this sorts caps first, then lower case -
# which is what we want)
d2_var_names.sort()
d3_var_names.sort()
# All vars is 3d vars first (sorted), the 2d vars
all_var_names = list(d3_var_names)
all_var_names += d2_var_names
n_all_var_names = len(all_var_names)
if verbose == True:
print "num vars = ", n_all_var_names, "(3d = ", num_3d, " and 2d = ", num_2d, ")"
# Create new summary ensemble file
this_sumfile = opts_dict["sumfile"]
if verbose == True:
print "Creating ", this_sumfile, " ..."
if me.get_rank() == 0 | opts_dict["popens"]:
if os.path.exists(this_sumfile):
os.unlink(this_sumfile)
opt = Nio.options()
opt.PreFill = False
opt.Format = "NetCDF4Classic"
nc_sumfile = Nio.open_file(this_sumfile, "w", options=opt)
# Set dimensions
if verbose == True:
print "Setting dimensions ....."
if is_SE == True:
nc_sumfile.create_dimension("ncol", ncol)
else:
nc_sumfile.create_dimension("nlat", nlat)
nc_sumfile.create_dimension("nlon", nlon)
nc_sumfile.create_dimension("nlev", nlev)
nc_sumfile.create_dimension("ens_size", esize)
nc_sumfile.create_dimension("nvars", num_3d + num_2d)
nc_sumfile.create_dimension("nvars3d", num_3d)
nc_sumfile.create_dimension("nvars2d", num_2d)
nc_sumfile.create_dimension("str_size", str_size)
# Set global attributes
now = time.strftime("%c")
if verbose == True:
print "Setting global attributes ....."
setattr(nc_sumfile, "creation_date", now)
setattr(nc_sumfile, "title", "CAM verification ensemble summary file")
setattr(nc_sumfile, "tag", opts_dict["tag"])
setattr(nc_sumfile, "compset", opts_dict["compset"])
setattr(nc_sumfile, "resolution", opts_dict["res"])
setattr(nc_sumfile, "machine", opts_dict["mach"])
# Create variables
if verbose == True:
print "Creating variables ....."
v_lev = nc_sumfile.create_variable("lev", "f", ("nlev",))
v_vars = nc_sumfile.create_variable("vars", "S1", ("nvars", "str_size"))
v_var3d = nc_sumfile.create_variable("var3d", "S1", ("nvars3d", "str_size"))
v_var2d = nc_sumfile.create_variable("var2d", "S1", ("nvars2d", "str_size"))
if not opts_dict["gmonly"]:
if is_SE == True:
v_ens_avg3d = nc_sumfile.create_variable("ens_avg3d", "f", ("nvars3d", "nlev", "ncol"))
v_ens_stddev3d = nc_sumfile.create_variable("ens_stddev3d", "f", ("nvars3d", "nlev", "ncol"))
v_ens_avg2d = nc_sumfile.create_variable("ens_avg2d", "f", ("nvars2d", "ncol"))
v_ens_stddev2d = nc_sumfile.create_variable("ens_stddev2d", "f", ("nvars2d", "ncol"))
else:
v_ens_avg3d = nc_sumfile.create_variable("ens_avg3d", "f", ("nvars3d", "nlev", "nlat", "nlon"))
v_ens_stddev3d = nc_sumfile.create_variable("ens_stddev3d", "f", ("nvars3d", "nlev", "nlat", "nlon"))
v_ens_avg2d = nc_sumfile.create_variable("ens_avg2d", "f", ("nvars2d", "nlat", "nlon"))
v_ens_stddev2d = nc_sumfile.create_variable("ens_stddev2d", "f", ("nvars2d", "nlat", "nlon"))
v_RMSZ = nc_sumfile.create_variable("RMSZ", "f", ("nvars", "ens_size"))
v_gm = nc_sumfile.create_variable("global_mean", "f", ("nvars", "ens_size"))
v_loadings_gm = nc_sumfile.create_variable("loadings_gm", "f", ("nvars", "nvars"))
v_mu_gm = nc_sumfile.create_variable("mu_gm", "f", ("nvars",))
v_sigma_gm = nc_sumfile.create_variable("sigma_gm", "f", ("nvars",))
v_sigma_scores_gm = nc_sumfile.create_variable("sigma_scores_gm", "f", ("nvars",))
# Assign vars, var3d and var2d
if verbose == True:
print "Assigning vars, var3d, and var2d ....."
eq_all_var_names = []
eq_d3_var_names = []
eq_d2_var_names = []
l_eq = len(all_var_names)
for i in range(l_eq):
tt = list(all_var_names[i])
l_tt = len(tt)
if l_tt < str_size:
extra = list(" ") * (str_size - l_tt)
tt.extend(extra)
eq_all_var_names.append(tt)
l_eq = len(d3_var_names)
for i in range(l_eq):
tt = list(d3_var_names[i])
l_tt = len(tt)
if l_tt < str_size:
extra = list(" ") * (str_size - l_tt)
tt.extend(extra)
eq_d3_var_names.append(tt)
l_eq = len(d2_var_names)
for i in range(l_eq):
tt = list(d2_var_names[i])
l_tt = len(tt)
if l_tt < str_size:
extra = list(" ") * (str_size - l_tt)
tt.extend(extra)
eq_d2_var_names.append(tt)
v_vars[:] = eq_all_var_names[:]
v_var3d[:] = eq_d3_var_names[:]
v_var2d[:] = eq_d2_var_names[:]
# Time-invarient metadata
if verbose == True:
print "Assigning time invariant metadata ....."
lev_data = vars_dict["lev"]
v_lev = lev_data
# Form ensembles, each missing one member; compute RMSZs and global means
# for each variable, we also do max norm also (currently done in pyStats)
tslice = opts_dict["tslice"]
if not opts_dict["cumul"]:
# Partition the var list
var3_list_loc = me.partition(d3_var_names, func=EqualStride(), involved=True)
var2_list_loc = me.partition(d2_var_names, func=EqualStride(), involved=True)
else:
var3_list_loc = d3_var_names
var2_list_loc = d2_var_names
# Calculate global means #
if verbose == True:
print "Calculating global means ....."
if not opts_dict["cumul"]:
gm3d, gm2d = pyEnsLib.generate_global_mean_for_summary(
o_files, var3_list_loc, var2_list_loc, is_SE, False, opts_dict
)
if verbose == True:
print "Finish calculating global means ....."
# Calculate RMSZ scores
if verbose == True:
print "Calculating RMSZ scores ....."
if (not opts_dict["gmonly"]) | (opts_dict["cumul"]):
zscore3d, zscore2d, ens_avg3d, ens_stddev3d, ens_avg2d, ens_stddev2d, temp1, temp2 = pyEnsLib.calc_rmsz(
o_files, var3_list_loc, var2_list_loc, is_SE, opts_dict
)
# Calculate max norm ensemble
if opts_dict["maxnorm"]:
if verbose == True:
print "Calculating max norm of ensembles ....."
pyEnsLib.calculate_maxnormens(opts_dict, var3_list_loc)
pyEnsLib.calculate_maxnormens(opts_dict, var2_list_loc)
if opts_dict["mpi_enable"] & (not opts_dict["popens"]):
if not opts_dict["cumul"]:
# Gather the 3d variable results from all processors to the master processor
slice_index = get_stride_list(len(d3_var_names), me)
# Gather global means 3d results
gm3d = gather_npArray(gm3d, me, slice_index, (len(d3_var_names), len(o_files)))
if not opts_dict["gmonly"]:
# Gather zscore3d results
zscore3d = gather_npArray(zscore3d, me, slice_index, (len(d3_var_names), len(o_files)))
# Gather ens_avg3d and ens_stddev3d results
shape_tuple3d = get_shape(ens_avg3d.shape, len(d3_var_names), me.get_rank())
ens_avg3d = gather_npArray(ens_avg3d, me, slice_index, shape_tuple3d)
ens_stddev3d = gather_npArray(ens_stddev3d, me, slice_index, shape_tuple3d)
# Gather 2d variable results from all processors to the master processor
slice_index = get_stride_list(len(d2_var_names), me)
# Gather global means 2d results
gm2d = gather_npArray(gm2d, me, slice_index, (len(d2_var_names), len(o_files)))
if not opts_dict["gmonly"]:
# Gather zscore2d results
zscore2d = gather_npArray(zscore2d, me, slice_index, (len(d2_var_names), len(o_files)))
# Gather ens_avg3d and ens_stddev2d results
shape_tuple2d = get_shape(ens_avg2d.shape, len(d2_var_names), me.get_rank())
ens_avg2d = gather_npArray(ens_avg2d, me, slice_index, shape_tuple2d)
ens_stddev2d = gather_npArray(ens_stddev2d, me, slice_index, shape_tuple2d)
else:
gmall = np.concatenate((temp1, temp2), axis=0)
gmall = pyEnsLib.gather_npArray_pop(gmall, me, (me.get_size(), len(d3_var_names) + len(d2_var_names)))
# Assign to file:
if me.get_rank() == 0 | opts_dict["popens"]:
if not opts_dict["cumul"]:
gmall = np.concatenate((gm3d, gm2d), axis=0)
if not opts_dict["gmonly"]:
Zscoreall = np.concatenate((zscore3d, zscore2d), axis=0)
v_RMSZ[:, :] = Zscoreall[:, :]
if not opts_dict["gmonly"]:
if is_SE == True:
v_ens_avg3d[:, :, :] = ens_avg3d[:, :, :]
v_ens_stddev3d[:, :, :] = ens_stddev3d[:, :, :]
v_ens_avg2d[:, :] = ens_avg2d[:, :]
v_ens_stddev2d[:, :] = ens_stddev2d[:, :]
else:
v_ens_avg3d[:, :, :, :] = ens_avg3d[:, :, :, :]
v_ens_stddev3d[:, :, :, :] = ens_stddev3d[:, :, :, :]
v_ens_avg2d[:, :, :] = ens_avg2d[:, :, :]
v_ens_stddev2d[:, :, :] = ens_stddev2d[:, :, :]
else:
gmall_temp = np.transpose(gmall[:, :])
gmall = gmall_temp
mu_gm, sigma_gm, standardized_global_mean, loadings_gm, scores_gm = pyEnsLib.pre_PCA(gmall)
v_gm[:, :] = gmall[:, :]
v_mu_gm[:] = mu_gm[:]
v_sigma_gm[:] = sigma_gm[:].astype(np.float32)
v_loadings_gm[:, :] = loadings_gm[:, :]
v_sigma_scores_gm[:] = scores_gm[:]
print "All Done"
def combine_met_data(rootdir, date, ofilepath):
#
# Set the dirs based on date
#
day = timedelta(days=1)
date0 = date - day
dir0 = rootdir + "/" + date0.strftime("Y%Y/M%m/D%d")
dir1 = rootdir + "/" + date.strftime("Y%Y/M%m/D%d")
#
# Set the PreFill option to False to improve writing performance
#
opt = Nio.options()
opt.PreFill = False
#
# Options for writing NetCDF4 "classic" file.
#
# If Nio wasn't built with netcdf 4 support, you will get a
# warning here, and the code will use netcdf 3 instead.
#
opt.Format = "netcdf4classic"
#opt.Format = "LargeFile"
vrt_file = Nio.open_file(
'/glade/p/acom/acom-climate/fvitt/GEOS/GEOS5_orig_res_20180715.nc',
mode='r')
# define vertical coordinate
yyyymmdd = date.strftime("%Y%m%d")
os.system("/bin/rm -f " + ofilepath)
now = datetime.now()
hist_str = 'created by combine_met_data.py : ' + now.strftime(
"%a %d %b %Y %H:%M:%S")
out_file = Nio.open_file(ofilepath,
mode='c',
options=opt,
history=hist_str)
# vertical dimension ...
# define dimensions and ALL variables before writing the data ....
length = vrt_file.dimensions["lev"]
out_file.create_dimension("lev", length)
length = vrt_file.dimensions["ilev"]
out_file.create_dimension("ilev", length)
# define horizontal coordinates
hrz_file = Nio.open_file(
'/glade/p/acom/acom-climate/fvitt/GEOS/GEOS.fp.asm.const_2d_asm_Nx.00000000_0000.V01.nc4'
)
length = hrz_file.dimensions["lat"]
out_file.create_dimension("lat", length)
length = hrz_file.dimensions["lon"]
out_file.create_dimension("lon", length)
# time dimension ...
out_file.create_dimension("time", None)
refdate = datetime(1900, 01, 01)
dims = ('time', )
out_file.create_variable("time", 'd', dims)
setattr(out_file.variables['time'], 'units', 'days')
setattr(out_file.variables['time'], 'long_name',
'days since ' + refdate.strftime("%d %b %Y %H:%M:%S"))
out_file.create_variable("date", 'i', dims)
setattr(out_file.variables["date"], 'units', 'current date (YYYYMMDD)')
setattr(out_file.variables["date"], 'long_name', 'current date (YYYYMMDD)')
out_file.create_variable("datesec", 'i', dims)
setattr(out_file.variables["datesec"], 'units', 'seconds')
setattr(out_file.variables["datesec"], 'long_name',
'current seconds of current date')
vrt_vars = ["lev", "ilev", "hyam", "hybm", "hyai", "hybi"]
for var in vrt_vars:
type = vrt_file.variables[var].typecode()
vdims = vrt_file.variables[var].dimensions
out_file.create_variable(var, type, vdims)
varatts = vrt_file.variables[var].__dict__.keys()
for att in varatts:
val = getattr(vrt_file.variables[var], att)
setattr(out_file.variables[var], att, val)
hrz_vars = ["lon", "lat", "PHIS"]
for var in hrz_vars:
type = hrz_file.variables[var].typecode()
vdims = hrz_file.variables[var].dimensions
out_file.create_variable(var, type, vdims)
varatts = hrz_file.variables[var].__dict__.keys()
for att in varatts:
val = getattr(hrz_file.variables[var], att)
setattr(out_file.variables[var], att, val)
type = hrz_file.variables["FRLAND"].typecode()
vdims = hrz_file.variables["FRLAND"].dimensions
out_file.create_variable("ORO", type, vdims)
varatts = hrz_file.variables["FRLAND"].__dict__.keys()
for att in varatts:
val = getattr(hrz_file.variables["FRLAND"], att)
setattr(out_file.variables["ORO"], att, val)
tavg_flx_vars = {
'HFLUX': 'SHFLX',
'TAUX': 'TAUX',
'TAUY': 'TAUY',
'EVAP': 'QFLX'
} # flx
tavg_flx_filem = glob.glob(dir0 +
'/GEOS.fp.asm.tavg1_2d_flx_Nx.*_2330.V01.nc4')
define_flds(tavg_flx_vars, tavg_flx_filem, out_file)
tavg_rad_vars = {'ALBEDO': 'ALB', 'TS': 'TS', 'SWGDN': 'FSDS'} # rad
tavg_rad_filem = glob.glob(dir0 +
'/GEOS.fp.asm.tavg1_2d_rad_Nx.*_2330.V01.nc4')
define_flds(tavg_rad_vars, tavg_rad_filem, out_file)
tavg_lnd_vars = {'GWETTOP': 'SOILW', 'SNOMAS': 'SNOWH'} # lnd
tavg_lnd_filem = glob.glob(dir0 +
'/GEOS.fp.asm.tavg1_2d_lnd_Nx.*_2330.V01.nc4')
define_flds(tavg_lnd_vars, tavg_lnd_filem, out_file)
inst_vars = {'PS': 'PS', 'T': 'T', 'U': 'U', 'V': 'V', 'QV': 'Q'}
inst_files = glob.glob(dir1 + '/GEOS.fp.asm.inst3_3d_asm_Nv.*.nc4')
inst_files.sort()
define_flds(inst_vars, inst_files, out_file)
# definitions should be done at this point
# Write coordinate dimension variables first
for var in vrt_vars:
if vrt_file.dimensions.keys().count(var) > 0:
v = vrt_file.variables[var].get_value()
out_file.variables[var].assign_value(v)
for var in vrt_vars:
if vrt_file.dimensions.keys().count(var) == 0:
v = vrt_file.variables[var].get_value()
out_file.variables[var].assign_value(v)
vrt_file.close()
# set time/date data ...
times = [i * 3 for i in range(8)] # hours
days = list()
datesecs = list()
for hr in times:
d = datetime(date.year, date.month, date.day, hr, 0, 0)
dd = d - refdate
days.append(dd.days + (dd.seconds / 86400.0))
datesecs.append(dd.seconds)
out_file.variables['time'].assign_value(days)
out_file.variables['date'].assign_value(int(yyyymmdd))
out_file.variables['datesec'].assign_value(datesecs)
var = "lat"
v = hrz_file.variables[var].get_value()
out_file.variables[var].assign_value(v)
var = "lon"
v = hrz_file.variables[var].get_value()
# want logitudes from 0 to 360 ( rather than -180 to 180)
neglons = numpy.where(v < 0.0)
nroll = neglons[0][-1] + 1
lons = numpy.roll(v, nroll)
lons = numpy.where(lons < 0., lons + 360., lons)
lons = numpy.where(lons < 1.e-3, 0.,
lons) # GEOS data has a small value rather than zero
out_file.variables[var].assign_value(lons)
for var in hrz_vars:
if hrz_file.dimensions.keys().count(var) == 0:
v = hrz_file.variables[var].get_value()
v = numpy.roll(v, nroll, axis=2)
v = numpy.tile(v, (8, 1, 1))
out_file.variables[var].assign_value(v)
files = glob.glob(dir1 + '/GEOS.fp.asm.tavg1_2d_flx_Nx.*.nc4')
files.sort()
filepaths = tavg_flx_filem + files
write_tavg_flds(tavg_flx_vars, filepaths, nroll, out_file)
# special code for ORO
ivar = 'FRSEAICE'
for n in range(1, 24, 3):
filem = Nio.open_file(filepaths[n - 1])
filep = Nio.open_file(filepaths[n])
valm = filem.variables[ivar].get_value()
valp = filep.variables[ivar].get_value()
ndims = filep.variables[ivar].rank
vala = 0.5 * (valm + valp)
vala = numpy.roll(vala, nroll, ndims - 1)
if n > 1:
val = numpy.append(val, vala, axis=0)
else:
val = vala
seaice = val
v = hrz_file.variables["FRLAND"].get_value()
v = numpy.roll(v, nroll, axis=2)
v = numpy.tile(v, (8, 1, 1))
#v = numpy.where(v==2, 1, v)
v = numpy.where(seaice > 0.5, 2, v)
out_file.variables["ORO"].assign_value(v)
hrz_file.close()
files = glob.glob(dir1 + '/GEOS.fp.asm.tavg1_2d_rad_Nx.*.nc4')
files.sort()
filepaths = tavg_rad_filem + files
write_tavg_flds(tavg_rad_vars, filepaths, nroll, out_file)
files = glob.glob(dir1 + '/GEOS.fp.asm.tavg1_2d_lnd_Nx.*.nc4')
files.sort()
filepaths = tavg_lnd_filem + files
write_tavg_flds(tavg_lnd_vars, filepaths, nroll, out_file)
# instantaneous fields ....
write_inst_flds(inst_vars, inst_files, nroll, out_file)
out_file.close()
return True
def setUp(self):
do_setup(filename)
opt = Nio.options()
opt.MaskedArrayMode = "MaskedIfFillAttAndValue"
self.f = Nio.open_file(filename, options=opt)
def open_new_file(self, file_name, info=None,
var_name='X',
long_name=None,
units_name='None',
dtype='float64',
### dtype='float64'
time_units='minutes',
comment='',
shape=(1,1,1),
res=(1.,1.,1.),
MAKE_RTI=True, MAKE_BOV=False):
#--------------------------------------------------
# Try to import the Nio module from PyNIO package
#--------------------------------------------------
Nio = self.import_nio ()
if not Nio:
return False
#----------------------------
# Does file already exist ?
#----------------------------
file_name = file_utils.check_overwrite( file_name )
self.file_name = file_name
#---------------------------------------
# Check and store the grid information
#---------------------------------------
self.format = 'nccs'
self.file_name = file_name
self.time_index = 0
self.var_name = var_name
self.shape = shape
self.res = res
if (long_name is None):
long_name = var_name
self.long_name = long_name
self.units_name = units_name
self.dtype = dtype
#-----------------------------------
# Get Nio type code for this dtype
#------------------------------------
nio_type_map = self.get_nio_type_map()
nio_type_code = nio_type_map[ dtype.lower() ]
self.nio_type_code = nio_type_code
#-------------------------------------
# Open a new netCDF file for writing
#-------------------------------------
# Sample output from time.asctime():
# "Thu Oct 8 17:10:18 2009"
#-------------------------------------
opt = Nio.options()
opt.PreFill = False # (for efficiency)
opt.HeaderReserveSpace = 4000 # (4000 bytes, for efficiency)
history = "Created using PyNIO " + Nio.__version__ + " on "
history = history + time.asctime() + ". "
history = history + comment
# print 'MADE IT PAST history BLOCK'
try:
nccs_unit = Nio.open_file (file_name, mode="w",
options=opt, history=history)
OK = True
except:
OK = False
return OK
#----------------------------------------------
# Create grid dimensions nx and ny, plus time
#----------------------------------------------
# Without using "int()" here, we get this:
# TypeError: size must be None or integer
#----------------------------------------------
nccs_unit.create_dimension("nz", self.shape[0])
nccs_unit.create_dimension("ny", self.shape[1])
nccs_unit.create_dimension("nx", self.shape[2])
nccs_unit.create_dimension("time", None) # (unlimited dimension)
# print 'MADE IT PAST create_dimension CALLS.'
#-------------------------
# Create a time variable
#------------------------------------------
#('d' = float64; must match in add_cube()
#------------------------------------------
tvar = nccs_unit.create_variable ('time', 'd', ("time",))
nccs_unit.variables['time'].units = time_units
#--------------------------------
# Create a variable in the file
#----------------------------------
# Returns "var" as a PyNIO object
#----------------------------------
var = nccs_unit.create_variable (var_name, nio_type_code,
("time", "nz", "ny", "nx"))
#----------------------------------
# Specify a "nodata" fill value ?
#----------------------------------
var._FillValue = -9999.0 ## Does this jive with Prefill above ??
#------------------------------------
# Create attributes of the variable
#------------------------------------
nccs_unit.variables[var_name].long_name = long_name
nccs_unit.variables[var_name].units = units_name
nccs_unit.variables[var_name].dz = self.res[0]
nccs_unit.variables[var_name].dy = self.res[1]
nccs_unit.variables[var_name].dx = self.res[2]
nccs_unit.variables[var_name].y_south_edge = 0.
nccs_unit.variables[var_name].y_north_edge = self.res[1]*self.shape[1]
nccs_unit.variables[var_name].x_west_edge = 0.
nccs_unit.variables[var_name].x_east_edge = self.res[2]*self.shape[2]
nccs_unit.variables[var_name].z_bottom_edge = 0.
nccs_unit.variables[var_name].z_top_edge = self.res[0]*self.shape[0]
self.nccs_unit = nccs_unit
return OK
def setUp(self):
# print 'Creating temporary file'
do_setup(filename)
opt = Nio.options()
opt.MaskedArrayMode = "MaskedIfFillAtt"
self.f = Nio.open_file(filename, options=opt)
def main(argv):
# Get command line stuff and store in a dictionary
s = 'tag= compset= esize= tslice= res= sumfile= indir= sumfiledir= mach= verbose jsonfile= mpi_enable maxnorm gmonly popens cumul regx= startMon= endMon= fIndex='
optkeys = s.split()
try:
opts, args = getopt.getopt(argv, "h", optkeys)
except getopt.GetoptError:
pyEnsLib.EnsSum_usage()
sys.exit(2)
# Put command line options in a dictionary - also set defaults
opts_dict = {}
# Defaults
opts_dict['tag'] = 'cesm2_0_beta08'
opts_dict['compset'] = 'F2000'
opts_dict['mach'] = 'cheyenne'
opts_dict['esize'] = 350
opts_dict['tslice'] = 1
opts_dict['res'] = 'f19_f19'
opts_dict['sumfile'] = 'ens.summary.nc'
opts_dict['indir'] = './'
opts_dict['sumfiledir'] = './'
opts_dict['jsonfile'] = 'exclude_empty.json'
opts_dict['verbose'] = False
opts_dict['mpi_enable'] = False
opts_dict['maxnorm'] = False
opts_dict['gmonly'] = True
opts_dict['popens'] = False
opts_dict['cumul'] = False
opts_dict['regx'] = 'test'
opts_dict['startMon'] = 1
opts_dict['endMon'] = 1
opts_dict['fIndex'] = 151
# This creates the dictionary of input arguments
opts_dict = pyEnsLib.getopt_parseconfig(opts, optkeys, 'ES', opts_dict)
verbose = opts_dict['verbose']
st = opts_dict['esize']
esize = int(st)
if not (opts_dict['tag'] and opts_dict['compset'] and opts_dict['mach']
or opts_dict['res']):
print 'Please specify --tag, --compset, --mach and --res options'
sys.exit()
# Now find file names in indir
input_dir = opts_dict['indir']
# The var list that will be excluded
ex_varlist = []
inc_varlist = []
# Create a mpi simplecomm object
if opts_dict['mpi_enable']:
me = simplecomm.create_comm()
else:
me = simplecomm.create_comm(not opts_dict['mpi_enable'])
if me.get_rank() == 0:
print 'Running pyEnsSum!'
if me.get_rank() == 0 and (verbose == True):
print opts_dict
print 'Ensemble size for summary = ', esize
exclude = False
if me.get_rank() == 0:
if opts_dict['jsonfile']:
inc_varlist = []
# Read in the excluded or included var list
ex_varlist, exclude = pyEnsLib.read_jsonlist(
opts_dict['jsonfile'], 'ES')
if exclude == False:
inc_varlist = ex_varlist
ex_varlist = []
# Read in the included var list
#inc_varlist=pyEnsLib.read_jsonlist(opts_dict['jsonfile'],'ES')
# Broadcast the excluded var list to each processor
#if opts_dict['mpi_enable']:
# ex_varlist=me.partition(ex_varlist,func=Duplicate(),involved=True)
# Broadcast the excluded var list to each processor
if opts_dict['mpi_enable']:
exclude = me.partition(exclude, func=Duplicate(), involved=True)
if exclude:
ex_varlist = me.partition(ex_varlist,
func=Duplicate(),
involved=True)
else:
inc_varlist = me.partition(inc_varlist,
func=Duplicate(),
involved=True)
in_files = []
if (os.path.exists(input_dir)):
# Get the list of files
in_files_temp = os.listdir(input_dir)
in_files = sorted(in_files_temp)
# Make sure we have enough
num_files = len(in_files)
if me.get_rank() == 0 and (verbose == True):
print 'Number of files in input directory = ', num_files
if (num_files < esize):
if me.get_rank() == 0 and (verbose == True):
print 'Number of files in input directory (',num_files,\
') is less than specified ensemble size of ', esize
sys.exit(2)
if (num_files > esize):
if me.get_rank() == 0 and (verbose == True):
print 'NOTE: Number of files in ', input_dir, \
'is greater than specified ensemble size of ', esize ,\
'\nwill just use the first ', esize, 'files'
else:
if me.get_rank() == 0:
print 'Input directory: ', input_dir, ' not found'
sys.exit(2)
if opts_dict['cumul']:
if opts_dict['regx']:
in_files_list = get_cumul_filelist(opts_dict, opts_dict['indir'],
opts_dict['regx'])
in_files = me.partition(in_files_list,
func=EqualLength(),
involved=True)
if me.get_rank() == 0 and (verbose == True):
print 'in_files=', in_files
# Open the files in the input directory
o_files = []
if me.get_rank() == 0 and opts_dict['verbose']:
print 'Input files are: '
print "\n".join(in_files)
#for i in in_files:
# print "in_files =",i
for onefile in in_files[0:esize]:
if (os.path.isfile(input_dir + '/' + onefile)):
o_files.append(Nio.open_file(input_dir + '/' + onefile, "r"))
else:
if me.get_rank() == 0:
print "COULD NOT LOCATE FILE " + input_dir + onefile + "! EXITING...."
sys.exit()
# Store dimensions of the input fields
if me.get_rank() == 0 and (verbose == True):
print "Getting spatial dimensions"
nlev = -1
nilev = -1
ncol = -1
nlat = -1
nlon = -1
lonkey = ''
latkey = ''
# Look at first file and get dims
input_dims = o_files[0].dimensions
ndims = len(input_dims)
for key in input_dims:
if key == "lev":
nlev = input_dims["lev"]
elif key == "ilev":
nilev = input_dims["ilev"]
elif key == "ncol":
ncol = input_dims["ncol"]
elif (key == "nlon") or (key == "lon"):
nlon = input_dims[key]
lonkey = key
elif (key == "nlat") or (key == "lat"):
nlat = input_dims[key]
latkey = key
if (nlev == -1):
if me.get_rank() == 0:
print "COULD NOT LOCATE valid dimension lev => EXITING...."
sys.exit()
if ((ncol == -1) and ((nlat == -1) or (nlon == -1))):
if me.get_rank() == 0:
print "Need either lat/lon or ncol => EXITING...."
sys.exit()
# Check if this is SE or FV data
if (ncol != -1):
is_SE = True
else:
is_SE = False
# Make sure all files have the same dimensions
if me.get_rank() == 0 and (verbose == True):
print "Checking dimensions across files...."
print 'lev = ', nlev
if (is_SE == True):
print 'ncol = ', ncol
else:
print 'nlat = ', nlat
print 'nlon = ', nlon
for count, this_file in enumerate(o_files):
input_dims = this_file.dimensions
if (is_SE == True):
if (nlev != int(input_dims["lev"])
or (ncol != int(input_dims["ncol"]))):
if me.get_rank() == 0:
print "Dimension mismatch between ", in_files[
0], 'and', in_files[0], '!!!'
sys.exit()
else:
if ( nlev != int(input_dims["lev"]) or ( nlat != int(input_dims[latkey]))\
or ( nlon != int(input_dims[lonkey]))):
if me.get_rank() == 0:
print "Dimension mismatch between ", in_files[
0], 'and', in_files[0], '!!!'
sys.exit()
# Get 2d vars, 3d vars and all vars (For now include all variables)
vars_dict_all = o_files[0].variables
# Remove the excluded variables (specified in json file) from variable dictionary
#print len(vars_dict_all)
if exclude:
vars_dict = vars_dict_all
for i in ex_varlist:
if i in vars_dict:
del vars_dict[i]
#Given an included var list, remove all float var that are not on the list
else:
vars_dict = vars_dict_all.copy()
for k, v in vars_dict_all.iteritems():
if (k not in inc_varlist) and (vars_dict_all[k].typecode() == 'f'):
#print vars_dict_all[k].typecode()
#print k
del vars_dict[k]
num_vars = len(vars_dict)
#print num_vars
#if me.get_rank() == 0:
# for k,v in vars_dict.iteritems():
# print 'vars_dict',k,vars_dict[k].typecode()
str_size = 0
d2_var_names = []
d3_var_names = []
num_2d = 0
num_3d = 0
# Which are 2d, which are 3d and max str_size
for k, v in vars_dict.iteritems():
var = k
vd = v.dimensions # all the variable's dimensions (names)
vr = v.rank # num dimension
vs = v.shape # dim values
is_2d = False
is_3d = False
if (is_SE == True): # (time, lev, ncol) or (time, ncol)
if ((vr == 2) and (vs[1] == ncol)):
is_2d = True
num_2d += 1
elif ((vr == 3) and (vs[2] == ncol and vs[1] == nlev)):
is_3d = True
num_3d += 1
else: # (time, lev, nlon, nlon) or (time, nlat, nlon)
if ((vr == 3) and (vs[1] == nlat and vs[2] == nlon)):
is_2d = True
num_2d += 1
elif ((vr == 4) and (vs[2] == nlat and vs[3] == nlon and
(vs[1] == nlev or vs[1] == nilev))):
is_3d = True
num_3d += 1
if (is_3d == True):
str_size = max(str_size, len(k))
d3_var_names.append(k)
elif (is_2d == True):
str_size = max(str_size, len(k))
d2_var_names.append(k)
#else:
# print 'var=',k
if me.get_rank() == 0 and (verbose == True):
print 'Number of variables found: ', num_3d + num_2d
print '3D variables: ' + str(num_3d) + ', 2D variables: ' + str(num_2d)
# Now sort these and combine (this sorts caps first, then lower case -
# which is what we want)
d2_var_names.sort()
d3_var_names.sort()
if esize < num_2d + num_3d:
if me.get_rank() == 0:
print "************************************************************************************************************************************"
print " Error: the total number of 3D and 2D variables " + str(
num_2d + num_3d
) + " is larger than the number of ensemble files " + str(esize)
print " Cannot generate ensemble summary file, please remove more variables from your included variable list,"
print " or add more varaibles in your excluded variable list!!!"
print "************************************************************************************************************************************"
sys.exit()
# All vars is 3d vars first (sorted), the 2d vars
all_var_names = list(d3_var_names)
all_var_names += d2_var_names
n_all_var_names = len(all_var_names)
#if me.get_rank() == 0 and (verbose == True):
# print 'num vars = ', n_all_var_names, '(3d = ', num_3d, ' and 2d = ', num_2d, ")"
# Create new summary ensemble file
this_sumfile = opts_dict["sumfile"]
if me.get_rank() == 0 and (verbose == True):
print "Creating ", this_sumfile, " ..."
if (me.get_rank() == 0 | opts_dict["popens"]):
if os.path.exists(this_sumfile):
os.unlink(this_sumfile)
opt = Nio.options()
opt.PreFill = False
opt.Format = 'NetCDF4Classic'
nc_sumfile = Nio.open_file(this_sumfile, 'w', options=opt)
# Set dimensions
if me.get_rank() == 0 and (verbose == True):
print "Setting dimensions ....."
if (is_SE == True):
nc_sumfile.create_dimension('ncol', ncol)
else:
nc_sumfile.create_dimension('nlat', nlat)
nc_sumfile.create_dimension('nlon', nlon)
nc_sumfile.create_dimension('nlev', nlev)
nc_sumfile.create_dimension('ens_size', esize)
nc_sumfile.create_dimension('nvars', num_3d + num_2d)
nc_sumfile.create_dimension('nvars3d', num_3d)
nc_sumfile.create_dimension('nvars2d', num_2d)
nc_sumfile.create_dimension('str_size', str_size)
# Set global attributes
now = time.strftime("%c")
if me.get_rank() == 0 and (verbose == True):
print "Setting global attributes ....."
setattr(nc_sumfile, 'creation_date', now)
setattr(nc_sumfile, 'title', 'CAM verification ensemble summary file')
setattr(nc_sumfile, 'tag', opts_dict["tag"])
setattr(nc_sumfile, 'compset', opts_dict["compset"])
setattr(nc_sumfile, 'resolution', opts_dict["res"])
setattr(nc_sumfile, 'machine', opts_dict["mach"])
# Create variables
if me.get_rank() == 0 and (verbose == True):
print "Creating variables ....."
v_lev = nc_sumfile.create_variable("lev", 'f', ('nlev', ))
v_vars = nc_sumfile.create_variable("vars", 'S1',
('nvars', 'str_size'))
v_var3d = nc_sumfile.create_variable("var3d", 'S1',
('nvars3d', 'str_size'))
v_var2d = nc_sumfile.create_variable("var2d", 'S1',
('nvars2d', 'str_size'))
if not opts_dict['gmonly']:
if (is_SE == True):
v_ens_avg3d = nc_sumfile.create_variable(
"ens_avg3d", 'f', ('nvars3d', 'nlev', 'ncol'))
v_ens_stddev3d = nc_sumfile.create_variable(
"ens_stddev3d", 'f', ('nvars3d', 'nlev', 'ncol'))
v_ens_avg2d = nc_sumfile.create_variable(
"ens_avg2d", 'f', ('nvars2d', 'ncol'))
v_ens_stddev2d = nc_sumfile.create_variable(
"ens_stddev2d", 'f', ('nvars2d', 'ncol'))
else:
v_ens_avg3d = nc_sumfile.create_variable(
"ens_avg3d", 'f', ('nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_stddev3d = nc_sumfile.create_variable(
"ens_stddev3d", 'f', ('nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_avg2d = nc_sumfile.create_variable(
"ens_avg2d", 'f', ('nvars2d', 'nlat', 'nlon'))
v_ens_stddev2d = nc_sumfile.create_variable(
"ens_stddev2d", 'f', ('nvars2d', 'nlat', 'nlon'))
v_RMSZ = nc_sumfile.create_variable("RMSZ", 'f',
('nvars', 'ens_size'))
v_gm = nc_sumfile.create_variable("global_mean", 'f',
('nvars', 'ens_size'))
v_standardized_gm = nc_sumfile.create_variable("standardized_gm", 'f',
('nvars', 'ens_size'))
v_loadings_gm = nc_sumfile.create_variable('loadings_gm', 'f',
('nvars', 'nvars'))
v_mu_gm = nc_sumfile.create_variable('mu_gm', 'f', ('nvars', ))
v_sigma_gm = nc_sumfile.create_variable('sigma_gm', 'f', ('nvars', ))
v_sigma_scores_gm = nc_sumfile.create_variable('sigma_scores_gm', 'f',
('nvars', ))
# Assign vars, var3d and var2d
if me.get_rank() == 0 and (verbose == True):
print "Assigning vars, var3d, and var2d ....."
eq_all_var_names = []
eq_d3_var_names = []
eq_d2_var_names = []
l_eq = len(all_var_names)
for i in range(l_eq):
tt = list(all_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ') * (str_size - l_tt)
tt.extend(extra)
eq_all_var_names.append(tt)
l_eq = len(d3_var_names)
for i in range(l_eq):
tt = list(d3_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ') * (str_size - l_tt)
tt.extend(extra)
eq_d3_var_names.append(tt)
l_eq = len(d2_var_names)
for i in range(l_eq):
tt = list(d2_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ') * (str_size - l_tt)
tt.extend(extra)
eq_d2_var_names.append(tt)
v_vars[:] = eq_all_var_names[:]
v_var3d[:] = eq_d3_var_names[:]
v_var2d[:] = eq_d2_var_names[:]
# Time-invarient metadata
if me.get_rank() == 0 and (verbose == True):
print "Assigning time invariant metadata ....."
lev_data = vars_dict["lev"]
v_lev = lev_data
# Form ensembles, each missing one member; compute RMSZs and global means
#for each variable, we also do max norm also (currently done in pyStats)
tslice = opts_dict['tslice']
if not opts_dict['cumul']:
# Partition the var list
var3_list_loc = me.partition(d3_var_names,
func=EqualStride(),
involved=True)
var2_list_loc = me.partition(d2_var_names,
func=EqualStride(),
involved=True)
else:
var3_list_loc = d3_var_names
var2_list_loc = d2_var_names
# Calculate global means #
if me.get_rank() == 0 and (verbose == True):
print "Calculating global means ....."
if not opts_dict['cumul']:
gm3d, gm2d, var_list = pyEnsLib.generate_global_mean_for_summary(
o_files, var3_list_loc, var2_list_loc, is_SE, False, opts_dict)
if me.get_rank() == 0 and (verbose == True):
print "Finish calculating global means ....."
# Calculate RMSZ scores
if (not opts_dict['gmonly']) | (opts_dict['cumul']):
if me.get_rank() == 0 and (verbose == True):
print "Calculating RMSZ scores ....."
zscore3d, zscore2d, ens_avg3d, ens_stddev3d, ens_avg2d, ens_stddev2d, temp1, temp2 = pyEnsLib.calc_rmsz(
o_files, var3_list_loc, var2_list_loc, is_SE, opts_dict)
# Calculate max norm ensemble
if opts_dict['maxnorm']:
if me.get_rank() == 0 and (verbose == True):
print "Calculating max norm of ensembles ....."
pyEnsLib.calculate_maxnormens(opts_dict, var3_list_loc)
pyEnsLib.calculate_maxnormens(opts_dict, var2_list_loc)
if opts_dict['mpi_enable'] & (not opts_dict['popens']):
if not opts_dict['cumul']:
# Gather the 3d variable results from all processors to the master processor
slice_index = get_stride_list(len(d3_var_names), me)
# Gather global means 3d results
gm3d = gather_npArray(gm3d, me, slice_index,
(len(d3_var_names), len(o_files)))
if not opts_dict['gmonly']:
# Gather zscore3d results
zscore3d = gather_npArray(zscore3d, me, slice_index,
(len(d3_var_names), len(o_files)))
# Gather ens_avg3d and ens_stddev3d results
shape_tuple3d = get_shape(ens_avg3d.shape, len(d3_var_names),
me.get_rank())
ens_avg3d = gather_npArray(ens_avg3d, me, slice_index,
shape_tuple3d)
ens_stddev3d = gather_npArray(ens_stddev3d, me, slice_index,
shape_tuple3d)
# Gather 2d variable results from all processors to the master processor
slice_index = get_stride_list(len(d2_var_names), me)
# Gather global means 2d results
gm2d = gather_npArray(gm2d, me, slice_index,
(len(d2_var_names), len(o_files)))
var_list = gather_list(var_list, me)
if not opts_dict['gmonly']:
# Gather zscore2d results
zscore2d = gather_npArray(zscore2d, me, slice_index,
(len(d2_var_names), len(o_files)))
# Gather ens_avg3d and ens_stddev2d results
shape_tuple2d = get_shape(ens_avg2d.shape, len(d2_var_names),
me.get_rank())
ens_avg2d = gather_npArray(ens_avg2d, me, slice_index,
shape_tuple2d)
ens_stddev2d = gather_npArray(ens_stddev2d, me, slice_index,
shape_tuple2d)
else:
gmall = np.concatenate((temp1, temp2), axis=0)
gmall = pyEnsLib.gather_npArray_pop(
gmall, me,
(me.get_size(), len(d3_var_names) + len(d2_var_names)))
# Assign to file:
if me.get_rank() == 0 | opts_dict['popens']:
if not opts_dict['cumul']:
gmall = np.concatenate((gm3d, gm2d), axis=0)
if not opts_dict['gmonly']:
Zscoreall = np.concatenate((zscore3d, zscore2d), axis=0)
v_RMSZ[:, :] = Zscoreall[:, :]
if not opts_dict['gmonly']:
if (is_SE == True):
v_ens_avg3d[:, :, :] = ens_avg3d[:, :, :]
v_ens_stddev3d[:, :, :] = ens_stddev3d[:, :, :]
v_ens_avg2d[:, :] = ens_avg2d[:, :]
v_ens_stddev2d[:, :] = ens_stddev2d[:, :]
else:
v_ens_avg3d[:, :, :, :] = ens_avg3d[:, :, :, :]
v_ens_stddev3d[:, :, :, :] = ens_stddev3d[:, :, :, :]
v_ens_avg2d[:, :, :] = ens_avg2d[:, :, :]
v_ens_stddev2d[:, :, :] = ens_stddev2d[:, :, :]
else:
gmall_temp = np.transpose(gmall[:, :])
gmall = gmall_temp
mu_gm, sigma_gm, standardized_global_mean, loadings_gm, scores_gm = pyEnsLib.pre_PCA(
gmall, all_var_names, var_list, me)
v_gm[:, :] = gmall[:, :]
v_standardized_gm[:, :] = standardized_global_mean[:, :]
v_mu_gm[:] = mu_gm[:]
v_sigma_gm[:] = sigma_gm[:].astype(np.float32)
v_loadings_gm[:, :] = loadings_gm[:, :]
v_sigma_scores_gm[:] = scores_gm[:]
if me.get_rank() == 0:
print "All Done"
def main(argv):
print 'Running pyEnsSumPop!'
# Get command line stuff and store in a dictionary
s = 'nyear= nmonth= npert= tag= res= mach= compset= sumfile= indir= tslice= verbose jsonfile= mpi_enable zscoreonly nrand= rand seq= jsondir='
optkeys = s.split()
try:
opts, args = getopt.getopt(argv, "h", optkeys)
except getopt.GetoptError:
pyEnsLib.EnsSumPop_usage()
sys.exit(2)
# Put command line options in a dictionary - also set defaults
opts_dict={}
# Defaults
opts_dict['tag'] = 'cesm1_2_0'
opts_dict['compset'] = 'FC5'
opts_dict['mach'] = 'yellowstone'
opts_dict['tslice'] = 0
opts_dict['nyear'] = 3
opts_dict['nmonth'] = 12
opts_dict['npert'] = 40
opts_dict['nbin'] = 40
opts_dict['minrange'] = 0.0
opts_dict['maxrange'] = 4.0
opts_dict['res'] = 'ne30_ne30'
opts_dict['sumfile'] = 'ens.pop.summary.nc'
opts_dict['indir'] = './'
opts_dict['jsonfile'] = ''
opts_dict['verbose'] = True
opts_dict['mpi_enable'] = False
opts_dict['zscoreonly'] = False
opts_dict['popens'] = True
opts_dict['nrand'] = 40
opts_dict['rand'] = False
opts_dict['seq'] = 0
opts_dict['jsondir'] = '/glade/scratch/haiyingx/'
# This creates the dictionary of input arguments
print "before parseconfig"
opts_dict = pyEnsLib.getopt_parseconfig(opts,optkeys,'ESP',opts_dict)
verbose = opts_dict['verbose']
nbin = opts_dict['nbin']
if verbose:
print opts_dict
# Now find file names in indir
input_dir = opts_dict['indir']
# Create a mpi simplecomm object
if opts_dict['mpi_enable']:
me=simplecomm.create_comm()
else:
me=simplecomm.create_comm(not opts_dict['mpi_enable'])
if opts_dict['jsonfile']:
# Read in the included var list
Var2d,Var3d=pyEnsLib.read_jsonlist(opts_dict['jsonfile'],'ESP')
str_size=0
for str in Var3d:
if str_size < len(str):
str_size=len(str)
for str in Var2d:
if str_size < len(str):
str_size=len(str)
in_files=[]
if(os.path.exists(input_dir)):
# Pick up the 'nrand' random number of input files to generate summary files
if opts_dict['rand']:
in_files=pyEnsLib.Random_pickup_pop(input_dir,opts_dict,opts_dict['nrand'])
else:
# Get the list of files
in_files_temp = os.listdir(input_dir)
in_files=sorted(in_files_temp)
# Make sure we have enough
num_files = len(in_files)
else:
print 'Input directory: ',input_dir,' not found'
sys.exit(2)
# Create a mpi simplecomm object
if opts_dict['mpi_enable']:
me=simplecomm.create_comm()
else:
me=simplecomm.create_comm(not opts_dict['mpi_enable'])
#Partition the input file list
in_file_list=me.partition(in_files,func=EqualStride(),involved=True)
# Open the files in the input directory
o_files=[]
for onefile in in_file_list:
if (os.path.isfile(input_dir+'/' + onefile)):
o_files.append(Nio.open_file(input_dir+'/' + onefile,"r"))
else:
print "COULD NOT LOCATE FILE "+ input_dir + onefile + "! EXITING...."
sys.exit()
print in_file_list
# Store dimensions of the input fields
if (verbose == True):
print "Getting spatial dimensions"
nlev = -1
nlat = -1
nlon = -1
# Look at first file and get dims
input_dims = o_files[0].dimensions
ndims = len(input_dims)
# Make sure all files have the same dimensions
for key in input_dims:
if key == "z_t":
nlev = input_dims["z_t"]
elif key == "nlon":
nlon = input_dims["nlon"]
elif key == "nlat":
nlat = input_dims["nlat"]
for count, this_file in enumerate(o_files):
input_dims = this_file.dimensions
if ( nlev != int(input_dims["z_t"]) or ( nlat != int(input_dims["nlat"]))\
or ( nlon != int(input_dims["nlon"]))):
print "Dimension mismatch between ", in_file_list[0], 'and', in_file_list[count], '!!!'
sys.exit()
# Create new summary ensemble file
this_sumfile = opts_dict["sumfile"]
if verbose:
print "Creating ", this_sumfile, " ..."
if (me.get_rank() == 0 ):
if os.path.exists(this_sumfile):
os.unlink(this_sumfile)
opt =Nio.options()
opt.PreFill = False
opt.Format = 'NetCDF4Classic'
nc_sumfile = Nio.open_file(this_sumfile, 'w', options=opt)
# Set dimensions
if (verbose == True):
print "Setting dimensions ....."
nc_sumfile.create_dimension('nlat', nlat)
nc_sumfile.create_dimension('nlon', nlon)
nc_sumfile.create_dimension('nlev', nlev)
nc_sumfile.create_dimension('time',None)
nc_sumfile.create_dimension('ens_size', opts_dict['npert'])
nc_sumfile.create_dimension('nbin', opts_dict['nbin'])
nc_sumfile.create_dimension('nvars', len(Var3d) + len(Var2d))
nc_sumfile.create_dimension('nvars3d', len(Var3d))
nc_sumfile.create_dimension('nvars2d', len(Var2d))
nc_sumfile.create_dimension('str_size', str_size)
# Set global attributes
now = time.strftime("%c")
if (verbose == True):
print "Setting global attributes ....."
setattr(nc_sumfile, 'creation_date',now)
setattr(nc_sumfile, 'title', 'POP verification ensemble summary file')
setattr(nc_sumfile, 'tag', opts_dict["tag"])
setattr(nc_sumfile, 'compset', opts_dict["compset"])
setattr(nc_sumfile, 'resolution', opts_dict["res"])
setattr(nc_sumfile, 'machine', opts_dict["mach"])
# Create variables
if (verbose == True):
print "Creating variables ....."
v_lev = nc_sumfile.create_variable("lev", 'f', ('nlev',))
v_vars = nc_sumfile.create_variable("vars", 'S1', ('nvars', 'str_size'))
v_var3d = nc_sumfile.create_variable("var3d", 'S1', ('nvars3d', 'str_size'))
v_var2d = nc_sumfile.create_variable("var2d", 'S1', ('nvars2d', 'str_size'))
v_time = nc_sumfile.create_variable("time",'d',('time',))
v_ens_avg3d = nc_sumfile.create_variable("ens_avg3d", 'f', ('time','nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_stddev3d = nc_sumfile.create_variable("ens_stddev3d", 'f', ('time','nvars3d', 'nlev', 'nlat', 'nlon'))
v_ens_avg2d = nc_sumfile.create_variable("ens_avg2d", 'f', ('time','nvars2d', 'nlat', 'nlon'))
v_ens_stddev2d = nc_sumfile.create_variable("ens_stddev2d", 'f', ('time','nvars2d', 'nlat', 'nlon'))
v_RMSZ = nc_sumfile.create_variable("RMSZ", 'f', ('time','nvars', 'ens_size','nbin'))
if not opts_dict['zscoreonly']:
v_gm = nc_sumfile.create_variable("global_mean", 'f', ('time','nvars', 'ens_size'))
# Assign vars, var3d and var2d
if (verbose == True):
print "Assigning vars, var3d, and var2d ....."
eq_all_var_names =[]
eq_d3_var_names = []
eq_d2_var_names = []
all_var_names = list(Var3d)
all_var_names += Var2d
l_eq = len(all_var_names)
for i in range(l_eq):
tt = list(all_var_names[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ')*(str_size - l_tt)
tt.extend(extra)
eq_all_var_names.append(tt)
l_eq = len(Var3d)
for i in range(l_eq):
tt = list(Var3d[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ')*(str_size - l_tt)
tt.extend(extra)
eq_d3_var_names.append(tt)
l_eq = len(Var2d)
for i in range(l_eq):
tt = list(Var2d[i])
l_tt = len(tt)
if (l_tt < str_size):
extra = list(' ')*(str_size - l_tt)
tt.extend(extra)
eq_d2_var_names.append(tt)
v_vars[:] = eq_all_var_names[:]
v_var3d[:] = eq_d3_var_names[:]
v_var2d[:] = eq_d2_var_names[:]
# Time-invarient metadata
if (verbose == True):
print "Assigning time invariant metadata ....."
vars_dict = o_files[0].variables
lev_data = vars_dict["z_t"]
v_lev = lev_data
# Time-varient metadata
if verbose:
print "Assigning time variant metadata ....."
vars_dict = o_files[0].variables
time_value = vars_dict['time']
time_array = np.array([time_value])
time_array = pyEnsLib.gather_npArray_pop(time_array,me,(me.get_size(),))
if me.get_rank() == 0:
v_time[:]=time_array[:]
# Calculate global mean, average, standard deviation
if verbose:
print "Calculating global means ....."
is_SE = False
tslice=0
if not opts_dict['zscoreonly']:
gm3d,gm2d = pyEnsLib.generate_global_mean_for_summary(o_files,Var3d,Var2d, is_SE,False,opts_dict)
if verbose:
print "Finish calculating global means ....."
# Calculate RMSZ scores
if (verbose == True):
print "Calculating RMSZ scores ....."
zscore3d,zscore2d,ens_avg3d,ens_stddev3d,ens_avg2d,ens_stddev2d,temp1,temp2=pyEnsLib.calc_rmsz(o_files,Var3d,Var2d,is_SE,opts_dict)
# Collect from all processors
if opts_dict['mpi_enable'] :
# Gather the 3d variable results from all processors to the master processor
# Gather global means 3d results
if not opts_dict['zscoreonly']:
gmall=np.concatenate((gm3d,gm2d),axis=0)
#print "before gather, gmall.shape=",gmall.shape
gmall=pyEnsLib.gather_npArray_pop(gmall,me,(me.get_size(),len(Var3d)+len(Var2d),len(o_files)))
zmall=np.concatenate((zscore3d,zscore2d),axis=0)
zmall=pyEnsLib.gather_npArray_pop(zmall,me,(me.get_size(),len(Var3d)+len(Var2d),len(o_files),nbin))
#print 'zmall=',zmall
#print "after gather, gmall.shape=",gmall.shape
ens_avg3d=pyEnsLib.gather_npArray_pop(ens_avg3d,me,(me.get_size(),len(Var3d),nlev,(nlat),nlon))
ens_avg2d=pyEnsLib.gather_npArray_pop(ens_avg2d,me,(me.get_size(),len(Var2d),(nlat),nlon))
ens_stddev3d=pyEnsLib.gather_npArray_pop(ens_stddev3d,me,(me.get_size(),len(Var3d),nlev,(nlat),nlon))
ens_stddev2d=pyEnsLib.gather_npArray_pop(ens_stddev2d,me,(me.get_size(),len(Var2d),(nlat),nlon))
# Assign to file:
if me.get_rank() == 0 :
#Zscoreall=np.concatenate((zscore3d,zscore2d),axis=0)
v_RMSZ[:,:,:,:]=zmall[:,:,:,:]
v_ens_avg3d[:,:,:,:,:]=ens_avg3d[:,:,:,:,:]
v_ens_stddev3d[:,:,:,:,:]=ens_stddev3d[:,:,:,:,:]
v_ens_avg2d[:,:,:,:]=ens_avg2d[:,:,:,:]
v_ens_stddev2d[:,:,:,:]=ens_stddev2d[:,:,:,:]
if not opts_dict['zscoreonly']:
v_gm[:,:,:]=gmall[:,:,:]
print "All done"
def __init__(self, spec, serial=False, verbosity=1, once=False):
'''
Constructor
@param spec An instance of the Specifier class, defining the
input specification for this reshaper operation.
@param serial True or False, indicating whether the operation
should be performed in serial (True) or parallel
(False). The default is to assume parallel operation
(but serial will be chosen if the mpi4py cannot be
found when trying to initialize decomposition.
@param verbosity Level of printed output (stdout). A value of 0 means
no output, and a higher value means more output. The
default value is 1.
@param once True or False, indicating whether the Reshaper should
write all metadata to a 'once' file (separately).
'''
# Type checking (or double-checking)
if (not isinstance(spec, Slice2SeriesSpecifier)):
err_msg = "Slice2SeriesReshaper requires a Slice2SeriesSpecifier" \
+ " as input."
raise TypeError(err_msg)
# Call the base-class constructor
super(Slice2SeriesReshaper, self).__init__(spec,
serial=serial,
verbosity=verbosity,
once=once)
# Setup PyNIO options (including disabling the default PreFill option)
opt = Nio.options()
opt.PreFill = False
# Determine the Format and CompressionLevel options
# from the NetCDF format string in the Specifier
if (self._specifier.netcdf_format == 'netcdf'):
opt.Format = 'Classic'
elif (self._specifier.netcdf_format == 'netcdf4'):
opt.Format = 'NetCDF4Classic'
opt.CompressionLevel = 0
elif (self._specifier.netcdf_format == 'netcdf4c'):
opt.Format = 'NetCDF4Classic'
opt.CompressionLevel = 1
self._nio_options = opt
self._messenger.print_once('PyNIO options set', vlevel=2)
# Open all of the input files
self._timer.start('Open Input Files')
self._input_files = []
for filename in self._specifier.input_file_list:
self._input_files.append(Nio.open_file(filename, "r"))
self._timer.stop('Open Input Files')
self._messenger.print_once('Input files opened', vlevel=2)
# Validate the input files themselves
self._timer.start('Input File Validation')
self._validate_input_files()
self._timer.stop('Input File Validation')
self._messenger.print_once('Input files validated', vlevel=2)
# Sort the input files by time
self._timer.start('Sort Input Files')
self._sort_input_files_by_time()
self._timer.stop('Sort Input Files')
self._messenger.print_once('Input files sorted', vlevel=2)
# Retrieve and sort the variables in each time-slice file
# (To determine if it is time-invariant metadata, time-variant
# metadata, or if it is a time-series variable)
self._timer.start('Sort Variables')
self._sort_variables()
self._timer.stop('Sort Variables')
self._messenger.print_once('Variables sorted', vlevel=2)
# Helpful debugging message
self._messenger.print_once('Reshaper initialized.', vlevel=1)
# Sync before continuing..
self._messenger.sync()
def setUp(self):
do_setup(filename)
opt = Nio.options()
opt.UseAxisAttribute = True
self.f = Nio.open_file(filename, options = opt)
def __init__(self, spec, serial=False, verbosity=1, once=False):
'''
Constructor
@param spec An instance of the Specifier class, defining the
input specification for this reshaper operation.
@param serial True or False, indicating whether the operation
should be performed in serial (True) or parallel
(False). The default is to assume parallel operation
(but serial will be chosen if the mpi4py cannot be
found when trying to initialize decomposition.
@param verbosity Level of printed output (stdout). A value of 0 means
no output, and a higher value means more output. The
default value is 1.
@param once True or False, indicating whether the Reshaper should
write all metadata to a 'once' file (separately).
'''
# Type checking (or double-checking)
if (not isinstance(spec, Slice2SeriesSpecifier)):
err_msg = "Slice2SeriesReshaper requires a Slice2SeriesSpecifier" \
+ " as input."
raise TypeError(err_msg)
# Call the base-class constructor
super(Slice2SeriesReshaper, self).__init__(spec,
serial=serial,
verbosity=verbosity,
once=once)
# Setup PyNIO options (including disabling the default PreFill option)
opt = Nio.options()
opt.PreFill = False
# Determine the Format and CompressionLevel options
# from the NetCDF format string in the Specifier
if (self._specifier.netcdf_format == 'netcdf'):
opt.Format = 'Classic'
elif (self._specifier.netcdf_format == 'netcdf4'):
opt.Format = 'NetCDF4Classic'
opt.CompressionLevel = 0
elif (self._specifier.netcdf_format == 'netcdf4c'):
opt.Format = 'NetCDF4Classic'
opt.CompressionLevel = 1
self._nio_options = opt
self._messenger.print_once('PyNIO options set', vlevel=2)
# Open all of the input files
self._timer.start('Open Input Files')
self._input_files = []
for filename in self._specifier.input_file_list:
self._input_files.append(Nio.open_file(filename, "r"))
self._timer.stop('Open Input Files')
self._messenger.print_once('Input files opened', vlevel=2)
# Validate the input files themselves
self._timer.start('Input File Validation')
self._validate_input_files()
self._timer.stop('Input File Validation')
self._messenger.print_once('Input files validated', vlevel=2)
# Sort the input files by time
self._timer.start('Sort Input Files')
self._sort_input_files_by_time()
self._timer.stop('Sort Input Files')
self._messenger.print_once('Input files sorted', vlevel=2)
# Retrieve and sort the variables in each time-slice file
# (To determine if it is time-invariant metadata, time-variant
# metadata, or if it is a time-series variable)
self._timer.start('Sort Variables')
self._sort_variables()
self._timer.stop('Sort Variables')
self._messenger.print_once('Variables sorted', vlevel=2)
# Helpful debugging message
self._messenger.print_once('Reshaper initialized.', vlevel=1)
# Sync before continuing..
self._messenger.sync()
def open_new_file(
self,
file_name,
info=None,
var_name='X',
long_name=None,
units_name='None',
dtype='float64',
### dtype='float64'
time_units='minutes',
comment='',
shape=(1, 1, 1),
res=(1., 1., 1.),
MAKE_RTI=True,
MAKE_BOV=False):
#--------------------------------------------------
# Try to import the Nio module from PyNIO package
#--------------------------------------------------
Nio = self.import_nio()
if not Nio:
return False
#----------------------------
# Does file already exist ?
#----------------------------
file_name = file_utils.check_overwrite(file_name)
self.file_name = file_name
#---------------------------------------
# Check and store the grid information
#---------------------------------------
self.format = 'nccs'
self.file_name = file_name
self.time_index = 0
self.var_name = var_name
self.shape = shape
self.res = res
if (long_name is None):
long_name = var_name
self.long_name = long_name
self.units_name = units_name
self.dtype = dtype
#-----------------------------------
# Get Nio type code for this dtype
#------------------------------------
nio_type_map = self.get_nio_type_map()
nio_type_code = nio_type_map[dtype.lower()]
self.nio_type_code = nio_type_code
#-------------------------------------
# Open a new netCDF file for writing
#-------------------------------------
# Sample output from time.asctime():
# "Thu Oct 8 17:10:18 2009"
#-------------------------------------
opt = Nio.options()
opt.PreFill = False # (for efficiency)
opt.HeaderReserveSpace = 4000 # (4000 bytes, for efficiency)
history = "Created using PyNIO " + Nio.__version__ + " on "
history = history + time.asctime() + ". "
history = history + comment
# print 'MADE IT PAST history BLOCK'
try:
nccs_unit = Nio.open_file(file_name,
mode="w",
options=opt,
history=history)
OK = True
except:
OK = False
return OK
#----------------------------------------------
# Create grid dimensions nx and ny, plus time
#----------------------------------------------
# Without using "int()" here, we get this:
# TypeError: size must be None or integer
#----------------------------------------------
nccs_unit.create_dimension("nz", self.shape[0])
nccs_unit.create_dimension("ny", self.shape[1])
nccs_unit.create_dimension("nx", self.shape[2])
nccs_unit.create_dimension("time", None) # (unlimited dimension)
# print 'MADE IT PAST create_dimension CALLS.'
#-------------------------
# Create a time variable
#------------------------------------------
#('d' = float64; must match in add_cube()
#------------------------------------------
tvar = nccs_unit.create_variable('time', 'd', ("time", ))
nccs_unit.variables['time'].units = time_units
#--------------------------------
# Create a variable in the file
#----------------------------------
# Returns "var" as a PyNIO object
#----------------------------------
var = nccs_unit.create_variable(var_name, nio_type_code,
("time", "nz", "ny", "nx"))
#----------------------------------
# Specify a "nodata" fill value ?
#----------------------------------
var._FillValue = -9999.0 ## Does this jive with Prefill above ??
#------------------------------------
# Create attributes of the variable
#------------------------------------
nccs_unit.variables[var_name].long_name = long_name
nccs_unit.variables[var_name].units = units_name
nccs_unit.variables[var_name].dz = self.res[0]
nccs_unit.variables[var_name].dy = self.res[1]
nccs_unit.variables[var_name].dx = self.res[2]
nccs_unit.variables[var_name].y_south_edge = 0.
nccs_unit.variables[
var_name].y_north_edge = self.res[1] * self.shape[1]
nccs_unit.variables[var_name].x_west_edge = 0.
nccs_unit.variables[var_name].x_east_edge = self.res[2] * self.shape[2]
nccs_unit.variables[var_name].z_bottom_edge = 0.
nccs_unit.variables[var_name].z_top_edge = self.res[0] * self.shape[0]
self.nccs_unit = nccs_unit
return OK
def open_new_file(self, file_name, info=None,
var_name='X',
long_name=None,
units_name='None',
dtype='float32',
### dtype='float64'
time_units='minutes',
comment='',
MAKE_RTI=True, MAKE_BOV=False):
#--------------------------------------------------
# Try to import the Nio module from PyNIO package
#--------------------------------------------------
Nio = self.import_nio()
if not(Nio): return False
#----------------------------
# Does file already exist ?
#----------------------------
file_name = file_utils.check_overwrite( file_name )
self.file_name = file_name
#---------------------------------------
# Check and store the grid information
#---------------------------------------
self.check_and_store_info( file_name, info, var_name,
dtype, MAKE_RTI, MAKE_BOV )
if (long_name == None): long_name = var_name
self.long_name = long_name
self.units_name = units_name
self.dtype = dtype
#-------------------------
# Save the Nio type code
#-------------------------
nio_type_map = self.get_nio_type_map()
nio_type_code = nio_type_map[ dtype.lower() ]
self.nio_type_code = nio_type_code
#-------------------------------------
# Open a new netCDF file for writing
#-------------------------------------
# Sample output from time.asctime():
# "Thu Oct 8 17:10:18 2009"
#-------------------------------------
opt = Nio.options()
opt.PreFill = False # (for efficiency)
opt.HeaderReserveSpace = 4000 # (4000 bytes, for efficiency)
history = "Created using PyNIO " + Nio.__version__ + " on "
history = history + time.asctime() + ". "
history = history + comment
# print 'MADE IT PAST history BLOCK'
try:
ncgs_unit = Nio.open_file(file_name, mode="w",
options=opt, history=history )
OK = True
except:
OK = False
return OK
## print 'nx =', self.info.ncols
## print 'ny =', self.info.nrows
## print 'dx =', self.info.xres
## print 'dy =', self.info.yres
## print ' '
#----------------------------------------------
# Create grid dimensions nx and ny, plus time
#----------------------------------------------
# Without using "int()" here, we get this:
# TypeError: size must be None or integer
#----------------------------------------------
ncgs_unit.create_dimension("nx", int(self.info.ncols))
ncgs_unit.create_dimension("ny", int(self.info.nrows))
ncgs_unit.create_dimension("time", None) # (unlimited dimension)
# print 'MADE IT PAST create_dimension CALLS.'
#-------------------------
# Create a time variable
#------------------------------------------
#('d' = float64; must match in add_grid()
#------------------------------------------
tvar = ncgs_unit.create_variable('time', 'd', ("time",))
ncgs_unit.variables['time'].units = time_units
#--------------------------------
# Create a variable in the file
#----------------------------------
# Returns "var" as a PyNIO object
#----------------------------------
var = ncgs_unit.create_variable(var_name, nio_type_code,
("time", "ny", "nx"))
## var = nc_unit.create_variable(var_name, nio_type_code,
## ("time", "nx", "ny"))
#-------------------------------------------
# Create a separate, scalar "time stamp" ?
#-------------------------------------------
# t = nc_unit.create_variable("time", nio_type_code, ("time"))
#----------------------------------
# Specify a "nodata" fill value ?
#----------------------------------
var._FillValue = -9999.0 ## Does this jive with Prefill above ??
#------------------------------------
# Create attributes of the variable
#------------------------------------
ncgs_unit.variables[var_name].long_name = long_name
ncgs_unit.variables[var_name].units = units_name
ncgs_unit.variables[var_name].dx = self.info.xres
ncgs_unit.variables[var_name].dy = self.info.yres ### (12/2/09)
## ncgs_unit.variables[var_name].dx = dx
## ncgs_unit.variables[var_name].dy = dy ### (10/15/09)
ncgs_unit.variables[var_name].y_south_edge = self.info.y_south_edge
ncgs_unit.variables[var_name].y_north_edge = self.info.y_north_edge
ncgs_unit.variables[var_name].x_west_edge = self.info.x_west_edge
ncgs_unit.variables[var_name].x_east_edge = self.info.x_east_edge
self.ncgs_unit = ncgs_unit
return OK
def setUp(self):
self.filename = tempfile.mktemp(prefix="test_", suffix=".nc")
do_setup(self.filename)
opt = Nio.options()
opt.UseAxisAttribute = True
self.f = Nio.open_file(self.filename, options=opt)
def setUp(self):
#print 'Creating temporary file'
do_setup(filename)
opt = Nio.options()
opt.MaskedArrayMode = 'MaskedIfFillAtt'
self.f = Nio.open_file(filename, options=opt)
f = Nio.open_file(dirc + fname)
#
# Print the input file contents
#
# print f
#
# If the output file already exists, remove it
#
os.system("rm -f " + fname + ".nc")
#
# Set the PreFill option to False to improve writing performance
#
opt = Nio.options()
opt.PreFill = False
#
# Options for writing NetCDF4 "classic" file.
#
# If Nio wasn't built with netcdf 4 support, you will get a
# warning here, and the code will use netcdf 3 instead.
#
opt.Format = "netcdf4classic"
opt.CompressionLevel = 5 # Can go up to 9
#
# Set the history attribute
#
hatt = "Converted from GRIB2: " + time.ctime(time.time())
def setUp(self):
#print 'Creating temporary file: ', filename
do_setup(filename)
opt = Nio.options()
opt.MaskedArrayMode = 'MaskedAlways'
self.f = Nio.open_file(filename, options=opt)
def __init__(self,
specifier,
serial=False,
verbosity=1,
skip_existing=False,
overwrite=False,
once=False,
simplecomm=None):
"""
Constructor
Parameters:
specifier (Specifier): An instance of the Specifier class,
defining the input specification for this reshaper operation.
Keyword Arguments:
serial (bool): True or False, indicating whether the operation
should be performed in serial (True) or parallel
(False). The default is to assume parallel operation
(but serial will be chosen if the mpi4py cannot be
found when trying to initialize decomposition.
verbosity(int): Level of printed output (stdout). A value of 0
means no output, and a higher value means more output. The
default value is 1.
skip_existing (bool): Flag specifying whether to skip the generation
of time-series for variables with time-series files that already
exist. Default is False.
overwrite (bool): Flag specifying whether to forcefully overwrite
output files if they already exist. Default is False.
once (bool): True or False, indicating whether the Reshaper should
write all metadata to a 'once' file (separately).
simplecomm (SimpleComm): A SimpleComm object to handle the parallel
communication, if necessary
"""
# Type checking (or double-checking)
if not isinstance(specifier, Specifier):
err_msg = "Input must be given in the form of a Specifier object"
raise TypeError(err_msg)
if type(serial) is not bool:
err_msg = "Serial indicator must be True or False."
raise TypeError(err_msg)
if type(verbosity) is not int:
err_msg = "Verbosity level must be an integer."
raise TypeError(err_msg)
if type(skip_existing) is not bool:
err_msg = "Skip_existing flag must be True or False."
raise TypeError(err_msg)
if type(once) is not bool:
err_msg = "Once-file indicator must be True or False."
raise TypeError(err_msg)
if simplecomm is not None:
if not (isinstance(simplecomm, SimpleComm) or \
isinstance(simplecomm, SimpleCommMPI)):
err_msg = (
"Simple communicator object is not a SimpleComm or ",
"SimpleCommMPI")
raise TypeError(err_msg)
# Whether to write a once file
self._use_once_file = once
# Internal timer data
self._timer = TimeKeeper()
# Dictionary storing read/write data amounts
self.assumed_block_size = float(4 * 1024 * 1024)
self._byte_counts = {}
self._timer.start('Initializing Simple Communicator')
if simplecomm is None:
simplecomm = create_comm(serial=serial)
# Reference to the simple communicator
self._simplecomm = simplecomm
self._timer.stop('Initializing Simple Communicator')
# Contruct the print header
header = ''.join([
'[',
str(self._simplecomm.get_rank()), '/',
str(self._simplecomm.get_size()), '] '
])
# Reference to the verbose printer tool
self._vprint = VPrinter(header=header, verbosity=verbosity)
# Debug output starting
if self._simplecomm.is_manager():
self._vprint('Initializing Reshaper', verbosity=1)
# Validate the user input data
self._timer.start('Specifier Validation')
specifier.validate()
self._timer.stop('Specifier Validation')
if self._simplecomm.is_manager():
self._vprint('Specifier validated', verbosity=1)
# Setup PyNIO options (including disabling the default PreFill option)
opt = Nio.options()
opt.PreFill = False
# Determine the Format and CompressionLevel options
# from the NetCDF format string in the Specifier
if specifier.netcdf_format == 'netcdf':
opt.Format = 'Classic'
elif specifier.netcdf_format == 'netcdf4':
opt.Format = 'NetCDF4Classic'
opt.CompressionLevel = 0
elif specifier.netcdf_format == 'netcdf4c':
opt.Format = 'NetCDF4Classic'
opt.CompressionLevel = specifier.netcdf_deflate
if self._simplecomm.is_manager():
self._vprint('PyNIO compression level: {0}'.format(\
specifier.netcdf_deflate), verbosity=2)
self._nio_options = opt
if self._simplecomm.is_manager():
self._vprint('PyNIO options set', verbosity=2)
# Open all of the input files
self._timer.start('Open Input Files')
self._input_files = []
for filename in specifier.input_file_list:
self._input_files.append(Nio.open_file(filename, "r"))
self._timer.stop('Open Input Files')
if self._simplecomm.is_manager():
self._vprint('Input files opened', verbosity=2)
# Validate the input files themselves
self._timer.start('Input File Validation')
self._validate_input_files(specifier)
self._timer.stop('Input File Validation')
if self._simplecomm.is_manager():
self._vprint('Input files validated', verbosity=2)
# Sort the input files by time
self._timer.start('Sort Input Files')
self._sort_input_files_by_time(specifier)
self._timer.stop('Sort Input Files')
if self._simplecomm.is_manager():
self._vprint('Input files sorted', verbosity=2)
# Retrieve and sort the variables in each time-slice file
# (To determine if it is time-invariant metadata, time-variant
# metadata, or if it is a time-series variable)
self._timer.start('Sort Variables')
self._sort_variables(specifier)
self._timer.stop('Sort Variables')
if self._simplecomm.is_manager():
self._vprint('Variables sorted', verbosity=2)
# Validate the output files
self._timer.start('Output File Validation')
self._validate_output_files(specifier, skip_existing, overwrite)
self._timer.stop('Output File Validation')
if self._simplecomm.is_manager():
self._vprint('Output files validated', verbosity=2)
# Helpful debugging message
if self._simplecomm.is_manager():
self._vprint('Reshaper initialized.', verbosity=1)
# Sync before continuing..
self._simplecomm.sync()
def setUp(self):
do_setup(filename)
opt = Nio.options()
opt.MaskedArrayMode = 'MaskedIfFillAttAndValue'
self.f = Nio.open_file(filename, options=opt)
