def cov_io(self, context, value_array, comp_val=None):
pdict = ParameterDictionary()
time = ParameterContext(name='time', param_type=QuantityType(value_encoding=np.float64))
pdict.add_context(context)
pdict.add_context(time, True)
# Construct temporal and spatial Coordinate Reference System objects
tcrs = CRS([AxisTypeEnum.TIME])
scrs = CRS([AxisTypeEnum.LON, AxisTypeEnum.LAT])
# Construct temporal and spatial Domain objects
tdom = GridDomain(GridShape('temporal', [0]), tcrs, MutabilityEnum.EXTENSIBLE) # 1d (timeline)
sdom = GridDomain(GridShape('spatial', [0]), scrs, MutabilityEnum.IMMUTABLE) # 0d spatial topology (station/trajectory)
# Instantiate the SimplexCoverage providing the ParameterDictionary, spatial Domain and temporal Domain
cov = SimplexCoverage('test_data', create_guid(), 'sample coverage_model', parameter_dictionary=pdict, temporal_domain=tdom, spatial_domain=sdom)
cov.insert_timesteps(len(value_array))
cov.set_parameter_values('test', tdoa=slice(0,len(value_array)), value=value_array)
comp_val = comp_val if comp_val is not None else value_array
testval = cov.get_parameter_values('test')
try:
np.testing.assert_array_equal(testval, comp_val)
except:
print repr(value_array)
raise
def _create_parameter(self):
pdict = ParameterDictionary()
pdict = self._add_location_time_ctxt(pdict)
pres_ctxt = ParameterContext('pressure', param_type=QuantityType(value_encoding=numpy.float32))
pres_ctxt.uom = 'Pascal'
pres_ctxt.fill_value = 0x0
pdict.add_context(pres_ctxt)
temp_ctxt = ParameterContext('temp', param_type=QuantityType(value_encoding=numpy.float32))
temp_ctxt.uom = 'degree_Celsius'
temp_ctxt.fill_value = 0e0
pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext('conductivity', param_type=QuantityType(value_encoding=numpy.float32))
cond_ctxt.uom = 'unknown'
cond_ctxt.fill_value = 0e0
pdict.add_context(cond_ctxt)
raw_fixed_ctxt = ParameterContext('raw_fixed', param_type=QuantityType(value_encoding=numpy.float32))
raw_fixed_ctxt.uom = 'unknown'
raw_fixed_ctxt.fill_value = 0e0
pdict.add_context(raw_fixed_ctxt)
raw_blob_ctxt = ParameterContext('raw_blob', param_type=QuantityType(value_encoding=numpy.float32))
raw_blob_ctxt.uom = 'unknown'
raw_blob_ctxt.fill_value = 0e0
pdict.add_context(raw_blob_ctxt)
return pdict
def get_param_dict(param_dict_name = None):
raise NotImplementedError('This method has been replaced by DatasetManagementService, please use read_parameter_dictionary_by_name instead')
# read the file just once, not every time needed
global _PARAMETER_DICTIONARIES
global _PARAMETER_CONTEXTS
if not _PARAMETER_DICTIONARIES:
param_dict_defs_file = "res/config/param_dict_defs.yml"
with open(param_dict_defs_file, "r") as f_dict:
dict_string = f_dict.read()
_PARAMETER_DICTIONARIES = yaml.load(dict_string)
param_context_defs_file = "res/config/param_context_defs.yml"
with open(param_context_defs_file, "r") as f_ctxt:
ctxt_string = f_ctxt.read()
_PARAMETER_CONTEXTS = yaml.load(ctxt_string)
# make sure we have the one requested
context_names = _PARAMETER_DICTIONARIES[param_dict_name]
for name in context_names:
if not _PARAMETER_CONTEXTS.has_key(name):
raise AssertionError('The parameter dict has a context that does not exist in the parameter context defs specified in yml: %s' % name)
# package and ship
pdict = ParameterDictionary()
for ctxt_name in context_names:
param_context = ParameterContext.load(_PARAMETER_CONTEXTS[ctxt_name])
pdict.add_context(param_context)
return pdict
def get_param_dict(param_dict_name=None):
raise NotImplementedError(
'This method has been replaced by DatasetManagementService, please use read_parameter_dictionary_by_name instead'
)
# read the file just once, not every time needed
global _PARAMETER_DICTIONARIES
global _PARAMETER_CONTEXTS
if not _PARAMETER_DICTIONARIES:
param_dict_defs_file = "res/config/param_dict_defs.yml"
with open(param_dict_defs_file, "r") as f_dict:
dict_string = f_dict.read()
_PARAMETER_DICTIONARIES = yaml.load(dict_string)
param_context_defs_file = "res/config/param_context_defs.yml"
with open(param_context_defs_file, "r") as f_ctxt:
ctxt_string = f_ctxt.read()
_PARAMETER_CONTEXTS = yaml.load(ctxt_string)
# make sure we have the one requested
context_names = _PARAMETER_DICTIONARIES[param_dict_name]
for name in context_names:
if not _PARAMETER_CONTEXTS.has_key(name):
raise AssertionError(
'The parameter dict has a context that does not exist in the parameter context defs specified in yml: %s'
% name)
# package and ship
pdict = ParameterDictionary()
for ctxt_name in context_names:
param_context = ParameterContext.load(_PARAMETER_CONTEXTS[ctxt_name])
pdict.add_context(param_context)
return pdict
def sync_rdt_with_coverage(self, coverage=None, tdoa=None, start_time=None, end_time=None, stride_time=None, parameters=None):
'''
Builds a granule based on the coverage
'''
if coverage is None:
coverage = self.coverage
slice_ = slice(None) # Defaults to all values
if tdoa is not None and isinstance(tdoa,slice):
slice_ = tdoa
elif stride_time is not None:
validate_is_instance(start_time, Number, 'start_time must be a number for striding.')
validate_is_instance(end_time, Number, 'end_time must be a number for striding.')
validate_is_instance(stride_time, Number, 'stride_time must be a number for striding.')
ugly_range = np.arange(start_time, end_time, stride_time)
idx_values = [TimeUtils.get_relative_time(coverage,i) for i in ugly_range]
slice_ = [idx_values]
elif not (start_time is None and end_time is None):
time_var = coverage._temporal_param_name
uom = coverage.get_parameter_context(time_var).uom
if start_time is not None:
start_units = TimeUtils.ts_to_units(uom,start_time)
log.info('Units: %s', start_units)
start_idx = TimeUtils.get_relative_time(coverage,start_units)
log.info('Start Index: %s', start_idx)
start_time = start_idx
if end_time is not None:
end_units = TimeUtils.ts_to_units(uom,end_time)
log.info('End units: %s', end_units)
end_idx = TimeUtils.get_relative_time(coverage,end_units)
log.info('End index: %s', end_idx)
end_time = end_idx
slice_ = slice(start_time,end_time,stride_time)
log.info('Slice: %s', slice_)
if parameters is not None:
pdict = ParameterDictionary()
params = set(coverage.list_parameters()).intersection(parameters)
for param in params:
pdict.add_context(coverage.get_parameter_context(param))
rdt = RecordDictionaryTool(param_dictionary=pdict)
self.pdict = pdict
else:
rdt = RecordDictionaryTool(param_dictionary=coverage.parameter_dictionary)
fields = coverage.list_parameters()
if parameters is not None:
fields = set(fields).intersection(parameters)
for d in fields:
rdt[d] = coverage.get_parameter_values(d,tdoa=slice_)
self.rdt = rdt # Sync
def _create_parameter_dictionary(self):
pdict = ParameterDictionary()
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lat_ctxt.axis = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lon_ctxt.axis = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
pdict.add_context(lon_ctxt)
return pdict
def sync_rdt_with_coverage(self, coverage=None, tdoa=None, start_time=None, end_time=None, parameters=None):
'''
Builds a granule based on the coverage
'''
if coverage is None:
coverage = self.coverage
slice_ = slice(None) # Defaults to all values
if tdoa is not None and isinstance(tdoa,slice):
slice_ = tdoa
elif not (start_time is None and end_time is None):
uom = coverage.get_parameter_context('time').uom
if start_time is not None:
start_units = self.ts_to_units(uom,start_time)
log.info('Units: %s', start_units)
start_idx = self.get_relative_time(coverage,start_units)
log.info('Start Index: %s', start_idx)
start_time = start_idx
if end_time is not None:
end_units = self.ts_to_units(uom,end_time)
log.info('End units: %s', end_units)
end_idx = self.get_relative_time(coverage,end_units)
log.info('End index: %s', end_idx)
end_time = end_idx
slice_ = slice(start_time,end_time)
log.info('Slice: %s', slice_)
if parameters is not None:
pdict = ParameterDictionary()
params = set(coverage.list_parameters()).intersection(parameters)
for param in params:
pdict.add_context(coverage.get_parameter_context(param))
rdt = RecordDictionaryTool(param_dictionary=pdict)
self.pdict = pdict
else:
rdt = RecordDictionaryTool(param_dictionary=coverage.parameter_dictionary)
fields = coverage.list_parameters()
if parameters is not None:
fields = set(fields).intersection(parameters)
for d in fields:
rdt[d] = coverage.get_parameter_values(d,tdoa=slice_)
self.rdt = rdt # Sync
def rdt_to_granule(self, context, value_array, comp_val=None):
pdict = ParameterDictionary()
pdict.add_context(context)
rdt = RecordDictionaryTool(param_dictionary=pdict)
rdt["test"] = value_array
granule = rdt.to_granule()
rdt2 = RecordDictionaryTool.load_from_granule(granule)
testval = comp_val if comp_val is not None else value_array
actual = rdt2["test"]
if isinstance(testval, basestring):
self.assertEquals(testval, actual)
else:
np.testing.assert_array_equal(testval, actual)
def rdt_to_granule(self, context, value_array, comp_val=None):
pdict = ParameterDictionary()
pdict.add_context(context)
rdt = RecordDictionaryTool(param_dictionary=pdict)
rdt['test'] = value_array
granule = rdt.to_granule()
rdt2 = RecordDictionaryTool.load_from_granule(granule)
testval = comp_val if comp_val is not None else value_array
actual = rdt2['test']
if isinstance(testval, basestring):
self.assertEquals(testval, actual)
else:
np.testing.assert_array_equal(testval, actual)
def create(self, path):
mkdir_silent(path)
tcrs = CRS([AxisTypeEnum.TIME])
scrs = CRS([AxisTypeEnum.LON, AxisTypeEnum.LAT, AxisTypeEnum.HEIGHT])
tdom = GridDomain(GridShape('temporal', [0]), tcrs, MutabilityEnum.EXTENSIBLE)
sdom = GridDomain(GridShape('spatial', [0]), scrs, MutabilityEnum.IMMUTABLE) # Dimensionality is excluded for now
pdict = ParameterDictionary()
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.axis = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
pdict.add_context(t_ctxt)
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.axis = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.axis = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
pdict.add_context(lon_ctxt)
dens_ctxt = ParameterContext('data_quantity', param_type=QuantityType(value_encoding=np.float32))
dens_ctxt.uom = 'unknown'
dens_ctxt.fill_value = 0x0
pdict.add_context(dens_ctxt)
serial_ctxt = ParameterContext('data_array', param_type=ArrayType())
serial_ctxt.uom = 'unknown'
serial_ctxt.fill_value = 0x0
pdict.add_context(serial_ctxt)
guid = str(uuid.uuid4()).upper()
self.path = path
self.cov = SimplexCoverage(path, guid, name='test_cov', parameter_dictionary=pdict, temporal_domain=tdom, spatial_domain=sdom)
def _setup_resources(self):
pdict = ParameterDictionary()
t_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=numpy.dtype('int64')))
t_ctxt.axis = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 01-01-1970'
pdict.add_context(t_ctxt)
stream_id, stream_route, stream_def = self.create_stream_and_logger(name='fibonacci_stream', pdict=pdict)
# tx = TaxyTool()
# tx.add_taxonomy_set('data', 'external_data')
self.DVR_CONFIG['dh_cfg'] = {
'TESTING': True,
'stream_id': stream_id,
'stream_route': stream_route,
'stream_def': stream_def,
'data_producer_id': 'fibonacci_data_producer_id',
'max_records': 4,
}
def rdt_to_granule(self, context, value_array, comp_val=None):
time = ParameterContext(name='time', param_type=QuantityType(value_encoding=np.float64))
pdict = ParameterDictionary()
pdict.add_context(time, is_temporal=True)
pdict.add_context(context)
rdt = RecordDictionaryTool(param_dictionary=pdict)
rdt['time'] = np.arange(len(value_array))
rdt['test'] = value_array
granule = rdt.to_granule()
rdt2 = RecordDictionaryTool.load_from_granule(granule)
testval = comp_val if comp_val is not None else value_array
actual = rdt2['test']
if isinstance(testval, basestring):
self.assertEquals(testval, actual)
else:
np.testing.assert_array_equal(testval, actual)
def _create_parameter(self):
pdict = ParameterDictionary()
pdict = self._add_location_time_ctxt(pdict)
pres_ctxt = ParameterContext(
'pressure', param_type=QuantityType(value_encoding=numpy.float32))
pres_ctxt.uom = 'Pascal'
pres_ctxt.fill_value = 0x0
pdict.add_context(pres_ctxt)
temp_ctxt = ParameterContext(
'temp', param_type=QuantityType(value_encoding=numpy.float32))
temp_ctxt.uom = 'degree_Celsius'
temp_ctxt.fill_value = 0e0
pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext(
'conductivity',
param_type=QuantityType(value_encoding=numpy.float32))
cond_ctxt.uom = 'unknown'
cond_ctxt.fill_value = 0e0
pdict.add_context(cond_ctxt)
return pdict
def rdt_to_granule(self, context, value_array, comp_val=None):
time = ParameterContext(
name='time', param_type=QuantityType(value_encoding=np.float64))
pdict = ParameterDictionary()
pdict.add_context(time, is_temporal=True)
pdict.add_context(context)
rdt = RecordDictionaryTool(param_dictionary=pdict)
rdt['time'] = np.arange(len(value_array))
rdt['test'] = value_array
granule = rdt.to_granule()
rdt2 = RecordDictionaryTool.load_from_granule(granule)
testval = comp_val if comp_val is not None else value_array
actual = rdt2['test']
if isinstance(testval, basestring):
self.assertEquals(testval, actual)
else:
np.testing.assert_array_equal(testval, actual)
def adhoc_get_parameter_dictionary(stream_name):
"""
@param stream_name IGNORED in this adhoc function; it returns the same
ParameterDictionary definition always.
@retval corresponding ParameterDictionary.
"""
#@TODO Luke - Maybe we can make this a bit more versatile, we could make this a standard pdict...
pdict = ParameterDictionary()
# ctxt = ParameterContext('value', param_type=QuantityType(value_encoding=numpy.float32))
ctxt = ParameterContext('value', param_type=QuantityType(value_encoding=numpy.dtype('float64')))
ctxt.uom = 'unknown'
ctxt.fill_value = 0e0
pdict.add_context(ctxt)
ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=numpy.dtype('int64')))
ctxt.axis = AxisTypeEnum.TIME
ctxt.uom = 'seconds since 01-01-1970'
pdict.add_context(ctxt)
ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
ctxt.axis = AxisTypeEnum.LON
ctxt.uom = 'degree_east'
pdict.add_context(ctxt)
ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
ctxt.axis = AxisTypeEnum.LAT
ctxt.uom = 'degree_north'
pdict.add_context(ctxt)
ctxt = ParameterContext('height', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
ctxt.axis = AxisTypeEnum.HEIGHT
ctxt.uom = 'unknown'
pdict.add_context(ctxt)
return pdict
def cov_io(self, context, value_array, comp_val=None):
pdict = ParameterDictionary()
time = ParameterContext(
name='time', param_type=QuantityType(value_encoding=np.float64))
pdict.add_context(context)
pdict.add_context(time, True)
# Construct temporal and spatial Coordinate Reference System objects
tcrs = CRS([AxisTypeEnum.TIME])
scrs = CRS([AxisTypeEnum.LON, AxisTypeEnum.LAT])
# Construct temporal and spatial Domain objects
tdom = GridDomain(GridShape('temporal', [0]), tcrs,
MutabilityEnum.EXTENSIBLE) # 1d (timeline)
sdom = GridDomain(GridShape('spatial',
[0]), scrs, MutabilityEnum.IMMUTABLE
) # 0d spatial topology (station/trajectory)
# Instantiate the SimplexCoverage providing the ParameterDictionary, spatial Domain and temporal Domain
cov = SimplexCoverage('test_data',
create_guid(),
'sample coverage_model',
parameter_dictionary=pdict,
temporal_domain=tdom,
spatial_domain=sdom)
self.addCleanup(shutil.rmtree, cov.persistence_dir)
cov.insert_timesteps(len(value_array))
cov.set_parameter_values('test',
tdoa=slice(0, len(value_array)),
value=value_array)
comp_val = comp_val if comp_val is not None else value_array
testval = cov.get_parameter_values('test')
try:
np.testing.assert_array_equal(testval, comp_val)
except:
print repr(value_array)
raise
class SimplexCoverage(AbstractCoverage):
"""
A concrete implementation of AbstractCoverage consisting of 2 domains (temporal and spatial)
and a collection of parameters associated with one or both of the domains. Each parameter is defined by a
ParameterContext object (provided via the ParameterDictionary) and has content represented by a concrete implementation
of the AbstractParameterValue class.
"""
def __init__(self, root_dir, persistence_guid, name=None, parameter_dictionary=None, temporal_domain=None, spatial_domain=None, mode=None, in_memory_storage=False, bricking_scheme=None, inline_data_writes=True, auto_flush_values=True):
"""
Constructor for SimplexCoverage
@param root_dir The root directory for storage of this coverage
@param persistence_guid The persistence uuid for this coverage
@param name The name of the coverage
@param parameter_dictionary a ParameterDictionary object expected to contain one or more valid ParameterContext objects
@param spatial_domain a concrete instance of AbstractDomain for the spatial domain component
@param temporal_domain a concrete instance of AbstractDomain for the temporal domain component
@param mode the file mode for the coverage; one of 'r', 'a', 'r+', or 'w'; defaults to 'r'
@param in_memory_storage if False (default), HDF5 persistence is used; otherwise, nothing is written to disk and all data is held in memory only
@param bricking_scheme the bricking scheme for the coverage; a dict of the form {'brick_size': #, 'chunk_size': #}
@param inline_data_writes if True (default), brick data is written as it is set; otherwise it is written out-of-band by worker processes or threads
@param auto_flush_values if True (default), brick data is flushed immediately; otherwise it is buffered until SimplexCoverage.flush_values() is called
"""
AbstractCoverage.__init__(self, mode=mode)
try:
# Make sure root_dir and persistence_guid are both not None and are strings
if not isinstance(root_dir, str) or not isinstance(persistence_guid, str):
raise TypeError('\'root_dir\' and \'persistence_guid\' must be instances of str')
root_dir = root_dir if not root_dir.endswith(persistence_guid) else os.path.split(root_dir)[0]
pth=os.path.join(root_dir, persistence_guid)
def _doload(self):
# Make sure the coverage directory exists
if not os.path.exists(pth):
raise SystemError('Cannot find specified coverage: {0}'.format(pth))
# All appears well - load it up!
self._persistence_layer = PersistenceLayer(root_dir, persistence_guid, mode=self.mode)
self.name = self._persistence_layer.name
self.spatial_domain = self._persistence_layer.sdom
self.temporal_domain = self._persistence_layer.tdom
self._range_dictionary = ParameterDictionary()
self._range_value = RangeValues()
self._bricking_scheme = self._persistence_layer.global_bricking_scheme
self._in_memory_storage = False
auto_flush_values = self._persistence_layer.auto_flush_values
inline_data_writes = self._persistence_layer.inline_data_writes
from coverage_model.persistence import PersistedStorage
for parameter_name in self._persistence_layer.parameter_metadata.keys():
md = self._persistence_layer.parameter_metadata[parameter_name]
pc = md.parameter_context
self._range_dictionary.add_context(pc)
s = PersistedStorage(md, self._persistence_layer.brick_dispatcher, dtype=pc.param_type.storage_encoding, fill_value=pc.param_type.fill_value, mode=self.mode, inline_data_writes=inline_data_writes, auto_flush=auto_flush_values)
self._range_value[parameter_name] = get_value_class(param_type=pc.param_type, domain_set=pc.dom, storage=s)
if name is None or parameter_dictionary is None:
# This appears to be a load
_doload(self)
else:
# This appears to be a new coverage
# Make sure name and parameter_dictionary are not None
if name is None or parameter_dictionary is None:
raise SystemError('\'name\' and \'parameter_dictionary\' cannot be None')
# Make sure the specified root_dir exists
if not in_memory_storage and not os.path.exists(root_dir):
raise SystemError('Cannot find specified \'root_dir\': {0}'.format(root_dir))
# If the coverage directory exists, load it instead!!
if os.path.exists(pth):
log.warn('The specified coverage already exists - performing load of \'{0}\''.format(pth))
_doload(self)
return
# We've checked everything we can - this is a new coverage!!!
# Check the mode - must be in 'a' for a new coverage
if self.mode != 'a':
self.mode = 'a'
self.name = name
if temporal_domain is None:
self.temporal_domain = GridDomain(GridShape('temporal',[0]), CRS.standard_temporal(), MutabilityEnum.EXTENSIBLE)
elif isinstance(temporal_domain, AbstractDomain):
self.temporal_domain = deepcopy(temporal_domain)
else:
raise TypeError('\'temporal_domain\' must be an instance of AbstractDomain')
if spatial_domain is None or isinstance(spatial_domain, AbstractDomain):
self.spatial_domain = deepcopy(spatial_domain)
else:
raise TypeError('\'spatial_domain\' must be an instance of AbstractDomain')
if not isinstance(parameter_dictionary, ParameterDictionary):
raise TypeError('\'parameter_dictionary\' must be of type ParameterDictionary')
self._range_dictionary = ParameterDictionary()
self._range_value = RangeValues()
self._bricking_scheme = bricking_scheme or {'brick_size':10000,'chunk_size':500}
self._in_memory_storage = in_memory_storage
if self._in_memory_storage:
self._persistence_layer = InMemoryPersistenceLayer()
else:
self._persistence_layer = PersistenceLayer(root_dir, persistence_guid, name=name, tdom=temporal_domain, sdom=spatial_domain, mode=self.mode, bricking_scheme=self._bricking_scheme, inline_data_writes=inline_data_writes, auto_flush_values=auto_flush_values)
for o, pc in parameter_dictionary.itervalues():
self._append_parameter(pc)
except:
self._closed = True
raise
@classmethod
def _fromdict(cls, cmdict, arg_masks=None):
return super(SimplexCoverage, cls)._fromdict(cmdict, {'parameter_dictionary':'_range_dictionary'})
@property
def temporal_parameter_name(self):
return self._range_dictionary.temporal_parameter_name
@property
def parameter_dictionary(self):
return deepcopy(self._range_dictionary)
@property
def persistence_guid(self):
if isinstance(self._persistence_layer, InMemoryPersistenceLayer):
return None
else:
return self._persistence_layer.guid
@property
def persistence_dir(self):
if isinstance(self._persistence_layer, InMemoryPersistenceLayer):
return None
else:
return self._persistence_layer.master_manager.root_dir
def append_parameter(self, parameter_context):
"""
Append a ParameterContext to the coverage
@deprecated use a ParameterDictionary during construction of the coverage
"""
log.warn('SimplexCoverage.append_parameter() is deprecated: use a ParameterDictionary during construction of the coverage')
self._append_parameter(parameter_context)
def _append_parameter(self, parameter_context):
"""
Appends a ParameterContext object to the internal set for this coverage.
A <b>deep copy</b> of the supplied ParameterContext is added to self._range_dictionary. An AbstractParameterValue of the type
indicated by ParameterContext.param_type is added to self._range_value. If the ParameterContext indicates that
the parameter is a coordinate parameter, it is associated with the indicated axis of the appropriate CRS.
@param parameter_context The ParameterContext to append to the coverage <b>as a copy</b>
@throws StandardError If the ParameterContext.axis indicates that it is temporal and a temporal parameter
already exists in the coverage
"""
if self.closed:
raise IOError('I/O operation on closed file')
if self.mode == 'r':
raise IOError('Coverage not open for writing: mode == \'{0}\''.format(self.mode))
if not isinstance(parameter_context, ParameterContext):
raise TypeError('\'parameter_context\' must be an instance of ParameterContext')
# Create a deep copy of the ParameterContext
pcontext = deepcopy(parameter_context)
pname = pcontext.name
no_sdom = self.spatial_domain is None
## Determine the correct array shape
# Get the parameter variability; assign to VariabilityEnum.NONE if None
pv=pcontext.variability or VariabilityEnum.NONE
if no_sdom and pv in (VariabilityEnum.SPATIAL, VariabilityEnum.BOTH):
log.warn('Provided \'parameter_context\' indicates Spatial variability, but coverage has no Spatial Domain')
if pv == VariabilityEnum.TEMPORAL: # Only varies in the Temporal Domain
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, None)
elif pv == VariabilityEnum.SPATIAL: # Only varies in the Spatial Domain
pcontext.dom = DomainSet(None, self.spatial_domain.shape.extents)
elif pv == VariabilityEnum.BOTH: # Varies in both domains
# If the Spatial Domain is only a single point on a 0d Topology, the parameter's shape is that of the Temporal Domain only
if no_sdom or (len(self.spatial_domain.shape.extents) == 1 and self.spatial_domain.shape.extents[0] == 0):
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, None)
else:
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, self.spatial_domain.shape.extents)
elif pv == VariabilityEnum.NONE: # No variance; constant
# CBM TODO: Not sure we can have this constraint - precludes situations like a TextType with Variablity==None...
# # This is a constant - if the ParameterContext is not a ConstantType, make it one with the default 'x' expr
# if not isinstance(pcontext.param_type, ConstantType):
# pcontext.param_type = ConstantType(pcontext.param_type)
# The domain is the total domain - same value everywhere!!
# If the Spatial Domain is only a single point on a 0d Topology, the parameter's shape is that of the Temporal Domain only
if no_sdom or (len(self.spatial_domain.shape.extents) == 1 and self.spatial_domain.shape.extents[0] == 0):
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, None)
else:
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, self.spatial_domain.shape.extents)
else:
# Should never get here...but...
raise SystemError('Must define the variability of the ParameterContext: a member of VariabilityEnum')
# Assign the pname to the CRS (if applicable) and select the appropriate domain (default is the spatial_domain)
dom = self.spatial_domain
if not pcontext.axis is None and AxisTypeEnum.is_member(pcontext.axis, AxisTypeEnum.TIME):
dom = self.temporal_domain
dom.crs.axes[pcontext.axis] = pcontext.name
elif not no_sdom and (pcontext.axis in self.spatial_domain.crs.axes):
dom.crs.axes[pcontext.axis] = pcontext.name
self._range_dictionary.add_context(pcontext)
s = self._persistence_layer.init_parameter(pcontext, self._bricking_scheme)
self._range_value[pname] = get_value_class(param_type=pcontext.param_type, domain_set=pcontext.dom, storage=s)
def get_parameter(self, param_name):
"""
Get a Parameter object by name
The Parameter object contains the ParameterContext and AbstractParameterValue associated with the param_name
@param param_name The local name of the parameter to return
@returns A Parameter object containing the context and value for the specified parameter
@throws KeyError The coverage does not contain a parameter with name 'param_name'
"""
if self.closed:
raise ValueError('I/O operation on closed file')
if param_name in self._range_dictionary:
p = Parameter(deepcopy(self._range_dictionary.get_context(param_name)), self._range_value[param_name].shape, self._range_value[param_name])
return p
else:
raise KeyError('Coverage does not contain parameter \'{0}\''.format(param_name))
def list_parameters(self, coords_only=False, data_only=False):
"""
List the names of the parameters contained in the coverage
@param coords_only List only the coordinate parameters
@param data_only List only the data parameters (non-coordinate) - superseded by coords_only
@returns A list of parameter names
"""
if coords_only:
lst=[x for x, v in self._range_dictionary.iteritems() if v[1].is_coordinate]
elif data_only:
lst=[x for x, v in self._range_dictionary.iteritems() if not v[1].is_coordinate]
else:
lst=[x for x in self._range_dictionary]
lst.sort()
return lst
def insert_timesteps(self, count, origin=None, oob=True):
"""
Insert count # of timesteps beginning at the origin
The specified # of timesteps are inserted into the temporal value array at the indicated origin. This also
expands the temporal dimension of the AbstractParameterValue for each parameters
@param count The number of timesteps to insert
@param origin The starting location, from which to begin the insertion
@param oob Out of band operations, True will use greenlets, False will be in-band.
"""
if self.closed:
raise IOError('I/O operation on closed file')
if self.mode == 'r':
raise IOError('Coverage not open for writing: mode == \'{0}\''.format(self.mode))
# Get the current shape of the temporal_dimension
shp = self.temporal_domain.shape
# If not provided, set the origin to the end of the array
if origin is None or not isinstance(origin, int):
origin = shp.extents[0]
# Expand the shape of the temporal_domain - following works if extents is a list or tuple
shp.extents = (shp.extents[0]+count,)+tuple(shp.extents[1:])
# Expand the temporal dimension of each of the parameters - the parameter determines how to apply the change
for n in self._range_dictionary:
pc = self._range_dictionary.get_context(n)
# Update the dom of the parameter_context
if pc.dom.tdom is not None:
pc.dom.tdom = self.temporal_domain.shape.extents
self._persistence_layer.expand_domain(pc)
self._range_value[n].expand_content(VariabilityEnum.TEMPORAL, origin, count)
# Update the temporal_domain in the master_manager, do NOT flush!!
self._persistence_layer.update_domain(tdom=self.temporal_domain, do_flush=False)
# Flush the master_manager & parameter_managers in a separate greenlet
if oob:
spawn(self._persistence_layer.flush)
else:
self._persistence_layer.flush()
def set_time_values(self, value, tdoa=None):
"""
Convenience method for setting time values
@param value The value to set
@param tdoa The temporal DomainOfApplication; default to full Domain
"""
return self.set_parameter_values(self.temporal_parameter_name, value, tdoa, None)
def get_time_values(self, tdoa=None, return_value=None):
"""
Convenience method for retrieving time values
Delegates to get_parameter_values, supplying the temporal parameter name and sdoa == None
@param tdoa The temporal DomainOfApplication; default to full Domain
@param return_value If supplied, filled with response value
"""
return self.get_parameter_values(self.temporal_parameter_name, tdoa, None, return_value)
@property
def num_timesteps(self):
"""
The current number of timesteps
"""
return self.temporal_domain.shape.extents[0]
def set_parameter_values(self, param_name, value, tdoa=None, sdoa=None):
"""
Assign value to the specified parameter
Assigns the value to param_name within the coverage. Temporal and spatial DomainOfApplication objects can be
applied to constrain the assignment. See DomainOfApplication for details
@param param_name The name of the parameter
@param value The value to set
@param tdoa The temporal DomainOfApplication
@param sdoa The spatial DomainOfApplication
@throws KeyError The coverage does not contain a parameter with name 'param_name'
"""
if self.closed:
raise IOError('I/O operation on closed file')
if self.mode == 'r':
raise IOError('Coverage not open for writing: mode == \'{0}\''.format(self.mode))
if not param_name in self._range_value:
raise KeyError('Parameter \'{0}\' not found in coverage_model'.format(param_name))
slice_ = []
tdoa = get_valid_DomainOfApplication(tdoa, self.temporal_domain.shape.extents)
log.debug('Temporal doa: %s', tdoa.slices)
slice_.extend(tdoa.slices)
if self.spatial_domain is not None:
sdoa = get_valid_DomainOfApplication(sdoa, self.spatial_domain.shape.extents)
log.debug('Spatial doa: %s', sdoa.slices)
slice_.extend(sdoa.slices)
log.debug('Setting slice: %s', slice_)
self._range_value[param_name][slice_] = value
def get_parameter_values(self, param_name, tdoa=None, sdoa=None, return_value=None):
"""
Retrieve the value for a parameter
Returns the value from param_name. Temporal and spatial DomainOfApplication objects can be used to
constrain the response. See DomainOfApplication for details.
@param param_name The name of the parameter
@param tdoa The temporal DomainOfApplication
@param sdoa The spatial DomainOfApplication
@param return_value If supplied, filled with response value - currently via OVERWRITE
@throws KeyError The coverage does not contain a parameter with name 'param_name'
"""
if self.closed:
raise ValueError('I/O operation on closed file')
if not param_name in self._range_value:
raise KeyError('Parameter \'{0}\' not found in coverage'.format(param_name))
if return_value is not None:
log.warn('Provided \'return_value\' will be OVERWRITTEN')
slice_ = []
tdoa = get_valid_DomainOfApplication(tdoa, self.temporal_domain.shape.extents)
log.debug('Temporal doa: %s', tdoa.slices)
slice_.extend(tdoa.slices)
if self.spatial_domain is not None:
sdoa = get_valid_DomainOfApplication(sdoa, self.spatial_domain.shape.extents)
log.debug('Spatial doa: %s', sdoa.slices)
slice_.extend(sdoa.slices)
log.debug('Getting slice: %s', slice_)
return_value = self._range_value[param_name][slice_]
return return_value
def get_parameter_context(self, param_name):
"""
Retrieve a deepcopy of the ParameterContext object for the specified parameter
@param param_name The name of the parameter for which to retrieve context
@returns A deepcopy of the specified ParameterContext object
@throws KeyError The coverage does not contain a parameter with name 'param_name'
"""
if not param_name in self._range_dictionary:
raise KeyError('Parameter \'{0}\' not found in coverage'.format(param_name))
return deepcopy(self._range_dictionary.get_context(param_name))
def __axis_arg_to_params(self, axis=None):
"""
Helper function to compose a list of parameter names based on the <i>axis</i> argument
If <i>axis</i> is None, all coordinate parameters are included
@param axis A member of AxisTypeEnum; may be an iterable of such members
"""
params = []
if axis is None:
params.extend(pn for pk, pn in self.temporal_domain.crs.axes.iteritems())
params.extend(pn for pk, pn in self.spatial_domain.crs.axes.iteritems())
elif hasattr(axis, '__iter__'):
for a in axis:
if a in self.temporal_domain.crs.axes:
params.append(self.temporal_domain.crs.axes[a])
elif a in self.spatial_domain.crs.axes:
params.append(self.spatial_domain.crs.axes[a])
else:
raise ValueError('Specified axis ({0}) not found in coverage'.format(a))
elif axis in self.temporal_domain.crs.axes:
params.append(self.temporal_domain.crs.axes[axis])
elif axis in self.spatial_domain.crs.axes:
params.append(self.spatial_domain.crs.axes[axis])
else:
raise ValueError('Specified axis ({0}) not found in coverage'.format(axis))
return params
def __parameter_name_arg_to_params(self, parameter_name=None):
"""
Helper function to compose a list of parameter names based on the <i>parameter_name</i> argument
If <i>parameter_name</i> is None, all parameters in the coverage are included
@param parameter_name A string parameter name; may be an iterable of such members
"""
params = []
if parameter_name is None:
params.extend(self._range_dictionary.keys())
elif hasattr(parameter_name, '__iter__'):
params.extend(pn for pn in parameter_name if pn in self._range_dictionary.keys())
else:
params.append(parameter_name)
return params
def get_data_bounds(self, parameter_name=None):
"""
Returns the bounds (min, max) for the parameter(s) indicated by <i>parameter_name</i>
If <i>parameter_name</i> is None, all parameters in the coverage are included
If more than one parameter is indicated by <i>parameter_name</i>, a dict of {key:(min,max)} is returned;
otherwise, only the (min, max) tuple is returned
@param parameter_name A string parameter name; may be an iterable of such members
"""
from coverage_model import QuantityType, ConstantType
ret = {}
for pn in self.__parameter_name_arg_to_params(parameter_name):
ctxt = self._range_dictionary.get_context(pn)
fv = ctxt.fill_value
if isinstance(ctxt.param_type, QuantityType) or isinstance(ctxt.param_type, ConstantType):
varr = np.ma.masked_equal(self._range_value[pn][:], fv, copy=False)
r = (varr.min(), varr.max())
ret[pn] = tuple([fv if isinstance(x, np.ma.core.MaskedConstant) else x for x in r])
else:
# CBM TODO: Sort out if this is an appropriate way to deal with non-numeric types
ret[pn] = (fv, fv)
if len(ret) == 1:
ret = ret.values()[0]
return ret
def get_data_bounds_by_axis(self, axis=None):
"""
Returns the bounds (min, max) for the coordinate parameter(s) indicated by <i>axis</i>
If <i>axis</i> is None, all coordinate parameters are included
If more than one parameter is indicated by <i>axis</i>, a dict of {key:(min,max)} is returned;
otherwise, only the (min, max) tuple is returned
@param axis A member of AxisTypeEnum; may be an iterable of such members
"""
return self.get_data_bounds(self.__axis_arg_to_params(axis))
def get_data_extents(self, parameter_name=None):
"""
Returns the extents (dim_0,dim_1,...,dim_n) for the parameter(s) indicated by <i>parameter_name</i>
If <i>parameter_name</i> is None, all parameters in the coverage are included
If more than one parameter is indicated by <i>parameter_name</i>, a dict of {key:(dim_0,dim_1,...,dim_n)} is returned;
otherwise, only the (dim_0,dim_1,...,dim_n) tuple is returned
@param parameter_name A string parameter name; may be an iterable of such members
"""
ret = {}
for pn in self.__parameter_name_arg_to_params(parameter_name):
p = self._range_dictionary.get_context(pn)
ret[pn] = p.dom.total_extents
if len(ret) == 1:
ret = ret.values()[0]
return ret
def get_data_extents_by_axis(self, axis=None):
"""
Returns the extents (dim_0,dim_1,...,dim_n) for the coordinate parameter(s) indicated by <i>axis</i>
If <i>axis</i> is None, all coordinate parameters are included
If more than one parameter is indicated by <i>axis</i>, a dict of {key:(dim_0,dim_1,...,dim_n)} is returned;
otherwise, only the (dim_0,dim_1,...,dim_n) tuple is returned
@param axis A member of AxisTypeEnum; may be an iterable of such members
"""
return self.get_data_extents(self.__axis_arg_to_params(axis))
def get_data_size(self, parameter_name=None, slice_=None, in_bytes=False):
"""
Returns the size of the <b>data values</b> for the parameter(s) indicated by <i>parameter_name</i>.
ParameterContext and Coverage metadata is <b>NOT</b> included in the returned size.
If <i>parameter_name</i> is None, all parameters in the coverage are included
If more than one parameter is indicated by <i>parameter_name</i>, the sum of the indicated parameters is returned
If <i>slice_</i> is not None, it is applied to each parameter (after being run through utils.fix_slice) before
calculation of size
Sizes are calculated as:
size = itemsize * total_extent_size
where:
itemsize == the per-item size based on the data type of the parameter
total_extent_size == the total number of elements after slicing is applied (if applicable)
Sizes are in MB unless <i>in_bytes</i> == True
@param parameter_name A string parameter name; may be an iterable of such members
@param slice_ If not None, applied to each parameter before calculation of size
@param in_bytes If True, returns the size in bytes; otherwise, returns the size in MB (default)
"""
size = 0
if parameter_name is None:
for pn in self._range_dictionary.keys():
size += self.get_data_size(pn, in_bytes=in_bytes)
for pn in self.__parameter_name_arg_to_params(parameter_name):
p = self._range_dictionary.get_context(pn)
te=p.dom.total_extents
dt = np.dtype(p.param_type.value_encoding)
if slice_ is not None:
slice_ = utils.fix_slice(slice_, te)
a=np.empty(te, dtype=dt)[slice_]
size += a.nbytes
else:
size += dt.itemsize * utils.prod(te)
if not in_bytes:
size *= 9.53674e-7
return size
@property
def info(self):
"""
Returns a detailed string representation of the coverage contents
@returns string of coverage contents
"""
lst = []
indent = ' '
lst.append('ID: {0}'.format(self._id))
lst.append('Name: {0}'.format(self.name))
lst.append('Temporal Domain:\n{0}'.format(self.temporal_domain.__str__(indent*2)))
lst.append('Spatial Domain:\n{0}'.format(self.spatial_domain.__str__(indent*2)))
lst.append('Parameters:')
for x in self._range_value:
lst.append('{0}{1} {2}\n{3}'.format(indent*2,x,self._range_value[x].shape,self._range_dictionary.get_context(x).__str__(indent*4)))
return '\n'.join(lst)
def __str__(self):
lst = []
indent = ' '
lst.append('ID: {0}'.format(self._id))
lst.append('Name: {0}'.format(self.name))
lst.append('TemporalDomain: Shape=>{0} Axes=>{1}'.format(self.temporal_domain.shape.extents, self.temporal_domain.crs.axes))
lst.append('SpatialDomain: Shape=>{0} Axes=>{1}'.format(self.spatial_domain.shape.extents, self.spatial_domain.crs.axes))
lst.append('Coordinate Parameters: {0}'.format(self.list_parameters(coords_only=True)))
lst.append('Data Parameters: {0}'.format(self.list_parameters(coords_only=False, data_only=True)))
return '\n'.join(lst)
def _setup_resources(self):
# TODO: some or all of this (or some variation) should move to DAMS'
# Build the test resources for the dataset
dams_cli = DataAcquisitionManagementServiceClient()
dpms_cli = DataProductManagementServiceClient()
rr_cli = ResourceRegistryServiceClient()
pubsub_cli = PubsubManagementServiceClient()
eda = ExternalDatasetAgent()
eda_id = dams_cli.create_external_dataset_agent(eda)
eda_inst = ExternalDatasetAgentInstance()
eda_inst_id = dams_cli.create_external_dataset_agent_instance(eda_inst, external_dataset_agent_id=eda_id)
# Create and register the necessary resources/objects
# Create DataProvider
dprov = ExternalDataProvider(institution=Institution(), contact=ContactInformation())
dprov.contact.name = 'Christopher Mueller'
dprov.contact.email = '*****@*****.**'
# Create DataSource
dsrc = DataSource(protocol_type='FILE', institution=Institution(), contact=ContactInformation())
dsrc.connection_params['base_data_url'] = ''
dsrc.contact.name='Tim Giguere'
dsrc.contact.email = '*****@*****.**'
# Create ExternalDataset
ds_name = 'ruv_test_dataset'
dset = ExternalDataset(name=ds_name, dataset_description=DatasetDescription(), update_description=UpdateDescription(), contact=ContactInformation())
dset.dataset_description.parameters['base_url'] = 'test_data/ruv/'
dset.dataset_description.parameters['list_pattern'] = 'RDLi_SEAB_2011_08_24_1600.ruv'
dset.dataset_description.parameters['date_pattern'] = '%Y %m %d %H %M'
dset.dataset_description.parameters['date_extraction_pattern'] = 'RDLi_SEAB_([\d]{4})_([\d]{2})_([\d]{2})_([\d]{2})([\d]{2}).ruv'
dset.dataset_description.parameters['temporal_dimension'] = None
dset.dataset_description.parameters['zonal_dimension'] = None
dset.dataset_description.parameters['meridional_dimension'] = None
dset.dataset_description.parameters['vertical_dimension'] = None
dset.dataset_description.parameters['variables'] = [
]
# Create DataSourceModel
dsrc_model = DataSourceModel(name='ruv_model')
dsrc_model.model = 'RUV'
dsrc_model.data_handler_module = 'N/A'
dsrc_model.data_handler_class = 'N/A'
## Run everything through DAMS
ds_id = dams_cli.create_external_dataset(external_dataset=dset)
ext_dprov_id = dams_cli.create_external_data_provider(external_data_provider=dprov)
ext_dsrc_id = dams_cli.create_data_source(data_source=dsrc)
ext_dsrc_model_id = dams_cli.create_data_source_model(dsrc_model)
# Register the ExternalDataset
dproducer_id = dams_cli.register_external_data_set(external_dataset_id=ds_id)
# Or using each method
dams_cli.assign_data_source_to_external_data_provider(data_source_id=ext_dsrc_id, external_data_provider_id=ext_dprov_id)
dams_cli.assign_data_source_to_data_model(data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id)
dams_cli.assign_external_dataset_to_data_source(external_dataset_id=ds_id, data_source_id=ext_dsrc_id)
dams_cli.assign_external_dataset_to_agent_instance(external_dataset_id=ds_id, agent_instance_id=eda_inst_id)
# dams_cli.assign_external_data_agent_to_agent_instance(external_data_agent_id=self.eda_id, agent_instance_id=self.eda_inst_id)
#create temp streamdef so the data product can create the stream
craft = CoverageCraft
sdom, tdom = craft.create_domains()
sdom = sdom.dump()
tdom = tdom.dump()
parameter_dictionary = craft.create_parameters()
parameter_dictionary = parameter_dictionary.dump()
dprod = IonObject(RT.DataProduct,
name='ruv_parsed_product',
description='parsed ruv product',
temporal_domain = tdom,
spatial_domain = sdom)
streamdef_id = pubsub_cli.create_stream_definition(name="temp", description="temp")
# Generate the data product and associate it to the ExternalDataset
dproduct_id = dpms_cli.create_data_product(data_product=dprod,
stream_definition_id=streamdef_id,
parameter_dictionary=parameter_dictionary)
dams_cli.assign_data_product(input_resource_id=ds_id, data_product_id=dproduct_id)
stream_id, assn = rr_cli.find_objects(subject=dproduct_id, predicate=PRED.hasStream, object_type=RT.Stream, id_only=True)
stream_id = stream_id[0]
log.info('Created resources: {0}'.format({'ExternalDataset':ds_id, 'ExternalDataProvider':ext_dprov_id, 'DataSource':ext_dsrc_id, 'DataSourceModel':ext_dsrc_model_id, 'DataProducer':dproducer_id, 'DataProduct':dproduct_id, 'Stream':stream_id}))
#CBM: Use CF standard_names
#ttool = TaxyTool()
#
#ttool.add_taxonomy_set('data','test data')
pdict = ParameterDictionary()
t_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=numpy.dtype('int64')))
t_ctxt.axis = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 01-01-1970'
pdict.add_context(t_ctxt)
#CBM: Eventually, probably want to group this crap somehow - not sure how yet...
# Create the logger for receiving publications
self.create_stream_and_logger(name='ruv',stream_id=stream_id)
self.EDA_RESOURCE_ID = ds_id
self.EDA_NAME = ds_name
self.DVR_CONFIG['dh_cfg'] = {
'TESTING':True,
'stream_id':stream_id,
'external_dataset_res':dset,
'param_dictionary':pdict.dump(),
'data_producer_id':dproducer_id,#CBM: Should this be put in the main body of the config - with mod & cls?
'max_records':20,
}
def _setup_resources(self):
# TODO: some or all of this (or some variation) should move to DAMS'
# Build the test resources for the dataset
dams_cli = DataAcquisitionManagementServiceClient()
dpms_cli = DataProductManagementServiceClient()
rr_cli = ResourceRegistryServiceClient()
pubsub_cli = PubsubManagementServiceClient()
eda = ExternalDatasetAgent()
eda_id = dams_cli.create_external_dataset_agent(eda)
eda_inst = ExternalDatasetAgentInstance()
eda_inst_id = dams_cli.create_external_dataset_agent_instance(eda_inst, external_dataset_agent_id=eda_id)
# Create and register the necessary resources/objects
# Create DataProvider
dprov = ExternalDataProvider(institution=Institution(), contact=ContactInformation())
dprov.contact.name = "Christopher Mueller"
dprov.contact.email = "*****@*****.**"
# Create DataSource
dsrc = DataSource(protocol_type="FILE", institution=Institution(), contact=ContactInformation())
dsrc.connection_params["base_data_url"] = ""
dsrc.contact.name = "Tim Giguere"
dsrc.contact.email = "*****@*****.**"
# Create ExternalDataset
ds_name = "slocum_test_dataset"
dset = ExternalDataset(
name=ds_name,
dataset_description=DatasetDescription(),
update_description=UpdateDescription(),
contact=ContactInformation(),
)
dset.dataset_description.parameters["base_url"] = "test_data/slocum/"
dset.dataset_description.parameters["list_pattern"] = "ru05-2012-021-0-0-sbd.dat"
dset.dataset_description.parameters["date_pattern"] = "%Y %j"
dset.dataset_description.parameters["date_extraction_pattern"] = "ru05-([\d]{4})-([\d]{3})-\d-\d-sbd.dat"
dset.dataset_description.parameters["temporal_dimension"] = None
dset.dataset_description.parameters["zonal_dimension"] = None
dset.dataset_description.parameters["meridional_dimension"] = None
dset.dataset_description.parameters["vertical_dimension"] = None
dset.dataset_description.parameters["variables"] = [
"c_wpt_y_lmc",
"sci_water_cond",
"m_y_lmc",
"u_hd_fin_ap_inflection_holdoff",
"sci_m_present_time",
"m_leakdetect_voltage_forward",
"sci_bb3slo_b660_scaled",
"c_science_send_all",
"m_gps_status",
"m_water_vx",
"m_water_vy",
"c_heading",
"sci_fl3slo_chlor_units",
"u_hd_fin_ap_gain",
"m_vacuum",
"u_min_water_depth",
"m_gps_lat",
"m_veh_temp",
"f_fin_offset",
"u_hd_fin_ap_hardover_holdoff",
"c_alt_time",
"m_present_time",
"m_heading",
"sci_bb3slo_b532_scaled",
"sci_fl3slo_cdom_units",
"m_fin",
"x_cycle_overrun_in_ms",
"sci_water_pressure",
"u_hd_fin_ap_igain",
"sci_fl3slo_phyco_units",
"m_battpos",
"sci_bb3slo_b470_scaled",
"m_lat",
"m_gps_lon",
"sci_ctd41cp_timestamp",
"m_pressure",
"c_wpt_x_lmc",
"c_ballast_pumped",
"x_lmc_xy_source",
"m_lon",
"m_avg_speed",
"sci_water_temp",
"u_pitch_ap_gain",
"m_roll",
"m_tot_num_inflections",
"m_x_lmc",
"u_pitch_ap_deadband",
"m_final_water_vy",
"m_final_water_vx",
"m_water_depth",
"m_leakdetect_voltage",
"u_pitch_max_delta_battpos",
"m_coulomb_amphr",
"m_pitch",
]
# Create DataSourceModel
dsrc_model = DataSourceModel(name="slocum_model")
dsrc_model.model = "SLOCUM"
dsrc_model.data_handler_module = "N/A"
dsrc_model.data_handler_class = "N/A"
## Run everything through DAMS
ds_id = dams_cli.create_external_dataset(external_dataset=dset)
ext_dprov_id = dams_cli.create_external_data_provider(external_data_provider=dprov)
ext_dsrc_id = dams_cli.create_data_source(data_source=dsrc)
ext_dsrc_model_id = dams_cli.create_data_source_model(dsrc_model)
# Register the ExternalDataset
dproducer_id = dams_cli.register_external_data_set(external_dataset_id=ds_id)
# Or using each method
dams_cli.assign_data_source_to_external_data_provider(
data_source_id=ext_dsrc_id, external_data_provider_id=ext_dprov_id
)
dams_cli.assign_data_source_to_data_model(data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id)
dams_cli.assign_external_dataset_to_data_source(external_dataset_id=ds_id, data_source_id=ext_dsrc_id)
dams_cli.assign_external_dataset_to_agent_instance(external_dataset_id=ds_id, agent_instance_id=eda_inst_id)
# dams_cli.assign_external_data_agent_to_agent_instance(external_data_agent_id=self.eda_id, agent_instance_id=self.eda_inst_id)
# create temp streamdef so the data product can create the stream
streamdef_id = pubsub_cli.create_stream_definition(name="temp", description="temp")
# Generate the data product and associate it to the ExternalDataset
craft = CoverageCraft
sdom, tdom = craft.create_domains()
sdom = sdom.dump()
tdom = tdom.dump()
parameter_dictionary = craft.create_parameters()
parameter_dictionary = parameter_dictionary.dump()
dprod = IonObject(
RT.DataProduct,
name="slocum_parsed_product",
description="parsed slocum product",
temporal_domain=tdom,
spatial_domain=sdom,
)
dproduct_id = dpms_cli.create_data_product(
data_product=dprod, stream_definition_id=streamdef_id, parameter_dictionary=parameter_dictionary
)
dams_cli.assign_data_product(input_resource_id=ds_id, data_product_id=dproduct_id)
stream_id, assn = rr_cli.find_objects(
subject=dproduct_id, predicate=PRED.hasStream, object_type=RT.Stream, id_only=True
)
stream_id = stream_id[0]
log.info(
"Created resources: {0}".format(
{
"ExternalDataset": ds_id,
"ExternalDataProvider": ext_dprov_id,
"DataSource": ext_dsrc_id,
"DataSourceModel": ext_dsrc_model_id,
"DataProducer": dproducer_id,
"DataProduct": dproduct_id,
"Stream": stream_id,
}
)
)
# CBM: Use CF standard_names
# ttool = TaxyTool()
#
# ttool.add_taxonomy_set('c_wpt_y_lmc'),
# ttool.add_taxonomy_set('sci_water_cond'),
# ttool.add_taxonomy_set('m_y_lmc'),
# ttool.add_taxonomy_set('u_hd_fin_ap_inflection_holdoff'),
# ttool.add_taxonomy_set('sci_m_present_time'),
# ttool.add_taxonomy_set('m_leakdetect_voltage_forward'),
# ttool.add_taxonomy_set('sci_bb3slo_b660_scaled'),
# ttool.add_taxonomy_set('c_science_send_all'),
# ttool.add_taxonomy_set('m_gps_status'),
# ttool.add_taxonomy_set('m_water_vx'),
# ttool.add_taxonomy_set('m_water_vy'),
# ttool.add_taxonomy_set('c_heading'),
# ttool.add_taxonomy_set('sci_fl3slo_chlor_units'),
# ttool.add_taxonomy_set('u_hd_fin_ap_gain'),
# ttool.add_taxonomy_set('m_vacuum'),
# ttool.add_taxonomy_set('u_min_water_depth'),
# ttool.add_taxonomy_set('m_gps_lat'),
# ttool.add_taxonomy_set('m_veh_temp'),
# ttool.add_taxonomy_set('f_fin_offset'),
# ttool.add_taxonomy_set('u_hd_fin_ap_hardover_holdoff'),
# ttool.add_taxonomy_set('c_alt_time'),
# ttool.add_taxonomy_set('m_present_time'),
# ttool.add_taxonomy_set('m_heading'),
# ttool.add_taxonomy_set('sci_bb3slo_b532_scaled'),
# ttool.add_taxonomy_set('sci_fl3slo_cdom_units'),
# ttool.add_taxonomy_set('m_fin'),
# ttool.add_taxonomy_set('x_cycle_overrun_in_ms'),
# ttool.add_taxonomy_set('sci_water_pressure'),
# ttool.add_taxonomy_set('u_hd_fin_ap_igain'),
# ttool.add_taxonomy_set('sci_fl3slo_phyco_units'),
# ttool.add_taxonomy_set('m_battpos'),
# ttool.add_taxonomy_set('sci_bb3slo_b470_scaled'),
# ttool.add_taxonomy_set('m_lat'),
# ttool.add_taxonomy_set('m_gps_lon'),
# ttool.add_taxonomy_set('sci_ctd41cp_timestamp'),
# ttool.add_taxonomy_set('m_pressure'),
# ttool.add_taxonomy_set('c_wpt_x_lmc'),
# ttool.add_taxonomy_set('c_ballast_pumped'),
# ttool.add_taxonomy_set('x_lmc_xy_source'),
# ttool.add_taxonomy_set('m_lon'),
# ttool.add_taxonomy_set('m_avg_speed'),
# ttool.add_taxonomy_set('sci_water_temp'),
# ttool.add_taxonomy_set('u_pitch_ap_gain'),
# ttool.add_taxonomy_set('m_roll'),
# ttool.add_taxonomy_set('m_tot_num_inflections'),
# ttool.add_taxonomy_set('m_x_lmc'),
# ttool.add_taxonomy_set('u_pitch_ap_deadband'),
# ttool.add_taxonomy_set('m_final_water_vy'),
# ttool.add_taxonomy_set('m_final_water_vx'),
# ttool.add_taxonomy_set('m_water_depth'),
# ttool.add_taxonomy_set('m_leakdetect_voltage'),
# ttool.add_taxonomy_set('u_pitch_max_delta_battpos'),
# ttool.add_taxonomy_set('m_coulomb_amphr'),
# ttool.add_taxonomy_set('m_pitch'),
pdict = ParameterDictionary()
t_ctxt = ParameterContext("c_wpt_y_lmc", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("sci_water_cond", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_y_lmc", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"u_hd_fin_ap_inflection_holdoff", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("sci_m_present_time", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"m_leakdetect_voltage_forward", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"sci_bb3slo_b660_scaled", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("c_science_send_all", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_gps_status", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_water_vx", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_water_vy", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("c_heading", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"sci_fl3slo_chlor_units", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("u_hd_fin_ap_gain", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_vacuum", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("u_min_water_depth", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_gps_lat", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_veh_temp", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("f_fin_offset", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"u_hd_fin_ap_hardover_holdoff", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("c_alt_time", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_present_time", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_heading", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"sci_bb3slo_b532_scaled", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"sci_fl3slo_cdom_units", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_fin", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"x_cycle_overrun_in_ms", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("sci_water_pressure", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("u_hd_fin_ap_igain", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"sci_fl3slo_phyco_units", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_battpos", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"sci_bb3slo_b470_scaled", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_lat", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_gps_lon", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"sci_ctd41cp_timestamp", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_pressure", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("c_wpt_x_lmc", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("c_ballast_pumped", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("x_lmc_xy_source", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_lon", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_avg_speed", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("sci_water_temp", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("u_pitch_ap_gain", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_roll", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"m_tot_num_inflections", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_x_lmc", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("u_pitch_ap_deadband", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_final_water_vy", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_final_water_vx", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_water_depth", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"m_leakdetect_voltage", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext(
"u_pitch_max_delta_battpos", param_type=QuantityType(value_encoding=numpy.dtype("float32"))
)
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_coulomb_amphr", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext("m_pitch", param_type=QuantityType(value_encoding=numpy.dtype("float32")))
t_ctxt.uom = "unknown"
pdict.add_context(t_ctxt)
# CBM: Eventually, probably want to group this crap somehow - not sure how yet...
# Create the logger for receiving publications
self.create_stream_and_logger(name="slocum", stream_id=stream_id)
self.EDA_RESOURCE_ID = ds_id
self.EDA_NAME = ds_name
self.DVR_CONFIG["dh_cfg"] = {
"TESTING": True,
"stream_id": stream_id,
"external_dataset_res": dset,
"param_dictionary": pdict.dump(),
"data_producer_id": dproducer_id, # CBM: Should this be put in the main body of the config - with mod & cls?
"max_records": 20,
}
def _create_parameter_dictionary(self):
pdict = ParameterDictionary()
t_ctxt = ParameterContext('c_wpt_y_lmc', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_water_cond', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_y_lmc', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('u_hd_fin_ap_inflection_holdoff', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_m_present_time', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_leakdetect_voltage_forward', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_bb3slo_b660_scaled', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('c_science_send_all', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_gps_status', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_water_vx', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_water_vy', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('c_heading', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_fl3slo_chlor_units', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('u_hd_fin_ap_gain', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_vacuum', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('u_min_water_depth', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_gps_lat', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_veh_temp', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('f_fin_offset', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('u_hd_fin_ap_hardover_holdoff', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('c_alt_time', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_present_time', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_heading', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_bb3slo_b532_scaled', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_fl3slo_cdom_units', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_fin', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('x_cycle_overrun_in_ms', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_water_pressure', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('u_hd_fin_ap_igain', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_fl3slo_phyco_units', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_battpos', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_bb3slo_b470_scaled', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_lat', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_gps_lon', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_ctd41cp_timestamp', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_pressure', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('c_wpt_x_lmc', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('c_ballast_pumped', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('x_lmc_xy_source', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_lon', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_avg_speed', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('sci_water_temp', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('u_pitch_ap_gain', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_roll', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_tot_num_inflections', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_x_lmc', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('u_pitch_ap_deadband', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_final_water_vy', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_final_water_vx', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_water_depth', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_leakdetect_voltage', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('u_pitch_max_delta_battpos', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_coulomb_amphr', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
t_ctxt = ParameterContext('m_pitch', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
t_ctxt.uom = 'unknown'
pdict.add_context(t_ctxt)
return pdict
def _create_parameter_dictionary(self):
pdict = ParameterDictionary()
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lat_ctxt.axis = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lon_ctxt.axis = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
pdict.add_context(lon_ctxt)
temp_ctxt = ParameterContext('water_temperature', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
temp_ctxt = ParameterContext('water_temperature_bottom', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
temp_ctxt = ParameterContext('water_temperature_middle', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
temp_ctxt = ParameterContext('z', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'meters'
pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext('streamflow', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
cond_ctxt.uom = 'unknown'
pdict.add_context(cond_ctxt)
pres_ctxt = ParameterContext('specific_conductance', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
pres_ctxt.uom = 'unknown'
pdict.add_context(pres_ctxt)
pres_ctxt = ParameterContext('data_qualifier', param_type=QuantityType(value_encoding=numpy.dtype('bool')))
pres_ctxt.uom = 'unknown'
pdict.add_context(pres_ctxt)
return pdict
class ctd_L0_all(TransformDataProcess):
"""Model for a TransformDataProcess
"""
incoming_stream_def = SBE37_CDM_stream_definition()
def __init__(self):
super(ctd_L0_all, self).__init__()
# Make the stream definitions of the transform class attributes
#outgoing_stream_pressure = L0_pressure_stream_definition()
#outgoing_stream_temperature = L0_temperature_stream_definition()
#outgoing_stream_conductivity = L0_conductivity_stream_definition()
### Taxonomies are defined before hand out of band... somehow.
# pres = TaxyTool()
# pres.add_taxonomy_set('pres','long name for pres')
# pres.add_taxonomy_set('lat','long name for latitude')
# pres.add_taxonomy_set('lon','long name for longitude')
# pres.add_taxonomy_set('height','long name for height')
# pres.add_taxonomy_set('time','long name for time')
# # This is an example of using groups it is not a normative statement about how to use groups
# pres.add_taxonomy_set('coordinates','This group contains coordinates...')
# pres.add_taxonomy_set('data','This group contains data...')
#
# temp = TaxyTool()
# temp.add_taxonomy_set('temp','long name for temp')
# temp.add_taxonomy_set('lat','long name for latitude')
# temp.add_taxonomy_set('lon','long name for longitude')
# temp.add_taxonomy_set('height','long name for height')
# temp.add_taxonomy_set('time','long name for time')
# # This is an example of using groups it is not a normative statement about how to use groups
# temp.add_taxonomy_set('coordinates','This group contains coordinates...')
# temp.add_taxonomy_set('data','This group contains data...')
#
# coord = TaxyTool()
# coord.add_taxonomy_set('cond','long name for cond')
# coord.add_taxonomy_set('lat','long name for latitude')
# coord.add_taxonomy_set('lon','long name for longitude')
# coord.add_taxonomy_set('height','long name for height')
# coord.add_taxonomy_set('time','long name for time')
# # This is an example of using groups it is not a normative statement about how to use groups
# coord.add_taxonomy_set('coordinates','This group contains coordinates...')
# coord.add_taxonomy_set('data','This group contains data...')
### Parameter dictionaries
self.defining_parameter_dictionary()
self.publisher = Publisher(to_name=NameTrio(get_sys_name(), str(uuid.uuid4())[0:6]))
def defining_parameter_dictionary(self):
# Define the parameter context objects
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
height_ctxt = ParameterContext('height', param_type=QuantityType(value_encoding=np.float32))
height_ctxt.reference_frame = AxisTypeEnum.HEIGHT
height_ctxt.uom = 'meters'
height_ctxt.fill_value = 0e0
pres_ctxt = ParameterContext('pres', param_type=QuantityType(value_encoding=np.float32))
pres_ctxt.uom = 'degree_Celsius'
pres_ctxt.fill_value = 0e0
temp_ctxt = ParameterContext('temp', param_type=QuantityType(value_encoding=np.float32))
temp_ctxt.uom = 'degree_Celsius'
temp_ctxt.fill_value = 0e0
cond_ctxt = ParameterContext('cond', param_type=QuantityType(value_encoding=np.float32))
cond_ctxt.uom = 'unknown'
cond_ctxt.fill_value = 0e0
data_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=np.int8))
data_ctxt.uom = 'byte'
data_ctxt.fill_value = 0x0
# Define the parameter dictionary objects
self.pres = ParameterDictionary()
self.pres.add_context(t_ctxt)
self.pres.add_context(lat_ctxt)
self.pres.add_context(lon_ctxt)
self.pres.add_context(height_ctxt)
self.pres.add_context(pres_ctxt)
self.pres.add_context(data_ctxt)
self.temp = ParameterDictionary()
self.temp.add_context(t_ctxt)
self.temp.add_context(lat_ctxt)
self.temp.add_context(lon_ctxt)
self.temp.add_context(height_ctxt)
self.temp.add_context(temp_ctxt)
self.temp.add_context(data_ctxt)
self.cond = ParameterDictionary()
self.cond.add_context(t_ctxt)
self.cond.add_context(lat_ctxt)
self.cond.add_context(lon_ctxt)
self.cond.add_context(height_ctxt)
self.cond.add_context(cond_ctxt)
self.cond.add_context(data_ctxt)
def process(self, packet):
"""Processes incoming data!!!!
"""
# Use the PointSupplementStreamParser to pull data from a granule
#psd = PointSupplementStreamParser(stream_definition=self.incoming_stream_def, stream_granule=packet)
rdt = RecordDictionaryTool.load_from_granule(packet)
#todo: use only flat dicts for now, may change later...
# rdt0 = rdt['coordinates']
# rdt1 = rdt['data']
conductivity = get_safe(rdt, 'cond') #psd.get_values('conductivity')
pressure = get_safe(rdt, 'pres') #psd.get_values('pressure')
temperature = get_safe(rdt, 'temp') #psd.get_values('temperature')
longitude = get_safe(rdt, 'lon') # psd.get_values('longitude')
latitude = get_safe(rdt, 'lat') #psd.get_values('latitude')
time = get_safe(rdt, 'time') # psd.get_values('time')
height = get_safe(rdt, 'height') # psd.get_values('time')
log.warn('Got conductivity: %s' % str(conductivity))
log.warn('Got pressure: %s' % str(pressure))
log.warn('Got temperature: %s' % str(temperature))
g = self._build_granule_settings(self.cond, 'cond', conductivity, time, latitude, longitude, height)
# publish a granule
self.cond_publisher = self.publisher
self.cond_publisher.publish(g)
g = self._build_granule_settings(self.temp, 'temp', temperature, time, latitude, longitude, height)
# publish a granule
self.temp_publisher = self.publisher
self.temp_publisher.publish(g)
g = self._build_granule_settings(self.pres, 'pres', pressure, time, latitude, longitude, height)
# publish a granule
self.pres_publisher = self.publisher
self.pres_publisher.publish(g)
def _build_granule_settings(self, param_dictionary=None, field_name='', value=None, time=None, latitude=None, longitude=None, height=None):
root_rdt = RecordDictionaryTool(param_dictionary=param_dictionary)
#data_rdt = RecordDictionaryTool(taxonomy=taxonomy)
root_rdt[field_name] = value
#coor_rdt = RecordDictionaryTool(taxonomy=taxonomy)
root_rdt['time'] = time
root_rdt['lat'] = latitude
root_rdt['lon'] = longitude
root_rdt['height'] = height
#todo: use only flat dicts for now, may change later...
# root_rdt['coordinates'] = coor_rdt
# root_rdt['data'] = data_rdt
log.debug("ctd_L0_all:_build_granule_settings: logging published Record Dictionary:\n %s", str(root_rdt.pretty_print()))
return build_granule(data_producer_id='ctd_L0', param_dictionary=param_dictionary, record_dictionary=root_rdt)
def create_parameters(cls):
'''
WARNING: This method is a wrapper intended only for tests, it should not be used in production code.
It probably will not align to most datasets.
'''
pdict = ParameterDictionary()
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.axis = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
pdict.add_context(t_ctxt)
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.axis = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.axis = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
pdict.add_context(lon_ctxt)
temp_ctxt = ParameterContext('temp', param_type=QuantityType(value_encoding=np.float32))
temp_ctxt.uom = 'degree_Celsius'
temp_ctxt.fill_value = 0e0
pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext('conductivity', param_type=QuantityType(value_encoding=np.float32))
cond_ctxt.uom = 'unknown'
cond_ctxt.fill_value = 0e0
pdict.add_context(cond_ctxt)
data_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=np.int8))
data_ctxt.uom = 'byte'
data_ctxt.fill_value = 0x0
pdict.add_context(data_ctxt)
pres_ctxt = ParameterContext('pressure', param_type=QuantityType(value_encoding=np.float32))
pres_ctxt.uom = 'Pascal'
pres_ctxt.fill_value = 0x0
pdict.add_context(pres_ctxt)
sal_ctxt = ParameterContext('salinity', param_type=QuantityType(value_encoding=np.float32))
sal_ctxt.uom = 'PSU'
sal_ctxt.fill_value = 0x0
pdict.add_context(sal_ctxt)
dens_ctxt = ParameterContext('density', param_type=QuantityType(value_encoding=np.float32))
dens_ctxt.uom = 'unknown'
dens_ctxt.fill_value = 0x0
pdict.add_context(dens_ctxt)
return pdict
def create_parameters(cls):
'''
WARNING: This method is a wrapper intended only for tests, it should not be used in production code.
It probably will not align to most datasets.
'''
pdict = ParameterDictionary()
t_ctxt = ParameterContext(
'time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.axis = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
pdict.add_context(t_ctxt)
lat_ctxt = ParameterContext(
'lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.axis = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext(
'lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.axis = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
pdict.add_context(lon_ctxt)
temp_ctxt = ParameterContext(
'temp', param_type=QuantityType(value_encoding=np.float32))
temp_ctxt.uom = 'degree_Celsius'
temp_ctxt.fill_value = 0e0
pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext(
'conductivity', param_type=QuantityType(value_encoding=np.float32))
cond_ctxt.uom = 'unknown'
cond_ctxt.fill_value = 0e0
pdict.add_context(cond_ctxt)
data_ctxt = ParameterContext(
'data', param_type=QuantityType(value_encoding=np.int8))
data_ctxt.uom = 'byte'
data_ctxt.fill_value = 0x0
pdict.add_context(data_ctxt)
pres_ctxt = ParameterContext(
'pressure', param_type=QuantityType(value_encoding=np.float32))
pres_ctxt.uom = 'Pascal'
pres_ctxt.fill_value = 0x0
pdict.add_context(pres_ctxt)
sal_ctxt = ParameterContext(
'salinity', param_type=QuantityType(value_encoding=np.float32))
sal_ctxt.uom = 'PSU'
sal_ctxt.fill_value = 0x0
pdict.add_context(sal_ctxt)
dens_ctxt = ParameterContext(
'density', param_type=QuantityType(value_encoding=np.float32))
dens_ctxt.uom = 'unknown'
dens_ctxt.fill_value = 0x0
pdict.add_context(dens_ctxt)
return pdict
def create_parameters(cls):
pdict = ParameterDictionary()
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
pdict.add_context(t_ctxt)
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
pdict.add_context(lon_ctxt)
depth_ctxt = ParameterContext('depth', param_type=QuantityType(value_encoding=np.float32))
depth_ctxt.reference_frame = AxisTypeEnum.HEIGHT
depth_ctxt.uom = 'meters'
depth_ctxt.fill_value = 0e0
pdict.add_context(depth_ctxt)
temp_ctxt = ParameterContext('temp', param_type=QuantityType(value_encoding=np.float32))
temp_ctxt.uom = 'degree_Celsius'
temp_ctxt.fill_value = 0e0
pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext('conductivity', param_type=QuantityType(value_encoding=np.float32))
cond_ctxt.uom = 'unknown'
cond_ctxt.fill_value = 0e0
pdict.add_context(cond_ctxt)
data_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=np.int8))
data_ctxt.uom = 'byte'
data_ctxt.fill_value = 0x0
pdict.add_context(data_ctxt)
return pdict
def _create_input_param_dict_for_test(self, parameter_dict_name = ''):
pdict = ParameterDictionary()
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=numpy.dtype('float64')))
t_ctxt.axis = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 01-01-1900'
pdict.add_context(t_ctxt)
cond_ctxt = ParameterContext('conductivity', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
cond_ctxt.uom = 'Siemens_per_meter'
pdict.add_context(cond_ctxt)
pres_ctxt = ParameterContext('pressure', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
pres_ctxt.uom = 'Pascal'
pdict.add_context(pres_ctxt)
if parameter_dict_name == 'input_param_for_L0':
temp_ctxt = ParameterContext('temperature', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
else:
temp_ctxt = ParameterContext('temp', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_kelvin'
pdict.add_context(temp_ctxt)
dens_ctxt = ParameterContext('density', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
dens_ctxt.uom = 'g/m'
pdict.add_context(dens_ctxt)
sal_ctxt = ParameterContext('salinity', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
sal_ctxt.uom = 'PSU'
pdict.add_context(sal_ctxt)
#create temp streamdef so the data product can create the stream
pc_list = []
for pc_k, pc in pdict.iteritems():
ctxt_id = self.dataset_management.create_parameter_context(pc_k, pc[1].dump())
pc_list.append(ctxt_id)
if parameter_dict_name == 'input_param_for_L0':
self.addCleanup(self.dataset_management.delete_parameter_context,ctxt_id)
elif pc[1].name == 'temp':
self.addCleanup(self.dataset_management.delete_parameter_context,ctxt_id)
pdict_id = self.dataset_management.create_parameter_dictionary(parameter_dict_name, pc_list)
self.addCleanup(self.dataset_management.delete_parameter_dictionary, pdict_id)
return pdict_id
class CTDL1TemperatureTransform(TransformFunction):
''' A basic transform that receives input through a subscription,
parses the input from a CTD, extracts the temperature vaule and scales it accroding to
the defined algorithm. If the transform
has an output_stream it will publish the output on the output stream.
'''
# Make the stream definitions of the transform class attributes... best available option I can think of?
incoming_stream_def = L0_temperature_stream_definition()
outgoing_stream_def = L1_temperature_stream_definition()
def __init__(self):
### Parameter dictionaries
self.defining_parameter_dictionary()
def defining_parameter_dictionary(self):
# Define the parameter context objects
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
height_ctxt = ParameterContext('height', param_type=QuantityType(value_encoding=np.float32))
height_ctxt.reference_frame = AxisTypeEnum.HEIGHT
height_ctxt.uom = 'meters'
height_ctxt.fill_value = 0e0
temp_ctxt = ParameterContext('temp', param_type=QuantityType(value_encoding=np.float32))
temp_ctxt.uom = 'degree_Celsius'
temp_ctxt.fill_value = 0e0
data_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=np.int8))
data_ctxt.uom = 'byte'
data_ctxt.fill_value = 0x0
# Define the parameter dictionary objects
self.temp = ParameterDictionary()
self.temp.add_context(t_ctxt)
self.temp.add_context(lat_ctxt)
self.temp.add_context(lon_ctxt)
self.temp.add_context(height_ctxt)
self.temp.add_context(temp_ctxt)
self.temp.add_context(data_ctxt)
def execute(self, granule):
"""Processes incoming data!!!!
"""
rdt = RecordDictionaryTool.load_from_granule(granule)
#todo: use only flat dicts for now, may change later...
# rdt0 = rdt['coordinates']
# rdt1 = rdt['data']
temperature = get_safe(rdt, 'temp')
longitude = get_safe(rdt, 'lon')
latitude = get_safe(rdt, 'lat')
time = get_safe(rdt, 'time')
height = get_safe(rdt, 'height')
log.warn('Got temperature: %s' % str(temperature))
# The L1 temperature data product algorithm takes the L0 temperature data product and converts it into Celcius.
# Once the hexadecimal string is converted to decimal, only scaling (dividing by a factor and adding an offset) is
# required to produce the correct decimal representation of the data in Celsius.
# The scaling function differs by CTD make/model as described below.
# SBE 37IM, Output Format 0
# 1) Standard conversion from 5-character hex string (Thex) to decimal (tdec)
# 2) Scaling: T [C] = (tdec / 10,000) - 10
root_rdt = RecordDictionaryTool(param_dictionary=self.temp)
#todo: use only flat dicts for now, may change later...
# data_rdt = RecordDictionaryTool(taxonomy=self.tx)
# coord_rdt = RecordDictionaryTool(taxonomy=self.tx)
scaled_temperature = temperature
for i in xrange(len(temperature)):
scaled_temperature[i] = ( temperature[i] / 10000.0) - 10
root_rdt['temp'] = scaled_temperature
root_rdt['time'] = time
root_rdt['lat'] = latitude
root_rdt['lon'] = longitude
root_rdt['height'] = height
#todo: use only flat dicts for now, may change later...
# root_rdt['coordinates'] = coord_rdt
# root_rdt['data'] = data_rdt
return build_granule(data_producer_id='ctd_L1_temperature', param_dictionary=self.temp, record_dictionary=root_rdt)
class SimplexCoverage(AbstractCoverage):
"""
A concrete implementation of AbstractCoverage consisting of 2 domains (temporal and spatial)
and a collection of parameters associated with one or both of the domains. Each parameter is defined by a
ParameterContext object (provided via the ParameterDictionary) and has content represented by a concrete implementation
of the AbstractParameterValue class.
"""
def __init__(self, root_dir, persistence_guid, name=None, parameter_dictionary=None, temporal_domain=None, spatial_domain=None, in_memory_storage=False, bricking_scheme=None):
"""
Constructor for SimplexCoverage
@param root_dir The root directory for storage of this coverage
@param persistence_guid The persistence uuid for this coverage
@param name The name of the coverage
@param parameter_dictionary a ParameterDictionary object expected to contain one or more valid ParameterContext objects
@param spatial_domain a concrete instance of AbstractDomain for the spatial domain component
@param temporal_domain a concrete instance of AbstractDomain for the temporal domain component
"""
# Make sure root_dir and persistence_guid are both not None and are strings
if not isinstance(root_dir, str) or not isinstance(persistence_guid, str):
raise SystemError('\'root_dir\' and \'persistence_guid\' must be instances of str')
pth=os.path.join(root_dir, persistence_guid)
def _doload(self):
# Make sure the coverage directory exists
if not os.path.exists(pth):
raise SystemError('Cannot find specified coverage: {0}'.format(pth))
# All appears well - load it up!
self._persistence_layer = PersistenceLayer(root_dir, persistence_guid)
self.name = self._persistence_layer.name
self.spatial_domain = self._persistence_layer.sdom
self.temporal_domain = self._persistence_layer.tdom
self._range_dictionary = ParameterDictionary()
self._range_value = RangeValues()
self._bricking_scheme = self._persistence_layer.global_bricking_scheme
self._temporal_param_name = self._persistence_layer.temporal_param_name
self._in_memory_storage = False
from coverage_model.persistence import PersistedStorage
for parameter_name in self._persistence_layer.parameter_metadata.keys():
md = self._persistence_layer.parameter_metadata[parameter_name]
pc = md.parameter_context
self._range_dictionary.add_context(pc)
s = PersistedStorage(md, self._persistence_layer.brick_dispatcher, dtype=pc.param_type.value_encoding, fill_value=pc.param_type.fill_value)
self._range_value[parameter_name] = get_value_class(param_type=pc.param_type, domain_set=pc.dom, storage=s)
AbstractCoverage.__init__(self)
if name is None or parameter_dictionary is None:
# This appears to be a load
_doload(self)
else:
# This appears to be a new coverage
# Make sure name and parameter_dictionary are not None
if name is None or parameter_dictionary is None:
raise SystemError('\'name\' and \'parameter_dictionary\' cannot be None')
# Make sure the specified root_dir exists
if not in_memory_storage and not os.path.exists(root_dir):
raise SystemError('Cannot find specified \'root_dir\': {0}'.format(root_dir))
# If the coverage directory exists, load it instead!!
if os.path.exists(pth):
log.warn('The specified coverage already exists - performing load of \'{0}\''.format(pth))
_doload(self)
return
self.name = name
self.spatial_domain = deepcopy(spatial_domain)
self.temporal_domain = deepcopy(temporal_domain) or GridDomain(GridShape('temporal',[0]), CRS.standard_temporal(), MutabilityEnum.EXTENSIBLE)
if not isinstance(parameter_dictionary, ParameterDictionary):
raise TypeError('\'parameter_dictionary\' must be of type ParameterDictionary')
self._range_dictionary = ParameterDictionary()
self._range_value = RangeValues()
self._bricking_scheme = bricking_scheme or {'brick_size':10,'chunk_size':5}
self._temporal_param_name = None
self._in_memory_storage = in_memory_storage
if self._in_memory_storage:
self._persistence_layer = InMemoryPersistenceLayer()
else:
self._persistence_layer = PersistenceLayer(root_dir, persistence_guid, name=name, tdom=temporal_domain, sdom=spatial_domain, bricking_scheme=self._bricking_scheme)
for o, pc in parameter_dictionary.itervalues():
self._append_parameter(pc)
@classmethod
def _fromdict(cls, cmdict, arg_masks=None):
return super(SimplexCoverage, cls)._fromdict(cmdict, {'parameter_dictionary':'_range_dictionary'})
@property
def parameter_dictionary(self):
return deepcopy(self._range_dictionary)
@property
def persistence_guid(self):
if isinstance(self._persistence_layer, InMemoryPersistenceLayer):
return None
else:
return self._persistence_layer.guid
def append_parameter(self, parameter_context):
"""
Append a ParameterContext to the coverage
@deprecated use a ParameterDictionary during construction of the coverage
"""
log.warn('SimplexCoverage.append_parameter() is deprecated: use a ParameterDictionary during construction of the coverage')
self._append_parameter(parameter_context)
def _append_parameter(self, parameter_context):
"""
Appends a ParameterContext object to the internal set for this coverage.
A <b>deep copy</b> of the supplied ParameterContext is added to self._range_dictionary. An AbstractParameterValue of the type
indicated by ParameterContext.param_type is added to self._range_value. If the ParameterContext indicates that
the parameter is a coordinate parameter, it is associated with the indicated axis of the appropriate CRS.
@param parameter_context The ParameterContext to append to the coverage <b>as a copy</b>
@throws StandardError If the ParameterContext.axis indicates that it is temporal and a temporal parameter
already exists in the coverage
"""
if not isinstance(parameter_context, ParameterContext):
raise TypeError('\'parameter_context\' must be an instance of ParameterContext')
# Create a deep copy of the ParameterContext
pcontext = deepcopy(parameter_context)
pname = pcontext.name
no_sdom = self.spatial_domain is None
## Determine the correct array shape
# Get the parameter variability; assign to VariabilityEnum.NONE if None
pv=pcontext.variability or VariabilityEnum.NONE
if no_sdom and pv in (VariabilityEnum.SPATIAL, VariabilityEnum.BOTH):
log.warn('Provided \'parameter_context\' indicates Spatial variability, but coverage has no Spatial Domain')
if pv == VariabilityEnum.TEMPORAL: # Only varies in the Temporal Domain
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, None)
elif pv == VariabilityEnum.SPATIAL: # Only varies in the Spatial Domain
pcontext.dom = DomainSet(None, self.spatial_domain.shape.extents)
elif pv == VariabilityEnum.BOTH: # Varies in both domains
# If the Spatial Domain is only a single point on a 0d Topology, the parameter's shape is that of the Temporal Domain only
if no_sdom or (len(self.spatial_domain.shape.extents) == 1 and self.spatial_domain.shape.extents[0] == 0):
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, None)
else:
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, self.spatial_domain.shape.extents)
elif pv == VariabilityEnum.NONE: # No variance; constant
# CBM TODO: Not sure we can have this constraint - precludes situations like a TextType with Variablity==None...
# # This is a constant - if the ParameterContext is not a ConstantType, make it one with the default 'x' expr
# if not isinstance(pcontext.param_type, ConstantType):
# pcontext.param_type = ConstantType(pcontext.param_type)
# The domain is the total domain - same value everywhere!!
# If the Spatial Domain is only a single point on a 0d Topology, the parameter's shape is that of the Temporal Domain only
if no_sdom or (len(self.spatial_domain.shape.extents) == 1 and self.spatial_domain.shape.extents[0] == 0):
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, None)
else:
pcontext.dom = DomainSet(self.temporal_domain.shape.extents, self.spatial_domain.shape.extents)
else:
# Should never get here...but...
raise SystemError('Must define the variability of the ParameterContext: a member of VariabilityEnum')
# Assign the pname to the CRS (if applicable) and select the appropriate domain (default is the spatial_domain)
dom = self.spatial_domain
is_tparam = False
if not pcontext.reference_frame is None and AxisTypeEnum.is_member(pcontext.reference_frame, AxisTypeEnum.TIME):
if self._temporal_param_name is None:
self._temporal_param_name = pname
is_tparam = True
else:
raise StandardError("temporal_parameter already defined.")
dom = self.temporal_domain
dom.crs.axes[pcontext.reference_frame] = pcontext.name
elif not no_sdom and (pcontext.reference_frame in self.spatial_domain.crs.axes):
dom.crs.axes[pcontext.reference_frame] = pcontext.name
self._range_dictionary.add_context(pcontext)
s = self._persistence_layer.init_parameter(pcontext, self._bricking_scheme, is_temporal_param=is_tparam)
self._range_value[pname] = get_value_class(param_type=pcontext.param_type, domain_set=pcontext.dom, storage=s)
def get_parameter(self, param_name):
"""
Get a Parameter object by name
The Parameter object contains the ParameterContext and AbstractParameterValue associated with the param_name
@param param_name The local name of the parameter to return
@returns A Parameter object containing the context and value for the specified parameter
@throws KeyError The coverage does not contain a parameter with name 'param_name'
"""
if param_name in self._range_dictionary:
p = Parameter(self._range_dictionary.get_context(param_name), self._range_value[param_name].shape, self._range_value[param_name])
return p
else:
raise KeyError('Coverage does not contain parameter \'{0}\''.format(param_name))
def list_parameters(self, coords_only=False, data_only=False):
"""
List the names of the parameters contained in the coverage
@param coords_only List only the coordinate parameters
@param data_only List only the data parameters (non-coordinate) - superseded by coords_only
@returns A list of parameter names
"""
if coords_only:
lst=[x for x, v in self._range_dictionary.iteritems() if v[1].is_coordinate]
elif data_only:
lst=[x for x, v in self._range_dictionary.iteritems() if not v[1].is_coordinate]
else:
lst=[x for x in self._range_dictionary]
lst.sort()
return lst
def insert_timesteps(self, count, origin=None):
"""
Insert count # of timesteps beginning at the origin
The specified # of timesteps are inserted into the temporal value array at the indicated origin. This also
expands the temporal dimension of the AbstractParameterValue for each parameters
@param count The number of timesteps to insert
@param origin The starting location, from which to begin the insertion
"""
# Get the current shape of the temporal_dimension
shp = self.temporal_domain.shape
# If not provided, set the origin to the end of the array
if origin is None or not isinstance(origin, int):
origin = shp.extents[0]
# Expand the shape of the temporal_domain - following works if extents is a list or tuple
shp.extents = (shp.extents[0]+count,)+tuple(shp.extents[1:])
# Expand the temporal dimension of each of the parameters - the parameter determines how to apply the change
for n in self._range_dictionary:
pc = self._range_dictionary.get_context(n)
# Update the dom of the parameter_context
if pc.dom.tdom is not None:
pc.dom.tdom = self.temporal_domain.shape.extents
self._persistence_layer.expand_domain(pc, tdom=self.temporal_domain)
self._range_value[n].expand_content(VariabilityEnum.TEMPORAL, origin, count)
def set_time_values(self, value, tdoa):
"""
Convenience method for setting time values
@param value The value to set
@param tdoa The temporal DomainOfApplication; default to full Domain
"""
return self.set_parameter_values(self._temporal_param_name, value, tdoa, None)
def get_time_values(self, tdoa=None, return_value=None):
"""
Convenience method for retrieving time values
Delegates to get_parameter_values, supplying the temporal parameter name and sdoa == None
@param tdoa The temporal DomainOfApplication; default to full Domain
@param return_value If supplied, filled with response value
"""
return self.get_parameter_values(self._temporal_param_name, tdoa, None, return_value)
@property
def num_timesteps(self):
"""
The current number of timesteps
"""
return self.temporal_domain.shape.extents[0]
def set_parameter_values(self, param_name, value, tdoa=None, sdoa=None):
"""
Assign value to the specified parameter
Assigns the value to param_name within the coverage. Temporal and spatial DomainOfApplication objects can be
applied to constrain the assignment. See DomainOfApplication for details
@param param_name The name of the parameter
@param value The value to set
@param tdoa The temporal DomainOfApplication
@param sdoa The spatial DomainOfApplication
@throws KeyError The coverage does not contain a parameter with name 'param_name'
"""
if not param_name in self._range_value:
raise KeyError('Parameter \'{0}\' not found in coverage_model'.format(param_name))
slice_ = []
tdoa = get_valid_DomainOfApplication(tdoa, self.temporal_domain.shape.extents)
log.debug('Temporal doa: %s', tdoa.slices)
slice_.extend(tdoa.slices)
if self.spatial_domain is not None:
sdoa = get_valid_DomainOfApplication(sdoa, self.spatial_domain.shape.extents)
log.debug('Spatial doa: %s', sdoa.slices)
slice_.extend(sdoa.slices)
log.debug('Setting slice: %s', slice_)
self._range_value[param_name][slice_] = value
def get_parameter_values(self, param_name, tdoa=None, sdoa=None, return_value=None):
"""
Retrieve the value for a parameter
Returns the value from param_name. Temporal and spatial DomainOfApplication objects can be used to
constrain the response. See DomainOfApplication for details.
@param param_name The name of the parameter
@param tdoa The temporal DomainOfApplication
@param sdoa The spatial DomainOfApplication
@param return_value If supplied, filled with response value - currently via OVERWRITE
@throws KeyError The coverage does not contain a parameter with name 'param_name'
"""
if not param_name in self._range_value:
raise KeyError('Parameter \'{0}\' not found in coverage'.format(param_name))
if return_value is not None:
log.warn('Provided \'return_value\' will be OVERWRITTEN')
slice_ = []
tdoa = get_valid_DomainOfApplication(tdoa, self.temporal_domain.shape.extents)
log.debug('Temporal doa: %s', tdoa.slices)
slice_.extend(tdoa.slices)
if self.spatial_domain is not None:
sdoa = get_valid_DomainOfApplication(sdoa, self.spatial_domain.shape.extents)
log.debug('Spatial doa: %s', sdoa.slices)
slice_.extend(sdoa.slices)
log.debug('Getting slice: %s', slice_)
return_value = self._range_value[param_name][slice_]
return return_value
def get_parameter_context(self, param_name):
"""
Retrieve the ParameterContext object for the specified parameter
@param param_name The name of the parameter for which to retrieve context
@returns A ParameterContext object
@throws KeyError The coverage does not contain a parameter with name 'param_name'
"""
if not param_name in self._range_dictionary:
raise KeyError('Parameter \'{0}\' not found in coverage'.format(param_name))
return self._range_dictionary.get_context(param_name)
@property
def info(self):
"""
Returns a detailed string representation of the coverage contents
@returns string of coverage contents
"""
lst = []
indent = ' '
lst.append('ID: {0}'.format(self._id))
lst.append('Name: {0}'.format(self.name))
lst.append('Temporal Domain:\n{0}'.format(self.temporal_domain.__str__(indent*2)))
lst.append('Spatial Domain:\n{0}'.format(self.spatial_domain.__str__(indent*2)))
lst.append('Parameters:')
for x in self._range_value:
lst.append('{0}{1} {2}\n{3}'.format(indent*2,x,self._range_value[x].shape,self._range_dictionary.get_context(x).__str__(indent*4)))
return '\n'.join(lst)
def __str__(self):
lst = []
indent = ' '
lst.append('ID: {0}'.format(self._id))
lst.append('Name: {0}'.format(self.name))
lst.append('TemporalDomain: Shape=>{0} Axes=>{1}'.format(self.temporal_domain.shape.extents, self.temporal_domain.crs.axes))
lst.append('SpatialDomain: Shape=>{0} Axes=>{1}'.format(self.spatial_domain.shape.extents, self.spatial_domain.crs.axes))
lst.append('Coordinate Parameters: {0}'.format(self.list_parameters(coords_only=True)))
lst.append('Data Parameters: {0}'.format(self.list_parameters(coords_only=False, data_only=True)))
return '\n'.join(lst)
class CTDL1PressureTransform(TransformFunction):
''' A basic transform that receives input through a subscription,
parses the input from a CTD, extracts the pressure vaule and scales it accroding to
the defined algorithm. If the transform
has an output_stream it will publish the output on the output stream.
'''
# Make the stream definitions of the transform class attributes... best available option I can think of?
incoming_stream_def = L0_pressure_stream_definition()
outgoing_stream_def = L1_pressure_stream_definition()
def __init__(self):
### Parameter dictionaries
self.defining_parameter_dictionary()
def defining_parameter_dictionary(self):
# Define the parameter context objects
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
height_ctxt = ParameterContext('height', param_type=QuantityType(value_encoding=np.float32))
height_ctxt.reference_frame = AxisTypeEnum.HEIGHT
height_ctxt.uom = 'meters'
height_ctxt.fill_value = 0e0
pres_ctxt = ParameterContext('pres', param_type=QuantityType(value_encoding=np.float32))
pres_ctxt.uom = 'degree_Celsius'
pres_ctxt.fill_value = 0e0
data_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=np.int8))
data_ctxt.uom = 'byte'
data_ctxt.fill_value = 0x0
# Define the parameter dictionary objects
self.pres = ParameterDictionary()
self.pres.add_context(t_ctxt)
self.pres.add_context(lat_ctxt)
self.pres.add_context(lon_ctxt)
self.pres.add_context(height_ctxt)
self.pres.add_context(pres_ctxt)
self.pres.add_context(data_ctxt)
def execute(self, granule):
"""Processes incoming data!!!!
"""
rdt = RecordDictionaryTool.load_from_granule(granule)
#todo: use only flat dicts for now, may change later...
# rdt0 = rdt['coordinates']
# rdt1 = rdt['data']
pressure = get_safe(rdt, 'pres') #psd.get_values('conductivity')
longitude = get_safe(rdt, 'lon') # psd.get_values('longitude')
latitude = get_safe(rdt, 'lat') #psd.get_values('latitude')
time = get_safe(rdt, 'time') # psd.get_values('time')
height = get_safe(rdt, 'height') # psd.get_values('time')
log.warn('Got pressure: %s' % str(pressure))
# L1
# 1) The algorithm input is the L0 pressure data product (p_hex) and, in the case of the SBE 37IM, the pressure range (P_rng) from metadata.
# 2) Convert the hexadecimal string to a decimal string
# 3) For the SBE 37IM only, convert the pressure range (P_rng) from psia to dbar SBE 37IM
# Convert P_rng (input from metadata) from psia to dbar
# 4) Perform scaling operation
# SBE 37IM
# L1 pressure data product (in dbar):
# Use the constructor to put data into a granule
psc = PointSupplementConstructor(point_definition=self.outgoing_stream_def, stream_id=self.streams['output'])
### Assumes the config argument for output streams is known and there is only one 'output'.
### the stream id is part of the metadata which much go in each stream granule - this is awkward to do at the
### application level like this!
scaled_pressure = pressure
for i in xrange(len(pressure)):
#todo: get pressure range from metadata (if present) and include in calc
scaled_pressure[i] = ( pressure[i])
root_rdt = RecordDictionaryTool(taxonomy=self.tx)
#todo: use only flat dicts for now, may change later...
# data_rdt = RecordDictionaryTool(taxonomy=self.tx)
# coord_rdt = RecordDictionaryTool(taxonomy=self.tx)
root_rdt['pres'] = scaled_pressure
root_rdt['time'] = time
root_rdt['lat'] = latitude
root_rdt['lon'] = longitude
root_rdt['height'] = height
# root_rdt['coordinates'] = coord_rdt
# root_rdt['data'] = data_rdt
return build_granule(data_producer_id='ctd_L1_pressure', taxonomy=self.tx, record_dictionary=root_rdt)
return psc.close_stream_granule()
def _create_parameter_dictionary(self):
pdict = ParameterDictionary()
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lat_ctxt.axis = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lon_ctxt.axis = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
pdict.add_context(lon_ctxt)
temp_ctxt = ParameterContext('water_temperature', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
temp_ctxt = ParameterContext('water_temperature_bottom', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
temp_ctxt = ParameterContext('water_temperature_middle', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
temp_ctxt = ParameterContext('z', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'meters'
pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext('streamflow', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
cond_ctxt.uom = 'unknown'
pdict.add_context(cond_ctxt)
pres_ctxt = ParameterContext('specific_conductance', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
pres_ctxt.uom = 'unknown'
pdict.add_context(pres_ctxt)
pres_ctxt = ParameterContext('data_qualifier', param_type=QuantityType(value_encoding=numpy.dtype('bool')))
pres_ctxt.uom = 'unknown'
pdict.add_context(pres_ctxt)
return pdict
def get_param_dict(self):
pdict = ParameterDictionary()
cond_ctxt = ParameterContext(
'conductivity', param_type=QuantityType(value_encoding=np.float64))
cond_ctxt.uom = 'unknown'
cond_ctxt.fill_value = 0e0
pdict.add_context(cond_ctxt)
pres_ctxt = ParameterContext(
'pressure', param_type=QuantityType(value_encoding=np.float64))
pres_ctxt.uom = 'unknown'
pres_ctxt.fill_value = 0x0
pdict.add_context(pres_ctxt)
temp_ctxt = ParameterContext(
'temperature', param_type=QuantityType(value_encoding=np.float64))
temp_ctxt.uom = 'unknown'
temp_ctxt.fill_value = 0x0
pdict.add_context(temp_ctxt)
oxy_ctxt = ParameterContext(
'oxygen', param_type=QuantityType(value_encoding=np.float64))
oxy_ctxt.uom = 'unknown'
oxy_ctxt.fill_value = 0x0
pdict.add_context(oxy_ctxt)
internal_ts_ctxt = ParameterContext(
name='internal_timestamp',
param_type=QuantityType(value_encoding=np.float64))
internal_ts_ctxt._derived_from_name = 'time'
internal_ts_ctxt.uom = 'seconds'
internal_ts_ctxt.fill_value = -1
pdict.add_context(internal_ts_ctxt, is_temporal=True)
driver_ts_ctxt = ParameterContext(
name='driver_timestamp',
param_type=QuantityType(value_encoding=np.float64))
driver_ts_ctxt._derived_from_name = 'time'
driver_ts_ctxt.uom = 'seconds'
driver_ts_ctxt.fill_value = -1
pdict.add_context(driver_ts_ctxt)
return pdict
def sync_rdt_with_coverage(self,
coverage=None,
tdoa=None,
start_time=None,
end_time=None,
stride_time=None,
parameters=None):
'''
Builds a granule based on the coverage
'''
if coverage is None:
coverage = self.coverage
slice_ = slice(None) # Defaults to all values
if tdoa is not None and isinstance(tdoa, slice):
slice_ = tdoa
elif stride_time is not None:
validate_is_instance(start_time, Number,
'start_time must be a number for striding.')
validate_is_instance(end_time, Number,
'end_time must be a number for striding.')
validate_is_instance(stride_time, Number,
'stride_time must be a number for striding.')
ugly_range = np.arange(start_time, end_time, stride_time)
idx_values = [
TimeUtils.get_relative_time(coverage, i) for i in ugly_range
]
slice_ = [idx_values]
elif not (start_time is None and end_time is None):
time_var = coverage._temporal_param_name
uom = coverage.get_parameter_context(time_var).uom
if start_time is not None:
start_units = TimeUtils.ts_to_units(uom, start_time)
log.info('Units: %s', start_units)
start_idx = TimeUtils.get_relative_time(coverage, start_units)
log.info('Start Index: %s', start_idx)
start_time = start_idx
if end_time is not None:
end_units = TimeUtils.ts_to_units(uom, end_time)
log.info('End units: %s', end_units)
end_idx = TimeUtils.get_relative_time(coverage, end_units)
log.info('End index: %s', end_idx)
end_time = end_idx
slice_ = slice(start_time, end_time, stride_time)
log.info('Slice: %s', slice_)
if parameters is not None:
pdict = ParameterDictionary()
params = set(coverage.list_parameters()).intersection(parameters)
for param in params:
pdict.add_context(coverage.get_parameter_context(param))
rdt = RecordDictionaryTool(param_dictionary=pdict)
self.pdict = pdict
else:
rdt = RecordDictionaryTool(
param_dictionary=coverage.parameter_dictionary)
fields = coverage.list_parameters()
if parameters is not None:
fields = set(fields).intersection(parameters)
for d in fields:
rdt[d] = coverage.get_parameter_values(d, tdoa=slice_)
self.rdt = rdt # Sync
class DensityTransform(TransformFunction):
''' A basic transform that receives input through a subscription,
parses the input from a CTD, extracts the conductivity, density and Temperature value and calculates density
according to the defined algorithm. If the transform
has an output_stream it will publish the output on the output stream.
'''
# Make the stream definitions of the transform class attributes... best available option I can think of?
incoming_stream_def = SBE37_CDM_stream_definition()
outgoing_stream_def = L2_density_stream_definition()
def __init__(self):
# ### Taxonomies are defined before hand out of band... somehow.
# tx = TaxyTool()
# tx.add_taxonomy_set('density','long name for density')
# tx.add_taxonomy_set('lat','long name for latitude')
# tx.add_taxonomy_set('lon','long name for longitude')
# tx.add_taxonomy_set('height','long name for height')
# tx.add_taxonomy_set('time','long name for time')
# # This is an example of using groups it is not a normative statement about how to use groups
# tx.add_taxonomy_set('coordinates','This group contains coordinates...')
# tx.add_taxonomy_set('data','This group contains data...')
### Parameter dictionaries
self.defining_parameter_dictionary()
def defining_parameter_dictionary(self):
# Define the parameter context objects
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
height_ctxt = ParameterContext('height', param_type=QuantityType(value_encoding=np.float32))
height_ctxt.reference_frame = AxisTypeEnum.HEIGHT
height_ctxt.uom = 'meters'
height_ctxt.fill_value = 0e0
dens_ctxt = ParameterContext('dens', param_type=QuantityType(value_encoding=np.float32))
dens_ctxt.uom = 'degree_Celsius'
dens_ctxt.fill_value = 0e0
data_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=np.int8))
data_ctxt.uom = 'byte'
data_ctxt.fill_value = 0x0
# Define the parameter dictionary objects
self.dens = ParameterDictionary()
self.dens.add_context(t_ctxt)
self.dens.add_context(lat_ctxt)
self.dens.add_context(lon_ctxt)
self.dens.add_context(height_ctxt)
self.dens.add_context(dens_ctxt)
self.dens.add_context(data_ctxt)
def execute(self, granule):
"""Processes incoming data!!!!
"""
rdt = RecordDictionaryTool.load_from_granule(granule)
#todo: use only flat dicts for now, may change later...
# rdt0 = rdt['coordinates']
# rdt1 = rdt['data']
temperature = get_safe(rdt, 'temp')
conductivity = get_safe(rdt, 'cond')
density = get_safe(rdt, 'dens')
longitude = get_safe(rdt, 'lon')
latitude = get_safe(rdt, 'lat')
time = get_safe(rdt, 'time')
height = get_safe(rdt, 'height')
log.warn('Got conductivity: %s' % str(conductivity))
log.warn('Got density: %s' % str(density))
log.warn('Got temperature: %s' % str(temperature))
sp = SP_from_cndr(r=conductivity/cte.C3515, t=temperature, p=density)
sa = SA_from_SP(sp, density, longitude, latitude)
density = rho(sa, temperature, density)
log.warn('Got density: %s' % str(density))
# Use the constructor to put data into a granule
#psc = PointSupplementConstructor(point_definition=self.outgoing_stream_def, stream_id=self.streams['output'])
### Assumes the config argument for output streams is known and there is only one 'output'.
### the stream id is part of the metadata which much go in each stream granule - this is awkward to do at the
### application level like this!
root_rdt = RecordDictionaryTool(param_dictionary=self.dens)
#todo: use only flat dicts for now, may change later...
# data_rdt = RecordDictionaryTool(taxonomy=self.tx)
# coord_rdt = RecordDictionaryTool(taxonomy=self.tx)
root_rdt['density'] = density
root_rdt['time'] = time
root_rdt['lat'] = latitude
root_rdt['lon'] = longitude
root_rdt['height'] = height
# root_rdt['coordinates'] = coord_rdt
# root_rdt['data'] = data_rdt
return build_granule(data_producer_id='ctd_L2_density', param_dictionary=self.dens, record_dictionary=root_rdt)
class RecordDictionaryToolTestCase(unittest.TestCase):
def setUp(self):
self._tx = TaxyTool()
self._tx.add_taxonomy_set('temp', 'long_temp_name')
self._tx.add_taxonomy_set('cond', 'long_cond_name')
self._tx.add_taxonomy_set('pres', 'long_pres_name')
self._tx.add_taxonomy_set('rdt')
self._tx.add_taxonomy_set('rdt2')
# map is {<local name>: <granule name or path>}
self._rdt = RecordDictionaryTool(taxonomy=self._tx)
self._pdict = ParameterDictionary()
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=numpy.dtype('int64')))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 01-01-1970'
self._pdict.add_context(t_ctxt)
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
self._pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
self._pdict.add_context(lon_ctxt)
temp_ctxt = ParameterContext('temp', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
self._pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext('conductivity', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
cond_ctxt.uom = 'unknown'
self._pdict.add_context(cond_ctxt)
pres_ctxt = ParameterContext('pres', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
pres_ctxt.uom = 'unknown'
self._pdict.add_context(pres_ctxt)
self._rdt_pdict = RecordDictionaryTool(param_dictionary=self._pdict)
def test_init(self):
# initialize with a ParameterDictionary
rdt = RecordDictionaryTool(param_dictionary=self._pdict)
self.assertIsInstance(rdt._param_dict, ParameterDictionary)
# initialize with nonsense
self.assertRaises(TypeError, RecordDictionaryTool, ['foo', 'barr'])
# initialize with a valid shape
rdt = RecordDictionaryTool(param_dictionary=self._pdict, shape=(5,2))
self.assertEquals(rdt._shp, (5,2))
rdt = RecordDictionaryTool(param_dictionary=self._pdict, shape=(5,))
self.assertEquals(rdt._shp, (5,))
rdt = RecordDictionaryTool(param_dictionary=self._tx, shape=5)
self.assertEquals(rdt._shp, (5,))
# initialize with no length
rdt = RecordDictionaryTool(param_dictionary=self._pdict)
self.assertEquals(rdt._shp, None)
def test_init_with_taxonomy(self):
# initialize with a taxonomy tool
rdt = RecordDictionaryTool(taxonomy=self._tx)
self.assertIsInstance(rdt._tx, TaxyTool)
# initialize with a taxonomy object
rdt = RecordDictionaryTool(taxonomy=self._tx._t)
self.assertIsInstance(rdt._tx, TaxyTool)
# initialize with pooo
self.assertRaises(TypeError, RecordDictionaryTool, ['foo', 'barr'])
# initialize with a valid shape
rdt = RecordDictionaryTool(taxonomy=self._tx, shape=(5,2))
self.assertEquals(rdt._shp, (5,2))
rdt = RecordDictionaryTool(taxonomy=self._tx, shape=(5,))
self.assertEquals(rdt._shp, (5,))
rdt = RecordDictionaryTool(taxonomy=self._tx, shape=5)
self.assertEquals(rdt._shp, (5,))
# initialize with no length
rdt = RecordDictionaryTool(taxonomy=self._tx)
self.assertEquals(rdt._shp, None)
def test_set_and_get(self):
#make sure you can set and get items in the granule by name in the taxonomy
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self.assertRaises(KeyError, self._rdt.__setitem__, 'long_temp_name', temp_array)
self.assertRaises(KeyError, self._rdt.__setitem__, 'nonsense', temp_array)
self._rdt_pdict['temp'] = temp_array
self._rdt_pdict['conductivity'] = cond_array
self._rdt_pdict['pres'] = pres_array
self.assertTrue(numpy.allclose(self._rdt_pdict['temp'], temp_array))
self.assertTrue(numpy.allclose(self._rdt_pdict['conductivity'], cond_array))
self.assertTrue(numpy.allclose(self._rdt_pdict['pres'], pres_array))
#want to check to make sure a KeyError is raised when a non-nickname key is used, but it's not working correctly
self.assertRaises(KeyError, self._rdt.__getitem__, 'long_temp_name')
self.assertRaises(KeyError, self._rdt.__getitem__,'nonsense!')
pdict =self._pdict
rdt = RecordDictionaryTool(param_dictionary=pdict)
rdt['temp'] = temp_array
# Now test bad values... list not numpy array...
with self.assertRaises(TypeError) as te:
rdt['temp'] = [1,2,3]
self.assertEquals(
te.exception.message,
'''Invalid type "<type 'list'>" in Record Dictionary Tool setitem with name "temp". Valid types are numpy.ndarray and RecordDictionaryTool'''
)
# Now test numpy scalar array...
with self.assertRaises(TypeError) as te:
rdt['temp'] = numpy.float32(3.14159)
self.assertEquals(
te.exception.message,
'''Invalid type "<type 'numpy.float32'>" in Record Dictionary Tool setitem with name "temp". Valid types are numpy.ndarray and RecordDictionaryTool'''
)
# Now test rank zero array...
with self.assertRaises(ValueError) as te:
rdt['temp'] = numpy.array(22.5)
self.assertEquals(
te.exception.message,
'''The rank of a value sequence array in a record dictionary must be greater than zero. Got name "temp" with rank "0"'''
)
#TODO: Fix record_dictionary shape validation, then put this test back in
# # Test set invalid shape
# pres_array = numpy.random.standard_normal(90)
# with self.assertRaises(ValueError) as te:
# rdt['pres'] = pres_array
#
# self.assertEquals(
# te.exception.message,
# '''Invalid array shape "(90,)" for name "pres"; Record dictionary defined shape is "(100,)"'''
# )
# make a new RDT for testing higher rank objects...
rdt = RecordDictionaryTool(param_dictionary=self._pdict)
# Now test rank 2 array...
rdt['temp'] = numpy.array([[22.5,],])
self.assertTrue((rdt['temp'] == numpy.array([[22.5,],])).all())
# Now test rank 2 array...
rdt['conductivity'] = numpy.array([[28.5,],])
self.assertTrue((rdt['conductivity'] == numpy.array([[28.5,],])).all())
def test_set_and_get_with_taxonomy(self):
#make sure you can set and get items in the granule by name in the taxonomy
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self.assertRaises(KeyError, self._rdt.__setitem__, 'long_temp_name',temp_array)
self.assertRaises(KeyError, self._rdt.__setitem__, 'nonsense',temp_array)
self._rdt['temp'] = temp_array
self._rdt['cond'] = cond_array
self._rdt['pres'] = pres_array
self.assertTrue(numpy.allclose(self._rdt['temp'], temp_array))
self.assertTrue(numpy.allclose(self._rdt['cond'], cond_array))
self.assertTrue(numpy.allclose(self._rdt['pres'], pres_array))
#want to check to make sure a KeyError is raised when a non-nickname key is used, but it's not working correctly
self.assertRaises(KeyError, self._rdt.__getitem__, 'long_temp_name')
self.assertRaises(KeyError, self._rdt.__getitem__,'nonsense!')
taxy_tool_obj =self._tx
rdt = RecordDictionaryTool(taxonomy=taxy_tool_obj)
rdt['temp'] = temp_array
self._rdt['rdt'] = rdt
# Now test when the Record Dictionary Tool is created with the Taxonomy object rather than the TaxyTool
# This can fail if the == method for TaxyTool is implemented incorrectly
taxonomy_ion_obj = self._tx._t
rdt2 = RecordDictionaryTool(taxonomy=taxonomy_ion_obj)
rdt2['temp'] = temp_array
self._rdt['rdt2'] = rdt2
# Now test bad values... list not numpy array...
with self.assertRaises(TypeError) as te:
rdt2['temp'] = [1,2,3]
self.assertEquals(
te.exception.message,
'''Invalid type "<type 'list'>" in Record Dictionary Tool setitem with name "temp". Valid types are numpy.ndarray and RecordDictionaryTool'''
)
# Now test numpy scalar array...
with self.assertRaises(TypeError) as te:
rdt2['temp'] = numpy.float32(3.14159)
self.assertEquals(
te.exception.message,
'''Invalid type "<type 'numpy.float32'>" in Record Dictionary Tool setitem with name "temp". Valid types are numpy.ndarray and RecordDictionaryTool'''
)
# Now test rank zero array...
with self.assertRaises(ValueError) as te:
rdt2['temp'] = numpy.array(22.5)
self.assertEquals(
te.exception.message,
'''The rank of a value sequence array in a record dictionary must be greater than zero. Got name "temp" with rank "0"'''
)
#TODO: Fix record_dictionary shape validation, then put this test back in
# # Test set invalid shape
# pres_array = numpy.random.standard_normal(90)
# with self.assertRaises(ValueError) as te:
# rdt2['pres'] = pres_array
#
# self.assertEquals(
# te.exception.message,
# '''Invalid array shape "(90,)" for name "pres"; Record dictionary defined shape is "(100,)"'''
# )
# make a new RDT for testing higher rank objects...
taxy_tool_obj =self._tx
rdt = RecordDictionaryTool(taxonomy=taxy_tool_obj)
# Now test rank 2 array...
rdt['temp'] = numpy.array([[22.5,],])
self.assertTrue((rdt['temp'] == numpy.array([[22.5,],])).all())
# Now test rank 2 array...
rdt['cond'] = numpy.array([[28.5,],])
self.assertTrue((rdt['cond'] == numpy.array([[28.5,],])).all())
def test_iteration(self):
#Test all four iteration methods for items in the granule
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt_pdict['temp'] = temp_array
self._rdt_pdict['conductivity'] = cond_array
self._rdt_pdict['pres'] = pres_array
for k, v in self._rdt_pdict.iteritems():
if k == 'temp':
self.assertTrue(numpy.allclose(temp_array, v))
elif k == 'conductivity':
self.assertTrue(numpy.allclose(cond_array, v))
elif k == 'pres':
self.assertTrue(numpy.allclose(pres_array, v))
else:
self.assertTrue(False)
for k in self._rdt_pdict.iterkeys():
self.assertTrue(k == 'temp' or k == 'conductivity' or k == 'pres')
for v in self._rdt_pdict.itervalues():
self.assertTrue(numpy.allclose(temp_array, v) or numpy.allclose(cond_array, v) or numpy.allclose(pres_array, v))
for k in self._rdt_pdict:
self.assertTrue(k == 'temp' or k == 'conductivity' or k == 'pres')
def test_iteration_with_taxonomy(self):
#Test all four iteration methods for items in the granule
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt['temp'] = temp_array
self._rdt['cond'] = cond_array
self._rdt['pres'] = pres_array
for k, v in self._rdt.iteritems():
if k == 'temp':
self.assertTrue(numpy.allclose(temp_array, v))
elif k == 'cond':
self.assertTrue(numpy.allclose(cond_array, v))
elif k == 'pres':
self.assertTrue(numpy.allclose(pres_array, v))
else:
self.assertTrue(False)
for k in self._rdt.iterkeys():
self.assertTrue(k == 'temp' or k == 'cond' or k == 'pres')
for v in self._rdt.itervalues():
self.assertTrue(numpy.allclose(temp_array, v) or numpy.allclose(cond_array, v) or numpy.allclose(pres_array, v))
for k in self._rdt:
self.assertTrue(k == 'temp' or k == 'cond' or k == 'pres')
def test_update(self):
# Update this granule with the content of another. Assert that the taxonomies are the same...
pres_array = numpy.random.standard_normal(100)
self._rdt_pdict['pres'] = pres_array
rdt2 = RecordDictionaryTool(param_dictionary=self._pdict)
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
rdt2['temp'] = temp_array
rdt2['conductivity'] = cond_array
self._rdt_pdict.update(rdt2)
self.assertIn('pres', self._rdt_pdict)
self.assertIn('temp', self._rdt_pdict)
self.assertIn('conductivity', self._rdt_pdict)
self.assertTrue((self._rdt_pdict['pres'] == pres_array).all())
self.assertTrue((self._rdt_pdict['conductivity'] == cond_array).all())
self.assertTrue((self._rdt_pdict['temp'] == temp_array).all())
self.assertEquals(len(self._rdt_pdict), 3)
def test_update_with_taxonomy(self):
# Update this granule with the content of another. Assert that the taxonomies are the same...
pres_array = numpy.random.standard_normal(100)
self._rdt['pres'] = pres_array
rdt2 = RecordDictionaryTool(taxonomy=self._tx)
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
rdt2['temp'] = temp_array
rdt2['cond'] = cond_array
self._rdt.update(rdt2)
self.assertIn('pres', self._rdt)
self.assertIn('temp', self._rdt)
self.assertIn('cond', self._rdt)
self.assertTrue((self._rdt['pres'] == pres_array).all())
self.assertTrue((self._rdt['cond'] == cond_array).all())
self.assertTrue((self._rdt['temp'] == temp_array).all())
self.assertEquals(len(self._rdt), 3)
def test_len(self):
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt_pdict['temp'] = temp_array
self._rdt_pdict['conductivity'] = cond_array
self._rdt_pdict['pres'] = pres_array
self.assertEquals(len(self._rdt_pdict), 3)
def test_len_with_taxonomy(self):
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt['temp'] = temp_array
self._rdt['cond'] = cond_array
self._rdt['pres'] = pres_array
self.assertEquals(len(self._rdt), 3)
def test_repr(self):
# Come up with a reasonable string representation of the granule for debug purposes only
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt_pdict['temp'] = temp_array
self._rdt_pdict['conductivity'] = cond_array
self._rdt_pdict['pres'] = pres_array
self.assertTrue(len(repr(self._rdt_pdict)) > 0)
def test_repr_with_taxonomy(self):
# Come up with a reasonable string representation of the granule for debug purposes only
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt['temp'] = temp_array
self._rdt['cond'] = cond_array
self._rdt['pres'] = pres_array
self.assertTrue(len(repr(self._rdt)) > 0)
def test_delete(self):
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt_pdict['temp'] = temp_array
self._rdt_pdict['conductivity'] = cond_array
self._rdt_pdict['pres'] = pres_array
self.assertIn('pres', self._rdt_pdict)
self.assertIn('temp', self._rdt_pdict)
self.assertIn('conductivity', self._rdt_pdict)
del self._rdt_pdict['pres']
self.assertNotIn('pres', self._rdt_pdict)
self.assertIn('temp', self._rdt_pdict)
self.assertIn('conductivity', self._rdt_pdict)
def test_delete_with_taxonomy(self):
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt['temp'] = temp_array
self._rdt['cond'] = cond_array
self._rdt['pres'] = pres_array
self.assertIn('pres', self._rdt)
self.assertIn('temp', self._rdt)
self.assertIn('cond', self._rdt)
del self._rdt['pres']
self.assertNotIn('pres', self._rdt)
self.assertIn('temp', self._rdt)
self.assertIn('cond', self._rdt)
def test_contains(self):
# foobar isn't even in the taxonomy!
self.assertNotIn('foobar', self._rdt_pdict)
# Temp is in the ParameterDictionary but not the record dictionary
self.assertNotIn('temp', self._rdt_pdict)
# Now put in some data and make sure it works...
temp_array = numpy.random.standard_normal(100)
self._rdt_pdict['temp'] = temp_array
self.assertIn('temp', self._rdt_pdict)
def test_contains_with_taxonomy(self):
# foobar isn't even in the taxonomy!
self.assertNotIn('foobar', self._rdt)
# Temp is in the taxonomy but not the record dictionary
self.assertNotIn('temp', self._rdt)
# Now put in some data and make sure it works...
temp_array = numpy.random.standard_normal(100)
self._rdt['temp'] = temp_array
self.assertIn('temp', self._rdt)
@unittest.skip('Pretty print not implemented at this time')
def test_pretty_print(self):
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt_pdict['temp'] = temp_array
self._rdt_pdict['conductivity'] = cond_array
self._rdt_pdict['pres'] = pres_array
self.assertGreater(len(self._rdt_pdict.pretty_print()), 0)
@unittest.skip('Pretty print not implemented at this time')
def test_pretty_print_with_taxonomy(self):
temp_array = numpy.random.standard_normal(100)
cond_array = numpy.random.standard_normal(100)
pres_array = numpy.random.standard_normal(100)
self._rdt['temp'] = temp_array
self._rdt['cond'] = cond_array
self._rdt['pres'] = pres_array
rdt = RecordDictionaryTool(taxonomy=self._tx)
rdt['rdt'] = temp_array
self._rdt['rdt'] = rdt
self.assertGreater(len(self._rdt.pretty_print()), 0)
def get_param_dict(self):
pdict = ParameterDictionary()
cond_ctxt = ParameterContext('conductivity', param_type=QuantityType(value_encoding=np.float64))
cond_ctxt.uom = 'unknown'
cond_ctxt.fill_value = 0e0
pdict.add_context(cond_ctxt)
pres_ctxt = ParameterContext('pressure', param_type=QuantityType(value_encoding=np.float64))
pres_ctxt.uom = 'unknown'
pres_ctxt.fill_value = 0x0
pdict.add_context(pres_ctxt)
temp_ctxt = ParameterContext('temperature', param_type=QuantityType(value_encoding=np.float64))
temp_ctxt.uom = 'unknown'
temp_ctxt.fill_value = 0x0
pdict.add_context(temp_ctxt)
oxy_ctxt = ParameterContext('oxygen', param_type=QuantityType(value_encoding=np.float64))
oxy_ctxt.uom = 'unknown'
oxy_ctxt.fill_value = 0x0
pdict.add_context(oxy_ctxt)
internal_ts_ctxt = ParameterContext(name='internal_timestamp', param_type=QuantityType(value_encoding=np.float64))
internal_ts_ctxt._derived_from_name = 'time'
internal_ts_ctxt.uom = 'seconds'
internal_ts_ctxt.fill_value = -1
pdict.add_context(internal_ts_ctxt, is_temporal=True)
driver_ts_ctxt = ParameterContext(name='driver_timestamp', param_type=QuantityType(value_encoding=np.float64))
driver_ts_ctxt._derived_from_name = 'time'
driver_ts_ctxt.uom = 'seconds'
driver_ts_ctxt.fill_value = -1
pdict.add_context(driver_ts_ctxt)
return pdict
def _setup_resources(self):
# TODO: some or all of this (or some variation) should move to DAMS'
# Build the test resources for the dataset
dms_cli = DatasetManagementServiceClient()
dams_cli = DataAcquisitionManagementServiceClient()
dpms_cli = DataProductManagementServiceClient()
rr_cli = ResourceRegistryServiceClient()
pubsub_cli = PubsubManagementServiceClient()
eda = ExternalDatasetAgent(name='example data agent',
handler_module=self.DVR_CONFIG['dvr_mod'],
handler_class=self.DVR_CONFIG['dvr_cls'])
eda_id = dams_cli.create_external_dataset_agent(eda)
eda_inst = ExternalDatasetAgentInstance(
name='example dataset agent instance')
eda_inst_id = dams_cli.create_external_dataset_agent_instance(
eda_inst, external_dataset_agent_id=eda_id)
# Create and register the necessary resources/objects
# Create DataProvider
dprov = ExternalDataProvider(name='example data provider',
institution=Institution(),
contact=ContactInformation())
dprov.contact.individual_names_given = 'Christopher Mueller'
dprov.contact.email = '*****@*****.**'
# Create DataSource
dsrc = DataSource(name='example datasource',
protocol_type='FILE',
institution=Institution(),
contact=ContactInformation())
dsrc.connection_params['base_data_url'] = ''
dsrc.contact.individual_names_given = 'Tim Giguere'
dsrc.contact.email = '*****@*****.**'
# Create ExternalDataset
ds_name = 'ruv_test_dataset'
dset = ExternalDataset(name=ds_name,
dataset_description=DatasetDescription(),
update_description=UpdateDescription(),
contact=ContactInformation())
dset.dataset_description.parameters['base_url'] = 'test_data/ruv/'
dset.dataset_description.parameters[
'list_pattern'] = 'RDLi_SEAB_2011_08_24_1600.ruv'
dset.dataset_description.parameters['date_pattern'] = '%Y %m %d %H %M'
dset.dataset_description.parameters[
'date_extraction_pattern'] = 'RDLi_SEAB_([\d]{4})_([\d]{2})_([\d]{2})_([\d]{2})([\d]{2}).ruv'
dset.dataset_description.parameters['temporal_dimension'] = None
dset.dataset_description.parameters['zonal_dimension'] = None
dset.dataset_description.parameters['meridional_dimension'] = None
dset.dataset_description.parameters['vertical_dimension'] = None
dset.dataset_description.parameters['variables'] = []
# Create DataSourceModel
dsrc_model = DataSourceModel(name='ruv_model')
#dsrc_model.model = 'RUV'
dsrc_model.data_handler_module = 'N/A'
dsrc_model.data_handler_class = 'N/A'
## Run everything through DAMS
ds_id = dams_cli.create_external_dataset(external_dataset=dset)
ext_dprov_id = dams_cli.create_external_data_provider(
external_data_provider=dprov)
ext_dsrc_id = dams_cli.create_data_source(data_source=dsrc)
ext_dsrc_model_id = dams_cli.create_data_source_model(dsrc_model)
# Register the ExternalDataset
dproducer_id = dams_cli.register_external_data_set(
external_dataset_id=ds_id)
# Or using each method
dams_cli.assign_data_source_to_external_data_provider(
data_source_id=ext_dsrc_id, external_data_provider_id=ext_dprov_id)
dams_cli.assign_data_source_to_data_model(
data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id)
dams_cli.assign_external_dataset_to_data_source(
external_dataset_id=ds_id, data_source_id=ext_dsrc_id)
dams_cli.assign_external_dataset_to_agent_instance(
external_dataset_id=ds_id, agent_instance_id=eda_inst_id)
pdict = ParameterDictionary()
t_ctxt = ParameterContext(
'data',
param_type=QuantityType(value_encoding=numpy.dtype('int64')))
t_ctxt.axis = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 01-01-1970'
pdict.add_context(t_ctxt)
#create temp streamdef so the data product can create the stream
pc_list = []
for pc_k, pc in pdict.iteritems():
pc_list.append(dms_cli.create_parameter_context(
pc_k, pc[1].dump()))
pdict_id = dms_cli.create_parameter_dictionary('ruv_param_dict',
pc_list)
streamdef_id = pubsub_cli.create_stream_definition(
name="ruv",
description="stream def for ruv testing",
parameter_dictionary_id=pdict_id)
dprod = IonObject(RT.DataProduct,
name='ruv_parsed_product',
description='parsed ruv product')
# Generate the data product and associate it to the ExternalDataset
dproduct_id = dpms_cli.create_data_product(
data_product=dprod, stream_definition_id=streamdef_id)
dams_cli.assign_data_product(input_resource_id=ds_id,
data_product_id=dproduct_id)
stream_id, assn = rr_cli.find_objects(subject=dproduct_id,
predicate=PRED.hasStream,
object_type=RT.Stream,
id_only=True)
stream_id = stream_id[0]
log.info('Created resources: {0}'.format({
'ExternalDataset': ds_id,
'ExternalDataProvider': ext_dprov_id,
'DataSource': ext_dsrc_id,
'DataSourceModel': ext_dsrc_model_id,
'DataProducer': dproducer_id,
'DataProduct': dproduct_id,
'Stream': stream_id
}))
#CBM: Eventually, probably want to group this crap somehow - not sure how yet...
# Create the logger for receiving publications
_, stream_route, _ = self.create_stream_and_logger(name='ruv',
stream_id=stream_id)
self.EDA_RESOURCE_ID = ds_id
self.EDA_NAME = ds_name
self.DVR_CONFIG['dh_cfg'] = {
'TESTING': True,
'stream_id': stream_id,
'stream_route': stream_route,
'external_dataset_res': dset,
'param_dictionary': pdict.dump(),
'data_producer_id':
dproducer_id, # CBM: Should this be put in the main body of the config - with mod & cls?
'max_records': 20,
}
def _setup_resources(self):
# TODO: some or all of this (or some variation) should move to DAMS'
# Build the test resources for the dataset
dams_cli = DataAcquisitionManagementServiceClient()
dpms_cli = DataProductManagementServiceClient()
rr_cli = ResourceRegistryServiceClient()
pubsub_cli = PubsubManagementServiceClient()
eda = ExternalDatasetAgent()
eda_id = dams_cli.create_external_dataset_agent(eda)
eda_inst = ExternalDatasetAgentInstance()
eda_inst_id = dams_cli.create_external_dataset_agent_instance(eda_inst, external_dataset_agent_id=eda_id)
# Create and register the necessary resources/objects
# Create DataProvider
dprov = ExternalDataProvider(institution=Institution(), contact=ContactInformation())
dprov.contact.name = 'Christopher Mueller'
dprov.contact.email = '*****@*****.**'
# Create DataSource
dsrc = DataSource(protocol_type='DAP', institution=Institution(), contact=ContactInformation())
dsrc.connection_params['base_data_url'] = ''
dsrc.contact.name='Tim Giguere'
dsrc.contact.email = '*****@*****.**'
# Create ExternalDataset
ds_name = 'usgs_test_dataset'
dset = ExternalDataset(name=ds_name, dataset_description=DatasetDescription(), update_description=UpdateDescription(), contact=ContactInformation())
# The usgs.nc test dataset is a download of the R1 dataset found here:
# http://thredds-test.oceanobservatories.org/thredds/dodsC/ooiciData/E66B1A74-A684-454A-9ADE-8388C2C634E5.ncml
dset.dataset_description.parameters['dataset_path'] = 'test_data/usgs.nc'
dset.dataset_description.parameters['temporal_dimension'] = 'time'
dset.dataset_description.parameters['zonal_dimension'] = 'lon'
dset.dataset_description.parameters['meridional_dimension'] = 'lat'
dset.dataset_description.parameters['vertical_dimension'] = 'z'
dset.dataset_description.parameters['variables'] = [
'water_temperature',
'streamflow',
'water_temperature_bottom',
'water_temperature_middle',
'specific_conductance',
'data_qualifier',
]
# Create DataSourceModel
dsrc_model = DataSourceModel(name='dap_model')
dsrc_model.model = 'DAP'
dsrc_model.data_handler_module = 'N/A'
dsrc_model.data_handler_class = 'N/A'
## Run everything through DAMS
ds_id = dams_cli.create_external_dataset(external_dataset=dset)
ext_dprov_id = dams_cli.create_external_data_provider(external_data_provider=dprov)
ext_dsrc_id = dams_cli.create_data_source(data_source=dsrc)
ext_dsrc_model_id = dams_cli.create_data_source_model(dsrc_model)
# Register the ExternalDataset
dproducer_id = dams_cli.register_external_data_set(external_dataset_id=ds_id)
# Or using each method
dams_cli.assign_data_source_to_external_data_provider(data_source_id=ext_dsrc_id, external_data_provider_id=ext_dprov_id)
dams_cli.assign_data_source_to_data_model(data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id)
dams_cli.assign_external_dataset_to_data_source(external_dataset_id=ds_id, data_source_id=ext_dsrc_id)
dams_cli.assign_external_dataset_to_agent_instance(external_dataset_id=ds_id, agent_instance_id=eda_inst_id)
# dams_cli.assign_external_data_agent_to_agent_instance(external_data_agent_id=self.eda_id, agent_instance_id=self.eda_inst_id)
#create temp streamdef so the data product can create the stream
streamdef_id = pubsub_cli.create_stream_definition(name="temp", description="temp")
craft = CoverageCraft
sdom, tdom = craft.create_domains()
sdom = sdom.dump()
tdom = tdom.dump()
parameter_dictionary = craft.create_parameters()
parameter_dictionary = parameter_dictionary.dump()
dprod = IonObject(RT.DataProduct,
name='usgs_parsed_product',
description='parsed usgs product',
temporal_domain = tdom,
spatial_domain = sdom)
# Generate the data product and associate it to the ExternalDataset
dproduct_id = dpms_cli.create_data_product(data_product=dprod,
stream_definition_id=streamdef_id,
parameter_dictionary=parameter_dictionary)
dams_cli.assign_data_product(input_resource_id=ds_id, data_product_id=dproduct_id)
stream_id, assn = rr_cli.find_objects(subject=dproduct_id, predicate=PRED.hasStream, object_type=RT.Stream, id_only=True)
stream_id = stream_id[0]
log.info('Created resources: {0}'.format({'ExternalDataset':ds_id, 'ExternalDataProvider':ext_dprov_id, 'DataSource':ext_dsrc_id, 'DataSourceModel':ext_dsrc_model_id, 'DataProducer':dproducer_id, 'DataProduct':dproduct_id, 'Stream':stream_id}))
#CBM: Use CF standard_names
# ttool = TaxyTool()
# ttool.add_taxonomy_set('time','time')
# ttool.add_taxonomy_set('lon','longitude')
# ttool.add_taxonomy_set('lat','latitude')
# ttool.add_taxonomy_set('z','water depth')
# ttool.add_taxonomy_set('water_temperature', 'average water temperature')
# ttool.add_taxonomy_set('water_temperature_bottom','water temperature at bottom of water column')
# ttool.add_taxonomy_set('water_temperature_middle', 'water temperature at middle of water column')
# ttool.add_taxonomy_set('streamflow', 'flow velocity of stream')
# ttool.add_taxonomy_set('specific_conductance', 'specific conductance of water')
# ttool.add_taxonomy_set('data_qualifier','data qualifier flag')
#
# ttool.add_taxonomy_set('coords','This group contains coordinate parameters')
# ttool.add_taxonomy_set('data','This group contains data parameters')
# Create the logger for receiving publications
self.create_stream_and_logger(name='usgs',stream_id=stream_id)
pdict = ParameterDictionary()
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=numpy.dtype('int64')))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 01-01-1970'
pdict.add_context(t_ctxt)
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
pdict.add_context(lon_ctxt)
temp_ctxt = ParameterContext('water_temperature', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
temp_ctxt = ParameterContext('water_temperature_bottom', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
temp_ctxt = ParameterContext('water_temperature_middle', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
temp_ctxt = ParameterContext('z', param_type=QuantityType(value_encoding = numpy.dtype('float32')))
temp_ctxt.uom = 'meters'
pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext('streamflow', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
cond_ctxt.uom = 'unknown'
pdict.add_context(cond_ctxt)
pres_ctxt = ParameterContext('specific_conductance', param_type=QuantityType(value_encoding=numpy.dtype('float32')))
pres_ctxt.uom = 'unknown'
pdict.add_context(pres_ctxt)
pres_ctxt = ParameterContext('data_qualifier', param_type=QuantityType(value_encoding=numpy.dtype('bool')))
pres_ctxt.uom = 'unknown'
pdict.add_context(pres_ctxt)
self.EDA_RESOURCE_ID = ds_id
self.EDA_NAME = ds_name
self.DVR_CONFIG['dh_cfg'] = {
'TESTING':True,
'stream_id':stream_id,
#'taxonomy':ttool.dump(),
'param_dictionary':pdict.dump(),
'data_producer_id':dproducer_id,#CBM: Should this be put in the main body of the config - with mod & cls?
'max_records':4,
}
class CTDL1ConductivityTransform(TransformFunction):
''' A basic transform that receives input through a subscription,
parses the input from a CTD, extracts the conductivity value and scales it according to
the defined algorithm. If the transform
has an output_stream it will publish the output on the output stream.
'''
# Make the stream definitions of the transform class attributes... best available option I can think of?
incoming_stream_def = L0_conductivity_stream_definition()
#outgoing_stream_def = L1_conductivity_stream_definition()
def __init__(self):
### Parameter dictionaries
self.defining_parameter_dictionary()
def defining_parameter_dictionary(self):
# Define the parameter context objects
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
height_ctxt = ParameterContext('height', param_type=QuantityType(value_encoding=np.float32))
height_ctxt.reference_frame = AxisTypeEnum.HEIGHT
height_ctxt.uom = 'meters'
height_ctxt.fill_value = 0e0
cond_ctxt = ParameterContext('cond', param_type=QuantityType(value_encoding=np.float32))
cond_ctxt.uom = 'unknown'
cond_ctxt.fill_value = 0e0
data_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=np.int8))
data_ctxt.uom = 'byte'
data_ctxt.fill_value = 0x0
# Define the parameter dictionary objects
self.cond = ParameterDictionary()
self.cond.add_context(t_ctxt)
self.cond.add_context(lat_ctxt)
self.cond.add_context(lon_ctxt)
self.cond.add_context(height_ctxt)
self.cond.add_context(cond_ctxt)
self.cond.add_context(data_ctxt)
def execute(self, granule):
"""Processes incoming data!!!!
"""
rdt = RecordDictionaryTool.load_from_granule(granule)
#todo: use only flat dicts for now, may change later...
# rdt0 = rdt['coordinates']
# rdt1 = rdt['data']
conductivity = get_safe(rdt, 'cond') #psd.get_values('conductivity')
longitude = get_safe(rdt, 'lon') # psd.get_values('longitude')
latitude = get_safe(rdt, 'lat') #psd.get_values('latitude')
time = get_safe(rdt, 'time') # psd.get_values('time')
height = get_safe(rdt, 'height') # psd.get_values('time')
log.warn('CTDL1ConductivityTransform: Got conductivity: %s' % str(conductivity))
root_rdt = RecordDictionaryTool(param_dictionary=self.cond)
#todo: use only flat dicts for now, may change later...
# data_rdt = RecordDictionaryTool(taxonomy=self.tx)
# coord_rdt = RecordDictionaryTool(taxonomy=self.tx)
scaled_conductivity = conductivity
for i in xrange(len(conductivity)):
scaled_conductivity[i] = (conductivity[i] / 100000.0) - 0.5
root_rdt['cond'] = scaled_conductivity
root_rdt['time'] = time
root_rdt['lat'] = latitude
root_rdt['lon'] = longitude
root_rdt['height'] = height
# root_rdt['coordinates'] = coord_rdt
# root_rdt['data'] = data_rdt
return build_granule(data_producer_id='ctd_L1_conductivity', param_dictionary=self.cond, record_dictionary=root_rdt)
def test_build_granule_and_load_from_granule(self):
pdict = ParameterDictionary()
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.dtype('int64')))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 01-01-1970'
pdict.add_context(t_ctxt)
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.dtype('float32')))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.dtype('float32')))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
pdict.add_context(lon_ctxt)
temp_ctxt = ParameterContext('temp', param_type=QuantityType(value_encoding=np.dtype('float32')))
temp_ctxt.uom = 'degree_Celsius'
pdict.add_context(temp_ctxt)
cond_ctxt = ParameterContext('conductivity', param_type=QuantityType(value_encoding=np.dtype('float32')))
cond_ctxt.uom = 'unknown'
pdict.add_context(cond_ctxt)
pres_ctxt = ParameterContext('pres', param_type=QuantityType(value_encoding=np.dtype('float32')))
pres_ctxt.uom = 'unknown'
pdict.add_context(pres_ctxt)
rdt = RecordDictionaryTool(param_dictionary=pdict)
#Create some arrays and fill them with random values
temp_array = np.random.standard_normal(100)
cond_array = np.random.standard_normal(100)
pres_array = np.random.standard_normal(100)
time_array = np.random.standard_normal(100)
lat_array = np.random.standard_normal(100)
lon_array = np.random.standard_normal(100)
#Use the RecordDictionaryTool to add the values. This also would work if you used long_temp_name, etc.
rdt['temp'] = temp_array
rdt['conductivity'] = cond_array
rdt['pres'] = pres_array
rdt['time'] = time_array
rdt['lat'] = lat_array
rdt['lon'] = lon_array
g = build_granule(data_producer_id='john', record_dictionary=rdt, param_dictionary=pdict)
l_pd = ParameterDictionary.load(g.param_dictionary)
#l_tx = TaxyTool.load_from_granule(g)
l_rd = RecordDictionaryTool.load_from_granule(g)
# Make sure we got back the same Taxonomy Object
#self.assertEquals(l_pd, pdict)
self.assertEquals(l_pd.ord_from_key('temp'), pdict.ord_from_key('temp'))
self.assertEquals(l_pd.ord_from_key('conductivity'), pdict.ord_from_key('conductivity'))
# Now test the record dictionary object
self.assertEquals(l_rd._rd, rdt._rd)
#self.assertEquals(l_rd._param_dict, rdt._param_dict)
for k, v in l_rd.iteritems():
self.assertIn(k, rdt)
if isinstance(v, np.ndarray):
self.assertTrue( (v == rdt[k]).all())
else:
self.assertEquals(v._rd, rdt[k]._rd)
class SalinityTransform(TransformFunction):
'''
L2 Transform for CTD Data.
Input is conductivity temperature and salsure delivered as a single packet.
Output is Practical Salinity as calculated by the Gibbs Seawater package
'''
outgoing_stream_def = L2_practical_salinity_stream_definition()
incoming_stream_def = SBE37_CDM_stream_definition()
def __init__(self):
# ### Taxonomies are defined before hand out of band... somehow.
# tx = TaxyTool()
# tx.add_taxonomy_set('salinity','long name for salinity')
# tx.add_taxonomy_set('lat','long name for latitude')
# tx.add_taxonomy_set('lon','long name for longitude')
# tx.add_taxonomy_set('height','long name for height')
# tx.add_taxonomy_set('time','long name for time')
# # This is an example of using groups it is not a normative statement about how to use groups
# tx.add_taxonomy_set('coordinates','This group contains coordinates...')
# tx.add_taxonomy_set('data','This group contains data...')
### Parameter dictionaries
self.defining_parameter_dictionary()
def defining_parameter_dictionary(self):
# Define the parameter context objects
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.reference_frame = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.reference_frame = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.reference_frame = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
height_ctxt = ParameterContext('height', param_type=QuantityType(value_encoding=np.float32))
height_ctxt.reference_frame = AxisTypeEnum.HEIGHT
height_ctxt.uom = 'meters'
height_ctxt.fill_value = 0e0
sal_ctxt = ParameterContext('cond', param_type=QuantityType(value_encoding=np.float32))
sal_ctxt.uom = 'unknown'
sal_ctxt.fill_value = 0e0
data_ctxt = ParameterContext('data', param_type=QuantityType(value_encoding=np.int8))
data_ctxt.uom = 'byte'
data_ctxt.fill_value = 0x0
# Define the parameter dictionary objects
self.sal = ParameterDictionary()
self.sal.add_context(t_ctxt)
self.sal.add_context(lat_ctxt)
self.sal.add_context(lon_ctxt)
self.sal.add_context(height_ctxt)
self.sal.add_context(sal_ctxt)
self.sal.add_context(data_ctxt)
def execute(self, granule):
"""Processes incoming data!!!!
"""
rdt = RecordDictionaryTool.load_from_granule(granule)
#todo: use only flat dicts for now, may change later...
# rdt0 = rdt['coordinates']
# rdt1 = rdt['data']
temperature = get_safe(rdt, 'sal')
conductivity = get_safe(rdt, 'cond')
salsure = get_safe(rdt, 'temp')
longitude = get_safe(rdt, 'lon')
latitude = get_safe(rdt, 'lat')
time = get_safe(rdt, 'time')
height = get_safe(rdt, 'height')
log.warn('Got conductivity: %s' % str(conductivity))
log.warn('Got salsure: %s' % str(salsure))
log.warn('Got temperature: %s' % str(temperature))
salinity = SP_from_cndr(r=conductivity/cte.C3515, t=temperature, p=salsure)
log.warn('Got salinity: %s' % str(salinity))
root_rdt = RecordDictionaryTool(param_dictionary=self.sal)
#todo: use only flat dicts for now, may change later...
# data_rdt = RecordDictionaryTool(taxonomy=self.tx)
# coord_rdt = RecordDictionaryTool(taxonomy=self.tx)
root_rdt['salinity'] = salinity
root_rdt['time'] = time
root_rdt['lat'] = latitude
root_rdt['lon'] = longitude
root_rdt['height'] = height
# root_rdt['coordinates'] = coord_rdt
# root_rdt['data'] = data_rdt
return build_granule(data_producer_id='ctd_L2_salinity', param_dictionary=self.sal, record_dictionary=root_rdt)
def _create_input_param_dict_for_test(self, parameter_dict_name=''):
pdict = ParameterDictionary()
t_ctxt = ParameterContext(
'time',
param_type=QuantityType(value_encoding=numpy.dtype('float64')))
t_ctxt.axis = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 01-01-1900'
pdict.add_context(t_ctxt)
cond_ctxt = ParameterContext(
'conductivity',
param_type=QuantityType(value_encoding=numpy.dtype('float32')))
cond_ctxt.uom = ''
pdict.add_context(cond_ctxt)
pres_ctxt = ParameterContext(
'pressure',
param_type=QuantityType(value_encoding=numpy.dtype('float32')))
pres_ctxt.uom = ''
pdict.add_context(pres_ctxt)
temp_ctxt = ParameterContext(
'temperature',
param_type=QuantityType(value_encoding=numpy.dtype('float32')))
temp_ctxt.uom = ''
pdict.add_context(temp_ctxt)
dens_ctxt = ParameterContext(
'density',
param_type=QuantityType(value_encoding=numpy.dtype('float32')))
dens_ctxt.uom = ''
pdict.add_context(dens_ctxt)
sal_ctxt = ParameterContext(
'salinity',
param_type=QuantityType(value_encoding=numpy.dtype('float32')))
sal_ctxt.uom = ''
pdict.add_context(sal_ctxt)
#create temp streamdef so the data product can create the stream
pc_list = []
for pc_k, pc in pdict.iteritems():
ctxt_id = self.dataset_management.create_parameter_context(
pc_k, pc[1].dump())
pc_list.append(ctxt_id)
self.addCleanup(self.dataset_management.delete_parameter_context,
ctxt_id)
pdict_id = self.dataset_management.create_parameter_dictionary(
parameter_dict_name, pc_list)
self.addCleanup(self.dataset_management.delete_parameter_dictionary,
pdict_id)
return pdict_id
def _make_coverage(path):
tcrs = CRS([AxisTypeEnum.TIME])
scrs = CRS([AxisTypeEnum.LON, AxisTypeEnum.LAT, AxisTypeEnum.HEIGHT])
tdom = GridDomain(GridShape('temporal', [0]), tcrs, MutabilityEnum.EXTENSIBLE)
sdom = GridDomain(GridShape('spatial', [0]), scrs, MutabilityEnum.IMMUTABLE) # Dimensionality is excluded for now
pdict = ParameterDictionary()
t_ctxt = ParameterContext('time', param_type=QuantityType(value_encoding=np.int64))
t_ctxt.axis = AxisTypeEnum.TIME
t_ctxt.uom = 'seconds since 1970-01-01'
t_ctxt.fill_value = 0x0
pdict.add_context(t_ctxt)
lat_ctxt = ParameterContext('lat', param_type=QuantityType(value_encoding=np.float32))
lat_ctxt.axis = AxisTypeEnum.LAT
lat_ctxt.uom = 'degree_north'
lat_ctxt.fill_value = 0e0
pdict.add_context(lat_ctxt)
lon_ctxt = ParameterContext('lon', param_type=QuantityType(value_encoding=np.float32))
lon_ctxt.axis = AxisTypeEnum.LON
lon_ctxt.uom = 'degree_east'
lon_ctxt.fill_value = 0e0
pdict.add_context(lon_ctxt)
cat = {0:'lemon',1:'apple',2:'banana',99:'None'}
cat_ctxt = ParameterContext('category', param_type=CategoryType(categories=cat))
cat_ctxt.long_name = "example of category"
pdict.add_context(cat_ctxt)
dens_ctxt = ParameterContext('quantity', param_type=QuantityType(value_encoding=np.float32))
dens_ctxt.uom = 'unknown'
dens_ctxt.fill_value = 0x0
pdict.add_context(dens_ctxt)
const_ctxt = ParameterContext('constant', param_type=ConstantType())
const_ctxt.long_name = 'example of a parameter of type ConstantType'
pdict.add_context(const_ctxt)
rec_ctxt = ParameterContext('boolean', param_type=BooleanType())
rec_ctxt.long_name = 'example of a parameter of type BooleanType'
pdict.add_context(rec_ctxt)
rec_ctxt = ParameterContext('range', param_type=ConstantRangeType())
rec_ctxt.long_name = 'Range example'
rec_ctxt.fill_value = 0x0
pdict.add_context(rec_ctxt)
rec_ctxt = ParameterContext('record', param_type=RecordType())
rec_ctxt.long_name = 'example of a parameter of type RecordType, will be filled with dictionaries'
rec_ctxt.fill_value = 0x0
pdict.add_context(rec_ctxt)
serial_ctxt = ParameterContext('array', param_type=ArrayType())
serial_ctxt.uom = 'unknown'
serial_ctxt.fill_value = 0x0
pdict.add_context(serial_ctxt)
guid = create_guid()
guid = guid.replace("-", "")
cov = SimplexCoverage(path, guid, name="sample_cov", parameter_dictionary=pdict, temporal_domain=tdom, spatial_domain=sdom)
return (cov,path+os.sep+guid)
