def __init__(self,param_dictionary=None, stream_definition_id='', locator=None):
"""
"""
if type(param_dictionary) == dict:
self._pdict = ParameterDictionary.load(param_dictionary)
elif isinstance(param_dictionary,ParameterDictionary):
self._pdict = param_dictionary
elif stream_definition_id:
pdict = RecordDictionaryTool.pdict_from_stream_def(stream_definition_id)
self._pdict = ParameterDictionary.load(pdict)
self._stream_def = stream_definition_id
else:
raise BadRequest('Unable to create record dictionary with improper ParameterDictionary')
if stream_definition_id:
self._stream_def=stream_definition_id
self._shp = None
self._rd = {}
self._locator = locator
self._setup_params()
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 _new_coverage(self, root_dir, persistence_guid, name, reference_coverage_locs, parameter_dictionary, complex_type, reference_coverage_extents={}):
reference_coverage_locs = reference_coverage_locs or [] # Can be empty
# Coverage doesn't exist, make a new one
if name is None:
raise SystemError('\'reference_coverages\' and \'name\' cannot be None')
if not isinstance(name, basestring):
raise TypeError('\'name\' must be of type basestring')
self.name = name
if parameter_dictionary is None:
parameter_dictionary = ParameterDictionary()
# Must be in 'a' for a new coverage
self.mode = 'a'
self._reference_covs = collections.OrderedDict()
if not hasattr(reference_coverage_locs, '__iter__'):
reference_coverage_locs = [reference_coverage_locs]
self._persistence_layer = PostgresPersistenceLayer(root_dir,
persistence_guid,
name=self.name,
mode=self.mode,
param_dict=parameter_dictionary,
rcov_locs=reference_coverage_locs,
rcov_extents=reference_coverage_extents,
complex_type=complex_type,
coverage_type='complex',
version=self.version)
for pc in parameter_dictionary.itervalues():
self.append_parameter(pc[1])
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 _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 _get_data(cls, config):
new_flst = get_safe(config, 'constraints.new_files', [])
hdr_cnt = get_safe(config, 'header_count', SlocumParser.DEFAULT_HEADER_SIZE)
for f in new_flst:
try:
parser = SlocumParser(f[0], hdr_cnt)
#CBM: Not in use yet...
# ext_dset_res = get_safe(config, 'external_dataset_res', None)
# t_vname = ext_dset_res.dataset_description.parameters['temporal_dimension']
# x_vname = ext_dset_res.dataset_description.parameters['zonal_dimension']
# y_vname = ext_dset_res.dataset_description.parameters['meridional_dimension']
# z_vname = ext_dset_res.dataset_description.parameters['vertical_dimension']
# var_lst = ext_dset_res.dataset_description.parameters['variables']
max_rec = get_safe(config, 'max_records', 1)
dprod_id = get_safe(config, 'data_producer_id', 'unknown data producer')
#tx_yml = get_safe(config, 'taxonomy')
#ttool = TaxyTool.load(tx_yml) #CBM: Assertion inside RDT.__setitem__ requires same instance of TaxyTool
pdict = ParameterDictionary.load(get_safe(config, 'param_dictionary'))
cnt = calculate_iteration_count(len(parser.sensor_map), max_rec)
for x in xrange(cnt):
#rdt = RecordDictionaryTool(taxonomy=ttool)
rdt = RecordDictionaryTool(param_dictionary=pdict)
for name in parser.sensor_map:
d = parser.data_map[name][x*max_rec:(x+1)*max_rec]
rdt[name]=d
#g = build_granule(data_producer_id=dprod_id, taxonomy=ttool, record_dictionary=rdt)
g = build_granule(data_producer_id=dprod_id, record_dictionary=rdt, param_dictionary=pdict)
yield g
except SlocumParseException as spe:
# TODO: Decide what to do here, raise an exception or carry on
log.error('Error parsing data file: \'{0}\''.format(f))
def _construct_stream_and_publisher(self, stream_name, stream_config):
if log.isEnabledFor(logging.TRACE): # pragma: no cover
log.trace("%r: _construct_stream_and_publisher: "
"stream_name:%r, stream_config:\n%s",
self._platform_id, stream_name,
self._pp.pformat(stream_config))
decoder = IonObjectDeserializer(obj_registry=get_obj_registry())
if 'stream_def_dict' not in stream_config:
# should not happen: PlatformAgent._validate_configuration validates this.
log.error("'stream_def_dict' key not in configuration for stream %r" % stream_name)
return
stream_def_dict = stream_config['stream_def_dict']
stream_def_dict['type_'] = 'StreamDefinition'
stream_def_obj = decoder.deserialize(stream_def_dict)
self._stream_defs[stream_name] = stream_def_obj
routing_key = stream_config['routing_key']
stream_id = stream_config['stream_id']
exchange_point = stream_config['exchange_point']
parameter_dictionary = stream_def_dict['parameter_dictionary']
log.debug("%r: got parameter_dictionary from stream_def_dict", self._platform_id)
self._data_streams[stream_name] = stream_id
self._param_dicts[stream_name] = ParameterDictionary.load(parameter_dictionary)
stream_route = StreamRoute(exchange_point=exchange_point, routing_key=routing_key)
publisher = self._create_publisher(stream_id, stream_route)
self._data_publishers[stream_name] = publisher
log.debug("%r: created publisher for stream_name=%r", self._platform_id, stream_name)
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)
def _construct_stream_and_publisher(self, stream_name, stream_config):
if log.isEnabledFor(logging.TRACE): # pragma: no cover
log.trace("%r: _construct_stream_and_publisher: "
"stream_name:%r, stream_config:\n%s",
self._platform_id, stream_name,
self._pp.pformat(stream_config))
decoder = IonObjectDeserializer(obj_registry=get_obj_registry())
if 'stream_def_dict' not in stream_config:
# should not happen: PlatformAgent._validate_configuration validates this.
log.error("'stream_def_dict' key not in configuration for stream %r" % stream_name)
return
stream_def_dict = stream_config['stream_def_dict']
stream_def_dict['type_'] = 'StreamDefinition'
stream_def_obj = decoder.deserialize(stream_def_dict)
self._stream_defs[stream_name] = stream_def_obj
routing_key = stream_config['routing_key']
stream_id = stream_config['stream_id']
exchange_point = stream_config['exchange_point']
parameter_dictionary = stream_def_dict['parameter_dictionary']
log.debug("%r: got parameter_dictionary from stream_def_dict", self._platform_id)
self._data_streams[stream_name] = stream_id
self._param_dicts[stream_name] = ParameterDictionary.load(parameter_dictionary)
stream_route = StreamRoute(exchange_point=exchange_point, routing_key=routing_key)
publisher = self._create_publisher(stream_id, stream_route)
self._data_publishers[stream_name] = publisher
log.debug("%r: created publisher for stream_name=%r", self._platform_id, stream_name)
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 _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 load_from_granule(cls, g):
"""
@brief return an instance of Record Dictionary Tool from a granule. Used when a granule is received in a message
"""
if g.param_dictionary:
result = cls(param_dictionary=ParameterDictionary.load(g.param_dictionary))
else:
result = cls(TaxyTool(g.taxonomy))
result._rd = g.record_dictionary
if result._rd.has_key(0):
result._shp = result._rd[0].shape
return result
def load_from_granule(cls, g):
if isinstance(g.param_dictionary, str):
instance = cls(stream_definition_id=g.param_dictionary, locator=g.locator)
pdict = RecordDictionaryTool.pdict_from_stream_def(g.param_dictionary)
instance._pdict = ParameterDictionary.load(pdict)
else:
instance = cls(param_dictionary=g.param_dictionary, locator=g.locator)
instance._pdict = ParameterDictionary.load(g.param_dictionary)
if g.domain:
instance._shp = (g.domain[0],)
for k,v in g.record_dictionary.iteritems():
if v is not None:
ptype = instance._pdict.get_context(k).param_type
paramval = get_value_class(ptype, domain_set = instance.domain)
paramval[:] = v
paramval.storage._storage.flags.writeable = False
instance._rd[k] = paramval
return instance
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 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 _get_data(cls, config):
"""
Retrieves config['constraints']['count'] number of random samples of length config['constraints']['array_len']
@param config Dict of configuration parameters - must contain ['constraints']['count'] and ['constraints']['count']
"""
array_len = get_safe(config, 'constraints.array_len',1)
max_rec = get_safe(config, 'max_records', 1)
dprod_id = get_safe(config, 'data_producer_id')
#tx_yml = get_safe(config, 'taxonomy')
#ttool = TaxyTool.load(tx_yml)
pdict = ParameterDictionary.load(get_safe(config, 'param_dictionary'))
arr = npr.random_sample(array_len)
log.debug('Array to send using max_rec={0}: {1}'.format(max_rec, arr))
cnt = calculate_iteration_count(arr.size, max_rec)
for x in xrange(cnt):
rdt = RecordDictionaryTool(param_dictionary=pdict)
d = arr[x*max_rec:(x+1)*max_rec]
rdt['dummy'] = d
g = rdt.to_granule()
yield g
def _get_data(cls, config):
"""
A generator that retrieves config['constraints']['count'] number of sequential Fibonacci numbers
@param config Dict of configuration parameters - must contain ['constraints']['count']
"""
cnt = get_safe(config,'constraints.count',1)
max_rec = get_safe(config, 'max_records', 1)
dprod_id = get_safe(config, 'data_producer_id')
#tx_yml = get_safe(config, 'taxonomy')
#ttool = TaxyTool.load(tx_yml)
pdict = ParameterDictionary.load(get_safe(config, 'param_dictionary'))
def fibGenerator():
"""
A Fibonacci sequence generator
"""
count = 0
ret = []
a, b = 1, 1
while 1:
count += 1
ret.append(a)
if count == max_rec:
yield np.array(ret)
ret=[]
count = 0
a, b = b, a + b
gen=fibGenerator()
cnt = calculate_iteration_count(cnt, max_rec)
for i in xrange(cnt):
rdt = RecordDictionaryTool(param_dictionary=pdict)
d = gen.next()
rdt['data'] = d
g = rdt.to_granule()
yield g
def _do_build(self):
# Reset things to ensure we don't munge everything
self._reference_covs = collections.OrderedDict()
self._range_dictionary = ParameterDictionary()
self._range_value = RangeValues()
self._reference_covs = self._build_ordered_coverage_dict()
for parameter_name in self._persistence_layer.parameter_metadata:
md = self._persistence_layer.parameter_metadata[parameter_name]
mm = self._persistence_layer.master_manager
pc = md.parameter_context
# Assign the coverage's domain object(s)
self._assign_domain(pc)
# Get the callbacks for ParameterFunctionType parameters
if hasattr(pc, '_pval_callback'):
pc._pval_callback = self.get_parameter_values
pc._pctxt_callback = self.get_parameter_context
self._range_dictionary.add_context(pc)
s = PostgresPersistedStorage(md, metadata_manager=mm, parameter_context=pc, dtype=pc.param_type.storage_encoding, fill_value=pc.param_type.fill_value, mode=self._persistence_layer.mode)
self._persistence_layer.value_list[parameter_name] = s
self._range_value[parameter_name] = get_value_class(param_type=pc.param_type, domain_set=pc.dom, storage=s)
def _construct_stream_and_publisher(self, stream_name, stream_config):
# granule_publish_rate
# records_per_granule
if log.isEnabledFor(logging.TRACE): # pragma: no cover
log.trace("%r: _construct_stream_and_publisher: "
"stream_name:%r, stream_config:\n%s",
self._platform_id, stream_name,
self._pp.pformat(stream_config))
decoder = IonObjectDeserializer(obj_registry=get_obj_registry())
if 'stream_def_dict' in stream_config:
stream_def_dict = stream_config['stream_def_dict']
stream_def_dict['type_'] = 'StreamDefinition'
stream_def_obj = decoder.deserialize(stream_def_dict)
self._stream_defs[stream_name] = stream_def_obj
log.debug("%r: using stream_def_dict", self._platform_id)
else: # TODO this case to be removed.
stream_definition_ref = stream_config['stream_definition_ref']
self._stream_defs[stream_name] = stream_definition_ref
log.debug("%r: using stream_definition_ref", self._platform_id)
routing_key = stream_config['routing_key']
stream_id = stream_config['stream_id']
exchange_point = stream_config['exchange_point']
parameter_dictionary = stream_config['parameter_dictionary']
self._data_streams[stream_name] = stream_id
self._param_dicts[stream_name] = ParameterDictionary.load(parameter_dictionary)
stream_route = StreamRoute(exchange_point=exchange_point, routing_key=routing_key)
publisher = self._create_publisher(stream_id, stream_route)
self._data_publishers[stream_name] = publisher
log.debug("%r: created publisher for stream_name=%r", self._platform_id, stream_name)
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 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
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 _get_data(cls, config):
"""
Retrieves config['constraints']['count'] number of random samples of length config['constraints']['array_len']
@param config Dict of configuration parameters - must contain ['constraints']['count'] and ['constraints']['count']
"""
ext_dset_res = get_safe(config, 'external_dataset_res', None)
# Get the Dataset object from the config (should have been instantiated in _init_acquisition_cycle)
ds=get_safe(config, 'dataset_object')
if ext_dset_res and ds:
t_vname = ext_dset_res.dataset_description.parameters['temporal_dimension']
x_vname = ext_dset_res.dataset_description.parameters['zonal_dimension']
y_vname = ext_dset_res.dataset_description.parameters['meridional_dimension']
z_vname = ext_dset_res.dataset_description.parameters['vertical_dimension']
var_lst = ext_dset_res.dataset_description.parameters['variables']
t_slice = get_safe(config, 'constraints.temporal_slice', (slice(0,1)))
#TODO: Using 'eval' here is BAD - need to find a less sketchy way to pass constraints
if isinstance(t_slice,str):
t_slice=eval(t_slice)
lon = ds.variables[x_vname][:]
lat = ds.variables[y_vname][:]
z = ds.variables[z_vname][:]
t_arr = ds.variables[t_vname][t_slice]
data_arrays = {}
for varn in var_lst:
data_arrays[varn] = ds.variables[varn][t_slice]
max_rec = get_safe(config, 'max_records', 1)
dprod_id = get_safe(config, 'data_producer_id', 'unknown data producer')
#tx_yml = get_safe(config, 'taxonomy')
#ttool = TaxyTool.load(tx_yml) #CBM: Assertion inside RDT.__setitem__ requires same instance of TaxyTool
pdict = ParameterDictionary.load(get_safe(config, 'param_dictionary'))
cnt = calculate_iteration_count(t_arr.size, max_rec)
for x in xrange(cnt):
ta = t_arr[x*max_rec:(x+1)*max_rec]
# Make a 'master' RecDict
#rdt = RecordDictionaryTool(taxonomy=ttool)
rdt = RecordDictionaryTool(param_dictionary=pdict)
# Make a 'coordinate' RecDict
#rdt_c = RecordDictionaryTool(taxonomy=ttool)
#rdt_c = RecordDictionaryTool(param_dictionary=pdict)
# Make a 'data' RecDict
#rdt_d = RecordDictionaryTool(taxonomy=ttool)
#rdt_d = RecordDictionaryTool(param_dictionary=pdict)
# Assign values to the coordinate RecDict
rdt[x_vname] = lon
rdt[y_vname] = lat
rdt[z_vname] = z
# Assign values to the data RecDict
rdt[t_vname] = ta
for key, arr in data_arrays.iteritems():
d = arr[x*max_rec:(x+1)*max_rec]
rdt[key] = d
# Add the coordinate and data RecDicts to the master RecDict
#rdt['coords'] = rdt_c
#rdt['data'] = rdt_d
# Build and return a granule
# CBM: ttool must be passed
#g = build_granule(data_producer_id=dprod_id, taxonomy=ttool, record_dictionary=rdt)
g = build_granule(data_producer_id=dprod_id, record_dictionary=rdt, param_dictionary=pdict)
yield g
ds.close()
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 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 _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 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_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 _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,
}
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_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 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_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
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 _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 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
