def test_rank_daterange_start_overlap_overwrite():
o = ObsSurface.load()
o._rank_data.clear()
test_uid = "test-uid-123"
o.set_rank(uuid=test_uid, rank=1, date_range="2012-01-01_2013-01-01")
assert o._rank_data == {
"test-uid-123": {
"2012-01-01-00:00:00+00:00_2013-01-01-00:00:00+00:00": 1
}
}
o.set_rank(uuid=test_uid,
rank=2,
date_range="2012-01-01_2012-06-01",
overwrite=True)
assert o._rank_data == {
"test-uid-123": {
"2012-06-01-00:00:01+00:00_2013-01-01-00:00:00+00:00": 1,
"2012-01-01-00:00:00+00:00_2012-06-01-00:00:00+00:00": 2,
}
}
o.set_rank(uuid=test_uid,
rank=1,
date_range="2012-01-01_2013-01-01",
overwrite=True)
expected = {
"test-uid-123": {
"2012-01-01-00:00:00+00:00_2013-01-01-00:00:00+00:00": 1
}
}
assert o._rank_data == expected
def search(**kwargs): # type: ignore
"""Search for observations data. Any keyword arguments may be passed to the
the function and these keywords will be used to search the metadata associated
with each Datasource.
Example / commonly used arguments are given below.
Args:
species: Terms to search for in Datasources
locations: Where to search for the terms in species
inlet: Inlet height such as 100m
instrument: Instrument name such as picarro
find_all: Require all search terms to be satisfied
start_date: Start datetime for search.
If None a start datetime of UNIX epoch (1970-01-01) is set
end_date: End datetime for search.
If None an end datetime of the current datetime is set
skip_ranking: If True skip ranking system, defaults to False
Returns:
dict: List of keys of Datasources matching the search parameters
"""
from addict import Dict as aDict
from copy import deepcopy
from itertools import chain as iter_chain
from openghg.store import ObsSurface, Footprints, Emissions, EulerianModel
from openghg.store.base import Datasource
from openghg.util import (
timestamp_now,
timestamp_epoch,
timestamp_tzaware,
clean_string,
closest_daterange,
find_daterange_gaps,
split_daterange_str,
load_json,
)
from openghg.dataobjects import SearchResults
# Get a copy of kwargs as we make some modifications below
kwargs_copy = deepcopy(kwargs)
# Do this here otherwise we have to produce them for every datasource
start_date = kwargs.get("start_date")
end_date = kwargs.get("end_date")
if start_date is None:
start_date = timestamp_epoch()
else:
start_date = timestamp_tzaware(start_date)
if end_date is None:
end_date = timestamp_now()
else:
end_date = timestamp_tzaware(end_date)
kwargs_copy["start_date"] = start_date
kwargs_copy["end_date"] = end_date
skip_ranking = kwargs_copy.get("skip_ranking", False)
try:
del kwargs_copy["skip_ranking"]
except KeyError:
pass
# As we might have kwargs that are None we want to get rid of those
search_kwargs = {k: clean_string(v) for k, v in kwargs_copy.items() if v is not None}
# Speices translation
species = search_kwargs.get("species")
if species is not None:
if not isinstance(species, list):
species = [species]
translator = load_json("species_translator.json")
updated_species = []
for s in species:
updated_species.append(s)
try:
translated = translator[s]
except KeyError:
pass
else:
updated_species.extend(translated)
search_kwargs["species"] = updated_species
data_type = search_kwargs.get("data_type", "timeseries")
valid_data_types = ("timeseries", "footprints", "emissions", "eulerian_model")
if data_type not in valid_data_types:
raise ValueError(f"{data_type} is not a valid data type, please select one of {valid_data_types}")
# Assume we want timeseries data
obj: Union[ObsSurface, Footprints, Emissions, EulerianModel] = ObsSurface.load()
if data_type == "footprints":
obj = Footprints.load()
elif data_type == "emissions":
obj = Emissions.load()
elif data_type == "eulerian_model":
obj = EulerianModel.load()
datasource_uuids = obj.datasources()
# Shallow load the Datasources so we can search their metadata
datasources = (Datasource.load(uuid=uuid, shallow=True) for uuid in datasource_uuids)
# For the time being this will return a dict until we know how best to represent
# the footprints and emissions results in a SearchResult object
if data_type in {"emissions", "footprints", "eulerian_model"}:
sources: Dict = aDict()
for datasource in datasources:
if datasource.search_metadata(**search_kwargs):
uid = datasource.uuid()
sources[uid]["keys"] = datasource.keys_in_daterange(start_date=start_date, end_date=end_date)
sources[uid]["metadata"] = datasource.metadata()
return sources
# Find the Datasources that contain matching metadata
matching_sources = {d.uuid(): d for d in datasources if d.search_metadata(**search_kwargs)}
# TODO - Update this as it only uses the ACRG repo JSON at the moment
# Check if this site only has one inlet, if so skip ranking
# if "site" in search_kwargs:
# site = search_kwargs["site"]
# if not isinstance(site, list) and not multiple_inlets(site=site):
# skip_ranking = True
# If there isn't *any* ranking data at all, skip all the ranking functionality
if not obj._rank_data:
skip_ranking = True
# If only one datasource has been returned, skip all the ranking functionality
if len(matching_sources) == 1:
skip_ranking = True
# If we have the site, inlet and instrument then just return the data
# TODO - should instrument be added here
if {"site", "inlet", "species"} <= search_kwargs.keys() or skip_ranking is True:
specific_sources = aDict()
for datasource in matching_sources.values():
specific_keys = datasource.keys_in_daterange(start_date=start_date, end_date=end_date)
if not specific_keys:
continue
metadata = datasource.metadata()
site = metadata["site"]
species = metadata["species"]
inlet = metadata["inlet"]
specific_sources[site][species][inlet]["keys"] = specific_keys
specific_sources[site][species][inlet]["metadata"] = metadata
return SearchResults(results=specific_sources.to_dict(), ranked_data=False)
highest_ranked = aDict()
for uid, datasource in matching_sources.items():
# Find the site and then the ranking
metadata = datasource.metadata()
# Get the site inlet and species
site = metadata["site"]
species = metadata["species"]
rank_data = obj.get_rank(uuid=uid, start_date=start_date, end_date=end_date)
# If this Datasource doesn't have any ranking data skip it and move on
if not rank_data:
continue
# There will only be a single rank key
rank_value = next(iter(rank_data))
# Get the daterange this rank covers
rank_dateranges = rank_data[rank_value]
# Each match we store gives us the information we need
# to retrieve the data
match = {"uuid": uid, "dateranges": rank_dateranges}
# Need to ensure we get all the dates covered
if species in highest_ranked[site]:
species_rank_data = highest_ranked[site][species]
# If we have a higher (lower number) rank save it
if rank_value < species_rank_data["rank"]:
species_rank_data["rank"] = rank_value
species_rank_data["matching"] = [match]
# If another Datasource has the same rank for another daterange
# we want to save that as well
elif rank_value == species_rank_data["rank"]:
species_rank_data["matching"].append(match)
else:
highest_ranked[site][species]["rank"] = rank_value
highest_ranked[site][species]["matching"] = [match]
if not highest_ranked:
raise ValueError(
(
"No ranking data set for the given search parameters."
" Please refine your search to include a specific site, species and inlet."
)
)
# Now we have the highest ranked data the dateranges there are ranks for
# we want to fill in the gaps with (currently) the highest inlet from that site
# We just want some rank_metadata to go along with the final data scheme
# Can key a key of date - inlet
data_keys: Dict = aDict()
for site, species in highest_ranked.items():
for sp, data in species.items():
# data_keys[site][sp]["keys"] = []
species_keys = []
species_rank_data = {}
species_metadata = {}
for match_data in data["matching"]:
uuid = match_data["uuid"]
match_dateranges = match_data["dateranges"]
# Get the datasource as it's already in the dictionary
# we created earlier
datasource = matching_sources[uuid]
metadata = datasource.metadata()
inlet = metadata["inlet"]
keys = []
for dr in match_dateranges:
date_keys = datasource.keys_in_daterange_str(daterange=dr)
if date_keys:
keys.extend(date_keys)
# We'll add this to the metadata in the search results we return at the end
species_rank_data[dr] = inlet
species_keys.extend(keys)
species_metadata[inlet] = metadata
# Only create the dictionary keys if we have some data keys
if species_keys:
data_keys[site][sp]["keys"] = species_keys
data_keys[site][sp]["rank_metadata"] = species_rank_data
data_keys[site][sp]["metadata"] = species_metadata
else:
continue
# We now need to retrieve data for the dateranges for which we don't have ranking data
# To do this find the gaps in the daterange over which the user has requested data
# and the dates for which we have ranking information
# Get the dateranges that are covered by ranking information
daterange_strs = list(iter_chain.from_iterable([m["dateranges"] for m in data["matching"]]))
# Find the gaps in the ranking coverage
gap_dateranges = find_daterange_gaps(
start_search=start_date, end_search=end_date, dateranges=daterange_strs
)
# We want the dateranges and inlets for those dateranges
inlet_dateranges = data_keys[site][sp]["rank_metadata"]
# These are the dateranges for which we have ranking information for this site and species
ranked_dateranges = list(data_keys[site][sp]["rank_metadata"].keys())
for gap_daterange in gap_dateranges:
# We want to select the inlet that's ranked for dates closest to the ones we have here
closest_dr = closest_daterange(to_compare=gap_daterange, dateranges=ranked_dateranges)
gap_start, gap_end = split_daterange_str(gap_daterange)
# Find the closest ranked inlet by date
chosen_inlet = inlet_dateranges[closest_dr]
inlet_metadata = data_keys[site][sp]["metadata"][chosen_inlet]
inlet_instrument = inlet_metadata["instrument"]
inlet_sampling_period = inlet_metadata["sampling_period"]
# Then we want to retrieve the correct metadata for those inlets
results: SearchResults = search(
site=site,
species=sp,
inlet=chosen_inlet,
instrument=inlet_instrument,
sampling_period=inlet_sampling_period,
start_date=gap_start,
end_date=gap_end,
) # type: ignore
if not results:
continue
# Retrieve the data keys
inlet_data_keys = results.keys(site=site, species=sp, inlet=chosen_inlet)
data_keys[site][sp]["keys"].extend(inlet_data_keys)
# Remove any duplicate keys
data_keys[site][sp]["keys"] = list(set(data_keys[site][sp]["keys"]))
# TODO - create a stub for addict
dict_data_keys = data_keys.to_dict() # type: ignore
return SearchResults(results=dict_data_keys, ranked_data=True)
def data_read():
get_local_bucket(empty=True)
# DECC network sites
network = "DECC"
bsd_248_path = get_datapath(filename="bsd.picarro.1minute.248m.min.dat", data_type="CRDS")
bsd_108_path = get_datapath(filename="bsd.picarro.1minute.108m.min.dat", data_type="CRDS")
bsd_42_path = get_datapath(filename="bsd.picarro.1minute.42m.min.dat", data_type="CRDS")
bsd_paths = [bsd_248_path, bsd_108_path, bsd_42_path]
bsd_results = ObsSurface.read_file(filepath=bsd_paths, data_type="CRDS", site="bsd", network=network)
hfd_100_path = get_datapath(filename="hfd.picarro.1minute.100m.min.dat", data_type="CRDS")
hfd_50_path = get_datapath(filename="hfd.picarro.1minute.50m.min.dat", data_type="CRDS")
hfd_paths = [hfd_100_path, hfd_50_path]
ObsSurface.read_file(filepath=hfd_paths, data_type="CRDS", site="hfd", network=network)
tac_path = get_datapath(filename="tac.picarro.1minute.100m.test.dat", data_type="CRDS")
ObsSurface.read_file(filepath=tac_path, data_type="CRDS", site="tac", network=network)
# GCWERKS data (AGAGE network sites)
data_filepath = get_datapath(filename="capegrim-medusa.18.C", data_type="GC")
prec_filepath = get_datapath(filename="capegrim-medusa.18.precisions.C", data_type="GC")
ObsSurface.read_file(filepath=(data_filepath, prec_filepath), site="CGO", data_type="GCWERKS", network="AGAGE")
mhd_data_filepath = get_datapath(filename="macehead.12.C", data_type="GC")
mhd_prec_filepath = get_datapath(filename="macehead.12.precisions.C", data_type="GC")
ObsSurface.read_file(filepath=(mhd_data_filepath, mhd_prec_filepath), site="MHD", data_type="GCWERKS", network="AGAGE", instrument="GCMD")
# Set ranking information for BSD
obs = ObsSurface.load()
uid_248 = bsd_results["processed"]["bsd.picarro.1minute.248m.min.dat"]["ch4"]
obs.set_rank(uuid=uid_248, rank=1, date_range="2012-01-01_2013-01-01")
uid_108 = bsd_results["processed"]["bsd.picarro.1minute.108m.min.dat"]["ch4"]
obs.set_rank(uuid=uid_108, rank=1, date_range="2014-09-02_2014-11-01")
obs.set_rank(uuid=uid_248, rank=1, date_range="2015-01-01_2015-11-01")
obs.set_rank(uuid=uid_108, rank=1, date_range="2016-09-02_2018-11-01")
uid_42 = bsd_results["processed"]["bsd.picarro.1minute.42m.min.dat"]["ch4"]
obs.set_rank(uuid=uid_42, rank=1, date_range="2019-01-02_2021-01-01")
# Emissions data
test_datapath = get_emissions_datapath("co2-gpp-cardamom-mth_EUROPE_2012.nc")
Emissions.read_file(
filepath=test_datapath,
species="co2",
source="gpp-cardamom",
date="2012",
domain="europe",
high_time_resolution=False,
)
# Footprint data
datapath = get_footprint_datapath("footprint_test.nc")
site = "TMB"
network = "LGHG"
height = "10m"
domain = "EUROPE"
model = "test_model"
Footprints.read_file(
filepath=datapath, site=site, model=model, network=network, height=height, domain=domain
)
def test_read_GC():
get_local_bucket(empty=True)
data_filepath = get_datapath(filename="capegrim-medusa.18.C",
data_type="GC")
precision_filepath = get_datapath(
filename="capegrim-medusa.18.precisions.C", data_type="GC")
results = ObsSurface.read_file(filepath=(data_filepath,
precision_filepath),
data_type="GCWERKS",
site="CGO",
network="AGAGE")
# 30/11/2021: Species labels were updated to be standardised in line with variable naming
# This list of expected labels was updated.
expected_keys = [
'c2cl4_70m', 'c2f6_70m', 'c2h2_70m', 'c2h6_70m', 'c2hcl3_70m',
'c3f8_70m', 'c3h8_70m', 'c4f10_70m', 'c4f8_70m', 'c6f14_70m',
'c6h5ch3_70m', 'c6h6_70m', 'cc3h8_70m', 'ccl4_70m', 'cf4_70m',
'cfc112_70m', 'cfc113_70m', 'cfc114_70m', 'cfc115_70m', 'cfc11_70m',
'cfc12_70m', 'cfc13_70m', 'ch2br2_70m', 'ch2cl2_70m', 'ch3br_70m',
'ch3ccl3_70m', 'ch3cl_70m', 'ch3i_70m', 'chbr3_70m', 'chcl3_70m',
'cos_70m', 'desflurane_70m', 'halon1211_70m', 'halon1301_70m',
'halon2402_70m', 'hcfc124_70m', 'hcfc132b_70m', 'hcfc133a_70m',
'hcfc141b_70m', 'hcfc142b_70m', 'hcfc22_70m', 'hfc125_70m',
'hfc134a_70m', 'hfc143a_70m', 'hfc152a_70m', 'hfc227ea_70m',
'hfc236fa_70m', 'hfc23_70m', 'hfc245fa_70m', 'hfc32_70m',
'hfc365mfc_70m', 'hfc4310mee_70m', 'nf3_70m', 'sf5cf3_70m', 'sf6_70m',
'so2f2_70m'
]
assert sorted(list(
results["processed"]["capegrim-medusa.18.C"].keys())) == expected_keys
# Load in some data
uuid = results["processed"]["capegrim-medusa.18.C"]["hfc152a_70m"]
hfc152a_data = Datasource.load(uuid=uuid, shallow=False).data()
hfc152a_data = hfc152a_data[
"2018-01-01-02:24:00+00:00_2018-01-31-23:33:00+00:00"]
assert hfc152a_data.time[0] == Timestamp("2018-01-01T02:24:00")
assert hfc152a_data.time[-1] == Timestamp("2018-01-31T23:33:00")
assert hfc152a_data["hfc152a"][0] == 4.409
assert hfc152a_data["hfc152a"][-1] == 4.262
assert hfc152a_data["hfc152a_repeatability"][0] == 0.03557
assert hfc152a_data["hfc152a_repeatability"][-1] == 0.03271
assert hfc152a_data["hfc152a_status_flag"][0] == 0
assert hfc152a_data["hfc152a_status_flag"][-1] == 0
assert hfc152a_data["hfc152a_integration_flag"][0] == 0
assert hfc152a_data["hfc152a_integration_flag"][-1] == 0
# Check we have the Datasource info saved
obs = ObsSurface.load()
assert sorted(obs._datasource_uuids.values()) == expected_keys
attrs = hfc152a_data.attrs
assert attributes_checker_obssurface(attrs=attrs, species="hfc152a")
# # Now test that if we add more data it adds it to the same Datasource
uuid_one = obs.datasources()[0]
datasource = Datasource.load(uuid=uuid_one)
data_one = datasource.data()
assert list(data_one.keys()) == [
"2018-01-01-02:24:00+00:00_2018-01-31-23:33:00+00:00"
]
data_filepath = get_datapath(filename="capegrim-medusa.future.C",
data_type="GC")
precision_filepath = get_datapath(
filename="capegrim-medusa.future.precisions.C", data_type="GC")
results = ObsSurface.read_file(filepath=(data_filepath,
precision_filepath),
data_type="GCWERKS",
site="CGO",
network="AGAGE")
datasource = Datasource.load(uuid=uuid_one)
data_one = datasource.data()
assert sorted(list(data_one.keys())) == [
"2018-01-01-02:24:00+00:00_2018-01-31-23:33:00+00:00",
"2023-01-01-02:24:00+00:00_2023-01-31-23:33:00+00:00",
]
data_filepath = get_datapath(filename="trinidadhead.01.C", data_type="GC")
precision_filepath = get_datapath(filename="trinidadhead.01.precisions.C",
data_type="GC")
ObsSurface.read_file(
filepath=(data_filepath, precision_filepath),
data_type="GCWERKS",
site="THD",
instrument="gcmd",
network="AGAGE",
)
obs = ObsSurface.load()
table = obs._datasource_table
assert table["cgo"]["agage"]["nf3"]["70m"]
assert table["cgo"]["agage"]["hfc236fa"]["70m"]
assert table["cgo"]["agage"]["halon1211"]["70m"]
assert table["thd"]["agage"]["cfc11"]["10m"]
assert table["thd"]["agage"]["n2o"]["10m"]
assert table["thd"]["agage"]["ccl4"]["10m"]
def test_read_CRDS():
get_local_bucket(empty=True)
filepath = get_datapath(filename="bsd.picarro.1minute.248m.min.dat",
data_type="CRDS")
results = ObsSurface.read_file(filepath=filepath,
data_type="CRDS",
site="bsd",
network="DECC")
keys = results["processed"]["bsd.picarro.1minute.248m.min.dat"].keys()
assert sorted(keys) == ["ch4", "co", "co2"]
# Load up the assigned Datasources and check they contain the correct data
data = results["processed"]["bsd.picarro.1minute.248m.min.dat"]
ch4_data = Datasource.load(uuid=data["ch4"]).data()
ch4_data = ch4_data["2014-01-30-11:12:30+00:00_2014-11-30-11:23:30+00:00"]
assert ch4_data.time[0] == Timestamp("2014-01-30T11:12:30")
assert ch4_data["ch4"][0] == 1959.55
assert ch4_data["ch4"][-1] == 1962.8
assert ch4_data["ch4_variability"][-1] == 1.034
assert ch4_data["ch4_number_of_observations"][-1] == 26.0
obs = ObsSurface.load()
uuid_one = obs.datasources()[0]
datasource = Datasource.load(uuid=uuid_one)
data_keys = list(datasource.data().keys())
expected_keys = [
"2014-01-30-11:12:30+00:00_2014-11-30-11:23:30+00:00",
"2015-01-30-11:12:30+00:00_2015-11-30-11:23:30+00:00",
"2016-04-02-06:52:30+00:00_2016-11-02-12:54:30+00:00",
"2017-02-18-06:36:30+00:00_2017-12-18-15:41:30+00:00",
"2018-02-18-15:42:30+00:00_2018-12-18-15:42:30+00:00",
"2019-02-03-17:38:30+00:00_2019-12-09-10:47:30+00:00",
"2020-02-01-18:08:30+00:00_2020-12-01-22:31:30+00:00",
]
assert data_keys == expected_keys
filepath = get_datapath(filename="bsd.picarro.1minute.248m.future.dat",
data_type="CRDS")
results = ObsSurface.read_file(filepath=filepath,
data_type="CRDS",
site="bsd",
network="DECC")
uuid_one = obs.datasources()[0]
datasource = Datasource.load(uuid=uuid_one)
data_keys = sorted(list(datasource.data().keys()))
new_expected_keys = [
"2014-01-30-11:12:30+00:00_2014-11-30-11:23:30+00:00",
"2015-01-30-11:12:30+00:00_2015-11-30-11:23:30+00:00",
"2016-04-02-06:52:30+00:00_2016-11-02-12:54:30+00:00",
"2017-02-18-06:36:30+00:00_2017-12-18-15:41:30+00:00",
"2018-02-18-15:42:30+00:00_2018-12-18-15:42:30+00:00",
"2019-02-03-17:38:30+00:00_2019-12-09-10:47:30+00:00",
"2020-02-01-18:08:30+00:00_2020-12-01-22:31:30+00:00",
"2023-01-30-13:56:30+00:00_2023-01-30-14:20:30+00:00",
]
assert data_keys == new_expected_keys
table = obs._datasource_table
assert table["bsd"]["decc"]["ch4"]["248m"]
assert table["bsd"]["decc"]["co2"]["248m"]
assert table["bsd"]["decc"]["co"]["248m"]
def clear_rank(args: Dict) -> None:
obs = ObsSurface.load()
uuid = args["uuid"]
obs.clear_rank(uuid=uuid)