def test_write_data(specimen, path):
msg = sdmx.read_sdmx(path)
result = sdmx.to_pandas(msg)
expected = specimen.expected_data(path)
if expected is not None:
print(expected, result, sep="\n")
assert_pd_equal(expected, result)
# TODO incomplete
assert isinstance(result, (pd.Series, pd.DataFrame, list)), type(result)
def test_flat(specimen):
# Create a bare Message
msg = DataMessage()
# Recreate the content from exr-flat.json
header = Header(
id="62b5f19d-f1c9-495d-8446-a3661ed24753",
prepared="2012-11-29T08:40:26Z",
sender=model.Agency(id="ECB"),
)
msg.header = header
ds = DataSet()
# Create a Key and attributes
key = Key(
FREQ="D",
CURRENCY="NZD",
CURRENCY_DENOM="EUR",
EXR_TYPE="SP00",
EXR_SUFFIX="A",
TIME_PERIOD="2013-01-18",
)
obs_status = DataAttribute(id="OBS_STATUS")
attr = {"OBS_STATUS": AttributeValue(value_for=obs_status, value="A")}
ds.obs.append(Observation(dimension=key, value=1.5931, attached_attribute=attr))
key = key.copy(TIME_PERIOD="2013-01-21")
ds.obs.append(Observation(dimension=key, value=1.5925, attached_attribute=attr))
key = key.copy(CURRENCY="RUB", TIME_PERIOD="2013-01-18")
ds.obs.append(Observation(dimension=key, value=40.3426, attached_attribute=attr))
key = key.copy(TIME_PERIOD="2013-01-21")
ds.obs.append(Observation(dimension=key, value=40.3000, attached_attribute=attr))
msg.data.append(ds)
# Write to pd.Dataframe
df1 = sdmx.to_pandas(msg)
with specimen("flat.json") as f:
ref = sdmx.read_sdmx(f)
df2 = sdmx.to_pandas(ref)
assert_pd_equal(df1, df2)
def test_doc_usage_data():
"""Code examples in usage.rst."""
ecb = Client("ECB")
data_response = ecb.data(
resource_id="EXR",
key={"CURRENCY": "USD+JPY"},
params={
"startPeriod": "2016",
"endPeriod": "2016-12-31"
},
)
# # Commented: do the same without triggering requests for validation
# data_response = ecb.data(resource_id='EXR', key='.JPY+USD...',
# params={'startPeriod': '2016',
# 'endPeriod': '2016-12-31'})
data = data_response.data[0]
assert type(data) is GenericDataSet
# This message doesn't explicitly specify the remaining dimensions; unless
# they are inferred from the SeriesKeys, then the DimensionDescriptor is
# not complete
# assert data.structured_by.dimensions[-1] == 'TIME_PERIOD'
# data.dim_at_obs
series_keys = list(data.series)
assert len(series_keys) == 16
series_keys[5]
assert sorted(set(sk.FREQ.value
for sk in data.series)) == "A D H M Q".split()
daily = sdmx.to_pandas(data).xs("D", level="FREQ")
assert len(daily) == 514
assert_pd_equal(daily.tail().values,
np.array([1.0446, 1.0445, 1.0401, 1.0453, 1.0541]))
def test_write_dataflow(specimen):
# Read the INSEE dataflow definition
with specimen("INSEE/dataflow") as f:
msg = sdmx.read_sdmx(f)
# Convert to pandas
result = sdmx.to_pandas(msg, include="dataflow")
# Number of Dataflows described in the file
assert len(result["dataflow"]) == 663
# ID and names of first Dataflows
mbop = "Monthly Balance of Payments - "
expected = pd.Series(
{
"ACT-TRIM-ANC": "Activity by sex and age - Quarterly series",
"BPM6-CCAPITAL": "{}Capital account".format(mbop),
"BPM6-CFINANCIER": "{}Financial account".format(mbop),
"BPM6-CTRANSACTION": "{}Current transactions account".format(mbop),
"BPM6-TOTAL": "{}Overall total and main headings".format(mbop),
}
)
assert_pd_equal(result["dataflow"].head(), expected)
def test_doc_index1():
"""First code example in index.rst."""
estat = Client("ESTAT")
flow_response = estat.dataflow("une_rt_a")
with pytest.raises(TypeError):
# This presumes the DataStructureDefinition instance can conduct a
# network request for its own content
structure_response = flow_response.dataflow.une_rt_a.structure(
request=True, target_only=False)
# Same effect
structure_response = estat.get(
"datastructure", flow_response.dataflow.une_rt_a.structure.id)
# Even better: Client.get(…) should examine the class and ID of the object
# structure = estat.get(flow_response.dataflow.une_rt_a.structure)
# Show some codelists
s = sdmx.to_pandas(structure_response)
expected = pd.Series(
{
"AT": "Austria",
"BE": "Belgium",
"BG": "Bulgaria",
"CH": "Switzerland",
"CY": "Cyprus",
},
name="GEO",
).rename_axis("CL_GEO")
# Codelists are converted to a DictLike
assert isinstance(s.codelist, DictLike)
# Same effect
assert_pd_equal(s.codelist["CL_GEO"].sort_index().head(), expected)
def test_doc_usage_structure():
"""Code examples in walkthrough.rst."""
ecb = Client("ECB")
ecb_via_proxy = Client("ECB", proxies={"http": "http://1.2.3.4:5678"})
assert all(
getattr(ecb_via_proxy.session, k) == v for k, v in (
("proxies", {
"http": "http://1.2.3.4:5678"
}),
("stream", False),
("timeout", 30.1),
))
msg1 = ecb.categoryscheme(provider="all")
assert msg1.response.url == (
"https://sdw-wsrest.ecb.europa.eu/service/categoryscheme/all/latest"
"?references=parentsandsiblings")
# Check specific headers
headers = msg1.response.headers
assert headers["Content-Type"] == ("application/vnd.sdmx.structure+xml; "
"version=2.1")
assert all(k in headers for k in ["Connection", "Date", "Server"])
# Removed: in pandaSDMX 0.x this was a convenience method that (for this
# structure message) returned two DataStructureDefinitions. Contra the
# spec, that assumes:
# - There is 1 Categorization using the CategoryScheme; there could be
# many.
# - The Categorization maps DataStructureDefinitions to Categories, when
# there could be many.
# list(cat_response.category_scheme['MOBILE_NAVI']['07'])
dfs = sdmx.to_pandas(msg1.dataflow).head()
expected = pd.Series({
"AME":
"AMECO",
"BKN":
"Banknotes statistics",
"BLS":
"Bank Lending Survey Statistics",
"BOP": ("Euro Area Balance of Payments and International Investment "
"Position Statistics"),
"BSI":
"Balance Sheet Items",
})
assert_pd_equal(dfs, expected)
flows = ecb.dataflow() # noqa: F841
dsd_id = msg1.dataflow.EXR.structure.id
assert dsd_id == "ECB_EXR1"
refs = dict(references="all")
msg2 = ecb.datastructure(resource_id=dsd_id, params=refs)
dsd = msg2.structure[dsd_id]
assert sdmx.to_pandas(dsd.dimensions) == [
"FREQ",
"CURRENCY",
"CURRENCY_DENOM",
"EXR_TYPE",
"EXR_SUFFIX",
"TIME_PERIOD",
]
cl = sdmx.to_pandas(msg2.codelist["CL_CURRENCY"]).sort_index()
expected = pd.Series(
{
"ADF": "Andorran Franc (1-1 peg to the French franc)",
"ADP": "Andorran Peseta (1-1 peg to the Spanish peseta)",
"AED": "United Arab Emirates dirham",
"AFA": "Afghanistan afghani (old)",
"AFN": "Afghanistan, Afghanis",
},
name="Currency code list",
).rename_axis("CL_CURRENCY")
assert_pd_equal(cl.head(), expected)