def query():
field = Field(name="BEVMK3", fields=["value", "year"])
query = Query.region(region="05911", fields=["id", "name", field])
return query
def query_multi_regions():
field = Field(name="BEVMK3", fields=["value", "year"])
query = Query.region(region=["01", "02"], fields=["id", "name", field])
return query
def test_QueryExecutionerWorkflow(query):
"""Functional test for the query executioner"""
# Ira (W. Cotton, probably the first person to use the term API) want to
# try the query execution part of the datenguide GraphQL wrapper library.
# He already worked through Query builder objects ready for execution.
# He understands that he first has to create an executioner object that
# it uses the right by default, so that he does not have to supply any
# parameters.
qExec = QueryExecutioner()
# After creating the object Ira is actually a little sceptical whether
# the endpoint will correct so he extracts the endpoint and compares it
# with his expectations.
assert (qExec.endpoint == "https://api-next.datengui.de/graphql"
), "Default endpoint is wrong"
# Being satisfied that everything is setup with the correct endpoint Ira
# now wants to execute one of his queries to see that he gets some return
# values.
res_query1 = query.results()
assert res_query1 is not None, "query did not return results"
# He wants to have a closer look at the raw return query results and
# remembers that they are sorted in the results field and he has a look.
assert (type(res_query1) is
pd.DataFrame), "query results are not a python json representation"
stats = Query.get_info()
# Ira remembers that he read about the executioners functionality to
# return metadata along with the query results. So he wants to check
# whether this metadata is actually present. And that it only contains
# meta data related to his query
meta_query1 = query.meta_data()
# In particular Ira would like to have a more human readable description
# of the statistic he asked for.
assert "BEVMK3" in meta_query1, "statistic absend"
assert (meta_query1["BEVMK3"] !=
"NO DESCRIPTION FOUND"), "descrption was not obtained"
# Being satisfied with the results he obtained for his simple query
# he actually wants to try a larger one across several regions. He heard
# that this might be an issue for the server in general, but that the
# executioner takes care of addressing this issue by itself.
# Since this is a lot of information Ira would particularly
# like to drill down on the arguments that are allowed for his
# favorite statistic BEVMK3
stat_args = stats.fields["BEVMK3"].get_arguments()
assert len(stat_args) > 0
assert "statistics" in stat_args
# Although this is already really helpful Ira notices that
# one of the arguments is an ENUM and he would like to know
# the possible values that he can use for it.
enum_vals = Query.get_info("BEVMK3Statistics").enum_values
assert type(enum_vals) == dict, "Enum values should be dict"
assert len(enum_vals) > 0, "Enums should have values"
# Ira wants to add another statistic to his query.
statistic1 = query.add_field("BEV001")
statistic1.add_field("year")
statistic1.add_args({"year": 2017})
assert type(statistic1) == Field, "statistic is not a Field"
# Then he wants to get metainfo on the field.
stringio = io.StringIO()
sys.stdout = stringio
statistic1.get_info()
stats_info = re.sub(r"\n", "", stringio.getvalue())
assert "OBJECT" in stats_info, "BEV001 should be an object"
def get_df_datenguide(region_codes, stat_codes):
query = Query.region(region_codes, stat_codes)
res = (query.results().drop_duplicates(ignore_index=True))
res = res.loc[:, ~res.columns.str.contains("_source_")]
return res
def lau_query(lau_level):
q = Query.all_regions(lau=lau_level)
return q
def nuts_query(nuts_level):
q = Query.all_regions(nuts=nuts_level)
return q
def download_all_regions() -> pd.DataFrame:
"""[summary]
:raises RuntimeError: [description]
:raises RuntimeError: [description]
:return: [description]
:rtype: pd.DataFrame
"""
def nuts_query(nuts_level):
q = Query.all_regions(nuts=nuts_level)
return q
def lau_query(lau_level):
q = Query.all_regions(lau=lau_level)
return q
qb_all = Query.all_regions()
qe = QueryExecutioner()
print("start")
all_regions = qe.run_query(qb_all)
print("all")
r_nuts1 = qe.run_query(nuts_query(1))
print("nuts1")
r_nuts2 = qe.run_query(nuts_query(2))
print("nuts2")
r_nuts3 = qe.run_query(nuts_query(3))
print("nuts3")
r_lau1 = qe.run_query(lau_query(1))
print("lau")
# currently no distinction between different laus
# on datehenguide side
# r_lau2 = qe.run_query(lau_query(2))
levels = {
"nuts1": r_nuts1,
"nuts2": r_nuts2,
"nuts3": r_nuts3,
"lau": r_lau1,
# 'lau2':r_lau2
}
def isAnscestor(region_id, candidate):
"""[summary]
:param region_id: [description]
:type region_id: [type]
:param candidate: [description]
:type candidate: [type]
:return: [description]
:rtype: [type]
"""
return region_id.startswith(candidate) and candidate != region_id
def parent(region_id, region_details):
"""[summary]
:param region_id: [description]
:type region_id: [type]
:param region_details: [description]
:type region_details: [type]
:return: [description]
:rtype: [type]
"""
desc = region_details.assign(ansc=lambda df: df.index.map(
lambda i: isAnscestor(region_id, i))).query("ansc")
max_lev = desc.level.max() # noqa: F841
parent_frame = desc.query("level == @max_lev")
if not parent_frame.empty:
return parent_frame.iloc[0, :].name
else:
None
if all_regions is None:
raise RuntimeError("Was not able to download all regions")
for k in levels:
if levels[k] is None:
raise RuntimeError(f"Was not able to download {k} regions")
all_regions_df = pd.concat([
pd.DataFrame(page["data"]["allRegions"]["regions"])
for page in cast(List[ExecutionResults], all_regions)[0].query_results
]).set_index("id")
level_df = pd.concat(
pd.concat([
pd.DataFrame(page["data"]["allRegions"]["regions"]) for page in
cast(List[ExecutionResults], levels[k])[0].query_results
]).assign(level=k) for k in levels)
all_rg_parents = all_regions_df.join(
level_df.set_index("id").loc[:, "level"]).assign(
parent=lambda df: df.index.map(
partial(
parent,
region_details=all_regions_df.assign(level=lambda df: df.
index.map(len)),
)))
all_rg_parents.loc[all_rg_parents.level == "nuts1", "parent"] = "DG"
return all_rg_parents