third_codes/eland
1
0
Fork 0
mirror of https://github.com/elastic/eland.git synced 2025-07-24 00:00:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix unpacking of median aggregation

Browse Source
This commit is contained in:
Seth Michael Larson 2020-04-03 07:56:09 -05:00 committed by GitHub
parent 023a35c3b4
commit 29af76101e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 26 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
eland/operations.py
View File

@ -480,7 +480,6 @@ class Operations:
field_names = query_compiler.get_field_names(include_scripted_fields=False) field_names = query_compiler.get_field_names(include_scripted_fields=False)
body = Query(query_params["query"]) body = Query(query_params["query"])
# convert pandas aggs to ES equivalent # convert pandas aggs to ES equivalent
es_aggs = self._map_pd_aggs_to_es_aggs(pd_aggs) es_aggs = self._map_pd_aggs_to_es_aggs(pd_aggs)
@ -509,9 +508,13 @@ class Operations:
values = list() values = list()
for es_agg in es_aggs: for es_agg in es_aggs:
if isinstance(es_agg, tuple): if isinstance(es_agg, tuple):
values.append( agg_value = response["aggregations"][es_agg[0] + "_" + field]
response["aggregations"][es_agg[0] + "_" + field][es_agg[1]]
) # Pull multiple values from 'percentiles' result.
if es_agg[0] == "percentiles":
agg_value = agg_value["values"]
values.append(agg_value[es_agg[1]])
else: else:
values.append( values.append(
response["aggregations"][es_agg + "_" + field]["value"] response["aggregations"][es_agg + "_" + field]["value"]

19
eland/tests/dataframe/test_aggs_pytest.py
View File

@ -68,3 +68,22 @@ class TestDataFrameAggs(TestData):
print(ed_sum_min_std.dtypes) print(ed_sum_min_std.dtypes)
assert_almost_equal(pd_sum_min_std, ed_sum_min_std, check_less_precise=True) assert_almost_equal(pd_sum_min_std, ed_sum_min_std, check_less_precise=True)
def test_aggs_median_var(self):
pd_ecommerce = self.pd_ecommerce()
ed_ecommerce = self.ed_ecommerce()
pd_aggs = pd_ecommerce[
["taxful_total_price", "taxless_total_price", "total_quantity"]
].agg(["median", "var"])
ed_aggs = ed_ecommerce[
["taxful_total_price", "taxless_total_price", "total_quantity"]
].agg(["median", "var"])
print(pd_aggs, pd_aggs.dtypes)
print(ed_aggs, ed_aggs.dtypes)
# Eland returns all float values for all metric aggs, pandas can return int
# TODO - investigate this more
pd_aggs = pd_aggs.astype("float64")
assert_almost_equal(pd_aggs, ed_aggs, check_less_precise=2)