Skip to content

Commit

Permalink
augment single col filter cubes
Browse files Browse the repository at this point in the history
  • Loading branch information
@ernestoarbitrio
ernestoarbitrio committed Mar 18, 2024
1 parent 33948c7 commit c8fe440
Show file tree
Hide file tree
Showing 2 changed files with 156 additions and 7 deletions.
58 changes: 52 additions & 6 deletions src/cr/cube/cube.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -144,6 +144,39 @@ def valid_counts_summary_range(self) -> int:
"""The valid count summary values from first cube in this set."""
return self._cubes[0].valid_counts_summary_range

def _augment_cube_response(self, cube_response, summary_cube_resp):
all_elements = summary_cube_resp["result"]["dimensions"][0]["type"]["elements"]
values = [
el.get("value")
for el in cube_response["result"]["dimensions"][0]["type"]["elements"]
if isinstance(el.get("value"), (int, str))
]
positions = [item["id"] for item in all_elements if item["value"] in values]
cube_response["result"]["dimensions"][0]["type"]["elements"] = all_elements
data = [0] * len(summary_cube_resp["result"]["counts"])
for pos, value in zip(positions, cube_response["result"]["counts"]):
data[pos] = value
cube_response["result"]["counts"] = data
cube_response["result"]["measures"]["count"]["data"] = data
return cube_response

def _cube_needs_reshaping(self, cube_response, idx):
response = (

Check warning on line 164 in src/cr/cube/cube.py

View check run for this annotation

Codecov / codecov/patch

src/cr/cube/cube.py#L164 

Added line #L164 was not covered by tests
cube_response.get("value") if "value" in cube_response else cube_response
)
summary_cube_response = (

Check warning on line 167 in src/cr/cube/cube.py

View check run for this annotation

Codecov / codecov/patch

src/cr/cube/cube.py#L167 

Added line #L167 was not covered by tests
self._cube_responses[0].get("value")
if "value" in self._cube_responses[0]
else self._cube_responses[0]
)
return (

Check warning on line 172 in src/cr/cube/cube.py

View check run for this annotation

Codecov / codecov/patch

src/cr/cube/cube.py#L172 

Added line #L172 was not covered by tests
response["result"].get("is_single_col_cube")
and self._is_multi_cube
and idx > 0
and len(response["result"]["counts"])
!= len(summary_cube_response["result"]["counts"])
)

@lazyproperty
def _cubes(self) -> Tuple["Cube", ...]:
"""Sequence of Cube objects containing data for this analysis."""
Expand All @@ -155,8 +188,13 @@ def iter_cubes() -> Iterator[Cube]:
missing row dimension.
"""
for idx, cube_response in enumerate(self._cube_responses):
resp = (
self._augment_cube_response(cube_response, self._cube_responses[0])
if self._cube_needs_reshaping(cube_response, idx)
else cube_response
)
cube = Cube(
cube_response,
resp,
cube_idx=idx if self._is_multi_cube else None,
transforms=self._transforms_dicts[idx],
population=self._population,
Expand Down Expand Up @@ -927,7 +965,8 @@ def _flat_values(self) -> Optional[np.ndarray]:
return None
return np.array(
tuple(
np.nan if type(x) is dict else x for x in self._measure_payload["data"]
np.nan if isinstance(x, dict) else x
for x in self._measure_payload["data"]
),
dtype=np.float64,
).flatten()
Expand Down Expand Up @@ -969,7 +1008,9 @@ def _flat_values(self) -> Optional[np.ndarray]:
if measure_payload is None:
return None
return np.array(
tuple(np.nan if type(x) is dict else x for x in measure_payload["data"]),
tuple(
np.nan if isinstance(x, dict) else x for x in measure_payload["data"]
),
dtype=np.float64,
).flatten()

Expand All @@ -989,7 +1030,8 @@ def _flat_values(self) -> Optional[np.ndarray]:
return None
return np.array(
tuple(
np.nan if type(x) is dict else x for x in self._measure_payload["data"]
np.nan if isinstance(x, dict) else x
for x in self._measure_payload["data"]
),
dtype=np.float64,
).flatten()
Expand Down Expand Up @@ -1028,7 +1070,9 @@ def _flat_values(self) -> Optional[np.ndarray]:
return None

return np.array(
tuple(np.nan if type(x) is dict else x for x in measure_payload["data"]),
tuple(
np.nan if isinstance(x, dict) else x for x in measure_payload["data"]
),
dtype=np.float64,
).flatten()

Expand All @@ -1049,7 +1093,9 @@ def _flat_values(self) -> Optional[np.ndarray]:
return None

return np.array(
tuple(np.nan if type(x) is dict else x for x in measure_payload["data"]),
tuple(
np.nan if isinstance(x, dict) else x for x in measure_payload["data"]
),
dtype=np.float64,
).flatten()

Expand Down
105 changes: 104 additions & 1 deletion tests/unit/test_cube.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
from cr.cube.enums import DIMENSION_TYPE as DT

from ..fixtures import CR # ---mnemonic: CR = 'cube-response'---
from ..unitutil import call, class_mock, instance_mock, property_mock
from ..unitutil import call, class_mock, instance_mock, method_mock, property_mock


class DescribeCubeSet:
Expand Down Expand Up @@ -172,6 +172,7 @@ def it_constructs_its_sequence_of_cube_objects_to_help(
cubes_ = tuple(instance_mock(request, Cube) for _ in range(4))
Cube_.side_effect = iter(cubes_)
_is_numeric_measure_prop_.return_value = False
method_mock(request, CubeSet, "_cube_needs_reshaping", return_value=False)
cube_set = CubeSet(
cube_responses=[{"cube": "resp-1"}, {"cube": "resp-2"}, {"cube": "resp-3"}],
transforms=[{"xfrms": 1}, {"xfrms": 2}, {"xfrms": 3}],
Expand Down Expand Up @@ -213,6 +214,7 @@ def but_it_inflates_the_cubes_in_special_case_of_numeric_mean_payload(
cube_.inflate.side_effect = iter(cubes_)
Cube_.return_value = cube_
_is_numeric_measure_prop_.return_value = True
method_mock(request, CubeSet, "_cube_needs_reshaping", return_value=False)
cube_set = CubeSet(
cube_responses=[{"cube": "resp-1"}, {"cube": "resp-2"}, {"cube": "resp-3"}],
transforms=[{"xfrms": 1}, {"xfrms": 2}, {"xfrms": 3}],
Expand Down Expand Up @@ -248,6 +250,107 @@ def but_it_inflates_the_cubes_in_special_case_of_numeric_mean_payload(
assert cube_.inflate.call_args_list == [call(), call(), call()]
assert cubes == cubes_[:3]

def it_constructs_its_sequence_of_augmented_cube_objects_to_help(self, request):
# cubes_ = tuple(instance_mock(request, Cube) for _ in range(2))
# cube_.inflate.side_effect = iter(cubes_)
# Cube_.return_value = cube_
method_mock(request, CubeSet, "_cube_needs_reshaping", return_value=True)
cube_set = CubeSet(
cube_responses=[
{
"result": {
"counts": [1, 1, 1, 0],
"measures": {"count": {"data": [1, 1, 1, 0]}},
"dimensions": [
{
"type": {
"class": "enum",
"elements": [
{
"id": 0,
"missing": False,
"value": "1955-11-06",
},
{
"id": 1,
"missing": False,
"value": "1955-11-07",
},
{
"id": 2,
"missing": False,
"value": "1955-11-08",
},
{"id": -1, "missing": True, "value": {"?": -1}},
],
"subtype": {
"class": "datetime",
"missing_reasons": {"No Data": -1},
"missing_rules": {},
"resolution": "D",
},
},
}
],
}
},
{
"result": {
"measures": {"count": {"data": [1, 1, 0]}},
"counts": [1, 1, 0],
"dimensions": [
{
"type": {
"class": "enum",
"elements": [
{
"id": 0,
"missing": False,
"value": "1955-11-06",
},
{
"id": 1,
"missing": False,
"value": "1955-11-07",
},
{"id": -1, "missing": True, "value": {"?": -1}},
],
"subtype": {
"class": "datetime",
"missing_reasons": {"No Data": -1},
"missing_rules": {},
"resolution": "D",
},
},
}
],
}
},
],
transforms=[{"xfrms": 1}, {"xfrms": 2}],
population=1000,
min_base=10,
)

cubes = cube_set._cubes
summary_cube = cubes[0]
single_col_filter = cubes[1]

assert len(summary_cube.partitions) == len(single_col_filter.partitions)
assert summary_cube.dimension_types == single_col_filter.dimension_types
assert summary_cube.partitions[0].counts == pytest.approx(np.array([1, 1, 1]))
assert single_col_filter.partitions[0].counts == pytest.approx(
np.array([1, 1, 0])
)
assert (
single_col_filter._cube_response["result"]["dimensions"][0]["type"][
"elements"
]
== summary_cube._cube_response["result"]["dimensions"][0]["type"][
"elements"
]
)

@pytest.mark.parametrize(
("is_multi_cube", "cube_0_ndim", "expected_value"),
((False, 1, False), (False, 0, False), (True, 1, False), (True, 0, True)),
Expand Down

0 comments on commit c8fe440

Please sign in to comment.