Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

augment single col filter cubes #398

Merged
merged 5 commits into from
Mar 19, 2024
Merged

augment single col filter cubes #398

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c8fe440
augment single col filter cubes
ernestoarbitrio Mar 18, 2024
81e39c1
refactor code
ernestoarbitrio Mar 18, 2024
2e86ec8
cover missing line
ernestoarbitrio Mar 18, 2024
ae28017
docstring
ernestoarbitrio Mar 18, 2024
fff9313
make _is_single_filter_col_cube public
ernestoarbitrio Mar 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 83 additions & 5 deletions src/cr/cube/cube.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -162,6 +162,13 @@ def iter_cubes() -> Iterator[Cube]:
population=self._population,
mask_size=self._min_base,
)
cube = (
cube.augment_response(self._cube_responses[0])
if self._is_multi_cube
and cube._is_single_filter_col_cube
and idx > 0
else cube
)
# --- numeric-measures cubes require inflation to restore their
# --- rows-dimension, others don't
yield cube.inflate() if self._is_numeric_measure else cube
Expand Down Expand Up @@ -245,6 +252,69 @@ def available_measures(self) -> FrozenSet[CUBE_MEASURE]:
cube_measures = self._cube_response.get("result", {}).get("measures", {}).keys()
return frozenset(CUBE_MEASURE(m) for m in cube_measures)

def augment_response(self, summary_cube_resp) -> "Cube":
"""Inlfate counts, data and elements dict in case of a single filter cube.

This method is called though the CubeSet while we itearate over all the cube
responses. If a cube is a single column filter and its idx > 0 it will be
augmented but only if the summary cube shape is different from its own shape.

In a multitable example we can have a text variable on the rows and a single col
filter (text) on the columns. From zz9 result the 2 cubes (summary cube and
filter cube) will have a different shape. Basically the filter cube will miss
the row labes that have 0 as counts.

| FCUBE | CAT
----+-------+----
A | 1 | 1
B | 1 | 1
C | 1 | 1
D | | 1
E | | 1
F | | 1

The FUCBE have D E and F missing cause its results doesn't count them. And the
rendering starts from the top without the correct row label association.
For a correct result the FCUBE cube_response needs to be augmentes with all the
elements of the summary cube and position the values in the corresponding
position of the only existing labels in the response.

| FCUBE | CAT
----+-------+----
A | 0 | 1
B | 0 | 1
C | 1 | 1
D | 1 | 1
E | 1 | 1
F | 0 | 1
"""
cube_resp = self._cube_response

if len(cube_resp["result"]["counts"]) != len(
summary_cube_resp["result"]["counts"]
):
elements = summary_cube_resp["result"]["dimensions"][0]["type"]["elements"]
values = [
el.get("value")
for el in cube_resp["result"]["dimensions"][0]["type"]["elements"]
if isinstance(el.get("value"), (int, str))
]
positions = [item["id"] for item in elements if item["value"] in values]
cube_resp["result"]["dimensions"][0]["type"]["elements"] = elements
data = [0] * len(summary_cube_resp["result"]["counts"])
for pos, value in zip(positions, cube_resp["result"]["counts"]):
data[pos] = value
cube_resp["result"]["counts"] = data
cube_resp["result"]["measures"]["count"]["data"] = data
return Cube(
cube_resp,
self._cube_idx_arg,
self._transforms_dict,
self._population,
self._mask_size,
)
return self

@lazyproperty
def counts(self) -> np.ndarray:
return self.counts_with_missings[self._valid_idxs]
Expand Down Expand Up @@ -927,7 +997,8 @@ 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 +1040,9 @@ 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 +1062,8 @@ 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 +1102,9 @@ 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 +1125,9 @@ 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
115 changes: 115 additions & 0 deletions tests/unit/test_cube.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,6 +170,8 @@ def it_constructs_its_sequence_of_cube_objects_to_help(
self, request, Cube_, _is_numeric_measure_prop_
):
cubes_ = tuple(instance_mock(request, Cube) for _ in range(4))
for c in cubes_:
c._is_single_filter_col_cube = False
Cube_.side_effect = iter(cubes_)
_is_numeric_measure_prop_.return_value = False
cube_set = CubeSet(
Expand Down Expand Up @@ -211,6 +213,7 @@ def but_it_inflates_the_cubes_in_special_case_of_numeric_mean_payload(
):
cubes_ = tuple(instance_mock(request, Cube) for _ in range(4))
cube_.inflate.side_effect = iter(cubes_)
cube_._is_single_filter_col_cube = False
Cube_.return_value = cube_
_is_numeric_measure_prop_.return_value = True
cube_set = CubeSet(
Expand Down Expand Up @@ -248,6 +251,118 @@ 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):
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": "A"},
{"id": 1, "missing": False, "value": "B"},
{"id": 2, "missing": False, "value": "C"},
{"id": -1, "missing": True, "value": {"?": -1}},
],
"subtype": {
"class": "text",
"missing_reasons": {"No Data": -1},
"missing_rules": {},
},
},
}
],
}
},
{
"result": {
"is_single_col_cube": True,
"measures": {"count": {"data": [1, 1, 0]}},
"counts": [1, 1, 0],
"dimensions": [
{
"type": {
"class": "enum",
"elements": [
{"id": 0, "missing": False, "value": "A"},
{"id": 1, "missing": False, "value": "C"},
{"id": -1, "missing": True, "value": {"?": -1}},
],
"subtype": {
"class": "text",
"missing_reasons": {"No Data": -1},
"missing_rules": {},
},
},
}
],
}
},
{
"result": {
"is_single_col_cube": True,
"counts": [1, 1, 1, 0],
"measures": {"count": {"data": [1, 1, 1, 0]}},
"dimensions": [
{
"type": {
"class": "enum",
"elements": [
{"id": 0, "missing": False, "value": "A"},
{"id": 1, "missing": False, "value": "B"},
{"id": 2, "missing": False, "value": "C"},
{"id": -1, "missing": True, "value": {"?": -1}},
],
"subtype": {
"class": "text",
"missing_reasons": {"No Data": -1},
"missing_rules": {},
},
},
}
],
}
},
],
transforms=[{"xfrms": 1}, {"xfrms": 2}, {"xfrms": 3}],
population=1000,
min_base=10,
)

cubes = cube_set._cubes
summary_cube = cubes[0]
single_col_filter1 = cubes[1]
single_col_filter2 = cubes[2]

assert len(summary_cube.partitions) == len(single_col_filter1.partitions)
assert (
summary_cube.dimension_types
== single_col_filter1.dimension_types
== single_col_filter2.dimension_types
)
assert summary_cube.partitions[0].counts == pytest.approx(np.array([1, 1, 1]))
assert single_col_filter1.partitions[0].counts == pytest.approx(
np.array([1, 0, 1])
)
assert single_col_filter2.partitions[0].counts == pytest.approx(
np.array([1, 1, 1])
)
assert (
single_col_filter1._cube_response["result"]["dimensions"][0]["type"][
"elements"
]
== summary_cube._cube_response["result"]["dimensions"][0]["type"][
"elements"
]
== single_col_filter2._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
Loading