pt
/
superset
mirror of https://github.com/apache/superset.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: contribution operator meets nan value (#18782)

This commit is contained in:
Yongjie Zhao 2022-02-18 23:28:28 +08:00 committed by GitHub
parent 38cd696981
commit 987740aa8d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
8 changed files with 36 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
superset-frontend/plugins/plugin-chart-echarts/src/Timeseries/Area/controlPanel.tsx
View File

@ -72,10 +72,10 @@ const config: ControlPanelConfig = {
default: contributionMode,
choices: [
[null, 'None'],
[EchartsTimeseriesContributionType.Row, 'Total'],
[EchartsTimeseriesContributionType.Row, 'Row'],
[EchartsTimeseriesContributionType.Column, 'Series'],
],
description: t('Calculate contribution per series or total'),
description: t('Calculate contribution per series or row'),
},
},
],

4
superset-frontend/plugins/plugin-chart-echarts/src/Timeseries/Regular/Bar/controlPanel.tsx
View File

@ -69,10 +69,10 @@ const config: ControlPanelConfig = {
default: contributionMode,
choices: [
[null, 'None'],
[EchartsTimeseriesContributionType.Row, 'Total'],
[EchartsTimeseriesContributionType.Row, 'Row'],
[EchartsTimeseriesContributionType.Column, 'Series'],
],
description: t('Calculate contribution per series or total'),
description: t('Calculate contribution per series or row'),
},
},
],

4
superset-frontend/plugins/plugin-chart-echarts/src/Timeseries/Regular/controlPanel.tsx
View File

@ -66,10 +66,10 @@ const config: ControlPanelConfig = {
default: contributionMode,
choices: [
[null, 'None'],
[EchartsTimeseriesContributionType.Row, 'Total'],
[EchartsTimeseriesContributionType.Row, 'Row'],
[EchartsTimeseriesContributionType.Column, 'Series'],
],
description: t('Calculate contribution per series or total'),
description: t('Calculate contribution per series or row'),
},
},
],

4
superset-frontend/plugins/plugin-chart-echarts/src/Timeseries/Step/controlPanel.tsx
View File

@ -72,10 +72,10 @@ const config: ControlPanelConfig = {
default: contributionMode,
choices: [
[null, 'None'],
[EchartsTimeseriesContributionType.Row, 'Total'],
[EchartsTimeseriesContributionType.Row, 'Row'],
[EchartsTimeseriesContributionType.Column, 'Series'],
],
description: t('Calculate contribution per series or total'),
description: t('Calculate contribution per series or row'),
},
},
],

4
superset-frontend/plugins/plugin-chart-echarts/src/Timeseries/controlPanel.tsx
View File

@ -73,10 +73,10 @@ const config: ControlPanelConfig = {
default: contributionMode,
choices: [
[null, 'None'],
[EchartsTimeseriesContributionType.Row, 'Total'],
[EchartsTimeseriesContributionType.Row, 'Row'],
[EchartsTimeseriesContributionType.Column, 'Series'],
],
description: t('Calculate contribution per series or total'),
description: t('Calculate contribution per series or row'),
},
},
],

2
superset/common/query_object.py
View File

@ -19,6 +19,7 @@ from __future__ import annotations
import logging
from datetime import datetime, timedelta
from pprint import pformat
from typing import Any, Dict, List, NamedTuple, Optional, TYPE_CHECKING
from flask_babel import gettext as _
@ -395,6 +396,7 @@ class QueryObject: # pylint: disable=too-many-instance-attributes
:raises QueryObjectValidationError: If the post processing operation
is incorrect
"""
logger.debug("post_processing: %s", pformat(self.post_processing))
for post_process in self.post_processing:
operation = post_process.get("operation")
if not operation:

1
superset/utils/pandas_postprocessing/contribution.py
View File

@ -49,6 +49,7 @@ def contribution(
"""
contribution_df = df.copy()
numeric_df = contribution_df.select_dtypes(include=["number", Decimal])
numeric_df.fillna(0, inplace=True)
# verify column selections
if columns:
numeric_columns = numeric_df.columns.tolist()

36
tests/unit_tests/pandas_postprocessing/test_contribution.py
View File

@ -18,6 +18,8 @@
from datetime import datetime
import pytest
from numpy import nan
from numpy.testing import assert_array_equal
from pandas import DataFrame
from superset.exceptions import QueryObjectValidationError
@ -28,9 +30,14 @@ from superset.utils.pandas_postprocessing import contribution
def test_contribution():
df = DataFrame(
{
DTTM_ALIAS: [datetime(2020, 7, 16, 14, 49), datetime(2020, 7, 16, 14, 50),],
"a": [1, 3],
"b": [1, 9],
DTTM_ALIAS: [
datetime(2020, 7, 16, 14, 49),
datetime(2020, 7, 16, 14, 50),
datetime(2020, 7, 16, 14, 51),
],
"a": [1, 3, nan],
"b": [1, 9, nan],
"c": [nan, nan, nan],
}
)
with pytest.raises(QueryObjectValidationError, match="not numeric"):
@ -43,18 +50,20 @@ def test_contribution():
processed_df = contribution(
df, orientation=PostProcessingContributionOrientation.ROW,
)
assert processed_df.columns.tolist() == [DTTM_ALIAS, "a", "b"]
assert processed_df["a"].tolist() == [0.5, 0.25]
assert processed_df["b"].tolist() == [0.5, 0.75]
assert processed_df.columns.tolist() == [DTTM_ALIAS, "a", "b", "c"]
assert_array_equal(processed_df["a"].tolist(), [0.5, 0.25, nan])
assert_array_equal(processed_df["b"].tolist(), [0.5, 0.75, nan])
assert_array_equal(processed_df["c"].tolist(), [0, 0, nan])
# cell contribution across column without temporal column
df.pop(DTTM_ALIAS)
processed_df = contribution(
df, orientation=PostProcessingContributionOrientation.COLUMN
)
assert processed_df.columns.tolist() == ["a", "b"]
assert processed_df["a"].tolist() == [0.25, 0.75]
assert processed_df["b"].tolist() == [0.1, 0.9]
assert processed_df.columns.tolist() == ["a", "b", "c"]
assert_array_equal(processed_df["a"].tolist(), [0.25, 0.75, 0])
assert_array_equal(processed_df["b"].tolist(), [0.1, 0.9, 0])
assert_array_equal(processed_df["c"].tolist(), [nan, nan, nan])
# contribution only on selected columns
processed_df = contribution(
@ -63,7 +72,8 @@ def test_contribution():
columns=["a"],
rename_columns=["pct_a"],
)
assert processed_df.columns.tolist() == ["a", "b", "pct_a"]
assert processed_df["a"].tolist() == [1, 3]
assert processed_df["b"].tolist() == [1, 9]
assert processed_df["pct_a"].tolist() == [0.25, 0.75]
assert processed_df.columns.tolist() == ["a", "b", "c", "pct_a"]
assert_array_equal(processed_df["a"].tolist(), [1, 3, nan])
assert_array_equal(processed_df["b"].tolist(), [1, 9, nan])
assert_array_equal(processed_df["c"].tolist(), [nan, nan, nan])
assert processed_df["pct_a"].tolist() == [0.25, 0.75, 0]