2022-02-17 07:05:41 -05:00
|
|
|
# Licensed to the Apache Software Foundation (ASF) under one
|
|
|
|
# or more contributor license agreements. See the NOTICE file
|
|
|
|
# distributed with this work for additional information
|
|
|
|
# regarding copyright ownership. The ASF licenses this file
|
|
|
|
# to you under the Apache License, Version 2.0 (the
|
|
|
|
# "License"); you may not use this file except in compliance
|
|
|
|
# with the License. You may obtain a copy of the License at
|
|
|
|
#
|
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
#
|
|
|
|
# Unless required by applicable law or agreed to in writing,
|
|
|
|
# software distributed under the License is distributed on an
|
|
|
|
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
|
|
|
# KIND, either express or implied. See the License for the
|
|
|
|
# specific language governing permissions and limitations
|
|
|
|
# under the License.
|
|
|
|
import pytest
|
|
|
|
|
2022-03-23 01:46:28 -04:00
|
|
|
from superset.exceptions import InvalidPostProcessingError
|
2022-02-17 07:05:41 -05:00
|
|
|
from superset.utils.core import PostProcessingBoxplotWhiskerType
|
|
|
|
from superset.utils.pandas_postprocessing import boxplot
|
|
|
|
from tests.unit_tests.fixtures.dataframes import names_df
|
|
|
|
|
|
|
|
|
|
|
|
def test_boxplot_tukey():
|
|
|
|
df = boxplot(
|
|
|
|
df=names_df,
|
|
|
|
groupby=["region"],
|
|
|
|
whisker_type=PostProcessingBoxplotWhiskerType.TUKEY,
|
|
|
|
metrics=["cars"],
|
|
|
|
)
|
|
|
|
columns = {column for column in df.columns}
|
|
|
|
assert columns == {
|
|
|
|
"cars__mean",
|
|
|
|
"cars__median",
|
|
|
|
"cars__q1",
|
|
|
|
"cars__q3",
|
|
|
|
"cars__max",
|
|
|
|
"cars__min",
|
|
|
|
"cars__count",
|
|
|
|
"cars__outliers",
|
|
|
|
"region",
|
|
|
|
}
|
|
|
|
assert len(df) == 4
|
|
|
|
|
|
|
|
|
|
|
|
def test_boxplot_min_max():
|
|
|
|
df = boxplot(
|
|
|
|
df=names_df,
|
|
|
|
groupby=["region"],
|
|
|
|
whisker_type=PostProcessingBoxplotWhiskerType.MINMAX,
|
|
|
|
metrics=["cars"],
|
|
|
|
)
|
|
|
|
columns = {column for column in df.columns}
|
|
|
|
assert columns == {
|
|
|
|
"cars__mean",
|
|
|
|
"cars__median",
|
|
|
|
"cars__q1",
|
|
|
|
"cars__q3",
|
|
|
|
"cars__max",
|
|
|
|
"cars__min",
|
|
|
|
"cars__count",
|
|
|
|
"cars__outliers",
|
|
|
|
"region",
|
|
|
|
}
|
|
|
|
assert len(df) == 4
|
|
|
|
|
|
|
|
|
|
|
|
def test_boxplot_percentile():
|
|
|
|
df = boxplot(
|
|
|
|
df=names_df,
|
|
|
|
groupby=["region"],
|
|
|
|
whisker_type=PostProcessingBoxplotWhiskerType.PERCENTILE,
|
|
|
|
metrics=["cars"],
|
|
|
|
percentiles=[1, 99],
|
|
|
|
)
|
|
|
|
columns = {column for column in df.columns}
|
|
|
|
assert columns == {
|
|
|
|
"cars__mean",
|
|
|
|
"cars__median",
|
|
|
|
"cars__q1",
|
|
|
|
"cars__q3",
|
|
|
|
"cars__max",
|
|
|
|
"cars__min",
|
|
|
|
"cars__count",
|
|
|
|
"cars__outliers",
|
|
|
|
"region",
|
|
|
|
}
|
|
|
|
assert len(df) == 4
|
|
|
|
|
|
|
|
|
|
|
|
def test_boxplot_percentile_incorrect_params():
|
2022-03-23 01:46:28 -04:00
|
|
|
with pytest.raises(InvalidPostProcessingError):
|
2022-02-17 07:05:41 -05:00
|
|
|
boxplot(
|
|
|
|
df=names_df,
|
|
|
|
groupby=["region"],
|
|
|
|
whisker_type=PostProcessingBoxplotWhiskerType.PERCENTILE,
|
|
|
|
metrics=["cars"],
|
|
|
|
)
|
|
|
|
|
2022-03-23 01:46:28 -04:00
|
|
|
with pytest.raises(InvalidPostProcessingError):
|
2022-02-17 07:05:41 -05:00
|
|
|
boxplot(
|
|
|
|
df=names_df,
|
|
|
|
groupby=["region"],
|
|
|
|
whisker_type=PostProcessingBoxplotWhiskerType.PERCENTILE,
|
|
|
|
metrics=["cars"],
|
|
|
|
percentiles=[10],
|
|
|
|
)
|
|
|
|
|
2022-03-23 01:46:28 -04:00
|
|
|
with pytest.raises(InvalidPostProcessingError):
|
2022-02-17 07:05:41 -05:00
|
|
|
boxplot(
|
|
|
|
df=names_df,
|
|
|
|
groupby=["region"],
|
|
|
|
whisker_type=PostProcessingBoxplotWhiskerType.PERCENTILE,
|
|
|
|
metrics=["cars"],
|
|
|
|
percentiles=[90, 10],
|
|
|
|
)
|
|
|
|
|
2022-03-23 01:46:28 -04:00
|
|
|
with pytest.raises(InvalidPostProcessingError):
|
2022-02-17 07:05:41 -05:00
|
|
|
boxplot(
|
|
|
|
df=names_df,
|
|
|
|
groupby=["region"],
|
|
|
|
whisker_type=PostProcessingBoxplotWhiskerType.PERCENTILE,
|
|
|
|
metrics=["cars"],
|
|
|
|
percentiles=[10, 90, 10],
|
|
|
|
)
|
2022-06-01 22:00:04 -04:00
|
|
|
|
|
|
|
|
|
|
|
def test_boxplot_type_coercion():
|
|
|
|
df = names_df
|
|
|
|
df["cars"] = df["cars"].astype(str)
|
|
|
|
df = boxplot(
|
|
|
|
df=df,
|
|
|
|
groupby=["region"],
|
|
|
|
whisker_type=PostProcessingBoxplotWhiskerType.TUKEY,
|
|
|
|
metrics=["cars"],
|
|
|
|
)
|
|
|
|
|
|
|
|
columns = {column for column in df.columns}
|
|
|
|
assert columns == {
|
|
|
|
"cars__mean",
|
|
|
|
"cars__median",
|
|
|
|
"cars__q1",
|
|
|
|
"cars__q3",
|
|
|
|
"cars__max",
|
|
|
|
"cars__min",
|
|
|
|
"cars__count",
|
|
|
|
"cars__outliers",
|
|
|
|
"region",
|
|
|
|
}
|
|
|
|
assert len(df) == 4
|