QT/superset2
1
0
Fork 0
mirror of https://github.com/apache/superset.git synced 2026-04-19 08:04:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: set columns numeric datatypes when exporting to excel (#27229)

Browse Source 
Co-authored-by: Elizabeth Thompson <eschutho@gmail.com>
This commit is contained in:
squalou
2024-08-23 09:39:47 +02:00
committed by GitHub
parent 9d5268ab6d
commit ce72a0ac27
5 changed files with 90 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
tests/unit_tests/utils/excel_tests.py
View File

@@ -18,8 +18,10 @@
from datetime import datetime, timezone
import pandas as pd
from pandas.api.types import is_numeric_dtype
from superset.utils.excel import df_to_excel
from superset.utils.core import GenericDataType
from superset.utils.excel import apply_column_types, df_to_excel
def test_timezone_conversion() -> None:
@@ -27,5 +29,66 @@ def test_timezone_conversion() -> None:
Test that columns with timezones are converted to a string.
"""
df = pd.DataFrame({"dt": [datetime(2023, 1, 1, 0, 0, tzinfo=timezone.utc)]})
apply_column_types(df, [GenericDataType.TEMPORAL])
contents = df_to_excel(df)
assert pd.read_excel(contents)["dt"][0] == "2023-01-01 00:00:00+00:00"
def test_column_data_types_with_one_numeric_column():
df = pd.DataFrame(
{
"col0": ["123", "1", "2", "3"],
"col1": ["456", "5.67", "0", ".45"],
"col2": [
datetime(2023, 1, 1, 0, 0, tzinfo=timezone.utc),
datetime(2023, 1, 2, 0, 0, tzinfo=timezone.utc),
datetime(2023, 1, 3, 0, 0, tzinfo=timezone.utc),
datetime(2023, 1, 4, 0, 0, tzinfo=timezone.utc),
],
"col3": ["True", "False", "True", "False"],
}
)
coltypes: list[GenericDataType] = [
GenericDataType.STRING,
GenericDataType.NUMERIC,
GenericDataType.TEMPORAL,
GenericDataType.BOOLEAN,
]
# only col1 should be converted to numeric, according to coltypes definition
assert not is_numeric_dtype(df["col1"])
apply_column_types(df, coltypes)
assert not is_numeric_dtype(df["col0"])
assert is_numeric_dtype(df["col1"])
assert not is_numeric_dtype(df["col2"])
assert not is_numeric_dtype(df["col3"])
def test_column_data_types_with_failing_conversion():
df = pd.DataFrame(
{
"col0": ["123", "1", "2", "3"],
"col1": ["456", "non_numeric_value", "0", ".45"],
"col2": [
datetime(2023, 1, 1, 0, 0, tzinfo=timezone.utc),
datetime(2023, 1, 2, 0, 0, tzinfo=timezone.utc),
datetime(2023, 1, 3, 0, 0, tzinfo=timezone.utc),
datetime(2023, 1, 4, 0, 0, tzinfo=timezone.utc),
],
"col3": ["True", "False", "True", "False"],
}
)
coltypes: list[GenericDataType] = [
GenericDataType.STRING,
GenericDataType.NUMERIC,
GenericDataType.TEMPORAL,
GenericDataType.BOOLEAN,
]
# should not fail neither convert
assert not is_numeric_dtype(df["col1"])
apply_column_types(df, coltypes)
assert not is_numeric_dtype(df["col0"])
assert not is_numeric_dtype(df["col1"])
assert not is_numeric_dtype(df["col2"])
assert not is_numeric_dtype(df["col3"])